{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99173415,0.0002887904,0.00030755685,0.0021494415,0.000011318782,0.00012253359,0.00019983544,0.000006280798,0.0051801247],"genre_scores_gemma":[0.99616975,0.00016521316,0.00029559724,0.00021788431,0.0000024473827,0.000067176705,0.0000740229,0.0000042689057,0.0030035162],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9966444,0.0014080768,0.0000810079,0.00024055353,0.00055296876,0.0010730703],"domain_scores_gemma":[0.9944642,0.001960226,0.0006907137,0.00023104346,0.0016778029,0.000975956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00355054,0.00027661482,0.00039401872,0.0012999672,0.010999302,0.0045767245,0.0015299378,0.0013216208,0.003456436],"category_scores_gemma":[0.0070223412,0.00037065786,0.00029950068,0.0029199077,0.00654644,0.0015244917,0.0025429258,0.0015649103,0.00019847542],"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":[0.00014971662,0.00025007766,0.16029844,0.00030293933,0.00003874836,0.0022352051,0.79105186,0.0010020069,0.0021824522,0.0071717165,0.0038536664,0.03146321],"study_design_scores_gemma":[0.000010750487,0.000079326026,0.15772782,0.00014266747,0.000012870181,0.00006949961,0.82648873,0.0005812975,0.00030051763,0.0002277916,0.014323557,0.000035162262],"about_ca_topic_score_codex":0.97867924,"about_ca_topic_score_gemma":0.9921508,"teacher_disagreement_score":0.9238022,"about_ca_system_score_codex":0.0761978,"about_ca_system_score_gemma":0.06670943,"threshold_uncertainty_score":0.5528563},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041398713,0.001193644,0.94030136,0.033720475,0.0030919728,0.0037888933,0.00025458442,0.0034287204,0.010080579],"genre_scores_gemma":[0.013985363,0.000985851,0.97371316,0.0028889452,0.0006527995,0.005459108,0.00010128016,0.00044076785,0.0017727559],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8282254,0.14462462,0.012797745,0.0023967444,0.010880038,0.0010754117],"domain_scores_gemma":[0.53956485,0.37892383,0.015343327,0.028069181,0.032514323,0.0055844816],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19960058,0.001963238,0.0017111176,0.008984613,0.0040992615,0.011998434,0.004058073,0.0040485794,0.0056731296],"category_scores_gemma":[0.32506147,0.0016061501,0.0015660572,0.004225121,0.016164357,0.016774546,0.0120714465,0.015507149,0.0035066414],"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":[0.00026298335,0.0004895492,0.0016147654,0.0047921347,0.000105368905,0.0006465218,0.14491923,0.0018061711,0.007384733,0.21373503,0.14112611,0.48311758],"study_design_scores_gemma":[0.00024569512,0.00053576566,0.0015980279,0.006271425,0.000082641454,0.0020253705,0.025514998,0.0091111,0.003735784,0.39447653,0.5561095,0.00029313655],"about_ca_topic_score_codex":0.000925421,"about_ca_topic_score_gemma":0.0017664495,"teacher_disagreement_score":0.8003994,"about_ca_system_score_codex":0.005804868,"about_ca_system_score_gemma":0.012536972,"threshold_uncertainty_score":0.987035},"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":"commentary","genre_gemma":"review","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052414606,0.047059927,0.1891938,0.4731253,0.011726538,0.0025107036,0.0002927062,0.0002307149,0.27061886],"genre_scores_gemma":[0.37291375,0.064279445,0.3742986,0.08938112,0.009016445,0.023755793,0.0006710675,0.00091949146,0.06476432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.38870496,0.56739515,0.00975943,0.0075488035,0.022473216,0.00411844],"domain_scores_gemma":[0.60147554,0.33790067,0.006984328,0.02373991,0.023470292,0.0064293197],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3437381,0.0017415415,0.0020116628,0.004552417,0.009691451,0.024195537,0.002949933,0.009780767,0.010233691],"category_scores_gemma":[0.18993387,0.0011667757,0.0012532467,0.0075521218,0.041951515,0.015630811,0.017433766,0.017331025,0.0016661199],"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":[0.000070043134,0.00010869288,0.00042568136,0.0013162142,0.000046430014,0.00019098129,0.047868323,0.00078166235,0.00022296417,0.8433433,0.035816167,0.06980942],"study_design_scores_gemma":[0.00005332657,0.00015012221,0.00024884814,0.003944417,0.0000267819,0.0002992134,0.028882792,0.00070255634,0.00035837307,0.30952543,0.6557699,0.000038280014],"about_ca_topic_score_codex":0.0021710785,"about_ca_topic_score_gemma":0.0020959836,"teacher_disagreement_score":0.3437381,"about_ca_system_score_codex":0.012360246,"about_ca_system_score_gemma":0.027505165,"threshold_uncertainty_score":0.8092878},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42734084,0.049643762,0.012220106,0.23152903,0.004189142,0.000467656,0.0036753644,0.00049422326,0.2704399],"genre_scores_gemma":[0.97274595,0.0060606794,0.0047790064,0.007416595,0.00064003153,0.00014656161,0.000542338,0.00012524489,0.0075437417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.4414711,0.23109221,0.02947258,0.010303656,0.2759007,0.0117597105],"domain_scores_gemma":[0.14217788,0.5569165,0.06432305,0.028449813,0.20052235,0.0076104137],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3137248,0.0005727592,0.0011412846,0.032677006,0.00759925,0.020078931,0.0051386845,0.005279378,0.0016705443],"category_scores_gemma":[0.73783535,0.00109575,0.0009021913,0.024581024,0.011513894,0.007381004,0.005111248,0.005655345,0.0007060956],"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":[0.0007244548,0.00010936067,0.097033486,0.0026463594,0.0007630023,0.00078190956,0.11254333,0.0012736538,0.0015114833,0.14887445,0.13156351,0.50217503],"study_design_scores_gemma":[0.0001374991,0.00028819893,0.337878,0.012344861,0.0010735502,0.00107974,0.06946886,0.007227274,0.0067804176,0.043448392,0.5195533,0.00071995746],"about_ca_topic_score_codex":0.28079724,"about_ca_topic_score_gemma":0.33836192,"teacher_disagreement_score":0.9563659,"about_ca_system_score_codex":0.043634117,"about_ca_system_score_gemma":0.07216158,"threshold_uncertainty_score":0.8462995},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9089522,0.00066170876,0.0016114188,0.011230645,0.0002589872,0.0041534803,0.024173219,0.0003593004,0.0485991],"genre_scores_gemma":[0.9586494,0.0006844371,0.003763037,0.0023280773,0.000071389426,0.001981878,0.011426585,0.00004249771,0.021052679],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99876773,0.00023221022,0.0000417198,0.00006138037,0.00044568948,0.00045142678],"domain_scores_gemma":[0.99144346,0.00026614708,0.00077881716,0.00020254355,0.0027806961,0.004528351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037872973,0.00035974933,0.00015584708,0.0012826236,0.0014380696,0.0013990852,0.001501208,0.0007351846,0.0045488467],"category_scores_gemma":[0.0049372334,0.00020586407,0.0002834055,0.0008503695,0.0005064539,0.0008191047,0.0026021814,0.000614219,0.0009536703],"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":[0.0010732518,0.0015483157,0.7510546,0.00041628405,0.0000420361,0.0005728788,0.005605076,0.00072509685,0.0020398542,0.0022463738,0.0707387,0.16393752],"study_design_scores_gemma":[0.0000862539,0.0010347203,0.9419745,0.00010163252,0.000014201273,0.000090987145,0.012973981,0.00071114197,0.0003669602,0.00020242481,0.042424854,0.000018302868],"about_ca_topic_score_codex":0.22568838,"about_ca_topic_score_gemma":0.48708385,"teacher_disagreement_score":0.7743116,"about_ca_system_score_codex":0.0048845294,"about_ca_system_score_gemma":0.02156486,"threshold_uncertainty_score":0.44874948},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8467009,0.027506342,0.010292159,0.071002185,0.00020707236,0.0008266489,0.00007924738,0.000056675588,0.043328706],"genre_scores_gemma":[0.99221355,0.0038648474,0.0022002365,0.0010180176,0.000046807465,0.00018485366,0.000015919652,0.000008080415,0.0004477486],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7354825,0.22883882,0.0061478205,0.0022125368,0.021534838,0.005783574],"domain_scores_gemma":[0.6830006,0.23288037,0.032658566,0.008578338,0.03293017,0.009952014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1742924,0.000494116,0.0013782595,0.0034531103,0.0043002493,0.009598607,0.0016675314,0.00158628,0.0014887254],"category_scores_gemma":[0.26230887,0.00040677312,0.0007199202,0.0040934626,0.010246276,0.0065552783,0.006966157,0.001950267,0.00014218733],"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":[0.0005130295,0.00040602483,0.15596618,0.0055686096,0.00043611875,0.000470457,0.3662137,0.00094478985,0.00078563276,0.013586659,0.0019844177,0.45312437],"study_design_scores_gemma":[0.00009439665,0.0021591038,0.40963697,0.015957236,0.000531872,0.00077641057,0.4947459,0.0015985272,0.0022624538,0.025596846,0.046393994,0.0002463266],"about_ca_topic_score_codex":0.023689907,"about_ca_topic_score_gemma":0.027077058,"teacher_disagreement_score":0.1742924,"about_ca_system_score_codex":0.011985478,"about_ca_system_score_gemma":0.024568345,"threshold_uncertainty_score":0.92175734},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25282955,0.007867519,0.04155627,0.57380074,0.003674678,0.0011466047,0.00020191628,0.000098755256,0.118824],"genre_scores_gemma":[0.9721009,0.0021074722,0.0069650565,0.013386261,0.00027385505,0.00039030076,0.00005343554,0.000091454014,0.0046312534],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8461815,0.13727419,0.0016510551,0.0029179256,0.0068629384,0.005112306],"domain_scores_gemma":[0.7944398,0.18652192,0.0027950665,0.0034338401,0.008214131,0.0045952336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.144777,0.0012270912,0.0013151015,0.0037032852,0.03180808,0.030468144,0.0047383676,0.012577632,0.004053922],"category_scores_gemma":[0.116146326,0.0010482934,0.001105523,0.0030861779,0.05473935,0.040754557,0.020087944,0.019637236,0.0004779873],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096585005,0.00010834704,0.00065778283,0.00035093294,0.000021074256,0.00067368906,0.78885,0.00041688152,0.00037419083,0.1806456,0.008515793,0.019289164],"study_design_scores_gemma":[0.000024821542,0.00005957889,0.00053065334,0.0012276663,0.000021341993,0.00016405217,0.81992984,0.0006658452,0.00073962344,0.08255305,0.09401045,0.00007306292],"about_ca_topic_score_codex":0.011240829,"about_ca_topic_score_gemma":0.010651591,"teacher_disagreement_score":0.98875916,"about_ca_system_score_codex":0.03506484,"about_ca_system_score_gemma":0.024815844,"threshold_uncertainty_score":0.7656631},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9314904,0.007633475,0.0006216183,0.004105158,0.00006078926,0.00016530557,0.030604187,0.0002882661,0.025030874],"genre_scores_gemma":[0.9748942,0.005549034,0.0017171707,0.00041531044,0.000032368895,0.000073153635,0.009694842,0.000061438026,0.0075624245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981129,0.00009785022,0.00010985032,0.00020824409,0.00092682417,0.0005443659],"domain_scores_gemma":[0.9863236,0.00087068183,0.0016662059,0.00014631372,0.007891984,0.0031011885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015967936,0.0002802214,0.00025957913,0.00836491,0.0018094762,0.001440982,0.0011250274,0.0003365988,0.004486874],"category_scores_gemma":[0.0066781836,0.00020174013,0.00043902983,0.013608547,0.0004892055,0.00067297113,0.0009845749,0.00068691635,0.00043419423],"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":[0.00020700146,0.00009884462,0.8541778,0.00057928794,0.000046001005,0.00011192714,0.0039148764,0.00026477256,0.0011525494,0.0010398752,0.013369846,0.12503736],"study_design_scores_gemma":[0.0000023588054,0.000025032377,0.98684305,0.00009349961,0.000010619845,0.000054628727,0.002519363,0.00013420115,0.00018039871,0.000030943305,0.010092779,0.0000131359875],"about_ca_topic_score_codex":0.9670628,"about_ca_topic_score_gemma":0.98333746,"teacher_disagreement_score":0.9984032,"about_ca_system_score_codex":0.029309884,"about_ca_system_score_gemma":0.04784015,"threshold_uncertainty_score":0.21265906},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5203525,0.00298856,0.0013701741,0.02543841,0.00024364806,0.00038549086,0.00017833087,0.000057931706,0.44898498],"genre_scores_gemma":[0.85741466,0.00081784604,0.0012782995,0.0012598219,0.000023895824,0.000105622,0.00008487145,0.000027717868,0.13898717],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9947496,0.0013866408,0.000063566644,0.00024776283,0.0011876907,0.0023646464],"domain_scores_gemma":[0.99577206,0.0009182833,0.00014010236,0.00011017429,0.00066384,0.0023956255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004455432,0.00042608235,0.00041584982,0.0016090965,0.021041408,0.0075046937,0.0022440015,0.0029414112,0.007527982],"category_scores_gemma":[0.0060488894,0.00028595462,0.00039212345,0.0038528242,0.011222067,0.0018561153,0.005917158,0.0031352337,0.00028740705],"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":[0.00030044973,0.0008128541,0.02007374,0.00030898498,0.000029217432,0.0011262638,0.36385173,0.0016077184,0.0011288321,0.28220463,0.05490379,0.2736518],"study_design_scores_gemma":[0.000064003405,0.00021173584,0.111234464,0.0004971035,0.000046621277,0.0002491396,0.28112468,0.0011950259,0.001066159,0.018525409,0.58566946,0.00011613463],"about_ca_topic_score_codex":0.961258,"about_ca_topic_score_gemma":0.9929028,"teacher_disagreement_score":0.08877087,"about_ca_system_score_codex":0.08877087,"about_ca_system_score_gemma":0.14032137,"threshold_uncertainty_score":0.64408076},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004451209,0.11622469,0.14287686,0.69218516,0.006886263,0.00021402206,0.0000714111,0.00022848413,0.03686193],"genre_scores_gemma":[0.56919926,0.09016187,0.19974147,0.1105216,0.016812123,0.0024689152,0.00012879343,0.0005110691,0.010454922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5779284,0.36446765,0.014149122,0.010856746,0.029134555,0.0034635328],"domain_scores_gemma":[0.5283798,0.40860197,0.008359696,0.021767372,0.02957401,0.003317169],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.33675084,0.0018966069,0.0043890537,0.012551863,0.0074622887,0.03671425,0.006643146,0.016182156,0.0036133786],"category_scores_gemma":[0.31431067,0.001317818,0.0021831766,0.0069474857,0.12129353,0.05283792,0.011324224,0.025324188,0.0010930831],"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":[0.000061236344,0.000060258335,0.00029350838,0.0011137703,0.00006261317,0.000048444337,0.009563066,0.0007783501,0.00008050517,0.9477293,0.008055283,0.03215376],"study_design_scores_gemma":[0.00006534828,0.00010624901,0.00039352593,0.004535518,0.00004096186,0.00012450172,0.009336286,0.0018908468,0.0003033156,0.8915806,0.09154145,0.000081403836],"about_ca_topic_score_codex":0.009906937,"about_ca_topic_score_gemma":0.0071741613,"teacher_disagreement_score":0.33675084,"about_ca_system_score_codex":0.030339448,"about_ca_system_score_gemma":0.02693787,"threshold_uncertainty_score":0.8179043},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30923706,0.012329943,0.01886377,0.39082086,0.00043603597,0.00017751286,0.0011009503,0.00022610312,0.2668078],"genre_scores_gemma":[0.98035663,0.0018822296,0.002356725,0.005308032,0.00014083328,0.000036072866,0.000059477956,0.000103777806,0.009756208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9755308,0.0065984325,0.0006613776,0.0022784334,0.008451049,0.0064798635],"domain_scores_gemma":[0.89711314,0.059370097,0.003795599,0.00491553,0.025567243,0.00923839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028689705,0.00036468531,0.0013872829,0.005285549,0.018423045,0.022268338,0.0037336124,0.003541753,0.013014732],"category_scores_gemma":[0.110050984,0.0007253786,0.0006987037,0.013258989,0.028042784,0.008637593,0.00693403,0.007367004,0.00035587803],"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":[0.0002595638,0.00008592457,0.014010853,0.00022938626,0.0000876854,0.00015523034,0.012440512,0.0046742368,0.00034810076,0.8527967,0.026576944,0.08833497],"study_design_scores_gemma":[0.00027464182,0.00013664272,0.11182177,0.0015237847,0.0002470889,0.00016501806,0.049995717,0.018427141,0.0018138577,0.53819287,0.27692,0.00048140547],"about_ca_topic_score_codex":0.9807952,"about_ca_topic_score_gemma":0.9843237,"teacher_disagreement_score":0.8002825,"about_ca_system_score_codex":0.19971752,"about_ca_system_score_gemma":0.2861012,"threshold_uncertainty_score":0.92821425},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7845153,0.008853531,0.00039352666,0.07673192,0.0006729495,0.0003335183,0.0010708963,0.00006925851,0.12735899],"genre_scores_gemma":[0.9604579,0.0037218782,0.00032446117,0.001911948,0.00010076613,0.000094819865,0.00037799176,0.000030653195,0.03297952],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9948265,0.0006358281,0.0001305748,0.00040002534,0.0018794013,0.0021275913],"domain_scores_gemma":[0.9872907,0.0010115014,0.001395736,0.00048169633,0.0037817038,0.0060386346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031997354,0.00023659668,0.0003736344,0.00180104,0.01750365,0.007172504,0.0015270138,0.0020113576,0.004091212],"category_scores_gemma":[0.010617641,0.0005134453,0.0002443008,0.0045841034,0.009553361,0.003565054,0.0042697643,0.0023799094,0.0004004364],"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":true,"study_design_scores_codex":[0.00034225683,0.00021088045,0.1271882,0.00056890585,0.00002559876,0.00093508954,0.6544883,0.0002530282,0.0019778004,0.03315067,0.07522719,0.10563205],"study_design_scores_gemma":[0.000034286597,0.00006489325,0.2925318,0.00027331818,0.000017409242,0.00013042918,0.22836763,0.000098485514,0.00036568745,0.00054865575,0.47752196,0.00004553057],"about_ca_topic_score_codex":0.99321187,"about_ca_topic_score_gemma":0.9973084,"teacher_disagreement_score":0.78221035,"about_ca_system_score_codex":0.21778962,"about_ca_system_score_gemma":0.30358696,"threshold_uncertainty_score":0.90725315},"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":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067735114,0.013308096,0.04998019,0.8979164,0.0038362367,0.0005922846,0.000052837848,0.0002622516,0.027278181],"genre_scores_gemma":[0.54317087,0.01935114,0.2850072,0.12683974,0.0075279614,0.003078741,0.00026743667,0.00065442367,0.014102491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.4514503,0.46827593,0.021376263,0.008758484,0.03502097,0.015118073],"domain_scores_gemma":[0.40763417,0.41266662,0.02968388,0.0526626,0.06695429,0.03039841],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5126557,0.0011456793,0.0020963058,0.005403098,0.016547572,0.046001393,0.0066754576,0.01941598,0.0043861624],"category_scores_gemma":[0.3641983,0.0020833465,0.0025360568,0.005665426,0.0385303,0.053319417,0.03853884,0.032335512,0.0011063495],"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":[0.00022818659,0.00038338505,0.005410119,0.0021154226,0.00013566666,0.0009321052,0.046381466,0.003451507,0.0013341499,0.57232946,0.09885852,0.26843995],"study_design_scores_gemma":[0.00014855534,0.00034401883,0.0028592453,0.006542014,0.00006282561,0.0005537986,0.040897727,0.002956959,0.0016839154,0.27514482,0.6684947,0.00031148468],"about_ca_topic_score_codex":0.004088639,"about_ca_topic_score_gemma":0.0059569874,"teacher_disagreement_score":0.5126557,"about_ca_system_score_codex":0.024732849,"about_ca_system_score_gemma":0.090438925,"threshold_uncertainty_score":0.60098237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8208747,0.005744351,0.031679824,0.055754878,0.0005532083,0.0030703298,0.00007800375,0.000057873673,0.08218686],"genre_scores_gemma":[0.96920043,0.0030512745,0.017378768,0.0038353053,0.00013623407,0.0013056998,0.000022381519,0.000039767554,0.005030126],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8369499,0.14548455,0.0027997086,0.0012402833,0.008023588,0.005501984],"domain_scores_gemma":[0.8371333,0.14058648,0.004823931,0.0028669597,0.008402903,0.006186506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11244857,0.0008658094,0.0008751741,0.0028032628,0.027943853,0.010314052,0.0033571685,0.010416303,0.0034508428],"category_scores_gemma":[0.1186845,0.00090081175,0.0012162444,0.0035243095,0.017895458,0.0069683017,0.010920525,0.011303336,0.00045481746],"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":[0.0004008676,0.0043811183,0.0176652,0.0014467691,0.000083249055,0.078609005,0.67390543,0.0026286195,0.00083398964,0.10920621,0.014477211,0.09636242],"study_design_scores_gemma":[0.00019131406,0.0010499719,0.0053563556,0.0031170135,0.00008888822,0.031026749,0.8289547,0.0041061905,0.001999617,0.028397487,0.09556248,0.00014922889],"about_ca_topic_score_codex":0.008071973,"about_ca_topic_score_gemma":0.020628002,"teacher_disagreement_score":0.11244857,"about_ca_system_score_codex":0.01661272,"about_ca_system_score_gemma":0.015144812,"threshold_uncertainty_score":0.594692},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7288396,0.017624075,0.007971414,0.036601566,0.0010864374,0.00053799327,0.0008005266,0.0002160343,0.20632237],"genre_scores_gemma":[0.8416506,0.0038062325,0.002753098,0.0012432585,0.0000668547,0.00017614625,0.00015888269,0.00004792539,0.15009698],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99637586,0.0011702711,0.000105800566,0.00040646986,0.0010397008,0.0009019253],"domain_scores_gemma":[0.9866463,0.00243026,0.0006778695,0.00034403423,0.0066313925,0.0032701348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047907457,0.00038607116,0.00032520478,0.00160755,0.0072230496,0.0036920006,0.0009827806,0.0010216312,0.010291303],"category_scores_gemma":[0.011013005,0.00038568873,0.00023269636,0.002534147,0.0058680554,0.0013773856,0.00215951,0.0028505968,0.00071224745],"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":[0.0002901975,0.0004274262,0.055469982,0.00092616613,0.00005005718,0.00069392944,0.23794073,0.0016675746,0.0039024209,0.10924221,0.04315151,0.5462378],"study_design_scores_gemma":[0.000030351996,0.00026081287,0.3060736,0.0013276889,0.000036436675,0.000118973934,0.06378884,0.0007401381,0.0023048967,0.002457321,0.62275237,0.000108585366],"about_ca_topic_score_codex":0.94309527,"about_ca_topic_score_gemma":0.9727126,"teacher_disagreement_score":0.9018446,"about_ca_system_score_codex":0.09815539,"about_ca_system_score_gemma":0.10511958,"threshold_uncertainty_score":0.7121705},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002681291,0.059494995,0.0012488893,0.8999841,0.01153011,0.000028408975,0.000029755687,0.00011448371,0.024887966],"genre_scores_gemma":[0.2277506,0.13666104,0.009011538,0.50438553,0.02977643,0.000507207,0.00020377897,0.00023423429,0.0914696],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932231,0.003792717,0.00016873649,0.0006358588,0.0009209638,0.0012587146],"domain_scores_gemma":[0.98077124,0.0035271158,0.0010724779,0.00062472984,0.0021574823,0.011847022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007308428,0.00060177257,0.0008777873,0.0015940191,0.01170675,0.01778019,0.0013972836,0.013629968,0.020625481],"category_scores_gemma":[0.01422413,0.0004398159,0.00047140822,0.0015871426,0.014158349,0.025108082,0.007942723,0.013330616,0.006433434],"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":[0.000071663904,0.00024906427,0.0017640522,0.00092999,0.000008875,0.00033724084,0.026251033,0.000049941897,0.00020615826,0.14380158,0.6597276,0.16660282],"study_design_scores_gemma":[0.00003769633,0.00013371457,0.0017792496,0.0032804233,0.000006421887,0.00092099357,0.07046334,0.00010386653,0.00007055811,0.08611539,0.83705187,0.000036520683],"about_ca_topic_score_codex":0.004123326,"about_ca_topic_score_gemma":0.006187601,"teacher_disagreement_score":0.020625481,"about_ca_system_score_codex":0.0050426433,"about_ca_system_score_gemma":0.020657089,"threshold_uncertainty_score":0.06899905},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5022167,0.05972123,0.25925738,0.086244166,0.0061197244,0.0240519,0.001305848,0.00068906805,0.060393997],"genre_scores_gemma":[0.61206347,0.010446837,0.3520914,0.00473182,0.00044019567,0.017925728,0.0003629201,0.00016776432,0.0017699099],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7273841,0.22037902,0.013109917,0.003068666,0.03437188,0.001686397],"domain_scores_gemma":[0.34519774,0.59112185,0.010299863,0.0072140577,0.04215907,0.0040073968],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28089142,0.0014807654,0.0023471776,0.009401765,0.003257177,0.006074265,0.0038145664,0.0027008476,0.003417289],"category_scores_gemma":[0.5278591,0.0009829768,0.0024315037,0.009015247,0.00426327,0.012533596,0.004843982,0.0034392853,0.0004834498],"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":[0.0048781284,0.0017298029,0.09085082,0.007826833,0.0014596416,0.0002638126,0.03285644,0.0015040566,0.0009042845,0.025207428,0.007265576,0.8252531],"study_design_scores_gemma":[0.0030148895,0.020490807,0.5238384,0.029268915,0.0026765175,0.0020124956,0.21014968,0.049233105,0.004148584,0.104606204,0.04876715,0.0017932679],"about_ca_topic_score_codex":0.012523196,"about_ca_topic_score_gemma":0.020932673,"teacher_disagreement_score":0.28089142,"about_ca_system_score_codex":0.010030981,"about_ca_system_score_gemma":0.0130761685,"threshold_uncertainty_score":0.8867889},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75535816,0.0065879663,0.10935105,0.032879487,0.0016087693,0.00585139,0.00057265116,0.00016479084,0.087625824],"genre_scores_gemma":[0.9774016,0.00085698674,0.016994283,0.0013850278,0.00010618783,0.0024264783,0.000050426926,0.00010123937,0.00067772967],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.46454096,0.4729676,0.02032278,0.008368967,0.027056817,0.00674285],"domain_scores_gemma":[0.28006977,0.673278,0.01668197,0.011206207,0.015154135,0.0036099472],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33336136,0.00067086914,0.0014689071,0.004425526,0.006457579,0.01435672,0.002620196,0.0025416368,0.004684045],"category_scores_gemma":[0.54978395,0.0014999841,0.001194614,0.0035126435,0.016565353,0.00809898,0.011649557,0.003396617,0.00051103235],"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":[0.0014976946,0.00027311879,0.030407049,0.0034697603,0.0002837836,0.0008606452,0.78210163,0.00080017635,0.004903255,0.0798847,0.0012539176,0.09426418],"study_design_scores_gemma":[0.0010629793,0.002024582,0.05950115,0.013792487,0.0006513578,0.0010620663,0.7648943,0.004371252,0.008487562,0.09962268,0.044108175,0.0004214817],"about_ca_topic_score_codex":0.0064535546,"about_ca_topic_score_gemma":0.006990046,"teacher_disagreement_score":0.6666386,"about_ca_system_score_codex":0.014301273,"about_ca_system_score_gemma":0.015045851,"threshold_uncertainty_score":0.8220841},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026373477,0.6697032,0.04900449,0.22557858,0.010056181,0.00021063267,0.00049932644,0.0002829635,0.04202732],"genre_scores_gemma":[0.07587754,0.7744505,0.06124549,0.022932332,0.0074338336,0.00058351306,0.0006709532,0.00021913784,0.056586817],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960299,0.0013267914,0.00038464268,0.00028602843,0.0018181393,0.00015457942],"domain_scores_gemma":[0.97851926,0.013016218,0.0010122235,0.00041400362,0.0064781574,0.0005600766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007697541,0.0006998862,0.0007748108,0.0063921595,0.0021098615,0.0049474128,0.0015749916,0.0036101476,0.014143747],"category_scores_gemma":[0.021735774,0.0007867867,0.000398831,0.00552081,0.0045942715,0.0112255225,0.0028480103,0.0039153034,0.0054630763],"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":[0.000087894405,0.00006863265,0.0018725886,0.0012488462,0.00004161506,0.0001640007,0.0028804257,0.00025179217,0.00035938923,0.06618816,0.5333721,0.39346457],"study_design_scores_gemma":[0.00011010622,0.00012755943,0.013288659,0.004165637,0.00014715601,0.00065056205,0.005565701,0.0009813269,0.0019707254,0.16104086,0.81178904,0.00016273811],"about_ca_topic_score_codex":0.022831846,"about_ca_topic_score_gemma":0.040490087,"teacher_disagreement_score":0.022831846,"about_ca_system_score_codex":0.0029959069,"about_ca_system_score_gemma":0.005145061,"threshold_uncertainty_score":0.04731548},"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":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038423676,0.057599563,0.24642394,0.57916087,0.010863776,0.004833442,0.00022361506,0.0005671109,0.061904002],"genre_scores_gemma":[0.703957,0.023160039,0.19815774,0.060712043,0.0023339032,0.006739933,0.00014153065,0.00052123575,0.004276526],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3935691,0.5407359,0.013459781,0.006453588,0.040577207,0.005204373],"domain_scores_gemma":[0.3076421,0.59082115,0.017785238,0.024871923,0.048303686,0.010575876],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.54299206,0.0012666585,0.002872804,0.006230934,0.009208282,0.028373308,0.0063013565,0.008170901,0.0036923091],"category_scores_gemma":[0.5337839,0.0010108193,0.0024351983,0.00531189,0.052844364,0.03226676,0.020652005,0.021317858,0.0007930717],"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":[0.00027376812,0.0005069746,0.0051516066,0.011740951,0.000261775,0.00020249735,0.093481116,0.0023809273,0.00047452172,0.2836366,0.020193249,0.58169603],"study_design_scores_gemma":[0.0004093297,0.0016082446,0.011842933,0.08450728,0.0005028799,0.00048688598,0.092544,0.005573271,0.0035742554,0.4341466,0.36436558,0.00043866507],"about_ca_topic_score_codex":0.009917916,"about_ca_topic_score_gemma":0.012539009,"teacher_disagreement_score":0.45700794,"about_ca_system_score_codex":0.04251753,"about_ca_system_score_gemma":0.09339535,"threshold_uncertainty_score":0.56357217},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2698563,0.0013141468,0.48934188,0.017343165,0.00010017782,0.0004999599,0.00023514134,0.00032449383,0.22098479],"genre_scores_gemma":[0.92381746,0.00041043104,0.07087593,0.00013032136,0.000011864452,0.00032799316,0.0000706064,0.00005195308,0.0043034093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9894365,0.008246542,0.00025799384,0.0005258764,0.0011869097,0.00034620886],"domain_scores_gemma":[0.9589748,0.03342824,0.0016284271,0.002563618,0.0025237524,0.00088117184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00904004,0.000592667,0.00043131807,0.0019292432,0.0022405568,0.007196135,0.0031683876,0.0020963845,0.007435861],"category_scores_gemma":[0.037493955,0.00048172157,0.00060523115,0.0017095422,0.0057201055,0.0062419185,0.00221318,0.0019146447,0.0007913517],"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":[0.00005962274,0.00022950394,0.005844955,0.00012942945,0.000028142313,0.00011501618,0.01728775,0.015381,0.00020020822,0.9219558,0.0013526105,0.037415937],"study_design_scores_gemma":[0.00010126251,0.00023241929,0.0034713186,0.0003063324,0.00006674844,0.00024076477,0.012722495,0.13033769,0.0005988775,0.8249947,0.026879223,0.00004818157],"about_ca_topic_score_codex":0.007102351,"about_ca_topic_score_gemma":0.009598558,"teacher_disagreement_score":0.00904004,"about_ca_system_score_codex":0.0071271085,"about_ca_system_score_gemma":0.006132518,"threshold_uncertainty_score":0.051711023},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013866668,0.23419186,0.0056102187,0.66356725,0.0052341013,0.00013669362,0.0007740855,0.0003083257,0.076310806],"genre_scores_gemma":[0.6060733,0.23706943,0.01592499,0.10608174,0.0039074644,0.0002094548,0.00095537293,0.00044566058,0.02933258],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.90217644,0.016469376,0.005792735,0.0058996174,0.056859553,0.012802253],"domain_scores_gemma":[0.6852447,0.06093368,0.009523741,0.005108213,0.20620489,0.03298481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07149008,0.00057149323,0.001813608,0.008786651,0.0172781,0.025873698,0.0054464997,0.005894024,0.0055014472],"category_scores_gemma":[0.13033913,0.0010936231,0.001491633,0.012979315,0.020737782,0.007422897,0.006970331,0.01076757,0.0005634779],"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":[0.00020519225,0.00014077447,0.012360405,0.0022159854,0.00012515788,0.00026061866,0.0043829987,0.0029230095,0.00036872382,0.32920134,0.22584367,0.42197207],"study_design_scores_gemma":[0.00006869549,0.00012523298,0.04374957,0.0078888,0.00014087064,0.00020065627,0.0070513193,0.0040723714,0.0007040917,0.055915512,0.8796382,0.00044473622],"about_ca_topic_score_codex":0.9802744,"about_ca_topic_score_gemma":0.9812306,"teacher_disagreement_score":0.6917757,"about_ca_system_score_codex":0.3082243,"about_ca_system_score_gemma":0.5616629,"threshold_uncertainty_score":0.8023618},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9742813,0.0012125807,0.0021345501,0.005405467,0.00002177569,0.00009340912,0.0001697102,0.000035816993,0.01664539],"genre_scores_gemma":[0.99275804,0.00048652795,0.0010659166,0.00022062463,0.000006355222,0.000044358756,0.00005881727,0.0000122019155,0.0053470503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9721724,0.014877519,0.001166546,0.0014372796,0.0071236053,0.003222633],"domain_scores_gemma":[0.8212553,0.09451573,0.019228157,0.0059447093,0.047318153,0.011737932],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023640884,0.00031052495,0.00057482865,0.002648909,0.004609874,0.006510876,0.0013240107,0.0009958664,0.0049339756],"category_scores_gemma":[0.064766504,0.0003780172,0.00036895173,0.0039830436,0.0035087764,0.0017418027,0.002493662,0.001572588,0.00051053014],"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":[0.0003293452,0.00031606134,0.7866145,0.00042383277,0.00016596976,0.000760512,0.09328524,0.0023140362,0.0018190814,0.012524775,0.003360202,0.09808643],"study_design_scores_gemma":[0.00003957871,0.00026172047,0.8896944,0.00051696214,0.000105542116,0.00017878604,0.07261019,0.0030960306,0.0009366091,0.0013285812,0.031130869,0.00010083528],"about_ca_topic_score_codex":0.85336685,"about_ca_topic_score_gemma":0.88807124,"teacher_disagreement_score":0.9763591,"about_ca_system_score_codex":0.02818468,"about_ca_system_score_gemma":0.05162567,"threshold_uncertainty_score":0.29499334},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029790353,0.35613677,0.04838993,0.2634225,0.009983225,0.0002134647,0.00029081132,0.00025910695,0.29151398],"genre_scores_gemma":[0.6628987,0.19036634,0.038807046,0.03368633,0.0063521424,0.00036985046,0.00026863962,0.0004917656,0.06675916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9823982,0.008765443,0.0013595787,0.0017321168,0.0047727,0.00097197137],"domain_scores_gemma":[0.90590364,0.0635317,0.0037780064,0.005517366,0.018295767,0.0029734636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034841787,0.00038868087,0.0004695023,0.0066638826,0.0044959523,0.010196981,0.0014906512,0.003329294,0.005558582],"category_scores_gemma":[0.044829924,0.00055401423,0.00035306747,0.004432496,0.020618586,0.008838331,0.005377891,0.0076348293,0.0007908993],"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":[0.00006180116,0.00009406816,0.0030802947,0.0010935104,0.000012309462,0.0001878199,0.0148007665,0.00033292288,0.00050459045,0.52145344,0.032794055,0.42558447],"study_design_scores_gemma":[0.000009665611,0.00008827356,0.006317279,0.0047120065,0.000011817609,0.0005055464,0.0052277097,0.0005125223,0.001570483,0.05422748,0.9267505,0.00006675527],"about_ca_topic_score_codex":0.019356485,"about_ca_topic_score_gemma":0.021960905,"teacher_disagreement_score":0.034841787,"about_ca_system_score_codex":0.018185021,"about_ca_system_score_gemma":0.022514258,"threshold_uncertainty_score":0.18426323},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0118337525,0.005242504,0.08559889,0.85564446,0.0063507515,0.00008285062,0.0001558988,0.00073829596,0.034352675],"genre_scores_gemma":[0.4300304,0.010241804,0.26992986,0.11978391,0.009351667,0.00056594465,0.0003597401,0.002714222,0.15702245],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9739649,0.018465778,0.0009973246,0.0017064238,0.004085752,0.00077970367],"domain_scores_gemma":[0.8999091,0.077507064,0.0026051018,0.0047617825,0.0102935955,0.0049233036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031682003,0.00064505235,0.0011066889,0.0037512411,0.006685808,0.019732317,0.0024518066,0.011244603,0.03871783],"category_scores_gemma":[0.14992473,0.0008595802,0.0008346333,0.0047877138,0.007116962,0.026083741,0.008330022,0.0124136275,0.0059030326],"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":[0.00012394869,0.000087389635,0.0021999127,0.00026827026,0.000050070154,0.00024696824,0.011974473,0.001930128,0.0004942923,0.3512731,0.42357484,0.2077767],"study_design_scores_gemma":[0.000042654116,0.000033150445,0.0015514566,0.000760831,0.000033135082,0.00020809904,0.009305904,0.011152747,0.00080836023,0.56858796,0.4073529,0.00016286096],"about_ca_topic_score_codex":0.010742745,"about_ca_topic_score_gemma":0.025864277,"teacher_disagreement_score":0.03871783,"about_ca_system_score_codex":0.0072921594,"about_ca_system_score_gemma":0.008897215,"threshold_uncertainty_score":0.16755241},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08759931,0.01662403,0.59763575,0.039609324,0.00054073223,0.00017109758,0.00008400754,0.0002007793,0.257535],"genre_scores_gemma":[0.9320958,0.002291355,0.061778445,0.0006545862,0.0002905451,0.00031983442,0.000047060676,0.000065705695,0.0024566455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95215106,0.03930908,0.0014108542,0.0014715134,0.0046199905,0.0010375077],"domain_scores_gemma":[0.88549054,0.10126609,0.003552128,0.0039872117,0.003979967,0.0017239841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03641369,0.0011147966,0.0015407974,0.007929857,0.0060074213,0.019004777,0.0043542753,0.0062407237,0.0038515015],"category_scores_gemma":[0.077085055,0.001047398,0.0017837222,0.0044421735,0.05245237,0.03510879,0.012631828,0.00868411,0.000510059],"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":[0.000011740716,0.000016455468,0.00013752803,0.000058573452,0.0000131608085,0.000057295118,0.005068573,0.0008070038,0.000043250275,0.98988706,0.00013831483,0.0037610119],"study_design_scores_gemma":[0.0000059055756,0.000003865506,0.000025579144,0.000047449037,0.000002857992,0.000019976362,0.00085771707,0.0016046407,0.000021845848,0.99584985,0.0015568509,0.0000034296952],"about_ca_topic_score_codex":0.0011921506,"about_ca_topic_score_gemma":0.00080346013,"teacher_disagreement_score":0.03641369,"about_ca_system_score_codex":0.0072302376,"about_ca_system_score_gemma":0.0032785034,"threshold_uncertainty_score":0.19257629},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8408777,0.025298702,0.0063409605,0.0051853154,0.0004905845,0.00013485248,0.0043034004,0.0001529423,0.117215514],"genre_scores_gemma":[0.9772974,0.005688957,0.002235585,0.0003620793,0.00016373454,0.00011943304,0.0013734804,0.00012352828,0.012635864],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98898274,0.003906357,0.0009622124,0.0012618826,0.0030300438,0.0018567003],"domain_scores_gemma":[0.96942407,0.0108525,0.005579466,0.001805985,0.010869185,0.0014687891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0125460075,0.0007762811,0.0010314028,0.0045847865,0.0019054817,0.00795681,0.00075946783,0.0008416717,0.0107454015],"category_scores_gemma":[0.022068696,0.00033551548,0.001169042,0.009421979,0.0018235502,0.0040620505,0.004510696,0.0017304873,0.0015991454],"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":[0.0010340597,0.00023396811,0.61013174,0.0047590253,0.001104803,0.00066705834,0.15960151,0.00213583,0.0018257209,0.028165815,0.011282002,0.17905845],"study_design_scores_gemma":[0.000018956793,0.0003429041,0.7161818,0.0018990703,0.0006502015,0.00031163706,0.1493907,0.00052219606,0.001490792,0.003875903,0.12522452,0.00009130989],"about_ca_topic_score_codex":0.05141749,"about_ca_topic_score_gemma":0.0617429,"teacher_disagreement_score":0.05141749,"about_ca_system_score_codex":0.003732087,"about_ca_system_score_gemma":0.005834792,"threshold_uncertainty_score":0.10223645},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03144242,0.46256903,0.2784951,0.08942761,0.021749314,0.06797106,0.0076004504,0.0031399091,0.037605014],"genre_scores_gemma":[0.24197856,0.066455066,0.58225757,0.014241671,0.0034329777,0.085695066,0.0016048633,0.00085518503,0.0034790353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.17042376,0.73646015,0.04595796,0.0059269415,0.04020789,0.0010234115],"domain_scores_gemma":[0.15905368,0.7364784,0.04135232,0.029189417,0.03179759,0.0021286444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5713279,0.0049280445,0.010484718,0.017471258,0.0036053858,0.015654234,0.005437723,0.009600978,0.008759044],"category_scores_gemma":[0.77562594,0.0032541642,0.020096874,0.016203282,0.008753151,0.00957015,0.008727165,0.0072310385,0.00083270995],"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":[0.012106144,0.0005478312,0.009364876,0.27433214,0.21404037,0.00058059674,0.007033931,0.010509302,0.0015800215,0.06513683,0.046886224,0.3578818],"study_design_scores_gemma":[0.013757173,0.0060108984,0.0151098315,0.34382328,0.2537829,0.0007425805,0.0027126991,0.01596102,0.009964218,0.13888662,0.1977423,0.0015065578],"about_ca_topic_score_codex":0.005048352,"about_ca_topic_score_gemma":0.008902544,"teacher_disagreement_score":0.42867208,"about_ca_system_score_codex":0.021519661,"about_ca_system_score_gemma":0.031106675,"threshold_uncertainty_score":0.52862906},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055823284,0.8743861,0.019115929,0.06174097,0.00306663,0.00013077632,0.000499922,0.00033769963,0.035139613],"genre_scores_gemma":[0.063404776,0.89488375,0.028765043,0.0020442952,0.0010305058,0.00021443712,0.0002882665,0.00016165845,0.009207306],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99510765,0.0020728046,0.000499163,0.00029166444,0.0017675174,0.0002611697],"domain_scores_gemma":[0.9805917,0.012714108,0.0015449191,0.00065070164,0.0031862303,0.0013124236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0150059,0.0019053048,0.0017105589,0.007900195,0.0046154484,0.015623461,0.0025497358,0.0033832656,0.009149927],"category_scores_gemma":[0.017330205,0.0018163319,0.00081554166,0.011165873,0.0072760815,0.014714462,0.0035179148,0.0060178516,0.004856509],"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":[0.00012908553,0.00006219321,0.0028136692,0.003216825,0.000054696106,0.00013225299,0.017590743,0.0005422814,0.00037539334,0.027282218,0.14174901,0.8060515],"study_design_scores_gemma":[0.00006640356,0.00022416121,0.02374898,0.015868774,0.00034914134,0.0015618039,0.050639857,0.0013693301,0.001937113,0.10879932,0.795166,0.00026917],"about_ca_topic_score_codex":0.05907148,"about_ca_topic_score_gemma":0.10492222,"teacher_disagreement_score":0.05907148,"about_ca_system_score_codex":0.007318256,"about_ca_system_score_gemma":0.013773442,"threshold_uncertainty_score":0.1174553},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9870658,0.005634777,0.0023612007,0.0005022556,0.00003918891,0.00014065576,0.000047912337,0.000016813747,0.0041914517],"genre_scores_gemma":[0.9988544,0.0003375328,0.0005788215,0.000031956853,0.000013147978,0.000021322923,0.000023224575,0.0000019151796,0.0001377809],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97124106,0.013964777,0.0039100735,0.0011932808,0.008882768,0.0008081414],"domain_scores_gemma":[0.84334946,0.088245414,0.04228937,0.004682643,0.016710546,0.0047226087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02516152,0.00024460102,0.00064937817,0.002859703,0.0008178876,0.0023659563,0.0005545394,0.0006201808,0.0012494928],"category_scores_gemma":[0.064714044,0.0002096335,0.00077019114,0.0025947269,0.0014448853,0.0011967944,0.0010205752,0.0009330729,0.00008947638],"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":[0.0001862177,0.00041148422,0.9396177,0.00046116646,0.00018029363,0.00006691969,0.0044602174,0.0001544083,0.0002143234,0.0005478418,0.00018752346,0.053511955],"study_design_scores_gemma":[0.000011050868,0.00032073792,0.9940824,0.000386288,0.00009731773,0.00014809295,0.0025991458,0.00042085425,0.0002739221,0.0003509024,0.0012865546,0.000022673956],"about_ca_topic_score_codex":0.0034567188,"about_ca_topic_score_gemma":0.0032329056,"teacher_disagreement_score":0.02516152,"about_ca_system_score_codex":0.002346242,"about_ca_system_score_gemma":0.0035480994,"threshold_uncertainty_score":0.13306844},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028005641,0.010178108,0.84037787,0.06776292,0.001674701,0.0033287134,0.00020967238,0.00027558656,0.048186865],"genre_scores_gemma":[0.50762826,0.004517096,0.4643979,0.0071885153,0.00067146757,0.011930008,0.00017374256,0.00025738924,0.0032357099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.42818615,0.5117105,0.02081586,0.009351315,0.026997926,0.0029381667],"domain_scores_gemma":[0.34809387,0.56707853,0.023317773,0.03073901,0.027173273,0.0035975503],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.404018,0.0014742266,0.0031886355,0.013585659,0.014371558,0.02830874,0.0054838965,0.0061612204,0.003914143],"category_scores_gemma":[0.42222157,0.0021987183,0.0018766992,0.010328645,0.10237891,0.033925496,0.024124824,0.011260965,0.0005528084],"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":[0.0000804837,0.000024061228,0.00076442596,0.0013708513,0.000045866404,0.00017970616,0.28658813,0.0005006515,0.0003711027,0.68698394,0.0012549736,0.02183571],"study_design_scores_gemma":[0.00006332673,0.000080178244,0.00054833625,0.004194404,0.000046712415,0.00039016345,0.10336627,0.0018301624,0.0005865258,0.8398636,0.048917387,0.00011288876],"about_ca_topic_score_codex":0.0026455969,"about_ca_topic_score_gemma":0.0030622156,"teacher_disagreement_score":0.59598196,"about_ca_system_score_codex":0.021527354,"about_ca_system_score_gemma":0.020712025,"threshold_uncertainty_score":0.7349519},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039338897,0.0027170556,0.00024908266,0.007428583,0.045987867,0.00032635278,0.003733145,0.0010477391,0.9381167],"genre_scores_gemma":[0.0005972157,0.0007048181,0.00007408218,0.0017753275,0.0016844681,0.000034393015,0.0011085352,0.00009519101,0.993926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993673,0.000049885435,0.000027441974,0.00009268541,0.0003451947,0.000117483214],"domain_scores_gemma":[0.99806863,0.00016047864,0.000058144906,0.00014823726,0.0010630764,0.0005013822],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009347653,0.001064743,0.0008623978,0.0013349011,0.0020500673,0.008101038,0.0018357709,0.0032664088,0.7621978],"category_scores_gemma":[0.003517746,0.0004813668,0.000829545,0.0011455232,0.00047987828,0.0023332206,0.001168867,0.0026022273,0.7266365],"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":[0.000028792769,0.000026236397,0.00006937764,0.00007142015,0.0000018861007,0.000020811523,0.000007496487,0.000009342323,0.00007020963,0.0003394104,0.98505706,0.014297899],"study_design_scores_gemma":[0.000012808469,0.000020669153,0.0006686062,0.00014766035,0.0000018281098,0.000021267988,0.000038258142,0.00002209672,0.00006236593,0.00013520142,0.99886477,0.000004474777],"about_ca_topic_score_codex":0.0072987587,"about_ca_topic_score_gemma":0.016754912,"teacher_disagreement_score":0.23780221,"about_ca_system_score_codex":0.0020783471,"about_ca_system_score_gemma":0.0016664427,"threshold_uncertainty_score":0.33919597},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016877813,0.0065996638,0.020537771,0.041921377,0.0011745379,0.0005505326,0.009911067,0.0019270696,0.90050024],"genre_scores_gemma":[0.5066982,0.020646062,0.17728765,0.005942605,0.00044864474,0.00062772434,0.0114879655,0.001010239,0.27585095],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99113256,0.0015648676,0.00021975648,0.00052903936,0.005477772,0.0010759498],"domain_scores_gemma":[0.99189746,0.0009817517,0.0002521585,0.00039846887,0.0053169453,0.0011531449],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007895879,0.0012077717,0.0005885751,0.0063102245,0.010827275,0.012061197,0.0024635145,0.0016510552,0.027926102],"category_scores_gemma":[0.017793328,0.0005740996,0.00052699674,0.018338228,0.0027298294,0.003142337,0.002993115,0.0015973329,0.0032611394],"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":[0.00006427225,0.000036839032,0.0054169144,0.0003512551,0.00002434851,0.00012698023,0.0030608715,0.0036132238,0.00036675873,0.21027789,0.43999156,0.33666897],"study_design_scores_gemma":[0.00001315935,0.000027804355,0.010448917,0.0005324439,0.000033186945,0.000052706266,0.0073540104,0.0044537103,0.00055189646,0.024970109,0.9514339,0.00012815582],"about_ca_topic_score_codex":0.9696343,"about_ca_topic_score_gemma":0.98048073,"teacher_disagreement_score":0.9921041,"about_ca_system_score_codex":0.1283045,"about_ca_system_score_gemma":0.19398175,"threshold_uncertainty_score":0.93091863},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030352553,0.06264922,0.089117475,0.49711272,0.0073797796,0.00047149733,0.0006079861,0.00065376353,0.311655],"genre_scores_gemma":[0.79112315,0.041240267,0.039279543,0.021338465,0.003629179,0.0011642342,0.00042870585,0.0007056561,0.101090714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.88011247,0.09356699,0.0038541039,0.00433486,0.016265536,0.0018659424],"domain_scores_gemma":[0.67972517,0.25327218,0.0070815166,0.020034077,0.03350116,0.006385886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12910707,0.0010258562,0.00096244266,0.0038733813,0.008386923,0.0326769,0.0026662543,0.0077081216,0.011215598],"category_scores_gemma":[0.1751924,0.0009896717,0.00078477553,0.0051655397,0.036353085,0.036613468,0.0096575245,0.0129891895,0.0029610388],"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":[0.00023653789,0.0000649184,0.0031361112,0.0011837947,0.000040794675,0.00032414592,0.12376175,0.0005116171,0.00054572045,0.6331704,0.06799746,0.16902679],"study_design_scores_gemma":[0.000069509864,0.00017389793,0.0021792557,0.0036774771,0.000024272931,0.00044238498,0.06114661,0.0004999749,0.00091611873,0.1093023,0.8214781,0.00008998068],"about_ca_topic_score_codex":0.031565547,"about_ca_topic_score_gemma":0.024016244,"teacher_disagreement_score":0.12910707,"about_ca_system_score_codex":0.019559063,"about_ca_system_score_gemma":0.034752235,"threshold_uncertainty_score":0.6827916},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027269043,0.001989986,0.0020443841,0.9072338,0.004493919,0.0002673778,0.00029681696,0.00019574746,0.056209054],"genre_scores_gemma":[0.23229726,0.0020501043,0.0051057083,0.61138755,0.0020455178,0.0008823071,0.00047972996,0.0003387034,0.1454131],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9698896,0.008630974,0.0010323887,0.0027644483,0.0047038533,0.012978802],"domain_scores_gemma":[0.9319612,0.010134519,0.0024485353,0.002314288,0.0069385385,0.046202958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022170547,0.0008434597,0.0007902334,0.0016437529,0.04823639,0.026989134,0.008532059,0.0328558,0.04524483],"category_scores_gemma":[0.039738566,0.0012414284,0.0012790693,0.003446214,0.014087815,0.02308195,0.038472172,0.022522261,0.0030268375],"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":[0.00011650812,0.00041186117,0.012930094,0.00024720732,0.000054250442,0.0018870627,0.024145178,0.0013284199,0.0007300115,0.22634165,0.67290664,0.058901157],"study_design_scores_gemma":[0.00009204476,0.00017244031,0.008244897,0.00073303416,0.000026256208,0.0002744597,0.03170884,0.0014507358,0.0002617514,0.030449199,0.92647433,0.00011205816],"about_ca_topic_score_codex":0.5475758,"about_ca_topic_score_gemma":0.66959864,"teacher_disagreement_score":0.5475758,"about_ca_system_score_codex":0.072591014,"about_ca_system_score_gemma":0.20228595,"threshold_uncertainty_score":0.9101773},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051624916,0.009882019,0.70122284,0.05426154,0.0012204212,0.018227428,0.00023444234,0.001781195,0.16154519],"genre_scores_gemma":[0.31697217,0.0068242177,0.65386164,0.0043407534,0.00027638054,0.011626218,0.00017869059,0.0003800472,0.005539981],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75454056,0.21684015,0.0067739333,0.0042052525,0.01486577,0.0027743806],"domain_scores_gemma":[0.7475864,0.18210033,0.009118676,0.021254422,0.030296937,0.009643222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20349191,0.001040656,0.0009343574,0.0041564927,0.0036081772,0.012008436,0.0035950884,0.0023819199,0.0063135806],"category_scores_gemma":[0.22391495,0.00073852565,0.0007129544,0.0029750327,0.011916386,0.009247537,0.012691462,0.004069154,0.001953891],"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":[0.00013418292,0.0009535286,0.0037825804,0.003566922,0.000056105117,0.0003476978,0.037386242,0.0012688352,0.00088338123,0.0692603,0.018926678,0.8634336],"study_design_scores_gemma":[0.00049924257,0.0023505187,0.010791807,0.03837007,0.0001972112,0.002078024,0.09393843,0.010224921,0.009632605,0.297894,0.53369075,0.00033248513],"about_ca_topic_score_codex":0.0018353969,"about_ca_topic_score_gemma":0.0024649925,"teacher_disagreement_score":0.20349191,"about_ca_system_score_codex":0.009919845,"about_ca_system_score_gemma":0.027361283,"threshold_uncertainty_score":0.98223627},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98821926,0.0004791358,0.00044997252,0.0035093813,0.00008295886,0.000045410736,0.000034439036,0.000020884385,0.007158475],"genre_scores_gemma":[0.9955723,0.00036647537,0.0002690094,0.0005754785,0.00001619218,0.000022026004,0.000025855323,0.00000923416,0.0031433518],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99056107,0.0057718186,0.00019438198,0.00035679547,0.00085678574,0.0022590926],"domain_scores_gemma":[0.9919288,0.0026699346,0.0007556043,0.0001843572,0.0008966274,0.0035646588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061076037,0.0003333636,0.0004514849,0.00073774805,0.012568563,0.006782151,0.0016020928,0.0017257697,0.0031373699],"category_scores_gemma":[0.01180716,0.000479507,0.00040611057,0.0009723262,0.0071547125,0.0023174745,0.0056679407,0.0038602857,0.00038166775],"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":[0.000105449086,0.00014349556,0.011302974,0.00006493296,0.000007974169,0.00112763,0.972851,0.00006396255,0.0006110906,0.0011865806,0.0025764944,0.009958378],"study_design_scores_gemma":[0.000004971856,0.00006166646,0.0036209144,0.000032703436,0.0000052438,0.00014822616,0.98432964,0.00004239002,0.0001392233,0.00006314131,0.011538759,0.000013073611],"about_ca_topic_score_codex":0.089184985,"about_ca_topic_score_gemma":0.18071048,"teacher_disagreement_score":0.089184985,"about_ca_system_score_codex":0.00939523,"about_ca_system_score_gemma":0.012428637,"threshold_uncertainty_score":0.17733175},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19383098,0.0061282353,0.24728167,0.055748686,0.000607064,0.00089452835,0.00011477446,0.0002170994,0.49517697],"genre_scores_gemma":[0.9811183,0.00042080163,0.016552597,0.0007280466,0.000084071915,0.000098320495,0.000016240258,0.000028016317,0.00095354044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.77591133,0.17904244,0.0059933304,0.005239694,0.029340195,0.0044729197],"domain_scores_gemma":[0.6437319,0.29281074,0.020743605,0.014064765,0.024324015,0.0043251053],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11897355,0.00072653947,0.0013043905,0.008952597,0.007388193,0.023022458,0.0025381213,0.0041001067,0.004495417],"category_scores_gemma":[0.22100055,0.0007243973,0.00085849233,0.0043820473,0.0783371,0.025082124,0.013310086,0.0057293638,0.00033693627],"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":[0.00009596281,0.000091655114,0.0049045277,0.0004253691,0.000061307,0.00025527074,0.04351084,0.0014064871,0.00024904392,0.9062387,0.002382814,0.040378105],"study_design_scores_gemma":[0.00003025347,0.00009619659,0.0030130867,0.0010817666,0.000051699444,0.00020084284,0.024141664,0.003951899,0.00076759886,0.94861424,0.017980402,0.000070349335],"about_ca_topic_score_codex":0.0042620194,"about_ca_topic_score_gemma":0.003921961,"teacher_disagreement_score":0.88102645,"about_ca_system_score_codex":0.010921066,"about_ca_system_score_gemma":0.012150626,"threshold_uncertainty_score":0.6291998},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6083973,0.017926734,0.0029587427,0.0588627,0.0006152463,0.0007843522,0.0025840413,0.00015391503,0.30771697],"genre_scores_gemma":[0.8220285,0.008274732,0.0016674954,0.000995959,0.00006573763,0.00023381927,0.0004916818,0.00005788857,0.16618414],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9979309,0.00045759827,0.00015453629,0.0001946598,0.00065321464,0.00060911744],"domain_scores_gemma":[0.9937238,0.0025990435,0.0006710847,0.00038450642,0.0016336341,0.0009880156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025673136,0.00025282978,0.00029647673,0.0022563685,0.020182725,0.003187737,0.0010161328,0.0010583703,0.00781955],"category_scores_gemma":[0.0077777095,0.0006702815,0.00018186061,0.0071678497,0.01137047,0.0021606877,0.002906727,0.001299039,0.00039876465],"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":[0.00037052546,0.000057587422,0.03839963,0.0015814553,0.000028276176,0.003919126,0.6514083,0.0012651335,0.0022376853,0.12794131,0.054976963,0.11781395],"study_design_scores_gemma":[0.000010548174,0.000029949993,0.0858506,0.0003579296,0.000015504043,0.00015763982,0.19233926,0.0002009073,0.000712103,0.0037093211,0.71658134,0.00003487379],"about_ca_topic_score_codex":0.9826665,"about_ca_topic_score_gemma":0.99317753,"teacher_disagreement_score":0.19735841,"about_ca_system_score_codex":0.19735841,"about_ca_system_score_gemma":0.17411973,"threshold_uncertainty_score":0.93095046},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013265157,0.032854185,0.0136555545,0.8981491,0.0052384017,0.000060439226,0.00005026276,0.00006830482,0.04859725],"genre_scores_gemma":[0.15692967,0.05459129,0.022089146,0.720001,0.017781474,0.00048346937,0.000115560324,0.00035492395,0.027653502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9208054,0.055322368,0.0042533246,0.0055687237,0.01102724,0.00302298],"domain_scores_gemma":[0.8188778,0.14790791,0.0033724406,0.005558377,0.019496405,0.0047870902],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.084219135,0.000869831,0.001180931,0.004101699,0.009869692,0.020883089,0.0031414127,0.019366087,0.006710461],"category_scores_gemma":[0.07189128,0.0005853496,0.0011785682,0.003934548,0.08236835,0.030499203,0.0106954025,0.025545644,0.001947882],"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":[0.000028348762,0.000029803232,0.0008769906,0.00070628326,0.000008342576,0.00019557752,0.030609509,0.00023091899,0.00015221516,0.741648,0.17959507,0.04591892],"study_design_scores_gemma":[0.000010594913,0.000050884886,0.0012685,0.0038746882,0.000008335384,0.0005122477,0.01764558,0.0003039926,0.00014204893,0.21954216,0.75658864,0.000052266398],"about_ca_topic_score_codex":0.01263326,"about_ca_topic_score_gemma":0.011574313,"teacher_disagreement_score":0.91578084,"about_ca_system_score_codex":0.020147663,"about_ca_system_score_gemma":0.019419806,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1766391,0.00454392,0.5287509,0.032804664,0.0007670104,0.017079223,0.0011092535,0.002233274,0.23607273],"genre_scores_gemma":[0.25143623,0.0007709895,0.7291175,0.0011492132,0.000103599814,0.004515385,0.000304357,0.00010082914,0.012501869],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91428614,0.060801595,0.006607026,0.0017971931,0.015471425,0.0010365845],"domain_scores_gemma":[0.85384476,0.07272822,0.007670899,0.0052494816,0.05805249,0.0024542345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08054817,0.001245876,0.0010403789,0.007842985,0.002780769,0.009720371,0.0020491926,0.0019024515,0.005398153],"category_scores_gemma":[0.1377451,0.0004926205,0.00088806596,0.0032151635,0.0014870514,0.0040347767,0.0029569594,0.0015543441,0.0015737975],"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":[0.00015996616,0.0004992662,0.019079445,0.0013505832,0.000113231654,0.00014017329,0.008858001,0.0034040664,0.0025608041,0.060191073,0.017599484,0.8860439],"study_design_scores_gemma":[0.0008122446,0.005190637,0.09976344,0.010483802,0.0010482755,0.00094342773,0.08316786,0.049391817,0.05725821,0.2529567,0.4381577,0.0008258582],"about_ca_topic_score_codex":0.0057485704,"about_ca_topic_score_gemma":0.011715342,"teacher_disagreement_score":0.08054817,"about_ca_system_score_codex":0.00707685,"about_ca_system_score_gemma":0.009460705,"threshold_uncertainty_score":0.4259845},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079099655,0.050205477,0.059317116,0.17696711,0.0017913469,0.0008708686,0.0014276137,0.0004526853,0.62986815],"genre_scores_gemma":[0.75892526,0.01386337,0.02729292,0.009261123,0.00043103643,0.00070186116,0.00062711124,0.00022890142,0.18866849],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9499664,0.021878973,0.0018676923,0.0028849407,0.019638238,0.0037636927],"domain_scores_gemma":[0.9362925,0.019550333,0.0025800876,0.0025221258,0.035337698,0.003717274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04864294,0.00082848046,0.0010673384,0.0058887457,0.009684474,0.017151041,0.0016634008,0.0029102971,0.010634636],"category_scores_gemma":[0.049754277,0.000562701,0.0005933704,0.006796318,0.016351437,0.004845865,0.0034341475,0.0052344673,0.001144087],"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":[0.00021295629,0.00016583074,0.011288138,0.0009605428,0.00008672689,0.00022917251,0.029870696,0.0016324181,0.0021846003,0.5799371,0.057526674,0.31590512],"study_design_scores_gemma":[0.00005355502,0.00017028567,0.040606964,0.0025248663,0.000049368966,0.00013882812,0.014681383,0.001566744,0.0024197155,0.044572286,0.89302623,0.00018984894],"about_ca_topic_score_codex":0.8677407,"about_ca_topic_score_gemma":0.8653893,"teacher_disagreement_score":0.89294416,"about_ca_system_score_codex":0.10705582,"about_ca_system_score_gemma":0.14671615,"threshold_uncertainty_score":0.77674794},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011902528,0.073212974,0.12855522,0.7388702,0.016681617,0.0032446338,0.00019155054,0.00055284135,0.026788443],"genre_scores_gemma":[0.476422,0.06352623,0.3113306,0.12270093,0.01018653,0.010779428,0.00022390699,0.00054515176,0.0042852648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.42799404,0.47114465,0.04544943,0.013134422,0.036837883,0.005439607],"domain_scores_gemma":[0.1081059,0.77521,0.020838473,0.0636656,0.029341595,0.0028384165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.52165246,0.0023409876,0.0065274206,0.010963785,0.0065098708,0.030520178,0.00818956,0.019741792,0.009571289],"category_scores_gemma":[0.67509276,0.002641987,0.0034926778,0.014834812,0.054432217,0.061209112,0.025839506,0.01852966,0.0024390297],"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":[0.00040703407,0.0004516698,0.0017294618,0.041323386,0.00036727096,0.0009928447,0.094052844,0.0008973202,0.0012215065,0.5219919,0.026674418,0.30989033],"study_design_scores_gemma":[0.0005283044,0.0004337097,0.0016100799,0.061164755,0.00035686756,0.0007336227,0.10443092,0.0042536343,0.0022133205,0.6861592,0.13786812,0.00024741227],"about_ca_topic_score_codex":0.0032064603,"about_ca_topic_score_gemma":0.0029526844,"teacher_disagreement_score":0.52165246,"about_ca_system_score_codex":0.01922616,"about_ca_system_score_gemma":0.08760768,"threshold_uncertainty_score":0.58988774},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041759843,0.010517747,0.35794762,0.11561965,0.0015955897,0.0070949974,0.0005310804,0.00047631763,0.5020409],"genre_scores_gemma":[0.16078012,0.0064953715,0.7869332,0.015598759,0.00041616592,0.01133565,0.00031157778,0.00017057074,0.017958699],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8900497,0.0842351,0.005638878,0.0025833794,0.014604477,0.0028885112],"domain_scores_gemma":[0.93085176,0.04452394,0.0024632062,0.0045457594,0.014253212,0.0033620968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0935935,0.002309583,0.001329332,0.01109135,0.010289772,0.01712651,0.0048577813,0.010169092,0.010360439],"category_scores_gemma":[0.05246415,0.001007048,0.002147926,0.0060821297,0.044879515,0.012296245,0.0092164865,0.0097677205,0.0024413152],"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":[0.000016960947,0.00008773452,0.0003685559,0.0004330105,0.00001275553,0.00012159146,0.0027331035,0.00042757762,0.000118971126,0.96826786,0.010108877,0.017303003],"study_design_scores_gemma":[0.00009073192,0.00033444766,0.0017741972,0.0047119046,0.000033809694,0.0004876047,0.009462904,0.0019484378,0.0004317642,0.6091663,0.37145415,0.00010363838],"about_ca_topic_score_codex":0.041223913,"about_ca_topic_score_gemma":0.032736413,"teacher_disagreement_score":0.0935935,"about_ca_system_score_codex":0.02752282,"about_ca_system_score_gemma":0.049320083,"threshold_uncertainty_score":0.4949757},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00979962,0.13688192,0.3089663,0.0971644,0.02001719,0.009576142,0.0088966,0.0010832879,0.40761456],"genre_scores_gemma":[0.24779804,0.11851404,0.48330495,0.040734,0.0060671195,0.022163318,0.0047167395,0.0005555865,0.07614626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.952675,0.029657343,0.003988022,0.002708797,0.010396276,0.00057446293],"domain_scores_gemma":[0.9036934,0.05729915,0.0057812403,0.010073335,0.02180198,0.0013507903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.038186103,0.0012884537,0.0025911778,0.026649984,0.0026351332,0.010266116,0.004224962,0.0034766954,0.049048364],"category_scores_gemma":[0.08315364,0.0006175499,0.0021418494,0.030891227,0.0035485632,0.013616083,0.006403317,0.0021499884,0.0073524117],"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":[0.00034209897,0.00020131435,0.0011205864,0.03714572,0.00074952416,0.00076695654,0.0031956783,0.00036637532,0.00073048513,0.5095965,0.091868535,0.35391617],"study_design_scores_gemma":[0.00034559704,0.00024353604,0.0015764034,0.024120726,0.00085308275,0.0012369185,0.0054461616,0.001282349,0.00067787815,0.14135335,0.8227708,0.00009316466],"about_ca_topic_score_codex":0.0027028455,"about_ca_topic_score_gemma":0.0064012245,"teacher_disagreement_score":0.9618139,"about_ca_system_score_codex":0.005499097,"about_ca_system_score_gemma":0.013297097,"threshold_uncertainty_score":0.20194983},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055665616,0.00063874986,0.0029213158,0.006831315,0.0033868328,0.0007505232,0.23000568,0.002169584,0.7527394],"genre_scores_gemma":[0.006417661,0.0011606646,0.0033800064,0.003673645,0.0010738072,0.00093661586,0.081658006,0.0015189096,0.9001806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99956244,0.000090117355,0.000042006373,0.0000658563,0.0001995531,0.00003989772],"domain_scores_gemma":[0.98689413,0.005185812,0.00034871005,0.000683115,0.0061982195,0.00069004437],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007009823,0.00064996263,0.0006201232,0.0021994046,0.0007215377,0.0013867451,0.0011915796,0.0012464907,0.8776661],"category_scores_gemma":[0.017924141,0.00028748132,0.00021661964,0.0031638097,0.00021427088,0.0016986099,0.0007741444,0.000938208,0.7153743],"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":[0.000005347963,0.0000065523363,0.00004085318,0.000051306204,4.2863482e-7,0.000009058786,0.00000929369,0.000020750032,0.000009514329,0.0002958881,0.9909046,0.008646392],"study_design_scores_gemma":[0.000025860216,0.000007854868,0.0006972603,0.00014408355,0.0000026808136,0.00005619902,0.00006194634,0.00011377898,0.00007195975,0.0013248256,0.9974868,0.0000066694624],"about_ca_topic_score_codex":0.010019254,"about_ca_topic_score_gemma":0.011660163,"teacher_disagreement_score":0.122333884,"about_ca_system_score_codex":0.0013651113,"about_ca_system_score_gemma":0.0018960915,"threshold_uncertainty_score":0.17449439},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008988124,0.013585565,0.79365027,0.04110232,0.0010400878,0.02057556,0.00031658084,0.00045083003,0.12029066],"genre_scores_gemma":[0.23347798,0.0056541883,0.72992915,0.003707414,0.0006863738,0.019166222,0.00021266115,0.00012326594,0.0070426622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6238613,0.31793898,0.012450863,0.008012263,0.03458869,0.0031478917],"domain_scores_gemma":[0.55112153,0.36268085,0.017358053,0.008204096,0.05562802,0.0050074384],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27610675,0.0030008042,0.0017597066,0.012636794,0.0048107635,0.014471194,0.0053767767,0.0056639593,0.0074974904],"category_scores_gemma":[0.28465083,0.0012603386,0.0023729063,0.0061764186,0.020318603,0.0133507075,0.005400265,0.0051387507,0.0015897456],"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":[0.00040363256,0.00021296025,0.0022817217,0.004446493,0.00033405257,0.0004208241,0.022459904,0.014138788,0.0004366482,0.7607801,0.010393306,0.18369159],"study_design_scores_gemma":[0.0008457686,0.001049667,0.002089223,0.0072808196,0.00036927333,0.00046151862,0.007935519,0.03981244,0.0012022825,0.8049225,0.1337808,0.0002501979],"about_ca_topic_score_codex":0.009458878,"about_ca_topic_score_gemma":0.0066196215,"teacher_disagreement_score":0.7238933,"about_ca_system_score_codex":0.03489076,"about_ca_system_score_gemma":0.053965066,"threshold_uncertainty_score":0.8926893},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8125443,0.003695498,0.014981351,0.02459992,0.0002918414,0.0017452302,0.0001824022,0.00015987626,0.14179963],"genre_scores_gemma":[0.98083204,0.0007097977,0.00868524,0.00057726185,0.0000044970357,0.00032292976,0.000038984963,0.000015993204,0.008813398],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.98462635,0.011602816,0.0004547211,0.00069712766,0.001307434,0.0013114765],"domain_scores_gemma":[0.9963051,0.0017529315,0.00021480305,0.0005090273,0.00079091254,0.00042724435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011830634,0.00035946205,0.0004501205,0.001166144,0.015620594,0.008045211,0.0013375889,0.0019262221,0.0028743818],"category_scores_gemma":[0.0076808194,0.00032559162,0.0003689382,0.0028486063,0.014139234,0.0044526556,0.009337276,0.0013863841,0.0002180293],"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":[0.00026341312,0.00034581227,0.027795788,0.000759977,0.000055873443,0.0026714604,0.4939574,0.0026494265,0.003018182,0.19718061,0.0065874606,0.26471466],"study_design_scores_gemma":[0.000070742426,0.00040762365,0.03146614,0.0009849861,0.000037500606,0.00028210663,0.7924266,0.0017938468,0.0012132903,0.044456523,0.12679154,0.000069065325],"about_ca_topic_score_codex":0.17169157,"about_ca_topic_score_gemma":0.30902278,"teacher_disagreement_score":0.82830846,"about_ca_system_score_codex":0.022471586,"about_ca_system_score_gemma":0.045533672,"threshold_uncertainty_score":0.3413844},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35078752,0.007339277,0.25570792,0.09687124,0.0010542201,0.013368799,0.00015732931,0.0019314804,0.2727822],"genre_scores_gemma":[0.8786912,0.00052127865,0.111828156,0.0018038151,0.000091090296,0.0043826546,0.000028325987,0.00007189444,0.002581591],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6583835,0.31459385,0.00399549,0.0029558435,0.01653305,0.0035383715],"domain_scores_gemma":[0.5752622,0.33776665,0.017597103,0.026644522,0.022960614,0.019768994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21163383,0.00062950206,0.00069281895,0.002013539,0.0067012953,0.011459394,0.0028021792,0.00271124,0.010836057],"category_scores_gemma":[0.21080898,0.0006412037,0.00057458924,0.001557393,0.009910975,0.008270128,0.015191167,0.0037077,0.0010882206],"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":[0.0012935344,0.0044777533,0.00940463,0.0027417182,0.000081183534,0.00016424035,0.04261436,0.003563838,0.0012924777,0.24330322,0.020324223,0.6707388],"study_design_scores_gemma":[0.006738246,0.011381026,0.043086007,0.011693601,0.0003613483,0.00094245584,0.06677875,0.049323466,0.015377829,0.29376388,0.49983317,0.0007203281],"about_ca_topic_score_codex":0.0061842767,"about_ca_topic_score_gemma":0.009608576,"teacher_disagreement_score":0.21163383,"about_ca_system_score_codex":0.017535752,"about_ca_system_score_gemma":0.038067732,"threshold_uncertainty_score":0.97219586},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12667418,0.0039767027,0.82948864,0.0013537374,0.001073853,0.003020232,0.002234685,0.0035061107,0.028671889],"genre_scores_gemma":[0.48720595,0.0005867164,0.50178176,0.0002107153,0.0003270405,0.0027269444,0.0028579317,0.00025114985,0.004051759],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9074576,0.038459327,0.014072453,0.0045144996,0.03359524,0.0019008088],"domain_scores_gemma":[0.7182005,0.16338551,0.026250707,0.0112513015,0.073713414,0.007198619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05229528,0.001169762,0.0016809136,0.01297187,0.0017171704,0.0069656163,0.0020119664,0.0025483621,0.0038091668],"category_scores_gemma":[0.22202225,0.00049229,0.00087271555,0.0062047667,0.0013225594,0.007919274,0.0030235443,0.0013551422,0.0017967006],"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":[0.0012364932,0.0007395894,0.08422364,0.0013954242,0.00045804013,0.0000805045,0.0014576073,0.016832663,0.010198949,0.031848114,0.015948888,0.83558],"study_design_scores_gemma":[0.0007952551,0.0103384685,0.1450448,0.0015061809,0.001159457,0.0009945179,0.00615939,0.5492751,0.06333379,0.1017943,0.119010665,0.0005881696],"about_ca_topic_score_codex":0.0017909305,"about_ca_topic_score_gemma":0.001959437,"teacher_disagreement_score":0.05229528,"about_ca_system_score_codex":0.004046067,"about_ca_system_score_gemma":0.0038065133,"threshold_uncertainty_score":0.27656722},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6263051,0.005495322,0.032339707,0.059338696,0.0002426751,0.00034518365,0.000086452754,0.000060316463,0.27578655],"genre_scores_gemma":[0.99295914,0.0009047493,0.004294306,0.0006731081,0.0000133670055,0.00006157912,0.0000127011,0.000019123045,0.0010619214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9521621,0.038302843,0.00093715556,0.0015199934,0.003775235,0.0033026815],"domain_scores_gemma":[0.912182,0.06936677,0.0062479596,0.0036263657,0.005028307,0.0035486436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04882835,0.00043228603,0.00048546784,0.0030973873,0.0060517653,0.014473452,0.0015525854,0.0028455767,0.0040919604],"category_scores_gemma":[0.08042924,0.0005211731,0.0005605408,0.0028778336,0.031633224,0.008683736,0.007417144,0.005623569,0.00034339348],"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":[0.00014026176,0.00039075277,0.021014499,0.0003384913,0.00008306177,0.0004591142,0.12805974,0.002475418,0.000423945,0.79753536,0.0016417626,0.047437567],"study_design_scores_gemma":[0.000074901975,0.00008507442,0.018013356,0.0006777134,0.000056593137,0.00016111741,0.108572915,0.0026829073,0.0019306259,0.8262369,0.04143441,0.00007350566],"about_ca_topic_score_codex":0.015221006,"about_ca_topic_score_gemma":0.016489923,"teacher_disagreement_score":0.04882835,"about_ca_system_score_codex":0.023570819,"about_ca_system_score_gemma":0.017292518,"threshold_uncertainty_score":0.25823206},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018358157,0.0019756332,0.054334104,0.011453963,0.0071984227,0.08777101,0.39453337,0.008304336,0.43259326],"genre_scores_gemma":[0.008467844,0.0038712015,0.2396478,0.007923665,0.002382331,0.17450488,0.16655324,0.0032491176,0.39340007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9834368,0.0077092205,0.003278427,0.00064123416,0.0045571006,0.00037713902],"domain_scores_gemma":[0.7859686,0.126018,0.005772719,0.0066384436,0.07320796,0.0023943142],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018520664,0.0015733871,0.0017688813,0.008485119,0.0019966462,0.0032336863,0.0026172178,0.0025366081,0.7193244],"category_scores_gemma":[0.14791466,0.0013460149,0.0015095882,0.006997868,0.0007997711,0.0032256946,0.0024404703,0.0032032505,0.35130557],"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":[0.000055611377,0.00005841188,0.000043261804,0.0014080204,0.000005644311,0.000027256063,0.000051557934,0.0001048873,0.000056561254,0.0010971866,0.9621166,0.03497495],"study_design_scores_gemma":[0.00043736043,0.000090931295,0.001495339,0.005275287,0.000033092783,0.00015698517,0.00032224818,0.00062792987,0.00044629315,0.008327257,0.98270977,0.00007733484],"about_ca_topic_score_codex":0.005429386,"about_ca_topic_score_gemma":0.010034547,"teacher_disagreement_score":0.7193244,"about_ca_system_score_codex":0.004508795,"about_ca_system_score_gemma":0.017605519,"threshold_uncertainty_score":0.40034962},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014757459,0.057530526,0.5510967,0.12883708,0.020200897,0.023970162,0.0056267143,0.011033677,0.20022856],"genre_scores_gemma":[0.0073241647,0.04618634,0.73889416,0.031017551,0.0045201085,0.021874864,0.0026081933,0.0033897369,0.14418484],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93169105,0.044339396,0.008988865,0.0014844589,0.012749056,0.0007472327],"domain_scores_gemma":[0.8572329,0.103250094,0.004295066,0.007135674,0.024772737,0.0033135142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069950715,0.0028807782,0.0035981948,0.006305634,0.0024259088,0.011152383,0.0044925157,0.006772881,0.058225945],"category_scores_gemma":[0.12639885,0.0027854578,0.0019795885,0.0055162413,0.0055675376,0.012686164,0.008427486,0.009228708,0.04839416],"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":[0.000067721485,0.00018414437,0.00014506381,0.0024623517,0.000029953084,0.00014085755,0.0025221067,0.0010145332,0.00044625095,0.030795166,0.6734961,0.28869566],"study_design_scores_gemma":[0.000037099322,0.000112842186,0.00033182502,0.0039316574,0.000009837095,0.00024334661,0.001033356,0.0005071793,0.00017458481,0.034873255,0.95867723,0.0000677744],"about_ca_topic_score_codex":0.003857208,"about_ca_topic_score_gemma":0.0067389645,"teacher_disagreement_score":0.069950715,"about_ca_system_score_codex":0.005667266,"about_ca_system_score_gemma":0.01632555,"threshold_uncertainty_score":0.36993915},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004512024,0.000554185,0.9450221,0.0038202242,0.00057782605,0.006889519,0.00022990383,0.00033573376,0.038058463],"genre_scores_gemma":[0.03854055,0.00057699566,0.93539035,0.0012012789,0.00013162175,0.020969702,0.00014403297,0.00015750958,0.0028879566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5275927,0.4343838,0.0077012777,0.008160794,0.020691453,0.0014698763],"domain_scores_gemma":[0.6316673,0.31481907,0.0064231856,0.022273192,0.022056915,0.0027603593],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.266412,0.0019672727,0.002289674,0.011809253,0.0066788285,0.010682216,0.0044523175,0.0042095194,0.014276632],"category_scores_gemma":[0.22350141,0.0013260804,0.0017747916,0.011957667,0.013334787,0.018265579,0.016243443,0.0053137327,0.0026755407],"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":[0.00018882944,0.00033818695,0.0012088456,0.002936743,0.00013450372,0.000259542,0.07067867,0.0015476566,0.0013657748,0.5266152,0.009433855,0.3852922],"study_design_scores_gemma":[0.0003264294,0.00056749786,0.0012647389,0.003764283,0.00010742307,0.0006093487,0.034370974,0.005245553,0.0023382762,0.63346875,0.3177334,0.00020336211],"about_ca_topic_score_codex":0.0015480026,"about_ca_topic_score_gemma":0.0021462343,"teacher_disagreement_score":0.266412,"about_ca_system_score_codex":0.0053533292,"about_ca_system_score_gemma":0.016255401,"threshold_uncertainty_score":0.9046446},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014286868,0.008034566,0.0003016194,0.9879611,0.0021933739,0.000011486671,0.000013003993,0.000012886477,0.0013290556],"genre_scores_gemma":[0.050712157,0.05776198,0.008013088,0.86553127,0.015059306,0.00019021366,0.000068270536,0.00016017321,0.0025035888],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5333592,0.33734092,0.027465485,0.012410481,0.07642996,0.012993832],"domain_scores_gemma":[0.35161418,0.4383,0.024654774,0.025623487,0.10689714,0.05291048],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42641634,0.0017278609,0.004676441,0.010514506,0.024437767,0.06363758,0.006503841,0.041006986,0.005356252],"category_scores_gemma":[0.5157881,0.002266813,0.0019468599,0.013346273,0.11130019,0.04835595,0.012490734,0.05498892,0.00292248],"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":[0.00024541226,0.00022065516,0.0038563123,0.006419209,0.00039882888,0.00048583755,0.012441552,0.0005659562,0.0003560112,0.3444015,0.5253641,0.10524463],"study_design_scores_gemma":[0.00017997289,0.00019555613,0.0029066727,0.0211293,0.00019292976,0.00048173257,0.040676612,0.00076398766,0.00053534185,0.33489567,0.59775645,0.00028574147],"about_ca_topic_score_codex":0.060991004,"about_ca_topic_score_gemma":0.05716577,"teacher_disagreement_score":0.57358366,"about_ca_system_score_codex":0.05095023,"about_ca_system_score_gemma":0.12969784,"threshold_uncertainty_score":0.7073308},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11033369,0.55384344,0.08924191,0.080852784,0.010910722,0.013890861,0.009277387,0.00036791744,0.13128129],"genre_scores_gemma":[0.42880875,0.40199408,0.10132796,0.014507434,0.001674895,0.025641741,0.005220159,0.00048995076,0.020335041],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8825286,0.08505141,0.011100297,0.0048217583,0.015193383,0.0013045152],"domain_scores_gemma":[0.59949917,0.34247655,0.012904713,0.011886599,0.032077216,0.0011557179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.089505166,0.001378177,0.0025051988,0.012734052,0.0037068757,0.012001904,0.0022201038,0.0031380502,0.020040514],"category_scores_gemma":[0.23436202,0.0013219474,0.0033910512,0.016013894,0.0067587504,0.011883239,0.0059742304,0.0049676327,0.0019988006],"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":[0.00076997245,0.00033753808,0.00662159,0.19115473,0.0027455091,0.000856505,0.3217893,0.0015932762,0.00201615,0.12426498,0.029010015,0.31884047],"study_design_scores_gemma":[0.00018675484,0.0005657465,0.0072828634,0.4178048,0.0036308845,0.00044436922,0.108915456,0.0006094977,0.002445242,0.02837013,0.42954686,0.00019733259],"about_ca_topic_score_codex":0.011775568,"about_ca_topic_score_gemma":0.017631574,"teacher_disagreement_score":0.089505166,"about_ca_system_score_codex":0.014615794,"about_ca_system_score_gemma":0.03569069,"threshold_uncertainty_score":0.47335422},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9715826,0.0003050185,0.0023690152,0.0019260509,0.00001795215,0.0004096857,0.00029193528,0.00019963429,0.022898065],"genre_scores_gemma":[0.9897742,0.0004311902,0.0062434836,0.0002382317,0.000024839088,0.00026891148,0.00028530526,0.00003251244,0.002701234],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9909961,0.00550479,0.00047030754,0.0002558054,0.0022912796,0.00048175425],"domain_scores_gemma":[0.9626469,0.027031938,0.0023857148,0.0013726922,0.0047345394,0.0018283555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012242058,0.00020760638,0.00035863539,0.00268642,0.0018457992,0.004182717,0.000530529,0.0007645295,0.011787194],"category_scores_gemma":[0.027844504,0.00026876893,0.00033175648,0.0044142082,0.000994648,0.005644279,0.0033217634,0.0008146674,0.0017199732],"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":[0.00067033654,0.0028072612,0.35635883,0.003548193,0.00006694913,0.002572556,0.21244527,0.0006258949,0.006599072,0.0036190723,0.014717672,0.39596888],"study_design_scores_gemma":[0.00009030712,0.0023943272,0.39020595,0.0014731145,0.00007729609,0.0015864735,0.49428952,0.0014557994,0.0040683574,0.0020151762,0.10224484,0.00009888292],"about_ca_topic_score_codex":0.0011650182,"about_ca_topic_score_gemma":0.0026422685,"teacher_disagreement_score":0.9877579,"about_ca_system_score_codex":0.0014335485,"about_ca_system_score_gemma":0.0027861902,"threshold_uncertainty_score":0.06474298},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01973745,0.016641084,0.06048966,0.5924214,0.007104952,0.00035221622,0.00009211645,0.00011789212,0.3030433],"genre_scores_gemma":[0.84831494,0.008094476,0.035702344,0.07275525,0.0048668045,0.00088264514,0.000094717434,0.00031121133,0.02897766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84216607,0.13075548,0.002637188,0.0041049803,0.018198112,0.0021381758],"domain_scores_gemma":[0.7050767,0.2628883,0.00541187,0.010216669,0.014830764,0.0015757513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10040923,0.0006014818,0.0012105464,0.0025695614,0.006011734,0.019025022,0.0025261946,0.0070749745,0.006318588],"category_scores_gemma":[0.2555495,0.0007013882,0.0007399375,0.0021426568,0.045042045,0.026663445,0.006939893,0.010517413,0.00081168837],"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":[0.000025121482,0.00002312422,0.00017705209,0.000109669316,0.000016969814,0.00007809785,0.006656816,0.00013030734,0.00005472607,0.96701205,0.016630141,0.0090859085],"study_design_scores_gemma":[0.00004446672,0.000056531982,0.00065875205,0.0016172824,0.000033615663,0.000086093605,0.012565251,0.0013686536,0.000664743,0.84102315,0.14183752,0.000043842338],"about_ca_topic_score_codex":0.003517228,"about_ca_topic_score_gemma":0.0023540827,"teacher_disagreement_score":0.8995908,"about_ca_system_score_codex":0.008304209,"about_ca_system_score_gemma":0.007916982,"threshold_uncertainty_score":0.5310211},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013590151,0.029862976,0.05548083,0.6895909,0.0068804147,0.00025894263,0.00012189268,0.00022955994,0.20398434],"genre_scores_gemma":[0.8409914,0.018071724,0.07403109,0.04355382,0.0020441038,0.0014262104,0.00022969057,0.00036936623,0.019282632],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9010856,0.08077519,0.0031076777,0.004594916,0.0066588027,0.0037777212],"domain_scores_gemma":[0.95151204,0.025176449,0.003480869,0.005272842,0.008705942,0.0058518224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05848246,0.0012298666,0.0017919051,0.004245417,0.011897653,0.028820053,0.0058557843,0.0069033448,0.004853144],"category_scores_gemma":[0.06275224,0.00054935925,0.0014194166,0.005271438,0.08049377,0.063345954,0.015658893,0.0136923175,0.0011596582],"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":[0.000018404267,0.000047666254,0.0010727649,0.00029937027,0.00001839837,0.00017159122,0.046313386,0.00012851243,0.00007709846,0.9061889,0.013455229,0.032208793],"study_design_scores_gemma":[0.000012576108,0.000039730636,0.0007914368,0.0015181195,0.000015121511,0.00026539672,0.0972985,0.0003274875,0.0001133963,0.7241836,0.17538531,0.000049312963],"about_ca_topic_score_codex":0.0076435087,"about_ca_topic_score_gemma":0.0066868183,"teacher_disagreement_score":0.05848246,"about_ca_system_score_codex":0.013861003,"about_ca_system_score_gemma":0.016638922,"threshold_uncertainty_score":0.30928844},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068327256,0.016566813,0.011692326,0.32052907,0.0046645883,0.001123482,0.0035335158,0.00077527313,0.57278764],"genre_scores_gemma":[0.5256223,0.0063433894,0.016993212,0.01240388,0.0004556603,0.00043775668,0.0009538866,0.00032317534,0.43646675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930467,0.0011596241,0.00016613437,0.00061120774,0.0027645528,0.0022518563],"domain_scores_gemma":[0.96164906,0.0026827878,0.0007486612,0.0012477306,0.014130458,0.019541252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004585283,0.00050839,0.0006252519,0.0025188997,0.020475727,0.010123724,0.0024157336,0.0048360513,0.04509727],"category_scores_gemma":[0.017700937,0.00065328425,0.00072218507,0.0030109931,0.006109193,0.0038695084,0.006404264,0.004482751,0.003850223],"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":[0.00018667748,0.00028902947,0.017566603,0.00037704044,0.000027450007,0.00046067958,0.00517448,0.0010085801,0.00042436636,0.17316835,0.5998202,0.20149653],"study_design_scores_gemma":[0.00007359787,0.00006642644,0.041447237,0.00074739044,0.000017773711,0.0001997827,0.009585773,0.0010101807,0.00053548825,0.02188016,0.92434967,0.00008658429],"about_ca_topic_score_codex":0.96261775,"about_ca_topic_score_gemma":0.99069256,"teacher_disagreement_score":0.8918321,"about_ca_system_score_codex":0.10816791,"about_ca_system_score_gemma":0.38603717,"threshold_uncertainty_score":0.7848168},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052580256,0.0734467,0.052300163,0.6638751,0.006667165,0.0003785168,0.000027188114,0.00027675825,0.19777045],"genre_scores_gemma":[0.6341994,0.03496795,0.04826209,0.23502651,0.011558977,0.0011215911,0.00003733118,0.00068873947,0.03413727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.79946434,0.1638618,0.0050437544,0.005963729,0.019932553,0.005733898],"domain_scores_gemma":[0.8879837,0.090696715,0.0019259921,0.0049232123,0.009777391,0.004693042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13352321,0.0013420153,0.0024138761,0.00966168,0.019466765,0.04881411,0.003785887,0.015344276,0.004931263],"category_scores_gemma":[0.099836975,0.0012345521,0.0016066381,0.005755227,0.12496544,0.052797873,0.018247036,0.021569261,0.0009867526],"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":[0.00003816187,0.000070611786,0.00033248524,0.00040382435,0.000024880144,0.00022818708,0.0710141,0.00016940178,0.000106651525,0.85994196,0.03362108,0.034048695],"study_design_scores_gemma":[0.000042460517,0.000062405124,0.00026911375,0.0022957902,0.000019783578,0.00026230526,0.04802468,0.00077258394,0.0001453967,0.6853811,0.26266477,0.000059546703],"about_ca_topic_score_codex":0.009607579,"about_ca_topic_score_gemma":0.0060414374,"teacher_disagreement_score":0.13352321,"about_ca_system_score_codex":0.034559328,"about_ca_system_score_gemma":0.026675643,"threshold_uncertainty_score":0.70614666},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3032286,0.008271389,0.19826654,0.023950875,0.0021225594,0.00043699658,0.0003046136,0.0005214658,0.46289703],"genre_scores_gemma":[0.9537909,0.0007382997,0.031461082,0.0003313255,0.00016816144,0.00008560796,0.000033930282,0.000032820844,0.013357882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810517,0.00083646533,0.00013976952,0.0002726104,0.00045913836,0.0001867261],"domain_scores_gemma":[0.9959253,0.0016671793,0.00044983265,0.0005265031,0.0010364953,0.00039468284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027961961,0.00025342635,0.00018051117,0.0016005656,0.0016157359,0.0067735678,0.00068582065,0.0011086653,0.0042482344],"category_scores_gemma":[0.0059297737,0.00017721782,0.00031732206,0.0013746624,0.004870197,0.0022175764,0.0022992548,0.0011831659,0.00042139852],"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":[0.00010062288,0.00007795119,0.01592712,0.0002819176,0.000031133095,0.0007397383,0.0026844745,0.005732089,0.0019362835,0.77534384,0.008837565,0.18830726],"study_design_scores_gemma":[0.00011033006,0.00078362145,0.11689914,0.0010613187,0.00010943576,0.0025352607,0.0068346984,0.08854846,0.008443086,0.4079485,0.36652908,0.00019713264],"about_ca_topic_score_codex":0.009402422,"about_ca_topic_score_gemma":0.008042529,"teacher_disagreement_score":0.009402422,"about_ca_system_score_codex":0.006129636,"about_ca_system_score_gemma":0.0063528935,"threshold_uncertainty_score":0.044473827},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08101485,0.0770849,0.0029958664,0.6762573,0.0013695959,0.00022562273,0.0005701335,0.00008522009,0.1603965],"genre_scores_gemma":[0.8470422,0.07327461,0.0046893144,0.060518067,0.0005249965,0.00018722468,0.00039532426,0.00021272754,0.013155584],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.93105334,0.023400024,0.004260152,0.00323174,0.027867176,0.010187589],"domain_scores_gemma":[0.7509924,0.11445294,0.0067076273,0.004374638,0.09506801,0.028404463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08719219,0.00060429604,0.0011623645,0.0074910005,0.029192327,0.026583968,0.0058127027,0.0066941543,0.005265151],"category_scores_gemma":[0.14086922,0.001165253,0.00091318216,0.023362273,0.027740212,0.00800179,0.0076710233,0.013649676,0.0003391354],"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":[0.00046232934,0.00038797376,0.022225326,0.0030800346,0.00034484998,0.0022580049,0.3230377,0.0024667396,0.00063752424,0.31301492,0.16880909,0.16327552],"study_design_scores_gemma":[0.000100148965,0.000098345845,0.029094653,0.003505315,0.000114840084,0.0004265183,0.13034283,0.0008555895,0.00045294996,0.01999086,0.8147127,0.00030530823],"about_ca_topic_score_codex":0.9868693,"about_ca_topic_score_gemma":0.98693335,"teacher_disagreement_score":0.7231164,"about_ca_system_score_codex":0.27688357,"about_ca_system_score_gemma":0.32845885,"threshold_uncertainty_score":0.8387126},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8701831,0.0025911203,0.0826143,0.005041927,0.00031997668,0.010128589,0.00034113904,0.00066779205,0.028111894],"genre_scores_gemma":[0.91416395,0.0012186985,0.07380412,0.0007914805,0.00015207488,0.0038878329,0.0002807312,0.00014246696,0.0055586877],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8520389,0.120779395,0.0050432743,0.0018217443,0.017594818,0.0027217686],"domain_scores_gemma":[0.6489714,0.2618987,0.0133179035,0.0069611375,0.06552865,0.0033222463],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.120477535,0.0009457348,0.0008819805,0.0031069075,0.0018070379,0.005299142,0.0021735737,0.0011937761,0.0016580471],"category_scores_gemma":[0.23180552,0.00057553034,0.0005628008,0.002024419,0.0018714453,0.002654083,0.0025225196,0.0019748886,0.0004355542],"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":[0.0021253482,0.006811473,0.059764702,0.0026439843,0.00009330179,0.00044182624,0.10103748,0.0019602138,0.007099298,0.002648936,0.003325845,0.81204766],"study_design_scores_gemma":[0.0010314793,0.046032008,0.44043067,0.006245095,0.00056919444,0.0023730712,0.30544817,0.029375644,0.08146711,0.009381124,0.076808006,0.00083853723],"about_ca_topic_score_codex":0.004476029,"about_ca_topic_score_gemma":0.007892366,"teacher_disagreement_score":0.87952244,"about_ca_system_score_codex":0.005449787,"about_ca_system_score_gemma":0.0062540546,"threshold_uncertainty_score":0.63715374},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25105467,0.017536422,0.05224811,0.09399542,0.0015557989,0.0013008644,0.001229003,0.0006639984,0.5804157],"genre_scores_gemma":[0.81246173,0.027652133,0.07419082,0.0048864055,0.00007074869,0.00089984614,0.0006758369,0.00017851336,0.07898397],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99828196,0.0009920128,0.00007087645,0.00008406022,0.0002889704,0.00028217223],"domain_scores_gemma":[0.9985071,0.00046314523,0.00005443215,0.000101378624,0.00045202873,0.00042185982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027275342,0.0011691772,0.0004812569,0.0009957223,0.0045215413,0.006435803,0.0018386871,0.00093260006,0.0062345196],"category_scores_gemma":[0.0023031894,0.0004897329,0.0004970983,0.0025153942,0.0037624438,0.0026106753,0.0048691155,0.0021016903,0.0007435647],"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":[0.0002826295,0.00074691547,0.019906534,0.0012707895,0.0002171723,0.0055815806,0.067293316,0.04999512,0.0032062684,0.20136258,0.11856843,0.53156865],"study_design_scores_gemma":[0.00016488697,0.00038923122,0.019742092,0.0026511631,0.00021706978,0.0011600727,0.21898338,0.013833217,0.0022517324,0.092277244,0.6480381,0.00029181363],"about_ca_topic_score_codex":0.6122265,"about_ca_topic_score_gemma":0.86897093,"teacher_disagreement_score":0.3877735,"about_ca_system_score_codex":0.029515957,"about_ca_system_score_gemma":0.04269752,"threshold_uncertainty_score":0.78011435},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19419515,0.014601635,0.016630424,0.39332134,0.0043954384,0.0011212152,0.00076248584,0.00039388245,0.37457845],"genre_scores_gemma":[0.8433982,0.0090414835,0.016985638,0.017542731,0.0002040386,0.00033188832,0.00029980124,0.00019836903,0.11199792],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9746241,0.009173535,0.0010267196,0.0012939435,0.009312254,0.0045693954],"domain_scores_gemma":[0.9292789,0.011960083,0.0015015523,0.002013017,0.032235567,0.023010863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037257075,0.00030940995,0.00032125396,0.0019555031,0.020188803,0.0073765474,0.0026195939,0.0021523067,0.008462339],"category_scores_gemma":[0.045955647,0.00047690186,0.00031949038,0.004317825,0.010349644,0.003870797,0.005922341,0.0040944987,0.0005946788],"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":[0.00022493752,0.00076954416,0.021852223,0.000551784,0.000017866723,0.0011560625,0.13606988,0.0012286109,0.00081385433,0.24458592,0.29262948,0.30009985],"study_design_scores_gemma":[0.00006953974,0.00014807934,0.016045291,0.00044188896,0.000012693001,0.0003639553,0.04568359,0.0007466643,0.00068073184,0.0057458994,0.9299415,0.000120226905],"about_ca_topic_score_codex":0.964298,"about_ca_topic_score_gemma":0.9854418,"teacher_disagreement_score":0.9627429,"about_ca_system_score_codex":0.14815925,"about_ca_system_score_gemma":0.37224182,"threshold_uncertainty_score":0.9880145},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595036,0.0006561845,0.001215358,0.0045449864,0.000046315436,0.00014450066,0.0053146407,0.00007540808,0.028498905],"genre_scores_gemma":[0.9965718,0.00022169344,0.00064567797,0.000095110845,0.000008067308,0.000026981732,0.000679758,0.000009212944,0.0017417653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.988049,0.0020684593,0.00053195277,0.0005024875,0.0068955417,0.0019525241],"domain_scores_gemma":[0.97017753,0.004373412,0.003033761,0.0005686425,0.018118452,0.003728143],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0056269555,0.0005243969,0.0004942361,0.0034445191,0.0032241098,0.0060856994,0.0015384686,0.0008618597,0.0016322053],"category_scores_gemma":[0.033244733,0.00021283256,0.00041826742,0.010814198,0.0027395631,0.0016394921,0.0019559732,0.0017276907,0.0003224752],"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":[0.00032958147,0.00036001706,0.86923265,0.0004290226,0.00032607396,0.0001357364,0.0056912717,0.010985682,0.0008083503,0.014135145,0.013399653,0.08416675],"study_design_scores_gemma":[0.000039710812,0.0002196448,0.96180373,0.00028399518,0.0001530303,0.000026331887,0.011711173,0.009833823,0.0020890357,0.002418222,0.0113501325,0.00007109528],"about_ca_topic_score_codex":0.9905427,"about_ca_topic_score_gemma":0.9910591,"teacher_disagreement_score":0.994373,"about_ca_system_score_codex":0.09610874,"about_ca_system_score_gemma":0.22484593,"threshold_uncertainty_score":0.697321},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028831519,0.0025660445,0.010102777,0.94041395,0.005599544,0.00010451478,0.00015547861,0.0006281089,0.037546437],"genre_scores_gemma":[0.27201954,0.017146787,0.13010147,0.4466221,0.0038471383,0.00061237015,0.0009106403,0.0017128097,0.12702714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98388577,0.006236001,0.0004305488,0.0006256248,0.006243737,0.002578277],"domain_scores_gemma":[0.974008,0.0027365943,0.0010690718,0.0012010811,0.007509382,0.013475899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018629389,0.0014352978,0.00089789444,0.0021235289,0.012129148,0.024662567,0.0023678534,0.009611154,0.039208926],"category_scores_gemma":[0.047474504,0.00077239284,0.0010923555,0.002425716,0.012870283,0.02356568,0.011330691,0.022784708,0.015548405],"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":[0.00007535694,0.00020319558,0.0023109498,0.00023938387,0.000044236484,0.00021413258,0.0036424294,0.00043246045,0.000357938,0.078196205,0.7809162,0.13336746],"study_design_scores_gemma":[0.000079400845,0.00019944797,0.0031790535,0.0014530962,0.0000592476,0.00037161852,0.027349904,0.0012630818,0.00075574016,0.14787151,0.81720465,0.00021326177],"about_ca_topic_score_codex":0.10120219,"about_ca_topic_score_gemma":0.1844611,"teacher_disagreement_score":0.10120219,"about_ca_system_score_codex":0.01616921,"about_ca_system_score_gemma":0.09060268,"threshold_uncertainty_score":0.20122623},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06639417,0.00757985,0.2284453,0.14452644,0.0012524794,0.0005096663,0.00017468777,0.00021132304,0.55090606],"genre_scores_gemma":[0.9661865,0.0017058798,0.022144908,0.0024948828,0.00027711326,0.0004177698,0.00005099316,0.00006223343,0.0066597653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9557816,0.034913454,0.0012541219,0.0016499592,0.0041953255,0.0022055905],"domain_scores_gemma":[0.90098345,0.07559327,0.0038179061,0.0052747712,0.011064532,0.0032661124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041458633,0.00088368513,0.00058087654,0.004957188,0.0050615207,0.018028855,0.0020369377,0.0052275,0.007687629],"category_scores_gemma":[0.06174754,0.00068566477,0.00052075746,0.0026631788,0.059706047,0.017366238,0.0115216365,0.0065382738,0.0005711409],"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":[0.000007568898,0.000011677303,0.00029918578,0.000045081084,0.0000028512998,0.000032285665,0.0042784703,0.00044005155,0.000080456295,0.98824126,0.0010942316,0.0054668216],"study_design_scores_gemma":[0.000016593714,0.00002561242,0.0007192267,0.0007522631,0.000011663308,0.00006353661,0.012614057,0.0026464085,0.00064559636,0.91337556,0.06908432,0.000045200828],"about_ca_topic_score_codex":0.009178755,"about_ca_topic_score_gemma":0.004943858,"teacher_disagreement_score":0.9585414,"about_ca_system_score_codex":0.016627043,"about_ca_system_score_gemma":0.015253942,"threshold_uncertainty_score":0.21925682},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97981685,0.00048707848,0.0021866276,0.00066259503,0.000030133582,0.00023408167,0.00011471265,0.000037297905,0.016430624],"genre_scores_gemma":[0.9929767,0.00021237446,0.001487471,0.000033624125,0.0000069984885,0.00015823277,0.000077719174,0.0000065478725,0.005040306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9915308,0.0036268649,0.00052512327,0.00043004536,0.00271073,0.0011764565],"domain_scores_gemma":[0.9460126,0.025393572,0.0061385324,0.0014738555,0.014981531,0.0060000056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01593953,0.00037320366,0.0003540929,0.0023088632,0.0016376013,0.003961,0.0007890294,0.0007660219,0.0063273627],"category_scores_gemma":[0.049080286,0.00027427706,0.00047292816,0.0012142799,0.0017139936,0.0023459385,0.0027796624,0.0013835976,0.0008396063],"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":[0.0016953805,0.0012639423,0.4820115,0.0007965463,0.0000868561,0.00042172876,0.1651908,0.0012791863,0.006227153,0.012165239,0.0029325527,0.32592916],"study_design_scores_gemma":[0.00003786462,0.0014449394,0.8839915,0.00043187485,0.000045279387,0.00014405427,0.08942137,0.000922515,0.0067902575,0.00252987,0.014150567,0.00008999422],"about_ca_topic_score_codex":0.014209388,"about_ca_topic_score_gemma":0.02187266,"teacher_disagreement_score":0.01593953,"about_ca_system_score_codex":0.0052061295,"about_ca_system_score_gemma":0.007561763,"threshold_uncertainty_score":0.0842973},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059012556,0.98565316,0.0024316998,0.0022371965,0.0006983047,0.00008114203,0.000055949437,0.000025695575,0.008226663],"genre_scores_gemma":[0.0027328415,0.9930843,0.002519431,0.0006131833,0.00023516781,0.00008199022,0.00007020295,0.000008294993,0.00065450295],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9914534,0.0034631742,0.0012114209,0.0005279919,0.003122809,0.00022110088],"domain_scores_gemma":[0.96717715,0.025672074,0.0015001023,0.0005442854,0.0047581675,0.0003481842],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008051474,0.0010425613,0.0023101203,0.016772298,0.0015393178,0.003221536,0.0018818688,0.0021521715,0.008545825],"category_scores_gemma":[0.024482638,0.00067814713,0.0011387493,0.021628657,0.0016611449,0.0053616376,0.0017114335,0.0016515448,0.0030717945],"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":[0.000043847238,0.00008609748,0.0005426138,0.039767466,0.0000800163,0.0007663316,0.0015004211,0.00038975396,0.0005065718,0.014663019,0.046193596,0.89546025],"study_design_scores_gemma":[0.000016555434,0.00008093386,0.0023167261,0.08260011,0.00013417508,0.0027352378,0.0020632946,0.00016463023,0.00025850988,0.008721103,0.90086055,0.00004817233],"about_ca_topic_score_codex":0.003423316,"about_ca_topic_score_gemma":0.007666992,"teacher_disagreement_score":0.99194854,"about_ca_system_score_codex":0.0030482507,"about_ca_system_score_gemma":0.0065231975,"threshold_uncertainty_score":0.042580724},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010692881,0.9650979,0.0009554095,0.010648715,0.015039267,0.00009221067,0.00018648093,0.000053211163,0.007819909],"genre_scores_gemma":[0.0028485693,0.9683516,0.0019447196,0.0053979894,0.011669003,0.00014787944,0.00038129886,0.000088157125,0.0091707865],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9721771,0.006530573,0.0045304815,0.0014783071,0.014727123,0.0005563367],"domain_scores_gemma":[0.9090649,0.04749696,0.005974191,0.0027490675,0.03295914,0.0017557607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025421813,0.0014400807,0.0037583853,0.018816704,0.0013506345,0.008398412,0.0026962713,0.003614761,0.021347344],"category_scores_gemma":[0.088023424,0.0011657764,0.0014980749,0.022887517,0.0038719927,0.0066568847,0.002056603,0.0028901442,0.01020154],"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":[0.000051094452,0.00004839325,0.00029609114,0.014448389,0.000094931456,0.000036801182,0.00020800195,0.0001786071,0.0002603116,0.009104424,0.6267799,0.34849307],"study_design_scores_gemma":[0.000015675221,0.00003302907,0.0012953363,0.0129206935,0.0000756276,0.00012305494,0.00013761668,0.00008190788,0.00012636633,0.0028213328,0.9823465,0.000022948387],"about_ca_topic_score_codex":0.01030087,"about_ca_topic_score_gemma":0.017553661,"teacher_disagreement_score":0.9745782,"about_ca_system_score_codex":0.011018937,"about_ca_system_score_gemma":0.02049391,"threshold_uncertainty_score":0.13444501},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50142664,0.0016394539,0.3001625,0.011561233,0.00041085383,0.0039721546,0.0029946873,0.0012876036,0.17654483],"genre_scores_gemma":[0.91611755,0.0004452585,0.074003264,0.00044715003,0.00006494851,0.0015329055,0.0014504789,0.00013457079,0.005803888],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98204905,0.0056000412,0.0031735455,0.0010880625,0.0064740074,0.0016152391],"domain_scores_gemma":[0.89200956,0.043788157,0.017426513,0.0089061875,0.031586036,0.0062835924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009047159,0.00055962795,0.0005456538,0.008880995,0.0018892869,0.005238255,0.0016293243,0.00196648,0.0075576524],"category_scores_gemma":[0.07287272,0.00034951788,0.0011747233,0.00749417,0.002625491,0.0075910236,0.0049829907,0.0023283625,0.0021850846],"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":[0.00037164328,0.0007126462,0.5056314,0.0016366651,0.00013889428,0.0009812922,0.026684951,0.0032235994,0.003521211,0.13467623,0.010599543,0.31182194],"study_design_scores_gemma":[0.00015652226,0.0020552138,0.51945394,0.0025079243,0.00028224968,0.009144843,0.063124545,0.03810813,0.005204702,0.1913718,0.16829225,0.00029790335],"about_ca_topic_score_codex":0.0050099446,"about_ca_topic_score_gemma":0.0062252646,"teacher_disagreement_score":0.009047159,"about_ca_system_score_codex":0.0042549525,"about_ca_system_score_gemma":0.008276371,"threshold_uncertainty_score":0.047846556},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87380975,0.0028451013,0.000998009,0.049687177,0.0002468698,0.0001252343,0.00004045376,0.000030817333,0.07221656],"genre_scores_gemma":[0.98187476,0.0025916174,0.0005944578,0.0026688974,0.00003244051,0.00007613026,0.000017601085,0.000028908631,0.012115247],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9904891,0.006269469,0.00024102567,0.0002160095,0.00072688004,0.0020575174],"domain_scores_gemma":[0.99193186,0.0038834827,0.0006954226,0.000283168,0.0010123088,0.0021937848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013616986,0.0003211474,0.000301503,0.0010555424,0.01895323,0.0047489777,0.0007622692,0.0017797016,0.009964157],"category_scores_gemma":[0.011655433,0.00055221224,0.0002019832,0.0018225288,0.0062027383,0.004599222,0.0073277997,0.005201592,0.00087682594],"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":[0.00008332057,0.00023881411,0.010410773,0.00021836767,0.000007835911,0.0021229084,0.9183166,0.00010779419,0.00086091715,0.026760532,0.008845406,0.032026667],"study_design_scores_gemma":[0.00001909982,0.00014800488,0.011284564,0.0006369855,0.000009015518,0.0012943863,0.77059764,0.00020030829,0.0009974265,0.0024946092,0.21229023,0.00002769839],"about_ca_topic_score_codex":0.021526625,"about_ca_topic_score_gemma":0.045824546,"teacher_disagreement_score":0.021526625,"about_ca_system_score_codex":0.0076942015,"about_ca_system_score_gemma":0.021859499,"threshold_uncertainty_score":0.07201433},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001136116,0.0023763378,0.957483,0.008635477,0.004197841,0.01067773,0.0015453114,0.004064376,0.009883718],"genre_scores_gemma":[0.0020843444,0.0010782044,0.96837807,0.0021524238,0.0002872845,0.02135664,0.00024210406,0.0005210712,0.0038998318],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93697405,0.053004134,0.0031229649,0.001463471,0.004816661,0.00061858917],"domain_scores_gemma":[0.78554845,0.18513486,0.004519307,0.013645499,0.0091736,0.001978245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06251479,0.0029188625,0.0017710245,0.0057299095,0.0037566358,0.0040291604,0.0039095203,0.0027432214,0.0238696],"category_scores_gemma":[0.1334283,0.0025131493,0.0016891588,0.005675236,0.007759736,0.0052580233,0.0057741553,0.008751305,0.01299306],"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":[0.00024378597,0.00064434635,0.00053304277,0.011244569,0.00009264207,0.0010922936,0.047773343,0.0011500653,0.00864352,0.07880544,0.3505695,0.49920732],"study_design_scores_gemma":[0.00028962523,0.0003574502,0.0010301553,0.0052273436,0.00005474018,0.0017619905,0.012562392,0.002564077,0.0048007285,0.122552775,0.8484862,0.00031256248],"about_ca_topic_score_codex":0.0013105958,"about_ca_topic_score_gemma":0.0047049616,"teacher_disagreement_score":0.9374852,"about_ca_system_score_codex":0.0018756586,"about_ca_system_score_gemma":0.0050598616,"threshold_uncertainty_score":0.3306138},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029213766,0.0008040577,0.36825025,0.0047160857,0.0017002821,0.006355172,0.011122162,0.00501862,0.5728196],"genre_scores_gemma":[0.30607706,0.001170169,0.39023516,0.0014297299,0.0007637416,0.005868056,0.0215692,0.0024373208,0.27044952],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9635184,0.010452321,0.002591389,0.0051227245,0.016036972,0.0022781324],"domain_scores_gemma":[0.9386466,0.014282747,0.0033526036,0.009726472,0.03200785,0.001983607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024673002,0.0017744015,0.0011914677,0.014165847,0.004392564,0.008780876,0.0038271442,0.0012562117,0.0754072],"category_scores_gemma":[0.082127616,0.00049418403,0.001947582,0.00958452,0.0018503898,0.007694736,0.009211132,0.0018777292,0.020757327],"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":[0.00041805694,0.0002504055,0.018738955,0.00094198994,0.00015111534,0.00023029045,0.006366585,0.0018997488,0.0012261601,0.27578783,0.094099484,0.59988934],"study_design_scores_gemma":[0.000071876384,0.00023207668,0.013243929,0.0009449221,0.00021925315,0.0005229587,0.0088054035,0.012913017,0.0047581117,0.13496923,0.8231684,0.00015075746],"about_ca_topic_score_codex":0.004909842,"about_ca_topic_score_gemma":0.0038344138,"teacher_disagreement_score":0.975327,"about_ca_system_score_codex":0.0047579585,"about_ca_system_score_gemma":0.009984725,"threshold_uncertainty_score":0.25226223},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034710296,0.8985472,0.01637438,0.013854114,0.012067299,0.013906866,0.006856812,0.0005564969,0.037489735],"genre_scores_gemma":[0.006044453,0.91090184,0.035982285,0.0055227065,0.003460012,0.023699937,0.0049797404,0.0003448556,0.00906419],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91798425,0.04285745,0.017208075,0.0039873337,0.016962212,0.0010006548],"domain_scores_gemma":[0.8383413,0.102637105,0.012349746,0.0101720225,0.034616616,0.0018831877],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0537139,0.0025395886,0.0061455253,0.027122406,0.0020955019,0.0075822556,0.0057782354,0.0047358475,0.06032349],"category_scores_gemma":[0.14476442,0.0018145345,0.0054002553,0.027058698,0.003674057,0.008870341,0.005428712,0.005679791,0.025621634],"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":[0.00009010558,0.00005844413,0.00029474578,0.22151943,0.0009263922,0.00015957872,0.0010718826,0.0002842234,0.00028817402,0.016228726,0.24749318,0.5115852],"study_design_scores_gemma":[0.00008795797,0.00007007801,0.00067778415,0.18415406,0.0004497857,0.00024975443,0.0005132488,0.00008906118,0.00016223802,0.009733284,0.80374193,0.000070736496],"about_ca_topic_score_codex":0.0045338497,"about_ca_topic_score_gemma":0.005090826,"teacher_disagreement_score":0.9462861,"about_ca_system_score_codex":0.008388581,"about_ca_system_score_gemma":0.034933835,"threshold_uncertainty_score":0.28406966},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029674353,0.0012379476,0.000085623054,0.025620703,0.97248757,0.000018599263,0.000027674207,0.000036636928,0.00045566462],"genre_scores_gemma":[0.00050354196,0.0012022037,0.00014441973,0.025149545,0.9685874,0.000030409316,0.000027434433,0.000045061533,0.0043100407],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98437446,0.0033108627,0.0023403226,0.0017433714,0.0070975088,0.0011334991],"domain_scores_gemma":[0.9363244,0.021902125,0.004732005,0.001680345,0.02675677,0.008604388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013046008,0.005765932,0.0082379915,0.0071600694,0.00662988,0.013707137,0.0059644263,0.030437369,0.012890944],"category_scores_gemma":[0.06573843,0.001715249,0.00447179,0.003313196,0.005625126,0.0061086635,0.0022938019,0.028241815,0.010083744],"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":[0.000030300584,0.000018512592,0.000022553997,0.00011638198,0.000021714988,0.00009864709,0.000010032405,0.000018797129,0.00003252555,0.00015631483,0.99757594,0.0018982827],"study_design_scores_gemma":[0.00015589107,0.00008370574,0.00063917896,0.0008919365,0.00020942435,0.00051280577,0.00014960006,0.0004327653,0.00025360947,0.0016381413,0.9949713,0.000061631166],"about_ca_topic_score_codex":0.0018516805,"about_ca_topic_score_gemma":0.0057151043,"teacher_disagreement_score":0.030437369,"about_ca_system_score_codex":0.0044114096,"about_ca_system_score_gemma":0.00602952,"threshold_uncertainty_score":0.0689947},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95290816,0.00266562,0.00020172022,0.022755325,0.00008519537,0.000061760446,0.0007513043,0.000031159056,0.02053966],"genre_scores_gemma":[0.99553704,0.0010633733,0.00022375688,0.0008692697,0.00001770678,0.000011151616,0.00022682257,0.0000072265293,0.0020436668],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9920476,0.0005989874,0.00056041725,0.0003602929,0.0036946328,0.002738009],"domain_scores_gemma":[0.94578576,0.0037148541,0.0062319874,0.0006082658,0.034401257,0.009257869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038956127,0.00013842438,0.00035771925,0.0040611867,0.0058674132,0.0042000017,0.0029703039,0.0018105824,0.0033374655],"category_scores_gemma":[0.018894598,0.00036441686,0.0004861481,0.010109762,0.0031600238,0.0020297803,0.002230788,0.0021722647,0.00023433616],"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":[0.000121517165,0.00020487288,0.92957723,0.00014561853,0.00003357029,0.0009827035,0.011312747,0.00050616555,0.00032151604,0.0054768347,0.010393935,0.040923323],"study_design_scores_gemma":[0.000009377788,0.000045795023,0.9587154,0.00014358143,0.000017744158,0.0004883158,0.028706694,0.0008378139,0.00014654269,0.00025419093,0.010600995,0.000033588785],"about_ca_topic_score_codex":0.9872804,"about_ca_topic_score_gemma":0.9934437,"teacher_disagreement_score":0.9470856,"about_ca_system_score_codex":0.052914396,"about_ca_system_score_gemma":0.09051739,"threshold_uncertainty_score":0.38392264},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91260374,0.0023805303,0.009867047,0.002177622,0.0002560495,0.0004835589,0.0002726579,0.00022851312,0.071730204],"genre_scores_gemma":[0.9778438,0.0007177076,0.007710332,0.0003138445,0.000040295294,0.00050590554,0.0002262051,0.000062192164,0.01257972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97632754,0.012055286,0.000963873,0.0018024254,0.0071695903,0.0016812673],"domain_scores_gemma":[0.9175925,0.03707578,0.005173931,0.003680984,0.030658795,0.0058179977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019501168,0.0010827513,0.0009047045,0.0021476184,0.0027626888,0.0054345177,0.0010145627,0.0014712722,0.012525489],"category_scores_gemma":[0.06463345,0.00057164195,0.0013001318,0.0012289082,0.0024962896,0.0041964194,0.0041586366,0.0019674029,0.0026835636],"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":[0.0029570898,0.0032121537,0.21258284,0.003704442,0.0005190629,0.00076972606,0.15400797,0.0028697199,0.014433067,0.012636413,0.009368647,0.5829388],"study_design_scores_gemma":[0.00019874852,0.005006597,0.8205004,0.0020659294,0.0004273398,0.0005211029,0.06592631,0.004813289,0.015048872,0.005952218,0.07924328,0.00029589195],"about_ca_topic_score_codex":0.025297116,"about_ca_topic_score_gemma":0.036910914,"teacher_disagreement_score":0.025297116,"about_ca_system_score_codex":0.0062228343,"about_ca_system_score_gemma":0.01050668,"threshold_uncertainty_score":0.10313326},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021086447,0.029108236,0.1352781,0.31812772,0.0035776624,0.00033950034,0.00020608277,0.00013725087,0.4921389],"genre_scores_gemma":[0.9234975,0.0067071845,0.037817623,0.019090662,0.002161998,0.0004995837,0.00006927065,0.00017265117,0.009983559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7128092,0.22632627,0.0070621185,0.008287271,0.041334853,0.004180312],"domain_scores_gemma":[0.6576813,0.28168708,0.0076138186,0.02238187,0.026715718,0.0039202655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13564959,0.0009395056,0.0017846455,0.0056382073,0.007040419,0.021834057,0.0029869685,0.0059609446,0.0050979895],"category_scores_gemma":[0.21293801,0.00070360926,0.0010614459,0.0038926846,0.116228126,0.021833658,0.012953847,0.010295587,0.0007903806],"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":[0.000018375133,0.000009838239,0.00046051154,0.00010902818,0.000015874593,0.00002733467,0.0014328787,0.00026916215,0.000039651015,0.98364073,0.003337322,0.010639313],"study_design_scores_gemma":[0.000012933749,0.000019505702,0.0003078637,0.00067846733,0.000011523235,0.000048903297,0.0011743358,0.0005626293,0.00020116428,0.9700435,0.026919777,0.000019394316],"about_ca_topic_score_codex":0.006053765,"about_ca_topic_score_gemma":0.0032058337,"teacher_disagreement_score":0.13564959,"about_ca_system_score_codex":0.017437622,"about_ca_system_score_gemma":0.016243039,"threshold_uncertainty_score":0.7173922},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0811191,0.006751296,0.6834691,0.0678099,0.00056488457,0.0016048348,0.00010273723,0.0003338488,0.15824431],"genre_scores_gemma":[0.7510026,0.00257691,0.24079655,0.0025926814,0.00010388998,0.001363567,0.000046793317,0.000068297304,0.001448787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8199651,0.15787454,0.0028735714,0.0018621124,0.015598147,0.0018265331],"domain_scores_gemma":[0.5861359,0.37888893,0.0072342507,0.008033902,0.01724327,0.0024636313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.116573736,0.0009010406,0.0011596892,0.005737048,0.0028090884,0.012908249,0.0022426983,0.0030014464,0.005064511],"category_scores_gemma":[0.14457485,0.0008878934,0.0009687994,0.0031427778,0.018164268,0.009758868,0.0069069806,0.005376157,0.0005258805],"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":[0.00013857741,0.0007052161,0.009061383,0.0033088312,0.0001694712,0.0001404178,0.011083708,0.01151277,0.00059601094,0.7448067,0.0029911506,0.21548578],"study_design_scores_gemma":[0.000191787,0.0009187857,0.0067368015,0.008489477,0.0002576826,0.00026685887,0.013526285,0.03708657,0.003260371,0.89500767,0.034120865,0.00013689102],"about_ca_topic_score_codex":0.0026449831,"about_ca_topic_score_gemma":0.004170395,"teacher_disagreement_score":0.116573736,"about_ca_system_score_codex":0.010992551,"about_ca_system_score_gemma":0.02323632,"threshold_uncertainty_score":0.61650825},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25931278,0.003755733,0.18415695,0.019677365,0.0014935505,0.010831801,0.003766039,0.0025313292,0.5144744],"genre_scores_gemma":[0.8452289,0.0006551847,0.1192299,0.0022032694,0.00007427444,0.0031488403,0.0019063653,0.00033652104,0.027216803],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.80604476,0.070196114,0.010487909,0.004759947,0.09992687,0.008584402],"domain_scores_gemma":[0.5214064,0.030684393,0.0071477783,0.009581304,0.42279094,0.008389266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21257748,0.0011551017,0.0011212747,0.0068652215,0.007067619,0.011989709,0.0039907615,0.0016336542,0.00413858],"category_scores_gemma":[0.22441871,0.0006354731,0.0013762036,0.004113114,0.004764839,0.0035291037,0.0057955687,0.0027523441,0.0014447647],"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":[0.0023251728,0.0011088377,0.10598376,0.0014993965,0.00035742848,0.00023104588,0.009951727,0.016956504,0.005345717,0.1758569,0.16636442,0.51401913],"study_design_scores_gemma":[0.00095154974,0.0033104096,0.35257885,0.0034537376,0.0006151008,0.0003980318,0.014248211,0.084497675,0.02380743,0.042425826,0.472331,0.001382146],"about_ca_topic_score_codex":0.7164484,"about_ca_topic_score_gemma":0.6857876,"teacher_disagreement_score":0.90056485,"about_ca_system_score_codex":0.09943515,"about_ca_system_score_gemma":0.22042163,"threshold_uncertainty_score":0.97103214},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12034929,0.00064931717,0.81082845,0.0032400687,0.00014049794,0.0028588544,0.000594061,0.0011722335,0.060167287],"genre_scores_gemma":[0.7164088,0.00032464648,0.27711537,0.00014627173,0.000041444644,0.0021452974,0.0005292912,0.000058971316,0.0032300279],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858905,0.007905437,0.0009626192,0.0010721904,0.003539575,0.0006296137],"domain_scores_gemma":[0.98054355,0.009759073,0.0013781458,0.0010079839,0.0067114113,0.0005997921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013997381,0.0008566044,0.0007775568,0.0030564114,0.0011676302,0.004802664,0.0016459258,0.0011364801,0.0033282437],"category_scores_gemma":[0.024513291,0.00042204818,0.001263847,0.001814627,0.0013449052,0.005856173,0.0016356433,0.0013062921,0.0005572137],"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":[0.00047224946,0.0011963423,0.058381565,0.0012396859,0.000273878,0.00032609134,0.0076908804,0.14197516,0.0028982162,0.3196459,0.011842722,0.45405725],"study_design_scores_gemma":[0.00020546744,0.0012710001,0.040997017,0.0011984817,0.0002773825,0.00028122033,0.007838911,0.81306404,0.004017193,0.100390635,0.03024087,0.00021781803],"about_ca_topic_score_codex":0.008533125,"about_ca_topic_score_gemma":0.0071313446,"teacher_disagreement_score":0.013997381,"about_ca_system_score_codex":0.006881581,"about_ca_system_score_gemma":0.0073592635,"threshold_uncertainty_score":0.07402611},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6101442,0.0020108065,0.17948368,0.026799543,0.0013021156,0.019056961,0.00024658634,0.0006194015,0.16033673],"genre_scores_gemma":[0.8314671,0.0012080554,0.11797382,0.005164587,0.00021406576,0.008267343,0.00016864116,0.00059553515,0.034940876],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.72258365,0.23921779,0.005469476,0.0060867625,0.019430298,0.0072120144],"domain_scores_gemma":[0.8769843,0.07953697,0.0065754745,0.011028169,0.018668154,0.0072069988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.124558106,0.0015325821,0.001203948,0.0040222337,0.018595537,0.012423895,0.0049438905,0.007763904,0.0046428577],"category_scores_gemma":[0.15091504,0.0014932873,0.0016898907,0.0034427976,0.015790725,0.010804817,0.011398301,0.0076076584,0.0012025154],"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":[0.0004450751,0.0032922688,0.009011018,0.0015380599,0.000094296156,0.01485454,0.7889462,0.0020434442,0.0039643655,0.05340023,0.015139275,0.10727118],"study_design_scores_gemma":[0.00028012192,0.0043845763,0.0058220155,0.0035459157,0.00012565267,0.005153686,0.668237,0.0049102204,0.0066314475,0.012918107,0.2876698,0.00032141],"about_ca_topic_score_codex":0.005878265,"about_ca_topic_score_gemma":0.00774425,"teacher_disagreement_score":0.124558106,"about_ca_system_score_codex":0.015281012,"about_ca_system_score_gemma":0.018467471,"threshold_uncertainty_score":0.6587341},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8274332,0.013038968,0.017890474,0.012568727,0.00040238374,0.000345711,0.0006148318,0.00007959334,0.12762614],"genre_scores_gemma":[0.98821867,0.0016385448,0.0038670157,0.0005275001,0.000041927364,0.00018695093,0.00020929404,0.000023361814,0.005286683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.977763,0.010374408,0.0012144753,0.0017453828,0.007188751,0.0017140514],"domain_scores_gemma":[0.92233044,0.027631529,0.0069569806,0.00385421,0.036678776,0.0025480702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0316196,0.00094552943,0.0008406811,0.0049513723,0.0039750854,0.008968252,0.0014610974,0.001004939,0.005022844],"category_scores_gemma":[0.0620302,0.00029614932,0.0006863834,0.0066115963,0.0069562085,0.004286728,0.0038331933,0.0021325245,0.00048293584],"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":[0.0007500762,0.0003510541,0.4568188,0.002026911,0.00066026946,0.00023897497,0.17386442,0.0028321082,0.00245674,0.08977279,0.008378114,0.2618498],"study_design_scores_gemma":[0.000047464076,0.0005161381,0.7454093,0.0030017411,0.00038941758,0.00014041552,0.16515459,0.0034021982,0.002240982,0.017256364,0.06226911,0.00017223769],"about_ca_topic_score_codex":0.47170126,"about_ca_topic_score_gemma":0.5750159,"teacher_disagreement_score":0.97185,"about_ca_system_score_codex":0.02815,"about_ca_system_score_gemma":0.026309533,"threshold_uncertainty_score":0.93791133},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917903,0.0011052106,0.00017164827,0.0005819959,0.00004851971,0.0000668203,0.00082067336,0.000011263793,0.005403587],"genre_scores_gemma":[0.98180455,0.0022421416,0.00048434394,0.0003448389,0.00002366189,0.00009732399,0.0012528873,0.00001408608,0.013736185],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977665,0.00031950237,0.00010167141,0.00014643252,0.0011138921,0.00055202324],"domain_scores_gemma":[0.9876637,0.0005435178,0.0010914161,0.00015171124,0.009286956,0.0012625899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033583543,0.00043013887,0.0004621333,0.0017129685,0.0048730006,0.0028146787,0.00069947843,0.0005021067,0.0023613384],"category_scores_gemma":[0.007712682,0.00021403363,0.00047338815,0.0027484978,0.001393947,0.0005215796,0.0014653249,0.0008182197,0.00035322603],"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":[0.00019011003,0.0000776866,0.87847555,0.00022810747,0.00007788578,0.0002565322,0.06621983,0.0001572193,0.0007729492,0.00034402573,0.0038808957,0.04931909],"study_design_scores_gemma":[0.000005487921,0.00012728134,0.9077254,0.00017609756,0.000045556575,0.00007591622,0.07724098,0.00012990973,0.00036757262,0.00004105697,0.014012943,0.000051760686],"about_ca_topic_score_codex":0.95621204,"about_ca_topic_score_gemma":0.9755916,"teacher_disagreement_score":0.043787956,"about_ca_system_score_codex":0.014468746,"about_ca_system_score_gemma":0.03286171,"threshold_uncertainty_score":0.10497856},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01944935,0.0019054946,0.28344762,0.016453704,0.00071924715,0.0003211912,0.0002548821,0.00047232653,0.67697614],"genre_scores_gemma":[0.84029895,0.0013822526,0.07079425,0.0051555606,0.0005634281,0.0008001264,0.00033833244,0.00041457408,0.0802526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9834831,0.005989563,0.0010274044,0.0047168094,0.0034784912,0.0013047167],"domain_scores_gemma":[0.9748862,0.01071706,0.001938076,0.00770472,0.003971703,0.0007822772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016237516,0.00064753153,0.0010624308,0.0015338893,0.0039920905,0.010104256,0.0028651634,0.0039001023,0.013667901],"category_scores_gemma":[0.02578118,0.0006191959,0.0019926983,0.0013657211,0.029964034,0.008471791,0.005486586,0.0049097855,0.0023417617],"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":[0.0000041186827,0.00000653362,0.00024181753,0.000021329424,0.000008362519,0.000031032327,0.0005910929,0.00061744376,0.00006561998,0.9939413,0.0011381998,0.0033331534],"study_design_scores_gemma":[0.000015000611,0.000008213067,0.00021552577,0.00007182804,0.000009707353,0.00004925571,0.0002501125,0.001942844,0.00016765372,0.95349663,0.043757744,0.00001547349],"about_ca_topic_score_codex":0.01436962,"about_ca_topic_score_gemma":0.006718721,"teacher_disagreement_score":0.016237516,"about_ca_system_score_codex":0.0069362465,"about_ca_system_score_gemma":0.0076078344,"threshold_uncertainty_score":0.08587319},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05392664,0.0049944087,0.15247604,0.07760583,0.0017676926,0.00035025063,0.00015496918,0.0005077887,0.70821637],"genre_scores_gemma":[0.77054864,0.0023782102,0.033596434,0.005575105,0.00032017424,0.00045410907,0.00010749356,0.00044214982,0.18657762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98180526,0.011027157,0.00046783185,0.0023258848,0.0032091944,0.0011646006],"domain_scores_gemma":[0.9862709,0.006332089,0.00091664266,0.0023106176,0.002541395,0.0016283597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016352473,0.0010730604,0.00073884527,0.0020740319,0.010340457,0.016190594,0.0021401553,0.004136776,0.0127388425],"category_scores_gemma":[0.0145852715,0.0004768633,0.00082958053,0.0017518697,0.041738585,0.013895014,0.009666153,0.008429513,0.0025120475],"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":[0.000022513857,0.00002748535,0.00067666976,0.00008868361,0.0000073665137,0.00015009748,0.08238887,0.00016657493,0.0007977622,0.8982635,0.0030882605,0.014322177],"study_design_scores_gemma":[0.00002888505,0.000081971455,0.0020555696,0.00045317534,0.000021510998,0.00038039227,0.058219247,0.0008349263,0.0021808404,0.22542474,0.71025014,0.00006859744],"about_ca_topic_score_codex":0.0426407,"about_ca_topic_score_gemma":0.059731748,"teacher_disagreement_score":0.0426407,"about_ca_system_score_codex":0.018655373,"about_ca_system_score_gemma":0.023195338,"threshold_uncertainty_score":0.13535488},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44431204,0.0022698487,0.4659158,0.0011726482,0.00041028648,0.05169218,0.0008469151,0.00050092663,0.032879353],"genre_scores_gemma":[0.63184273,0.00072895945,0.2848385,0.00043147733,0.00009785292,0.07948984,0.0006624493,0.00013420741,0.0017740899],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4836874,0.4008977,0.04396845,0.009350239,0.058347568,0.00374868],"domain_scores_gemma":[0.32788038,0.5103149,0.0567267,0.04402624,0.05874225,0.0023095151],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3356097,0.0017128437,0.0022991246,0.007973536,0.0030456926,0.005196416,0.004119138,0.0022614745,0.0014418626],"category_scores_gemma":[0.59191567,0.0016521503,0.003798804,0.006375811,0.004405748,0.004813173,0.0061108116,0.004844853,0.0003091204],"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":[0.0019068646,0.004523884,0.31371877,0.005030744,0.0036620337,0.0001627863,0.04220565,0.011827061,0.0025642102,0.022461368,0.0021027545,0.589834],"study_design_scores_gemma":[0.001579514,0.035844862,0.7469174,0.009709987,0.0035313854,0.0008476667,0.033890586,0.052457295,0.024183754,0.05577536,0.03415513,0.0011071071],"about_ca_topic_score_codex":0.005605187,"about_ca_topic_score_gemma":0.0078088474,"teacher_disagreement_score":0.3356097,"about_ca_system_score_codex":0.0067669014,"about_ca_system_score_gemma":0.008064013,"threshold_uncertainty_score":0.8193115},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008282812,0.18339904,0.19035901,0.16564175,0.04475592,0.18176477,0.021591455,0.0026849583,0.20152023],"genre_scores_gemma":[0.15252702,0.073787205,0.4497152,0.03173918,0.0059982804,0.22613169,0.010589892,0.0019757277,0.04753582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.49735817,0.32393548,0.10716371,0.0049874173,0.06257138,0.0039837435],"domain_scores_gemma":[0.3343085,0.36608618,0.04059535,0.038490143,0.2057117,0.014808129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30817,0.0021488664,0.006960971,0.026099583,0.004770434,0.014333559,0.006207793,0.0070714816,0.042188734],"category_scores_gemma":[0.71582115,0.0028411718,0.008141099,0.017880354,0.0055720066,0.012007135,0.013154441,0.01014098,0.008548339],"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":[0.0048726317,0.00043772184,0.0031088674,0.14399877,0.0045409435,0.0001674817,0.0030431289,0.0014632171,0.000637654,0.03180336,0.3332253,0.47270092],"study_design_scores_gemma":[0.004995092,0.0023040387,0.02652132,0.24347432,0.011849537,0.00037954765,0.004671208,0.004157229,0.0034343994,0.041940212,0.6552639,0.0010091687],"about_ca_topic_score_codex":0.02185936,"about_ca_topic_score_gemma":0.0608682,"teacher_disagreement_score":0.30817,"about_ca_system_score_codex":0.02171607,"about_ca_system_score_gemma":0.081203006,"threshold_uncertainty_score":0.8531496},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028055157,0.0020378567,0.0031972248,0.45348808,0.43469158,0.000277929,0.0013374083,0.0007636557,0.10140084],"genre_scores_gemma":[0.03731368,0.0010899311,0.0015403127,0.09238013,0.026667465,0.00021168296,0.00047226547,0.00073821435,0.8395864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741924,0.00049818214,0.00020646633,0.00031605814,0.0011741237,0.0003860035],"domain_scores_gemma":[0.9832895,0.002848485,0.00056046736,0.0008050229,0.01121486,0.0012816398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029161852,0.0005094245,0.00049434684,0.00070787675,0.004438649,0.0054086824,0.0012252097,0.0028062477,0.12214718],"category_scores_gemma":[0.02709484,0.00021159384,0.00043955081,0.00044338367,0.0019795839,0.003515801,0.0021291624,0.009142771,0.05810899],"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":[0.00006135527,0.000017401808,0.00017079417,0.00009259309,0.0000035841103,0.0001278021,0.00072798925,0.000033757748,0.0005379266,0.010460794,0.9775352,0.010230859],"study_design_scores_gemma":[0.0000050758463,0.000026142687,0.00045034182,0.00011006629,0.0000052519454,0.00008433275,0.0011149757,0.00006547635,0.0005769581,0.001961258,0.99558085,0.000019260347],"about_ca_topic_score_codex":0.013647565,"about_ca_topic_score_gemma":0.01235449,"teacher_disagreement_score":0.12214718,"about_ca_system_score_codex":0.0041183988,"about_ca_system_score_gemma":0.003951143,"threshold_uncertainty_score":0.40862298},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005617342,0.5294295,0.11679885,0.108836524,0.0064565064,0.00080850115,0.004026212,0.0015637745,0.22646289],"genre_scores_gemma":[0.12537281,0.59304637,0.11973713,0.009708374,0.0015057194,0.0016448884,0.0028350942,0.0011900563,0.14495954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964573,0.001103118,0.00046453474,0.00018766573,0.0016701177,0.00011721074],"domain_scores_gemma":[0.9659185,0.022387695,0.002084519,0.0010074358,0.00795178,0.00065011135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01217067,0.0011574229,0.00083887024,0.005505025,0.0026321197,0.0066238246,0.0022469372,0.002659363,0.02674139],"category_scores_gemma":[0.04092499,0.0012965229,0.0008566427,0.006239775,0.0041281614,0.011028441,0.0018012476,0.0042776866,0.012122647],"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":[0.000106505184,0.000110256035,0.003933466,0.0020096109,0.000047647187,0.0001229635,0.0022291266,0.0005264684,0.00035405837,0.049575172,0.35715,0.5838347],"study_design_scores_gemma":[0.00007716641,0.00015388524,0.014457015,0.008926075,0.00025453934,0.0005934126,0.003155869,0.00072743394,0.0021491684,0.11312045,0.8562163,0.0001686804],"about_ca_topic_score_codex":0.022567656,"about_ca_topic_score_gemma":0.050575487,"teacher_disagreement_score":0.02674139,"about_ca_system_score_codex":0.0029867839,"about_ca_system_score_gemma":0.005799691,"threshold_uncertainty_score":0.08945882},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000066175904,0.004182538,0.00008533073,0.9870006,0.008420929,0.00000320161,0.0000064406127,0.0000047630388,0.0002301007],"genre_scores_gemma":[0.002096841,0.0033470555,0.0002970706,0.9709581,0.022180513,0.00001649512,0.0000065277573,0.000018324003,0.0010792074],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.979901,0.008081665,0.003181553,0.002295724,0.0055826786,0.0009575013],"domain_scores_gemma":[0.8084923,0.1476465,0.00476916,0.0035051426,0.026107434,0.0094794305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030794088,0.0011685966,0.0035759145,0.0025922144,0.00554737,0.0084502,0.0041570747,0.05965403,0.005989319],"category_scores_gemma":[0.16254571,0.0016218718,0.0016966366,0.0033550619,0.016756736,0.011693165,0.005228911,0.09225755,0.0033615476],"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":[0.00006512824,0.000033146982,0.0004219899,0.00020132051,0.000043538777,0.00034170868,0.0006562221,0.000077767414,0.000067885274,0.0068382192,0.97545004,0.015803095],"study_design_scores_gemma":[0.0001970156,0.00009439192,0.0024085818,0.002360541,0.00014276207,0.0028520601,0.0039565186,0.0005457603,0.00023140019,0.039745066,0.94714487,0.0003210842],"about_ca_topic_score_codex":0.01271788,"about_ca_topic_score_gemma":0.019083228,"teacher_disagreement_score":0.05965403,"about_ca_system_score_codex":0.010098506,"about_ca_system_score_gemma":0.010164624,"threshold_uncertainty_score":0.16285664},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001969657,0.45775408,0.09620761,0.12357604,0.25647885,0.0035781567,0.002342297,0.0011976701,0.05866836],"genre_scores_gemma":[0.0074602994,0.47115713,0.1563224,0.06641684,0.15720259,0.011427352,0.0029132112,0.0013381334,0.125762],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9689033,0.015747547,0.005497516,0.0015731718,0.007829717,0.00044877507],"domain_scores_gemma":[0.8567856,0.099640094,0.005122373,0.005870551,0.029796999,0.0027844443],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028791558,0.002809174,0.0028377092,0.0127028255,0.0017576421,0.0047610053,0.0035940532,0.005628004,0.06332197],"category_scores_gemma":[0.1213134,0.0019745699,0.003071025,0.007558851,0.005211026,0.0059886468,0.003760698,0.0101503655,0.046043262],"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":[0.00009995231,0.000050341827,0.00006263087,0.011447563,0.000079421865,0.00014592393,0.00023918571,0.00038620346,0.00043151755,0.021697538,0.7341255,0.23123424],"study_design_scores_gemma":[0.000031101164,0.000085813386,0.00028638387,0.010633205,0.00003022941,0.00029907745,0.00010601663,0.00022259806,0.00014973886,0.0439107,0.94418067,0.0000645156],"about_ca_topic_score_codex":0.0017976826,"about_ca_topic_score_gemma":0.0025856416,"teacher_disagreement_score":0.97120845,"about_ca_system_score_codex":0.0047282237,"about_ca_system_score_gemma":0.009031454,"threshold_uncertainty_score":0.21183312},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0216171,0.030882103,0.2182924,0.011052457,0.002128458,0.011284606,0.0038055847,0.00093029265,0.700007],"genre_scores_gemma":[0.3340629,0.055226747,0.49806997,0.003894169,0.0010501995,0.018565936,0.003025124,0.00085529755,0.08524975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.913908,0.060059175,0.003567931,0.001956224,0.019570325,0.0009384253],"domain_scores_gemma":[0.852337,0.121298954,0.0071462,0.0065617533,0.011420853,0.0012352167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05725687,0.001640929,0.0025280253,0.0050973366,0.0008696756,0.00741254,0.0017127565,0.0016417423,0.033754],"category_scores_gemma":[0.1768291,0.0005363168,0.0017194501,0.0041100113,0.0029020098,0.0052551134,0.0038857684,0.0019930254,0.0040585934],"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":[0.0005754662,0.000709939,0.002665203,0.0058112266,0.00044546725,0.00003153597,0.0006257484,0.004884118,0.0003281113,0.1572845,0.01807035,0.80856836],"study_design_scores_gemma":[0.0013404959,0.003575467,0.027824795,0.036979802,0.0016623185,0.00028840685,0.004010406,0.029612524,0.011844976,0.46923575,0.41336378,0.00026126427],"about_ca_topic_score_codex":0.0039092028,"about_ca_topic_score_gemma":0.0032150843,"teacher_disagreement_score":0.05725687,"about_ca_system_score_codex":0.0069976468,"about_ca_system_score_gemma":0.011339021,"threshold_uncertainty_score":0.30280685},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33048722,0.025128923,0.028588714,0.111734144,0.0023479203,0.0006145019,0.0034956876,0.000903934,0.49669892],"genre_scores_gemma":[0.5709553,0.00737084,0.012155311,0.0023972269,0.00014091872,0.00013906778,0.0008506473,0.00014602255,0.40584472],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990236,0.0029564702,0.00042188916,0.0010592135,0.004206032,0.0011203551],"domain_scores_gemma":[0.95810455,0.006902442,0.0015803982,0.0012689384,0.026919076,0.0052245664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011719076,0.00048247154,0.00043840293,0.0023956867,0.009739999,0.008023751,0.0011721825,0.0014178711,0.022050098],"category_scores_gemma":[0.022639433,0.00036830478,0.00040797878,0.0036217216,0.0042640213,0.0022742178,0.0024402332,0.002258205,0.001935846],"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":[0.00042105975,0.0002730318,0.05400112,0.0010805483,0.00012084792,0.0011149867,0.088505246,0.0040724785,0.007849882,0.19463481,0.1720356,0.47589043],"study_design_scores_gemma":[0.000025195697,0.00011903949,0.07485725,0.0005099952,0.000036647918,0.00016417191,0.025558205,0.0013447199,0.0028353017,0.0021324325,0.89230484,0.0001121837],"about_ca_topic_score_codex":0.96917677,"about_ca_topic_score_gemma":0.9798181,"teacher_disagreement_score":0.98828095,"about_ca_system_score_codex":0.07856904,"about_ca_system_score_gemma":0.14523922,"threshold_uncertainty_score":0.57006097},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8825498,0.0024821332,0.019643106,0.0056265597,0.000613229,0.024819687,0.0020373715,0.00014304607,0.062084973],"genre_scores_gemma":[0.8936147,0.0018571352,0.029894184,0.0019879967,0.00007918662,0.031188903,0.00094071194,0.000076331096,0.040360805],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96801925,0.020829601,0.0011980551,0.0016560537,0.0064891996,0.0018077657],"domain_scores_gemma":[0.9425049,0.024997123,0.0022238817,0.0015306205,0.02596475,0.0027788212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041016605,0.0006515547,0.0008760831,0.002304761,0.0057934257,0.0033660494,0.0011351116,0.0010450985,0.007885252],"category_scores_gemma":[0.04572371,0.00056001777,0.0008065846,0.0026605215,0.004971337,0.0020705932,0.002612004,0.0016808809,0.0005730639],"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":[0.001374607,0.0019285189,0.021105947,0.005987157,0.00011341449,0.0005756374,0.73791647,0.0008731848,0.008726417,0.010321841,0.017164676,0.19391212],"study_design_scores_gemma":[0.00073858997,0.005046256,0.18346149,0.009388201,0.00030533373,0.00022572084,0.5435061,0.0015312566,0.010430768,0.0035011577,0.24156564,0.0002995366],"about_ca_topic_score_codex":0.1853339,"about_ca_topic_score_gemma":0.27753347,"teacher_disagreement_score":0.8146661,"about_ca_system_score_codex":0.032825965,"about_ca_system_score_gemma":0.048185427,"threshold_uncertainty_score":0.3685103},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9683583,0.0013853797,0.0004101739,0.010399008,0.00006670188,0.0002008966,0.00029015567,0.00002322537,0.018866181],"genre_scores_gemma":[0.99192154,0.0011444127,0.000543546,0.001809946,0.000023594284,0.00007269298,0.0001303877,0.000017281252,0.00433659],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9854622,0.004889877,0.0007155659,0.0008125946,0.0038232363,0.00429651],"domain_scores_gemma":[0.97065103,0.016920412,0.0024569484,0.0004922377,0.0043522906,0.005127024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012909956,0.000523919,0.00087169535,0.0046000537,0.037477914,0.013086425,0.001661795,0.0042113606,0.005291035],"category_scores_gemma":[0.033289168,0.00076901587,0.0005832866,0.0074780253,0.01111828,0.0034674483,0.007871071,0.0037452765,0.00044834038],"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":[0.000043245396,0.000020576097,0.004941522,0.00009379757,0.0000033929248,0.0005770066,0.9878781,0.00003130946,0.00038368805,0.0011876737,0.001004205,0.0038356404],"study_design_scores_gemma":[0.000008651129,0.000040338964,0.005945401,0.00014760983,0.000008060655,0.0001824364,0.96296084,0.00008688787,0.00020729512,0.00026181998,0.030105447,0.00004526988],"about_ca_topic_score_codex":0.81043243,"about_ca_topic_score_gemma":0.7677305,"teacher_disagreement_score":0.94621474,"about_ca_system_score_codex":0.053785276,"about_ca_system_score_gemma":0.0728734,"threshold_uncertainty_score":0.39024132},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014008403,0.024987252,0.13017963,0.7720021,0.006826298,0.001371602,0.00018296103,0.00047185432,0.04996999],"genre_scores_gemma":[0.48384318,0.023318019,0.4229778,0.060067188,0.0021770138,0.003120369,0.00033308862,0.0005252267,0.0036380596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.46970153,0.46605808,0.01960608,0.012488061,0.024806436,0.0073398906],"domain_scores_gemma":[0.3614527,0.51649904,0.018724622,0.041888855,0.040349636,0.021085106],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5018094,0.0019188557,0.0036890004,0.023223102,0.029400915,0.06300435,0.012254017,0.016907018,0.0060440064],"category_scores_gemma":[0.5072438,0.0030734097,0.0029691109,0.014882129,0.159144,0.07685321,0.07085992,0.025456032,0.0018836377],"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":[0.00026963858,0.00020605871,0.0054190415,0.0055431738,0.00044269586,0.0005721545,0.2333538,0.0018349085,0.00039026624,0.3697983,0.06100748,0.32116255],"study_design_scores_gemma":[0.00013757279,0.0002563966,0.0017165075,0.016761383,0.00017637004,0.00018780152,0.16547047,0.001333117,0.0004497556,0.70376444,0.10954261,0.00020352834],"about_ca_topic_score_codex":0.020069644,"about_ca_topic_score_gemma":0.040379394,"teacher_disagreement_score":0.5018094,"about_ca_system_score_codex":0.0361376,"about_ca_system_score_gemma":0.13602826,"threshold_uncertainty_score":0.6143577},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01557,0.124353185,0.38220644,0.025054991,0.0029056706,0.002855095,0.0017386228,0.002034516,0.44328147],"genre_scores_gemma":[0.10172024,0.11169917,0.74289995,0.0035641512,0.0012373979,0.003103894,0.0011699605,0.0004931209,0.034112073],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9579854,0.02464828,0.003194632,0.00092978135,0.01267095,0.0005709575],"domain_scores_gemma":[0.8465874,0.14096092,0.0028280262,0.0023957286,0.006338669,0.00088925473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04844708,0.0020062479,0.0016179373,0.0073868125,0.001156187,0.012791512,0.0025423684,0.0025275394,0.01588207],"category_scores_gemma":[0.0905566,0.000666051,0.0010502427,0.011159999,0.004318256,0.008682644,0.004893928,0.0037461696,0.0064888136],"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":[0.00007676445,0.00017636058,0.0013740184,0.0029926607,0.000060857976,0.00009707657,0.002074402,0.0038844459,0.00035772007,0.12637426,0.034138687,0.82839274],"study_design_scores_gemma":[0.00009469113,0.00043209962,0.0066465195,0.020466322,0.000116839205,0.0007541084,0.0053769588,0.011958787,0.0022580242,0.40579006,0.54585105,0.0002545734],"about_ca_topic_score_codex":0.002068098,"about_ca_topic_score_gemma":0.0032062377,"teacher_disagreement_score":0.04844708,"about_ca_system_score_codex":0.0037270857,"about_ca_system_score_gemma":0.005348885,"threshold_uncertainty_score":0.25621575},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78742975,0.011147383,0.008362431,0.093508534,0.00093538035,0.00038510293,0.00008670122,0.00036091643,0.09778377],"genre_scores_gemma":[0.9913623,0.0010067822,0.0021391194,0.0021233596,0.000039564522,0.00010729571,0.000019440262,0.00003900726,0.0031632518],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.93658835,0.05475028,0.00093857094,0.0011945349,0.0045174793,0.0020108067],"domain_scores_gemma":[0.9283414,0.041121047,0.0040105563,0.0021162564,0.008566713,0.015844028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0509956,0.00032816757,0.00050557754,0.0023212559,0.007176009,0.010774016,0.0016705729,0.0022865562,0.0023350827],"category_scores_gemma":[0.08772895,0.0004643177,0.0002639123,0.0012767513,0.01111701,0.006428322,0.010208789,0.004657676,0.00048256764],"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":[0.00004796549,0.0003208545,0.08387352,0.00013233368,0.000028288467,0.0003375088,0.7244522,0.000065992244,0.0003164219,0.0060764537,0.011129297,0.17321911],"study_design_scores_gemma":[0.000022054532,0.00030919744,0.06538174,0.00061692076,0.000027972648,0.00046160002,0.8510249,0.00064496446,0.0004699431,0.0065629594,0.07437678,0.00010095149],"about_ca_topic_score_codex":0.012632,"about_ca_topic_score_gemma":0.027487978,"teacher_disagreement_score":0.0509956,"about_ca_system_score_codex":0.0042068837,"about_ca_system_score_gemma":0.011710164,"threshold_uncertainty_score":0.26969373},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001135317,0.21721114,0.15264553,0.49487656,0.10168171,0.0038825893,0.0015107454,0.00039450589,0.026661914],"genre_scores_gemma":[0.057216246,0.1899857,0.35555917,0.275013,0.058551535,0.027732821,0.0016301675,0.00081256795,0.033498857],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.69063044,0.2574018,0.017848209,0.0066764676,0.02597161,0.0014714391],"domain_scores_gemma":[0.49231994,0.3543708,0.011390078,0.057487737,0.07787018,0.006561226],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32026565,0.002014293,0.0035127266,0.00709131,0.0031839951,0.012341801,0.006847717,0.0070223645,0.03624912],"category_scores_gemma":[0.42482406,0.001109983,0.002864217,0.006503844,0.013496847,0.021523928,0.009783714,0.013951459,0.011876578],"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":[0.0011063069,0.0003391251,0.0016777436,0.031620264,0.0008320889,0.00012033926,0.00089846534,0.00038331008,0.00052077393,0.25324282,0.20446368,0.5047951],"study_design_scores_gemma":[0.0005822996,0.0007540271,0.0021908407,0.07771435,0.0010305981,0.0003332751,0.0030317043,0.0015653963,0.0012704305,0.41829357,0.49300742,0.00022604597],"about_ca_topic_score_codex":0.002616858,"about_ca_topic_score_gemma":0.004372995,"teacher_disagreement_score":0.67973435,"about_ca_system_score_codex":0.008970097,"about_ca_system_score_gemma":0.022920689,"threshold_uncertainty_score":0.8382335},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06087147,0.008835799,0.5930356,0.07506555,0.012072835,0.00910849,0.004204303,0.0013096053,0.23549634],"genre_scores_gemma":[0.6622967,0.0027553577,0.25162408,0.02796748,0.003435789,0.02331537,0.0014544259,0.0011502093,0.026000572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7103827,0.20791037,0.010831855,0.018919554,0.049908094,0.0020473658],"domain_scores_gemma":[0.4911073,0.39437512,0.01482833,0.061721344,0.036055997,0.001911833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14481665,0.0011403483,0.0013357893,0.007046855,0.0039884215,0.012414089,0.0032668996,0.0022839296,0.018949507],"category_scores_gemma":[0.4102415,0.00084666297,0.0014493094,0.0065888106,0.024428077,0.010781113,0.012543012,0.0055662077,0.0027289223],"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":[0.00036115682,0.00018355132,0.010419931,0.005000008,0.00024876106,0.00033931618,0.06943469,0.0010794203,0.0020826352,0.6359799,0.031019969,0.24385062],"study_design_scores_gemma":[0.00012693403,0.00066011754,0.010634582,0.0065183053,0.0001248314,0.0005567203,0.04237693,0.0048322845,0.002648313,0.4709635,0.46041298,0.00014446555],"about_ca_topic_score_codex":0.0026877772,"about_ca_topic_score_gemma":0.0019008297,"teacher_disagreement_score":0.14481665,"about_ca_system_score_codex":0.0063001746,"about_ca_system_score_gemma":0.009744102,"threshold_uncertainty_score":0.76587284},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008216442,0.009769479,0.883988,0.0053639384,0.01449937,0.05130191,0.0055617797,0.0032699571,0.018028997],"genre_scores_gemma":[0.061639532,0.0023486423,0.8418075,0.0018291156,0.0011426174,0.08156922,0.0006944361,0.001351583,0.007617337],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7929836,0.14966704,0.020681998,0.011855856,0.023031387,0.001780189],"domain_scores_gemma":[0.6446978,0.28522515,0.011054155,0.03298093,0.024502138,0.0015398001],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.083864994,0.0025602838,0.006155246,0.010506735,0.0034647784,0.0032023736,0.006230034,0.0041804668,0.063741766],"category_scores_gemma":[0.4610067,0.002242724,0.009358843,0.008881776,0.0037031095,0.0037391325,0.0042533996,0.008550497,0.010068115],"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":[0.0062620277,0.00076173444,0.001660126,0.031122012,0.004070328,0.00026455204,0.0012611555,0.0015429426,0.0026995672,0.020768622,0.03590035,0.8936867],"study_design_scores_gemma":[0.014590865,0.012091221,0.023340797,0.043141108,0.03290674,0.0020292548,0.0034405417,0.043324884,0.030771606,0.2687496,0.5244217,0.0011916605],"about_ca_topic_score_codex":0.0015216288,"about_ca_topic_score_gemma":0.002716821,"teacher_disagreement_score":0.916135,"about_ca_system_score_codex":0.00311173,"about_ca_system_score_gemma":0.006033551,"threshold_uncertainty_score":0.4435258},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3946508,0.019594856,0.043707523,0.21029478,0.00196297,0.0004938201,0.00007596645,0.00018251997,0.3290368],"genre_scores_gemma":[0.97722936,0.005688777,0.008998516,0.002796289,0.00018210146,0.0002713979,0.000024838067,0.00005472461,0.0047540264],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.89080846,0.08796644,0.0025934905,0.002901814,0.01046174,0.0052679684],"domain_scores_gemma":[0.91463363,0.06382667,0.0039082253,0.0039393175,0.005767349,0.007924806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085135415,0.0006789989,0.00089019915,0.0030963745,0.02765899,0.06841773,0.0025959625,0.0062339613,0.0040868316],"category_scores_gemma":[0.06096182,0.0006496865,0.0005865546,0.004645136,0.055354845,0.024325639,0.022421809,0.006389295,0.0008278614],"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":[0.00004799814,0.00016213329,0.012186439,0.00067958044,0.000048338712,0.0009004507,0.5954083,0.00042661736,0.00035160707,0.2306109,0.014277632,0.14489993],"study_design_scores_gemma":[0.0000140321,0.0000681156,0.0032137448,0.00078262197,0.000021111295,0.000438746,0.82836604,0.00058539485,0.00025432865,0.06939891,0.09681737,0.0000396295],"about_ca_topic_score_codex":0.007468656,"about_ca_topic_score_gemma":0.011357055,"teacher_disagreement_score":0.085135415,"about_ca_system_score_codex":0.010888622,"about_ca_system_score_gemma":0.029818272,"threshold_uncertainty_score":0.4502445},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0120503325,0.11411879,0.076600194,0.69855607,0.008546335,0.0005570611,0.0009979425,0.00019624566,0.0883769],"genre_scores_gemma":[0.602088,0.054720215,0.12548201,0.16216882,0.03234268,0.00209206,0.0005083454,0.00066674035,0.019931177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.64981836,0.23855129,0.019722806,0.011714462,0.07657389,0.0036191503],"domain_scores_gemma":[0.20343693,0.68437135,0.02097824,0.029049229,0.055438817,0.006725433],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2952029,0.0014892053,0.0051982943,0.012106252,0.007839078,0.029652916,0.008652968,0.009307576,0.014627886],"category_scores_gemma":[0.56739557,0.0018341858,0.0021319392,0.01743068,0.06175066,0.04198267,0.010999452,0.007164424,0.0015829529],"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":[0.0003024203,0.00014953704,0.004751525,0.0024286185,0.0002915472,0.000052542622,0.0020352383,0.0007536385,0.00019635944,0.8455027,0.028423848,0.11511213],"study_design_scores_gemma":[0.00013165605,0.00010147913,0.002029148,0.0014220937,0.00011173312,0.000094597875,0.001106827,0.000803245,0.00027056714,0.9524869,0.041397393,0.00004443462],"about_ca_topic_score_codex":0.021695826,"about_ca_topic_score_gemma":0.027375847,"teacher_disagreement_score":0.7047971,"about_ca_system_score_codex":0.023762599,"about_ca_system_score_gemma":0.031691317,"threshold_uncertainty_score":0.86914027},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057842984,0.84678364,0.0058961054,0.07046028,0.010201532,0.00004996585,0.00060404936,0.00038672876,0.065039285],"genre_scores_gemma":[0.0060431194,0.89755106,0.004672585,0.0041358653,0.002837927,0.00004776978,0.0003980961,0.000203078,0.084110625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898463,0.00020066257,0.000064890875,0.00011522577,0.0005809726,0.000053521166],"domain_scores_gemma":[0.9962054,0.0018861424,0.00024973665,0.00008456732,0.0012727844,0.00030138818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025846998,0.0015289758,0.00089455215,0.0028763344,0.0011318248,0.0038264515,0.0012210946,0.0019054825,0.03099762],"category_scores_gemma":[0.0042991554,0.0008977118,0.00039664702,0.0033622188,0.0011386458,0.006317956,0.0012384646,0.002692065,0.030081438],"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":[0.000028526754,0.000013035139,0.00022755041,0.0007470129,0.0000072225357,0.00003494144,0.00043472555,0.00011187426,0.000090975074,0.003040082,0.7514194,0.24384464],"study_design_scores_gemma":[0.000008565039,0.000014676235,0.0011326876,0.0016713414,0.000021318798,0.00020861295,0.000833495,0.00014527784,0.00030531434,0.004218669,0.9914169,0.000023242503],"about_ca_topic_score_codex":0.027200537,"about_ca_topic_score_gemma":0.08359456,"teacher_disagreement_score":0.03099762,"about_ca_system_score_codex":0.0020145022,"about_ca_system_score_gemma":0.005985766,"threshold_uncertainty_score":0.10369742},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5494615,0.016301218,0.06595605,0.11535546,0.0015316132,0.004103851,0.00024211072,0.00050333276,0.24654487],"genre_scores_gemma":[0.9374199,0.004912679,0.03037633,0.008161482,0.00009973215,0.00077971723,0.00009255217,0.0002010104,0.017956683],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.88782936,0.081553765,0.0026635753,0.002706123,0.015742838,0.00950432],"domain_scores_gemma":[0.89200264,0.057184696,0.0034972283,0.0045241015,0.02813373,0.014657607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07766068,0.00092331826,0.00063439447,0.0029143419,0.047701396,0.009990354,0.0053807055,0.0036509184,0.0044055325],"category_scores_gemma":[0.07836291,0.00066621136,0.00081976294,0.006192482,0.022776056,0.0040029786,0.01076728,0.006151505,0.0005032816],"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":[0.00012564645,0.00059104484,0.010885436,0.0010593623,0.000058514725,0.006788886,0.7646674,0.0021733055,0.001360433,0.03673419,0.03582669,0.13972902],"study_design_scores_gemma":[0.00002836653,0.00017739195,0.00828259,0.0011916289,0.00003853803,0.0021701276,0.6119417,0.001833656,0.0013925601,0.007160468,0.3656259,0.00015705747],"about_ca_topic_score_codex":0.8062072,"about_ca_topic_score_gemma":0.90092486,"teacher_disagreement_score":0.9223393,"about_ca_system_score_codex":0.10244412,"about_ca_system_score_gemma":0.14134398,"threshold_uncertainty_score":0.74328756},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010304127,0.037938077,0.06735589,0.54134536,0.0017056991,0.00011205184,0.000093984585,0.000068314686,0.34107643],"genre_scores_gemma":[0.8279384,0.021216346,0.04123631,0.051167138,0.0026652957,0.00041614735,0.00005340373,0.0001939398,0.05511307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96216846,0.026252123,0.0009324005,0.0014047297,0.007931003,0.0013112639],"domain_scores_gemma":[0.9483115,0.042309366,0.0011216447,0.0012861089,0.0060749603,0.00089646905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041962486,0.0007119285,0.0008045818,0.003216108,0.0066798036,0.015834888,0.0025877098,0.007133597,0.0038431424],"category_scores_gemma":[0.032591052,0.00034630165,0.0005157898,0.0028578462,0.089577235,0.010930108,0.0044528753,0.009526124,0.00052609533],"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":[0.0000051351376,0.000004726584,0.000062423795,0.00005123551,0.0000025242127,0.000021126729,0.002797551,0.00019968224,0.0000251368,0.9876744,0.0034659172,0.0056902077],"study_design_scores_gemma":[0.00001547504,0.000017531069,0.00038112965,0.0005758743,0.000005214213,0.00006686553,0.0050557563,0.0009542596,0.00018964654,0.8634447,0.12926681,0.000026664675],"about_ca_topic_score_codex":0.09047172,"about_ca_topic_score_gemma":0.09825213,"teacher_disagreement_score":0.09047172,"about_ca_system_score_codex":0.03750131,"about_ca_system_score_gemma":0.018098293,"threshold_uncertainty_score":0.27209228},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031988014,0.011764554,0.62352955,0.10995308,0.0013227167,0.0074473387,0.00012161145,0.00045718145,0.21341595],"genre_scores_gemma":[0.55880135,0.0029527845,0.42238414,0.0063040513,0.00031891972,0.004826165,0.00007735299,0.0001222876,0.0042129555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5482283,0.3949724,0.015385639,0.0063284524,0.029711423,0.0053736693],"domain_scores_gemma":[0.7037707,0.20326525,0.009856616,0.011203183,0.06604079,0.0058635054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.37477827,0.0015570794,0.0019699389,0.010791549,0.013884839,0.02329494,0.006419277,0.0056357994,0.0017571904],"category_scores_gemma":[0.1820413,0.0009820202,0.0016356193,0.0052103074,0.05415861,0.01864165,0.019191833,0.009775716,0.0003761933],"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":[0.00006387779,0.00019967076,0.002282284,0.002049425,0.00012185555,0.00026917356,0.109421805,0.0025309497,0.000559381,0.78931844,0.005334386,0.08784875],"study_design_scores_gemma":[0.00011546696,0.000394034,0.0035153257,0.011286922,0.00028306476,0.000423618,0.1280249,0.011120956,0.0018801942,0.6758608,0.16682668,0.00026796458],"about_ca_topic_score_codex":0.025290063,"about_ca_topic_score_gemma":0.027506456,"teacher_disagreement_score":0.37477827,"about_ca_system_score_codex":0.042801093,"about_ca_system_score_gemma":0.07545284,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06721896,0.13609578,0.019948833,0.71868944,0.0026601462,0.0032799183,0.00030028808,0.00016815551,0.05163841],"genre_scores_gemma":[0.8117876,0.09199062,0.05104283,0.03611031,0.0024367122,0.0042473837,0.0002991828,0.000060971477,0.0020243858],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.81705475,0.1347093,0.015420535,0.002018375,0.027607309,0.0031896816],"domain_scores_gemma":[0.3551454,0.5328668,0.0132859275,0.008982779,0.07583314,0.0138860475],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24241006,0.00057825405,0.002133234,0.014215154,0.007725369,0.016891388,0.002232369,0.008007633,0.0045708255],"category_scores_gemma":[0.31488642,0.0009542456,0.0007612598,0.010349292,0.013851313,0.023124574,0.0068872864,0.006038045,0.0007703134],"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":[0.00024763733,0.0014948479,0.024733184,0.038949136,0.00009910335,0.0005446845,0.061027158,0.0011437669,0.0010480706,0.15712397,0.035321373,0.678267],"study_design_scores_gemma":[0.00019021542,0.0022181906,0.02728864,0.1558491,0.00016998644,0.0018261239,0.35981002,0.004048598,0.0015616626,0.1329394,0.31383786,0.00026021505],"about_ca_topic_score_codex":0.002836159,"about_ca_topic_score_gemma":0.003263121,"teacher_disagreement_score":0.9845385,"about_ca_system_score_codex":0.015461476,"about_ca_system_score_gemma":0.045248006,"threshold_uncertainty_score":0.93424326},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68922555,0.0009094466,0.041890237,0.03923155,0.000033522065,0.0005702719,0.0002689132,0.00014558516,0.2277249],"genre_scores_gemma":[0.97606397,0.00036638803,0.019280046,0.0005871387,0.0000063346088,0.00012327051,0.00007755439,0.00003871591,0.0034567227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9790189,0.016563017,0.00035719946,0.0004888954,0.0020583945,0.0015134972],"domain_scores_gemma":[0.940872,0.049093954,0.0015613963,0.0014872196,0.0052116206,0.0017737092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016874861,0.0004971291,0.00043733986,0.0021177782,0.008177461,0.01111069,0.0022792544,0.0015703727,0.0028421406],"category_scores_gemma":[0.037879236,0.0005058224,0.0004610012,0.0031364232,0.008801291,0.0045668636,0.00394302,0.0029034489,0.00024618473],"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":[0.0003367959,0.000976778,0.052012417,0.0005050268,0.00008483986,0.0028825146,0.26420993,0.048343826,0.0012262568,0.48586372,0.010034046,0.13352391],"study_design_scores_gemma":[0.00020915898,0.0002639598,0.025758095,0.0009784899,0.00013686717,0.0006141365,0.48396522,0.16431426,0.0020343917,0.23552316,0.08599208,0.00021018808],"about_ca_topic_score_codex":0.6844086,"about_ca_topic_score_gemma":0.7605874,"teacher_disagreement_score":0.3155914,"about_ca_system_score_codex":0.040262587,"about_ca_system_score_gemma":0.056529988,"threshold_uncertainty_score":0.6349},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002410316,0.6479089,0.025669744,0.2134866,0.010453095,0.00042331358,0.0062024416,0.0014994593,0.091946095],"genre_scores_gemma":[0.057461295,0.70897454,0.071439154,0.03268608,0.0046501686,0.00086064066,0.0038760665,0.000991276,0.11906086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762243,0.00067187217,0.00026004572,0.00012147194,0.0012070304,0.00011718598],"domain_scores_gemma":[0.97573143,0.014197152,0.0014978879,0.00044223192,0.0072066085,0.0009246187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009872148,0.0010122943,0.0006556845,0.004558061,0.0025826269,0.006007561,0.0017385812,0.0022239804,0.030783048],"category_scores_gemma":[0.036562823,0.0008782323,0.0005546813,0.0055004847,0.0019177884,0.009078618,0.0016013628,0.005295353,0.020058474],"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":[0.000042094223,0.000017042608,0.00083037623,0.00059148535,0.000013507604,0.000035598798,0.00047799505,0.00013036607,0.00013801467,0.003796642,0.80772495,0.18620189],"study_design_scores_gemma":[0.000049921542,0.00006207743,0.010179359,0.0051856316,0.00013391167,0.000246751,0.0013689635,0.0002870612,0.0008758517,0.02570034,0.9558352,0.000074884665],"about_ca_topic_score_codex":0.04252802,"about_ca_topic_score_gemma":0.12655964,"teacher_disagreement_score":0.04252802,"about_ca_system_score_codex":0.0036403735,"about_ca_system_score_gemma":0.008279593,"threshold_uncertainty_score":0.1029796},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13514106,0.026113879,0.03386168,0.76150423,0.0022590535,0.0031329696,0.00054479,0.00022774762,0.03721452],"genre_scores_gemma":[0.73116183,0.05601188,0.13303068,0.06835948,0.0007852,0.0029777945,0.0005139584,0.00021939402,0.006939653],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8655172,0.1146337,0.0064196284,0.002417387,0.006629116,0.004382917],"domain_scores_gemma":[0.58081275,0.37408108,0.007287163,0.0073770816,0.022409126,0.008032807],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17684902,0.0021445192,0.0026035272,0.010040977,0.015277734,0.034787454,0.00618712,0.012550905,0.004386614],"category_scores_gemma":[0.20297198,0.0016720837,0.0016289218,0.013239918,0.019918216,0.034319445,0.014911889,0.013270941,0.0011285644],"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":[0.0003244336,0.0014047629,0.027038556,0.00569025,0.00016418197,0.010916869,0.5980252,0.0015660624,0.0012835123,0.06473666,0.033370562,0.25547895],"study_design_scores_gemma":[0.0000528974,0.00016609981,0.0033192635,0.0066242814,0.00011308609,0.00088153005,0.8984716,0.00067208795,0.0005303328,0.036036056,0.053024508,0.00010835619],"about_ca_topic_score_codex":0.022541622,"about_ca_topic_score_gemma":0.08414438,"teacher_disagreement_score":0.823151,"about_ca_system_score_codex":0.018258795,"about_ca_system_score_gemma":0.049977947,"threshold_uncertainty_score":0.9352782},"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":"protocol","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0369102,0.058203083,0.41818476,0.00840843,0.0020157162,0.42546096,0.0045212656,0.0007790675,0.045516517],"genre_scores_gemma":[0.13413183,0.013585658,0.40518224,0.0028428459,0.0005196355,0.4398558,0.00097041164,0.00027456688,0.002636967],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.32004634,0.575198,0.052990098,0.0098740505,0.039742637,0.002148885],"domain_scores_gemma":[0.35258475,0.49243024,0.03258153,0.0397882,0.07950201,0.0031131955],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4762647,0.0019273417,0.005152689,0.010642665,0.005092367,0.012814885,0.0055089006,0.002851757,0.01245211],"category_scores_gemma":[0.4864238,0.0017179259,0.0030154136,0.012913864,0.0050148526,0.0061604264,0.0063982774,0.0029793666,0.0020186412],"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":[0.0016846715,0.0022178553,0.008720358,0.07735032,0.0024837048,0.00022382759,0.016175512,0.002059213,0.0009118037,0.038003575,0.010897195,0.839272],"study_design_scores_gemma":[0.005872655,0.0138864275,0.027165964,0.43049353,0.0055817687,0.00079687295,0.051660422,0.024332905,0.010448055,0.1328009,0.2960462,0.00091430626],"about_ca_topic_score_codex":0.0041435277,"about_ca_topic_score_gemma":0.005206942,"teacher_disagreement_score":0.4762647,"about_ca_system_score_codex":0.015879916,"about_ca_system_score_gemma":0.036289513,"threshold_uncertainty_score":0.6458589},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067835576,0.020113427,0.7798128,0.044459812,0.0043174936,0.001040646,0.00010114081,0.00039090565,0.14298022],"genre_scores_gemma":[0.20891389,0.012329604,0.73797244,0.014319569,0.0015831238,0.0023877253,0.00023284297,0.0002990228,0.021961782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82097304,0.14689925,0.0068763383,0.00771652,0.015314711,0.0022200996],"domain_scores_gemma":[0.80777526,0.14847486,0.0053868345,0.023956018,0.01223956,0.0021674435],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10296273,0.0018348527,0.0020193916,0.011129374,0.007578109,0.019470489,0.0063024317,0.008173193,0.008184754],"category_scores_gemma":[0.086158514,0.0012793667,0.0018663496,0.0062647853,0.043830108,0.03617106,0.019374058,0.013241488,0.0020868797],"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":[0.0000142409135,0.000018006409,0.0002434798,0.0003301597,0.00001135716,0.00027009883,0.008926588,0.00032072063,0.00019863715,0.9561196,0.0040091514,0.029537896],"study_design_scores_gemma":[0.000019343826,0.000037755446,0.00013724815,0.0014516914,0.000016288823,0.0010773208,0.0052036373,0.0012913902,0.00045563982,0.5445316,0.44573426,0.000043809738],"about_ca_topic_score_codex":0.0019372128,"about_ca_topic_score_gemma":0.0022400324,"teacher_disagreement_score":0.89703727,"about_ca_system_score_codex":0.00857389,"about_ca_system_score_gemma":0.0072327126,"threshold_uncertainty_score":0.5445255},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006518296,0.003447036,0.7097509,0.021426763,0.0031897568,0.15088736,0.015249251,0.052285936,0.03724474],"genre_scores_gemma":[0.002833166,0.0011311042,0.9420968,0.0028785877,0.00032440413,0.03741836,0.002006915,0.0015741703,0.009736521],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96773815,0.017683974,0.006117141,0.0014683848,0.006004978,0.0009872692],"domain_scores_gemma":[0.80789095,0.116911694,0.006945558,0.008520874,0.051576477,0.008154449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057431296,0.006455227,0.005877003,0.01309126,0.0041317386,0.0066700056,0.0075659114,0.0067031267,0.07736099],"category_scores_gemma":[0.13425617,0.0059709293,0.0032229025,0.0063030263,0.0029555033,0.005582498,0.0045874054,0.011340176,0.08937293],"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":[0.0005254084,0.0033465812,0.0035721266,0.0054967715,0.00032442625,0.001039849,0.0051608933,0.0042245225,0.006778686,0.003585526,0.6242217,0.3417236],"study_design_scores_gemma":[0.002502202,0.0015267767,0.014218284,0.0054485854,0.00039414017,0.0020893468,0.0076426947,0.017906955,0.006251727,0.033578992,0.9074463,0.0009937936],"about_ca_topic_score_codex":0.017215898,"about_ca_topic_score_gemma":0.049010545,"teacher_disagreement_score":0.07736099,"about_ca_system_score_codex":0.0028434587,"about_ca_system_score_gemma":0.019559108,"threshold_uncertainty_score":0.30372936},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7166082,0.005741356,0.13460396,0.027592342,0.0024011263,0.0044864463,0.0027770072,0.00046562747,0.105323896],"genre_scores_gemma":[0.9655254,0.0010239558,0.02355323,0.0027303586,0.00023386611,0.00452173,0.00038216024,0.00010100896,0.0019283175],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6569925,0.26457655,0.019888366,0.0076741367,0.047811087,0.003057238],"domain_scores_gemma":[0.3732545,0.4855524,0.04824416,0.022934262,0.06729997,0.0027147213],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19937822,0.00045455873,0.001081692,0.0042106146,0.0016955102,0.006136702,0.0014465393,0.0008823087,0.004607564],"category_scores_gemma":[0.5100618,0.0004179842,0.0007558089,0.0073032235,0.006388654,0.0066223345,0.0053498666,0.0018378535,0.0012310744],"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":[0.00080577744,0.00044756645,0.32766572,0.0076578613,0.0006020072,0.00037836705,0.2532941,0.000630029,0.0030642208,0.032542806,0.010086518,0.36282513],"study_design_scores_gemma":[0.00011870149,0.0017747204,0.2799819,0.012940638,0.0003443786,0.001082746,0.6003408,0.0053021326,0.004523043,0.037110675,0.056066748,0.0004135228],"about_ca_topic_score_codex":0.0011858586,"about_ca_topic_score_gemma":0.0016619532,"teacher_disagreement_score":0.80062175,"about_ca_system_score_codex":0.0030605318,"about_ca_system_score_gemma":0.004127536,"threshold_uncertainty_score":0.9873092},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028207993,0.004600804,0.0003240297,0.032946613,0.96096945,0.0001475658,0.000073516945,0.00007258157,0.0008372412],"genre_scores_gemma":[0.00056421856,0.004204645,0.00085242087,0.030715583,0.9575243,0.00022913645,0.00006268013,0.00008755876,0.005759504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.963011,0.012404222,0.0062707807,0.002273407,0.014774815,0.0012657157],"domain_scores_gemma":[0.7899553,0.08434778,0.014275322,0.005165138,0.09330682,0.012949638],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041063663,0.0062245596,0.010470395,0.011841035,0.0058728866,0.013568326,0.0068200454,0.02905385,0.019892346],"category_scores_gemma":[0.16080055,0.002602147,0.005554293,0.004609946,0.0052096746,0.005483496,0.0028671764,0.025368186,0.015229795],"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":[0.000056933924,0.000015552065,0.000013886139,0.00060925185,0.000046289955,0.000079419115,0.00001593366,0.000011445412,0.00003145195,0.00011272853,0.99516195,0.0038452218],"study_design_scores_gemma":[0.0007364091,0.00010357502,0.00047109395,0.0039886623,0.0006164805,0.0005134486,0.00010911163,0.00041952523,0.00029422797,0.0021493337,0.99052507,0.00007305553],"about_ca_topic_score_codex":0.0019420221,"about_ca_topic_score_gemma":0.005764874,"teacher_disagreement_score":0.95893633,"about_ca_system_score_codex":0.005062695,"about_ca_system_score_gemma":0.010315853,"threshold_uncertainty_score":0.21716803},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33539322,0.0058650626,0.13056494,0.27229133,0.001207993,0.00067541515,0.000051264455,0.0003055495,0.2536452],"genre_scores_gemma":[0.9757711,0.0008162172,0.015981907,0.0039418167,0.00008164768,0.00021074542,0.000010561103,0.000047891157,0.0031379424],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8512181,0.1386002,0.0013399682,0.0013729971,0.004375815,0.0030928962],"domain_scores_gemma":[0.8916349,0.072683774,0.004659233,0.0034162565,0.012797603,0.014808255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09869299,0.000385627,0.00046907554,0.0021627932,0.013521535,0.020966118,0.001889866,0.0024761327,0.0037038834],"category_scores_gemma":[0.07525007,0.00054450874,0.00046655757,0.0012473994,0.025598936,0.011298765,0.012624188,0.0060906736,0.0005106893],"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":[0.00015569,0.00047900432,0.030077782,0.00059189036,0.000043378182,0.0013824614,0.529067,0.00057218154,0.00083829294,0.2990719,0.015845949,0.12187449],"study_design_scores_gemma":[0.00009608668,0.00039226422,0.013465013,0.002388697,0.00008051314,0.0011141994,0.71867335,0.004431225,0.001789827,0.11257089,0.1448618,0.00013616343],"about_ca_topic_score_codex":0.00808459,"about_ca_topic_score_gemma":0.027844276,"teacher_disagreement_score":0.901307,"about_ca_system_score_codex":0.01239606,"about_ca_system_score_gemma":0.03367232,"threshold_uncertainty_score":0.52194464},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43008617,0.01267509,0.15543766,0.061737385,0.0018569267,0.0029093227,0.00051461364,0.0012875749,0.3334952],"genre_scores_gemma":[0.8777149,0.004486906,0.06264374,0.002050961,0.0002943779,0.0013204494,0.00029427576,0.0001820168,0.051012445],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9735748,0.016701087,0.0008883519,0.0020499984,0.004942907,0.0018427804],"domain_scores_gemma":[0.93015265,0.031919096,0.0060179573,0.00620488,0.019076524,0.006628929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04526549,0.00095888635,0.00056906714,0.00372433,0.006884563,0.014493005,0.0033356927,0.0033728227,0.0068451623],"category_scores_gemma":[0.05901347,0.00066357496,0.00083001266,0.0028714887,0.012259029,0.010808737,0.008486386,0.0031918986,0.0016598683],"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":[0.00030465593,0.00051152933,0.06460217,0.0013769917,0.000070089176,0.00045321105,0.2741646,0.00091259036,0.002265459,0.12856162,0.012689284,0.5140879],"study_design_scores_gemma":[0.00013196691,0.0015030854,0.14541307,0.0054164594,0.00021295546,0.00087245775,0.16548602,0.0028420046,0.006033514,0.026514513,0.6452468,0.0003270938],"about_ca_topic_score_codex":0.06959774,"about_ca_topic_score_gemma":0.11316004,"teacher_disagreement_score":0.06959774,"about_ca_system_score_codex":0.018870667,"about_ca_system_score_gemma":0.033879254,"threshold_uncertainty_score":0.2393896},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014906512,0.035906866,0.0025379532,0.927602,0.0042337803,0.00008732964,0.000012018968,0.00003906111,0.028090388],"genre_scores_gemma":[0.32954192,0.12655944,0.011236837,0.48323786,0.01799874,0.0014016399,0.00008271675,0.00036468997,0.029576225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6473873,0.2999704,0.0060747424,0.004393767,0.031349014,0.010824768],"domain_scores_gemma":[0.59819216,0.33193815,0.0070732324,0.010086788,0.027534718,0.025174992],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23268658,0.0009456457,0.0030706907,0.006415874,0.020510724,0.049463272,0.004897391,0.026943356,0.011017083],"category_scores_gemma":[0.32039684,0.0010464076,0.0015713051,0.007567691,0.07710597,0.06067346,0.02332797,0.032607287,0.0017337234],"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":[0.00013577729,0.0001785049,0.0016868911,0.0019046889,0.00007486173,0.00026594274,0.04553731,0.0002476686,0.00006737906,0.45845586,0.25999603,0.23144913],"study_design_scores_gemma":[0.00011746549,0.00013301092,0.0030697342,0.015820755,0.00006163783,0.000327787,0.087164216,0.0005700097,0.0001855034,0.49360472,0.39877003,0.00017511398],"about_ca_topic_score_codex":0.03157789,"about_ca_topic_score_gemma":0.04615178,"teacher_disagreement_score":0.7673134,"about_ca_system_score_codex":0.04401306,"about_ca_system_score_gemma":0.103279,"threshold_uncertainty_score":0.94623405},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85495716,0.00041705996,0.026746675,0.03287619,0.00037488696,0.0022348172,0.000118000826,0.00036155875,0.08191367],"genre_scores_gemma":[0.97874683,0.000258042,0.016978953,0.001166067,0.00006527523,0.00057366083,0.000054078228,0.0000148949475,0.00214227],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98165053,0.014408329,0.00031469483,0.00059603614,0.0012522239,0.0017782097],"domain_scores_gemma":[0.9581617,0.02932751,0.0015390827,0.0022510851,0.0017228767,0.0069976225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019254608,0.0006482753,0.00040388177,0.001301801,0.0030283977,0.0042174677,0.0019961142,0.002255597,0.009572754],"category_scores_gemma":[0.052844577,0.0003985163,0.0005353193,0.0005141096,0.0021637557,0.004218083,0.011671626,0.0023123708,0.0010965541],"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":[0.0005174874,0.02523946,0.041209083,0.0008786985,0.00018763523,0.0006156701,0.053025793,0.0046817507,0.0034810964,0.0102552995,0.0178419,0.8420661],"study_design_scores_gemma":[0.002025169,0.014272319,0.1610959,0.006266213,0.0010594887,0.0012587183,0.27882913,0.053463157,0.022670692,0.2631088,0.19515774,0.000792727],"about_ca_topic_score_codex":0.0026955442,"about_ca_topic_score_gemma":0.004434881,"teacher_disagreement_score":0.019254608,"about_ca_system_score_codex":0.0017364962,"about_ca_system_score_gemma":0.011734183,"threshold_uncertainty_score":0.10182935},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88296396,0.0012597777,0.03261763,0.0065536997,0.00043423672,0.002814435,0.00036699433,0.00012924947,0.072859965],"genre_scores_gemma":[0.9380683,0.0014510645,0.05221142,0.001594017,0.00008183856,0.0022749167,0.00014338766,0.000041105868,0.00413399],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.987688,0.009368879,0.00025710653,0.0007462224,0.0013046354,0.00063515094],"domain_scores_gemma":[0.9614792,0.031975802,0.0016999476,0.0021297487,0.0015774812,0.0011377428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021384694,0.0005575444,0.00038972532,0.0007615747,0.0019298043,0.0022830702,0.0019850999,0.0013385969,0.005104311],"category_scores_gemma":[0.033373415,0.0002761371,0.00041259415,0.00092140597,0.007172551,0.0028922695,0.0030861616,0.0021323308,0.00031613297],"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":[0.0057018623,0.043967195,0.03525397,0.0042746984,0.00069593586,0.0012187968,0.08037241,0.016398154,0.051418077,0.264663,0.01425934,0.48177654],"study_design_scores_gemma":[0.0058662286,0.032245096,0.046236333,0.002495565,0.00093732413,0.0003294944,0.04798635,0.024518583,0.076906815,0.62473655,0.1372712,0.00047051697],"about_ca_topic_score_codex":0.016014999,"about_ca_topic_score_gemma":0.02863586,"teacher_disagreement_score":0.021384694,"about_ca_system_score_codex":0.0055425055,"about_ca_system_score_gemma":0.0056110495,"threshold_uncertainty_score":0.11309445},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81477517,0.0018696269,0.05330378,0.0048842374,0.0001229626,0.001192061,0.002019537,0.0009904705,0.120842166],"genre_scores_gemma":[0.8949618,0.00082914013,0.06955716,0.00021757287,0.000018795981,0.00035907346,0.0012678859,0.00015381537,0.032634858],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9882287,0.0025699262,0.0005678338,0.00091303803,0.0064578056,0.0012627381],"domain_scores_gemma":[0.968474,0.0044039804,0.0011174552,0.0012511063,0.022854507,0.0018990135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0132377185,0.00077450526,0.0005482046,0.0045597744,0.003743352,0.0074403365,0.0014059218,0.00092130416,0.0046307375],"category_scores_gemma":[0.022578139,0.0005641368,0.00064653193,0.00414242,0.0018827458,0.0019815208,0.0020710346,0.0011159808,0.0006489692],"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":[0.00092017715,0.0007468419,0.11943471,0.00079221255,0.00017533137,0.0003041088,0.019855663,0.03150498,0.014126148,0.041942168,0.011876319,0.7583214],"study_design_scores_gemma":[0.00039266027,0.0013312339,0.5121405,0.001409656,0.0003512132,0.00030177724,0.036087167,0.099382654,0.05544481,0.006846876,0.28591114,0.000400308],"about_ca_topic_score_codex":0.9576746,"about_ca_topic_score_gemma":0.95516896,"teacher_disagreement_score":0.9285295,"about_ca_system_score_codex":0.07147051,"about_ca_system_score_gemma":0.14410982,"threshold_uncertainty_score":0.51855725},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044186106,0.00013322532,0.97709024,0.0018564,0.000047927504,0.0002405447,0.00007934804,0.000493401,0.015640307],"genre_scores_gemma":[0.1163725,0.0003927438,0.8767347,0.0005943719,0.000058001027,0.0005501782,0.00019505632,0.0002604761,0.004842014],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9870467,0.009309095,0.0005289218,0.0006480699,0.002016883,0.00045025846],"domain_scores_gemma":[0.9741193,0.021061722,0.0007263987,0.0016640383,0.002055863,0.0003727308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016271194,0.0008701187,0.00046389832,0.0019379845,0.001800734,0.0071197464,0.0020415771,0.0013995656,0.008398654],"category_scores_gemma":[0.03586483,0.00058585394,0.0015352739,0.0019423456,0.0055256714,0.0073376736,0.0044134683,0.0033922908,0.0011797161],"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":[0.00006890176,0.00010649815,0.0004883596,0.000154058,0.000025264233,0.00015680316,0.0016396145,0.022432888,0.0004130504,0.8906592,0.002248651,0.08160672],"study_design_scores_gemma":[0.00005098841,0.000081090555,0.00012418296,0.00021497796,0.000025975807,0.000107733584,0.0006963778,0.10853457,0.0019328734,0.85543907,0.032753702,0.000038509916],"about_ca_topic_score_codex":0.0081023825,"about_ca_topic_score_gemma":0.0076252506,"teacher_disagreement_score":0.016271194,"about_ca_system_score_codex":0.0046227886,"about_ca_system_score_gemma":0.0076661687,"threshold_uncertainty_score":0.086051285},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016462162,0.1132872,0.044625852,0.3014244,0.0036774394,0.00015831008,0.0001939319,0.00024326322,0.5199273],"genre_scores_gemma":[0.7399707,0.07546149,0.027180374,0.04427952,0.005179618,0.00052905176,0.00024709143,0.0005831403,0.10656904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9640377,0.023584248,0.0016190438,0.0034887036,0.0053541125,0.0019161784],"domain_scores_gemma":[0.9396957,0.040797316,0.0029231356,0.003084208,0.011020343,0.002479221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038494896,0.00090922357,0.0010964323,0.004968785,0.005074961,0.022620628,0.0017783764,0.006058601,0.01195717],"category_scores_gemma":[0.04473219,0.00050635496,0.0009240272,0.0049590417,0.03441042,0.019905733,0.008013847,0.008232523,0.0027645403],"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":[0.00005532993,0.000024750618,0.0016661831,0.00086351536,0.000019009016,0.00013221124,0.026611328,0.00037914191,0.0002297922,0.86704695,0.02810628,0.074865565],"study_design_scores_gemma":[0.000018621513,0.000095023475,0.0059329956,0.0037982885,0.000029344405,0.00040201336,0.027122464,0.00068636687,0.00043494278,0.32542062,0.6359882,0.000071055365],"about_ca_topic_score_codex":0.014555476,"about_ca_topic_score_gemma":0.010817193,"teacher_disagreement_score":0.038494896,"about_ca_system_score_codex":0.01637695,"about_ca_system_score_gemma":0.0147055825,"threshold_uncertainty_score":0.20358294},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3741866,0.0132770445,0.015115064,0.082447864,0.00097261096,0.0009688237,0.00054830697,0.00024998302,0.5122337],"genre_scores_gemma":[0.9342816,0.008653745,0.01740009,0.005023424,0.00023120201,0.0001913795,0.00034391292,0.00004064633,0.033833995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99650216,0.0020912483,0.000099133045,0.000068494264,0.0003456679,0.00089325896],"domain_scores_gemma":[0.995761,0.0018040538,0.00020092604,0.00014325177,0.001162869,0.0009279126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036846744,0.0003305729,0.00015059441,0.0014458968,0.0024498363,0.0021834176,0.00063763227,0.0020689385,0.010054362],"category_scores_gemma":[0.005926101,0.00012875408,0.00040127253,0.001789441,0.0008844946,0.001811296,0.0030695582,0.0012436422,0.0022883585],"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":[0.00044957336,0.0020723492,0.049862042,0.002775954,0.000022592358,0.010945573,0.049575128,0.003283043,0.0027647389,0.07676711,0.08214247,0.71933943],"study_design_scores_gemma":[0.00015549341,0.0010036591,0.07197418,0.0031137427,0.000038614085,0.008859538,0.10012804,0.0038659426,0.0034823625,0.0121919,0.79510814,0.000078403464],"about_ca_topic_score_codex":0.009223521,"about_ca_topic_score_gemma":0.019423813,"teacher_disagreement_score":0.010054362,"about_ca_system_score_codex":0.002921917,"about_ca_system_score_gemma":0.0071300953,"threshold_uncertainty_score":0.03363514},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.779311,0.0019826852,0.12039096,0.010548708,0.00018324227,0.0003982153,0.00055049383,0.0002440649,0.0863907],"genre_scores_gemma":[0.98373944,0.0003665164,0.013023805,0.0002451818,0.000019515606,0.00012019874,0.000100916666,0.0000399144,0.0023445922],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98883635,0.008177345,0.0002192714,0.00092793617,0.0011051835,0.0007338829],"domain_scores_gemma":[0.96985614,0.024841694,0.001433467,0.0018364999,0.0011260841,0.0009059664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008631214,0.00035022717,0.00044531072,0.0031209295,0.008849308,0.008409518,0.0019288328,0.0019197188,0.0063785575],"category_scores_gemma":[0.020320255,0.0005023571,0.00043378302,0.0029283576,0.01054805,0.013795468,0.010819178,0.0025424603,0.00042941002],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009678024,0.00010125443,0.02527393,0.00066839496,0.000067692294,0.0025466776,0.6807199,0.0020263444,0.0030383298,0.2270392,0.0041971337,0.054224316],"study_design_scores_gemma":[0.000027609207,0.000081208666,0.015092119,0.0005511781,0.00003722236,0.0012624374,0.671748,0.007035542,0.0013687349,0.17419192,0.12851955,0.00008450269],"about_ca_topic_score_codex":0.010230064,"about_ca_topic_score_gemma":0.021317894,"teacher_disagreement_score":0.9959373,"about_ca_system_score_codex":0.004062695,"about_ca_system_score_gemma":0.003662812,"threshold_uncertainty_score":0.045646787},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6331241,0.0034148518,0.013028715,0.11520115,0.00012782798,0.0004562285,0.00024896584,0.00013270373,0.23426545],"genre_scores_gemma":[0.99118525,0.00085636385,0.0029628424,0.0008960907,0.000009145443,0.00006792659,0.000028087861,0.000009592169,0.0039848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9792098,0.014250352,0.00071590586,0.0010017509,0.0021354263,0.0026867907],"domain_scores_gemma":[0.98516166,0.0072393846,0.0014353733,0.00097281474,0.0017555353,0.0034353049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014315894,0.00023544901,0.00032305683,0.0022039225,0.01261097,0.01802934,0.0019481853,0.0023645116,0.0045784474],"category_scores_gemma":[0.017475089,0.00035235193,0.00026588174,0.0041212137,0.022173002,0.0050061923,0.013080792,0.0025778497,0.00030526772],"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":[0.00009030355,0.0003353447,0.053730965,0.0005943858,0.00006712595,0.0005575601,0.09825923,0.0039464175,0.0008965171,0.6680346,0.009994344,0.16349325],"study_design_scores_gemma":[0.000056815406,0.00028274322,0.04852607,0.0021658104,0.00006793471,0.00021040527,0.49458975,0.0041754832,0.001594957,0.2002511,0.24796905,0.00010991824],"about_ca_topic_score_codex":0.32937977,"about_ca_topic_score_gemma":0.52749306,"teacher_disagreement_score":0.32937977,"about_ca_system_score_codex":0.07628689,"about_ca_system_score_gemma":0.1593828,"threshold_uncertainty_score":0.6549251},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016036499,0.5353429,0.04528494,0.27117884,0.008362984,0.000579508,0.004218323,0.0012058286,0.13222294],"genre_scores_gemma":[0.06419586,0.61813796,0.17391244,0.048491184,0.0032623147,0.0009856205,0.002404238,0.0008869946,0.08772333],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951007,0.0015247545,0.0005114204,0.0002527382,0.0024917214,0.00011878407],"domain_scores_gemma":[0.97775567,0.012560959,0.0014055886,0.0006261017,0.0070767575,0.00057492184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008237403,0.0010618086,0.0007487965,0.011112153,0.0029913837,0.0043116715,0.0032827116,0.003256807,0.024203442],"category_scores_gemma":[0.03661192,0.0011658119,0.00060868886,0.010661233,0.0033705716,0.0047835824,0.001983641,0.0044481475,0.009957988],"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":[0.000023070874,0.00002784928,0.001104878,0.0009369631,0.000020067619,0.00006544566,0.0006735678,0.00017520081,0.00016641917,0.009004076,0.72444177,0.2633606],"study_design_scores_gemma":[0.000014612477,0.000025842968,0.0044806306,0.0030470982,0.000030451183,0.0003392389,0.00082632585,0.00024364631,0.00048716224,0.017566767,0.9728967,0.00004157082],"about_ca_topic_score_codex":0.06489155,"about_ca_topic_score_gemma":0.21677068,"teacher_disagreement_score":0.06489155,"about_ca_system_score_codex":0.006666859,"about_ca_system_score_gemma":0.008356311,"threshold_uncertainty_score":0.12902766},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007578791,0.2168765,0.009305542,0.72781074,0.0053801415,0.0013329408,0.00067304453,0.000069810005,0.030972488],"genre_scores_gemma":[0.32497516,0.4222014,0.121162914,0.10704622,0.0049362266,0.0054749055,0.0007535692,0.00020836726,0.013241307],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.81596845,0.15208516,0.010224161,0.0021753034,0.016715357,0.0028315932],"domain_scores_gemma":[0.518778,0.35604385,0.016048994,0.008952377,0.093531504,0.006645327],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24472354,0.0007324336,0.0020623803,0.005775308,0.00339674,0.009890641,0.0033614056,0.003985553,0.006620879],"category_scores_gemma":[0.29935893,0.0005656268,0.0020010264,0.010601409,0.0065184715,0.008655987,0.0046962546,0.0059995875,0.0012022136],"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":[0.00018244235,0.00021483868,0.0089847315,0.019380065,0.0004567107,0.0005147675,0.010160027,0.0031546084,0.00027112995,0.08073368,0.1991801,0.676767],"study_design_scores_gemma":[0.00010890706,0.0003769245,0.027774237,0.09167935,0.0004337181,0.00050984387,0.053589687,0.002844591,0.0006941458,0.106434375,0.7152171,0.00033712637],"about_ca_topic_score_codex":0.090353504,"about_ca_topic_score_gemma":0.14582501,"teacher_disagreement_score":0.24472354,"about_ca_system_score_codex":0.015298035,"about_ca_system_score_gemma":0.08584573,"threshold_uncertainty_score":0.93139035},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012071935,0.15157399,0.36173186,0.42716524,0.0151694715,0.005727911,0.0042984863,0.003912478,0.029213428],"genre_scores_gemma":[0.012599224,0.14850704,0.62410694,0.14622758,0.0062892204,0.0122473845,0.0022475047,0.002932705,0.04484237],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9562097,0.028506963,0.004694957,0.0019464834,0.007841347,0.0008005137],"domain_scores_gemma":[0.79983133,0.15697429,0.0028931524,0.002845187,0.032881975,0.0045741387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06777482,0.003851002,0.0037777422,0.009521955,0.007910112,0.0135386875,0.007122292,0.011204615,0.017642876],"category_scores_gemma":[0.15284404,0.004284551,0.0021844336,0.011791598,0.009892477,0.021089064,0.005501306,0.021196947,0.016458895],"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":[0.000037827143,0.00013371794,0.00039622074,0.0020519919,0.00005814309,0.00019327705,0.005217607,0.00032287874,0.0002848661,0.015193164,0.89488584,0.08122446],"study_design_scores_gemma":[0.00022233781,0.00005099194,0.0010112106,0.004994354,0.00016889488,0.0003187367,0.0076980405,0.0014406962,0.00069807115,0.10703819,0.8761568,0.00020163838],"about_ca_topic_score_codex":0.06292618,"about_ca_topic_score_gemma":0.11084618,"teacher_disagreement_score":0.93222517,"about_ca_system_score_codex":0.0059547205,"about_ca_system_score_gemma":0.02778202,"threshold_uncertainty_score":0.35843176},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5571717,0.022441959,0.004428066,0.13666335,0.0019882298,0.00069111417,0.0009905116,0.00022244905,0.2754026],"genre_scores_gemma":[0.9361299,0.015363916,0.0029125488,0.008009801,0.00009291663,0.0001484022,0.00028403947,0.00013340026,0.036924973],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9761244,0.0075358427,0.00064217846,0.0012741366,0.00957144,0.0048520314],"domain_scores_gemma":[0.95620984,0.007029003,0.0010196059,0.00093783607,0.02114486,0.013658825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027174778,0.00038706965,0.0005748736,0.0017414263,0.021101013,0.008371206,0.002396625,0.0021037022,0.0075084167],"category_scores_gemma":[0.028296394,0.0005523502,0.00032602556,0.004428464,0.007495877,0.0032078198,0.0060754,0.0046033105,0.0005766884],"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":[0.00043743863,0.0008879087,0.05447154,0.0011668324,0.000056168796,0.0018485541,0.46469575,0.0007458357,0.0012608683,0.0696774,0.15492022,0.24983153],"study_design_scores_gemma":[0.000058310845,0.00028898008,0.046649028,0.0011725675,0.000034332963,0.00066041294,0.19773318,0.00044095097,0.0009628132,0.0016397744,0.7502143,0.00014531953],"about_ca_topic_score_codex":0.97525966,"about_ca_topic_score_gemma":0.99153674,"teacher_disagreement_score":0.85912573,"about_ca_system_score_codex":0.1408743,"about_ca_system_score_gemma":0.3809314,"threshold_uncertainty_score":0.996464},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09694147,0.033472512,0.36313307,0.21653534,0.0018120178,0.0022114583,0.0005624311,0.0022393514,0.28309226],"genre_scores_gemma":[0.61863655,0.025232768,0.31949267,0.009344232,0.00031038257,0.0014088998,0.00013671383,0.00052134745,0.024916425],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9835752,0.009790978,0.0009084467,0.00073993596,0.0045271986,0.00045825104],"domain_scores_gemma":[0.8232448,0.14759724,0.006037416,0.0044246526,0.014774477,0.003921468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053286184,0.0005317549,0.000503155,0.003065981,0.005913883,0.009296433,0.0019692988,0.00209814,0.008380437],"category_scores_gemma":[0.13299456,0.0009884137,0.00050325476,0.0015395698,0.007157463,0.01139706,0.0061515984,0.0064342143,0.002219435],"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":[0.00023469672,0.00024536168,0.013060741,0.0016012925,0.00009591043,0.00027727787,0.06559618,0.0012099607,0.0026187815,0.040691443,0.09409461,0.78027385],"study_design_scores_gemma":[0.0002721012,0.0009262179,0.06833031,0.008296078,0.0005576077,0.0019939544,0.063765,0.00712639,0.011697052,0.24180852,0.594713,0.0005137158],"about_ca_topic_score_codex":0.016401801,"about_ca_topic_score_gemma":0.05409766,"teacher_disagreement_score":0.053286184,"about_ca_system_score_codex":0.0049320585,"about_ca_system_score_gemma":0.01194457,"threshold_uncertainty_score":0.2818076},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011650422,0.0024325983,0.8221538,0.022135073,0.0006147827,0.0008549368,0.000050455827,0.00016824174,0.13993967],"genre_scores_gemma":[0.61575973,0.0026427254,0.3624572,0.002699753,0.0005417597,0.0018790392,0.00006911495,0.00014370929,0.013806963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.89522135,0.08443403,0.0020524627,0.005273375,0.010133888,0.0028849011],"domain_scores_gemma":[0.91401803,0.0654792,0.0030902564,0.01086895,0.005179958,0.0013636027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09458681,0.00131026,0.0011098995,0.004522595,0.0104329195,0.013747162,0.002967928,0.005317708,0.005718235],"category_scores_gemma":[0.07601226,0.0008176215,0.0012202575,0.003457011,0.057609703,0.021952605,0.014554286,0.006283518,0.001084746],"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":[0.000012192153,0.000014694711,0.00027685825,0.00013360746,0.000008672005,0.000069307695,0.008440442,0.0007152826,0.00015519916,0.97149897,0.00044029223,0.0182346],"study_design_scores_gemma":[0.000017256176,0.00005297236,0.00023685725,0.00030097357,0.000013348943,0.00013894419,0.0029653613,0.0015297337,0.00027223077,0.93600243,0.05844529,0.000024600746],"about_ca_topic_score_codex":0.0048944894,"about_ca_topic_score_gemma":0.0043598143,"teacher_disagreement_score":0.09458681,"about_ca_system_score_codex":0.0072407043,"about_ca_system_score_gemma":0.019297425,"threshold_uncertainty_score":0.5002289},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91430336,0.0006416833,0.003038117,0.002429314,0.00006201737,0.0010497549,0.0018793716,0.00016495593,0.07643141],"genre_scores_gemma":[0.9919992,0.00017398753,0.0042240787,0.000120585595,0.000006196973,0.00026152722,0.000606374,0.000014471533,0.002593557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98366654,0.0036179335,0.00076662865,0.00077087275,0.008598268,0.0025797903],"domain_scores_gemma":[0.9362344,0.006344948,0.003457631,0.0016948284,0.046591315,0.0056767827],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015467183,0.00034807425,0.00035509892,0.006664886,0.00700048,0.0037466004,0.0018851705,0.00053592736,0.002939616],"category_scores_gemma":[0.031026652,0.00034334254,0.00041068622,0.0056055454,0.00272967,0.0012178418,0.0030442178,0.0009840993,0.00026094838],"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":[0.00034488464,0.0007316595,0.7102209,0.00048374315,0.00016803975,0.00013507396,0.026367174,0.0065323296,0.0017854564,0.027221506,0.032976992,0.19303216],"study_design_scores_gemma":[0.000031341337,0.00014139594,0.92827606,0.00030545573,0.00004808122,0.000032526186,0.0206303,0.0054714037,0.002029125,0.0011696073,0.041751757,0.00011296162],"about_ca_topic_score_codex":0.97564405,"about_ca_topic_score_gemma":0.98268867,"teacher_disagreement_score":0.98453283,"about_ca_system_score_codex":0.13086712,"about_ca_system_score_gemma":0.18191469,"threshold_uncertainty_score":0.9495119},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8356464,0.0034724914,0.051217936,0.007872809,0.0008034618,0.02793365,0.00073042786,0.00025604546,0.07206666],"genre_scores_gemma":[0.91075766,0.001418508,0.05436249,0.0013871476,0.00008612359,0.019083342,0.00021783919,0.00007676042,0.012610169],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85766405,0.116964415,0.0046726754,0.0027406586,0.015150036,0.0028081825],"domain_scores_gemma":[0.8588842,0.08971377,0.010793788,0.0061031915,0.029187664,0.0053173318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10822767,0.00080771174,0.0011148072,0.0013350969,0.0038189287,0.004778371,0.0016407163,0.0016400629,0.009077399],"category_scores_gemma":[0.13829549,0.00056078774,0.0013013552,0.0014404621,0.0035449332,0.0032743302,0.0051672114,0.00221484,0.0010462542],"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":[0.0070142993,0.005979362,0.05050992,0.010590559,0.0006612493,0.00054843497,0.20394553,0.0033553755,0.008899869,0.037499648,0.0057339007,0.6652619],"study_design_scores_gemma":[0.005521815,0.075661585,0.2863966,0.020216918,0.002535938,0.0005917526,0.26077136,0.010666903,0.051616706,0.033653572,0.251682,0.000684879],"about_ca_topic_score_codex":0.013020859,"about_ca_topic_score_gemma":0.01818191,"teacher_disagreement_score":0.10822767,"about_ca_system_score_codex":0.00934559,"about_ca_system_score_gemma":0.03250315,"threshold_uncertainty_score":0.57236946},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043024924,0.06292876,0.078639224,0.83884704,0.005426715,0.0011543921,0.00003864468,0.0002829884,0.008379709],"genre_scores_gemma":[0.38330922,0.050080102,0.34718075,0.19280694,0.009232167,0.010496233,0.00011888238,0.000705749,0.00606995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16594806,0.6847111,0.051663015,0.021722429,0.06643029,0.009525091],"domain_scores_gemma":[0.086583875,0.7525179,0.028696219,0.048223365,0.07636725,0.007611472],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7990208,0.0052348697,0.011447754,0.024413258,0.022738464,0.06038363,0.013857965,0.03566354,0.006693371],"category_scores_gemma":[0.7652836,0.005199498,0.0050829803,0.019572366,0.11652152,0.09793044,0.05185396,0.054256704,0.0019271014],"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":[0.00055049814,0.00030069452,0.002886198,0.007947933,0.00035190693,0.0005311118,0.046826888,0.0013920498,0.00047999778,0.7281467,0.019826386,0.19075967],"study_design_scores_gemma":[0.0004944239,0.0004876644,0.002297022,0.023511281,0.0002722717,0.00067227415,0.052457538,0.0043094126,0.0012554735,0.77585673,0.13774389,0.00064193585],"about_ca_topic_score_codex":0.021155044,"about_ca_topic_score_gemma":0.01524084,"teacher_disagreement_score":0.20097917,"about_ca_system_score_codex":0.08065927,"about_ca_system_score_gemma":0.13574971,"threshold_uncertainty_score":0.5852267},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78647166,0.003365293,0.064083844,0.017253647,0.00049596623,0.008133194,0.00009858638,0.00015472305,0.119943105],"genre_scores_gemma":[0.9685761,0.0008366716,0.024337552,0.00092485157,0.00005340258,0.0019275469,0.00002271517,0.000032891527,0.0032882371],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7496751,0.22530273,0.0046165967,0.0021653057,0.01524181,0.002998424],"domain_scores_gemma":[0.8040201,0.15729344,0.0102189705,0.0050222045,0.020515496,0.0029297224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.20589434,0.0006899626,0.00077982707,0.0020092041,0.0055258516,0.008900992,0.0018279221,0.0017890553,0.002808868],"category_scores_gemma":[0.19691712,0.0004014049,0.00063867687,0.0012373232,0.010343415,0.0036842243,0.00869823,0.0029613697,0.00032165818],"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":[0.001068667,0.0011756974,0.011541307,0.0040757516,0.00022582842,0.0006860013,0.71428674,0.0022140117,0.0049313866,0.045415435,0.0024544545,0.21192466],"study_design_scores_gemma":[0.000532796,0.0062835827,0.029505415,0.0115070725,0.0006891054,0.00073583797,0.78533715,0.0073464634,0.029595068,0.050799698,0.07734101,0.00032674885],"about_ca_topic_score_codex":0.005701237,"about_ca_topic_score_gemma":0.008608016,"teacher_disagreement_score":0.99429876,"about_ca_system_score_codex":0.009931855,"about_ca_system_score_gemma":0.023208046,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014740154,0.7606975,0.12938261,0.054262873,0.020143216,0.0010814128,0.0037530407,0.0017259977,0.02747945],"genre_scores_gemma":[0.024752712,0.6689291,0.25268468,0.0098171085,0.0062359925,0.0031021978,0.0031486817,0.0014354367,0.029893989],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9809153,0.011225936,0.0026567494,0.0007300214,0.004289662,0.00018244765],"domain_scores_gemma":[0.7737542,0.1812876,0.006942024,0.005122178,0.031060794,0.001833106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04755094,0.00397031,0.002785002,0.011047127,0.0035555896,0.0052776053,0.0035388195,0.006582662,0.03893921],"category_scores_gemma":[0.12280375,0.0049210275,0.0018780563,0.012937414,0.005035605,0.00958888,0.0030451412,0.008673529,0.025595153],"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":[0.00018967611,0.00009176539,0.0010699437,0.0057844226,0.00012728339,0.00017606381,0.0017989242,0.0006453811,0.0005218579,0.009100213,0.37610266,0.6043918],"study_design_scores_gemma":[0.00038993324,0.00045541336,0.01356593,0.0405952,0.00080183457,0.0020078323,0.0025663099,0.003611783,0.0036291464,0.068758115,0.863067,0.0005515852],"about_ca_topic_score_codex":0.018764371,"about_ca_topic_score_gemma":0.04796703,"teacher_disagreement_score":0.04755094,"about_ca_system_score_codex":0.0033404357,"about_ca_system_score_gemma":0.009588631,"threshold_uncertainty_score":0.25147635},"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":"other","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060969046,0.001901429,0.2272404,0.07649268,0.007574134,0.006258956,0.100872636,0.18944626,0.38411668],"genre_scores_gemma":[0.050434496,0.0032525056,0.422249,0.014847755,0.0041900193,0.005502251,0.10208255,0.059628922,0.33781245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.985938,0.006245047,0.0011015848,0.0007042441,0.005130269,0.00088070997],"domain_scores_gemma":[0.8964168,0.042881507,0.0056441473,0.016859021,0.021153145,0.017045297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037541702,0.0012562105,0.0010008648,0.004514012,0.0016243948,0.013590676,0.0032676961,0.0029910055,0.23611014],"category_scores_gemma":[0.08227306,0.0015376161,0.0011111763,0.0057164705,0.0012161232,0.014562782,0.011030432,0.004463794,0.1303404],"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":[0.00018189386,0.00012083174,0.00067019433,0.00029080972,0.000019271909,0.00009395133,0.00031147318,0.0005462007,0.00044693833,0.012208179,0.8807137,0.1043965],"study_design_scores_gemma":[0.00015150574,0.00006603171,0.0011243996,0.00024729787,0.000009418717,0.00007291472,0.00020828105,0.0012675793,0.0008243982,0.012689975,0.98326117,0.000077027405],"about_ca_topic_score_codex":0.0056709456,"about_ca_topic_score_gemma":0.0069226325,"teacher_disagreement_score":0.23611014,"about_ca_system_score_codex":0.004943708,"about_ca_system_score_gemma":0.010857059,"threshold_uncertainty_score":0.7898671},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9571668,0.0006840633,0.00087915664,0.0062732245,0.00011165722,0.00006794179,0.00003492984,0.000014325146,0.034767788],"genre_scores_gemma":[0.99542266,0.00018745818,0.00020776322,0.0005258305,0.000016873619,0.000020988284,0.000019248659,0.00000478244,0.0035944104],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9856323,0.008137435,0.0005007606,0.0005894137,0.0028015603,0.002338483],"domain_scores_gemma":[0.96820754,0.009739166,0.0049208445,0.0008990191,0.009176189,0.0070573534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015070469,0.0001562424,0.00028812973,0.0023234808,0.008035114,0.005249747,0.0007030684,0.001033756,0.0059767845],"category_scores_gemma":[0.025819467,0.00018387887,0.00014233301,0.00093338935,0.003896364,0.0014350434,0.003827597,0.0012245768,0.0005263697],"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":[0.00043098125,0.000650708,0.43918902,0.00023424067,0.000029837842,0.000932157,0.4100115,0.00024804333,0.0015959156,0.022350674,0.014287985,0.110038914],"study_design_scores_gemma":[0.00004916076,0.00031609728,0.1684697,0.00065317855,0.000023095457,0.001063389,0.72046477,0.0012376145,0.001330363,0.0057465048,0.10054803,0.00009816266],"about_ca_topic_score_codex":0.01328284,"about_ca_topic_score_gemma":0.011891087,"teacher_disagreement_score":0.015070469,"about_ca_system_score_codex":0.0070167114,"about_ca_system_score_gemma":0.010031166,"threshold_uncertainty_score":0.079701185},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13273193,0.010069275,0.036060143,0.65911734,0.0013377384,0.00023449193,0.000043745837,0.00013212457,0.16027324],"genre_scores_gemma":[0.95972544,0.0044664713,0.01088798,0.015589567,0.00016244702,0.00016282717,0.00002146282,0.00005593641,0.008927858],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91874695,0.0641097,0.0014535341,0.001729842,0.008856626,0.0051034433],"domain_scores_gemma":[0.89544225,0.071803115,0.0052871406,0.002248426,0.01613219,0.009086858],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.069949426,0.00035031085,0.00053389504,0.002394117,0.015049399,0.015568249,0.0017264195,0.0040948177,0.005688509],"category_scores_gemma":[0.09058418,0.0003569851,0.00035123847,0.0013773895,0.027085546,0.016864574,0.00983663,0.0096924715,0.00068914803],"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":[0.00011023114,0.00021835158,0.016052898,0.00076080963,0.000017996335,0.000840094,0.41133967,0.00043081038,0.00077110843,0.40901792,0.027449135,0.13299097],"study_design_scores_gemma":[0.00003333057,0.00015346779,0.0085536465,0.004259522,0.000022386714,0.00088333985,0.5875081,0.0011526782,0.002219229,0.093020126,0.30205855,0.00013559873],"about_ca_topic_score_codex":0.02247965,"about_ca_topic_score_gemma":0.025146797,"teacher_disagreement_score":0.93005055,"about_ca_system_score_codex":0.018507244,"about_ca_system_score_gemma":0.057305705,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014175293,0.0035570476,0.1721112,0.6701478,0.005939875,0.03408552,0.0006910029,0.0018350317,0.0974572],"genre_scores_gemma":[0.11696151,0.002859354,0.7911143,0.03298633,0.000752738,0.018502101,0.0012178172,0.00048288243,0.03512299],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7225121,0.111921884,0.032732736,0.008431472,0.10291794,0.021483835],"domain_scores_gemma":[0.50268865,0.057601962,0.013999379,0.012796768,0.3511493,0.06176392],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4402716,0.0024166014,0.0021393418,0.016570022,0.031603783,0.023283763,0.011698103,0.019885546,0.005626345],"category_scores_gemma":[0.3117352,0.0027615905,0.0026655304,0.007023881,0.014432346,0.011561456,0.017922169,0.02340722,0.0024810028],"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":[0.00014050707,0.0013615952,0.011140733,0.001644623,0.000097678254,0.001214815,0.028615093,0.008119894,0.0025000544,0.24614955,0.42951995,0.26949552],"study_design_scores_gemma":[0.00028960523,0.00041431116,0.013786475,0.0069951396,0.000121358025,0.0004805766,0.035659496,0.012608164,0.0023500482,0.08233109,0.8441203,0.0008433617],"about_ca_topic_score_codex":0.4442008,"about_ca_topic_score_gemma":0.5037598,"teacher_disagreement_score":0.8588215,"about_ca_system_score_codex":0.1411785,"about_ca_system_score_gemma":0.61956847,"threshold_uncertainty_score":0.9961112},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013053896,0.00035254308,0.00021123236,0.9952708,0.0033786944,0.0000032250457,0.0000052840855,0.000004562266,0.00064311735],"genre_scores_gemma":[0.007807339,0.00052285707,0.0010504775,0.9698598,0.018366303,0.000055023975,0.0000072355206,0.000019889552,0.0023111496],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9427576,0.02359471,0.006045345,0.0053180167,0.0177919,0.004492558],"domain_scores_gemma":[0.82743037,0.10315407,0.010097266,0.008953141,0.026336962,0.024028141],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.06349209,0.0008751817,0.0022831084,0.0019914631,0.012932811,0.018675776,0.0057084076,0.10868019,0.0063227355],"category_scores_gemma":[0.19917615,0.0011735728,0.0018147186,0.0020810103,0.03857889,0.019195152,0.015585571,0.13160732,0.0033878235],"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":[0.00006597918,0.000058552843,0.001722775,0.00018448762,0.00006249042,0.0013083748,0.0029954452,0.00018334911,0.00033445025,0.12509967,0.8472236,0.020760775],"study_design_scores_gemma":[0.00015768618,0.00007595492,0.0016260569,0.0012934732,0.00004842237,0.0016911274,0.005118616,0.0010141453,0.00031287948,0.19405805,0.79434323,0.0002602485],"about_ca_topic_score_codex":0.013658159,"about_ca_topic_score_gemma":0.029115507,"teacher_disagreement_score":0.99800855,"about_ca_system_score_codex":0.010841569,"about_ca_system_score_gemma":0.029626975,"threshold_uncertainty_score":0.3357823},"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":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014357225,0.03115897,0.007534609,0.12561664,0.09460108,0.0003796229,0.002893164,0.00069656933,0.7356836],"genre_scores_gemma":[0.015296589,0.015450893,0.004797193,0.009923895,0.011867394,0.0001360892,0.0008589716,0.0004157639,0.9412531],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953805,0.00051312504,0.00018423778,0.00052126206,0.0027922906,0.0006085349],"domain_scores_gemma":[0.98948824,0.0008046143,0.00017168319,0.0005989253,0.0070172073,0.0019193832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005551673,0.0011794509,0.00091218686,0.0049517816,0.00703004,0.015355541,0.002537594,0.0052442816,0.14589524],"category_scores_gemma":[0.008862253,0.0008500135,0.0013079988,0.00419341,0.0040036994,0.0033308894,0.003055669,0.0069438647,0.03550316],"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":[0.000020812287,0.00003481877,0.00016302579,0.00008651705,0.000008282078,0.00008776744,0.00010579729,0.00033731264,0.00016606705,0.049423482,0.9194486,0.030117517],"study_design_scores_gemma":[0.0000039360352,0.0000044469034,0.0004164607,0.00007843878,0.0000029304238,0.000023208628,0.000100177785,0.000083948136,0.00005486474,0.0031168794,0.996104,0.000010737195],"about_ca_topic_score_codex":0.5986435,"about_ca_topic_score_gemma":0.70681256,"teacher_disagreement_score":0.5986435,"about_ca_system_score_codex":0.038229015,"about_ca_system_score_gemma":0.061245278,"threshold_uncertainty_score":0.8074404},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07170432,0.007813272,0.0069778664,0.8355242,0.0058252905,0.000066621855,0.000073426956,0.00009330282,0.07192166],"genre_scores_gemma":[0.9139628,0.005953522,0.0027057142,0.052865516,0.0009767137,0.000065812994,0.0000595032,0.00010539387,0.023305014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96631205,0.022103315,0.00066091307,0.0011096305,0.006154413,0.0036597294],"domain_scores_gemma":[0.94870263,0.01984015,0.003019486,0.00083699904,0.013575054,0.014025728],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026918475,0.00029835355,0.00047222426,0.0015514038,0.021310441,0.022741016,0.0017757119,0.0063124737,0.009158526],"category_scores_gemma":[0.07494007,0.0003570593,0.0003834643,0.001672266,0.01579057,0.013147633,0.0067191278,0.01832179,0.0009815473],"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":[0.00017131933,0.00020978508,0.012239319,0.0005267311,0.000023618946,0.0022591024,0.30484575,0.0005200055,0.0011435611,0.20109582,0.32549265,0.15147227],"study_design_scores_gemma":[0.00001696064,0.000060537197,0.0041306866,0.0012481721,0.000016574526,0.00048263796,0.40284362,0.0003269531,0.0006302811,0.016141495,0.5739928,0.00010921018],"about_ca_topic_score_codex":0.06173345,"about_ca_topic_score_gemma":0.071804784,"teacher_disagreement_score":0.9794242,"about_ca_system_score_codex":0.020575823,"about_ca_system_score_gemma":0.03856653,"threshold_uncertainty_score":0.14928871},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.391834,0.0059411596,0.07744625,0.19045953,0.0045743957,0.0011343217,0.000336793,0.00040271552,0.32787073],"genre_scores_gemma":[0.9513343,0.0018112483,0.020764003,0.0047117206,0.000646008,0.0010676961,0.00008799518,0.00019860567,0.019378452],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.907769,0.08173505,0.001161492,0.0018072922,0.0048233843,0.002703909],"domain_scores_gemma":[0.8091317,0.16305941,0.0050751925,0.007456117,0.00796297,0.0073145805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06802639,0.00067971175,0.0007681187,0.0035740277,0.013955291,0.019669684,0.0030963377,0.0051196422,0.010049722],"category_scores_gemma":[0.12573867,0.00048276735,0.00038108442,0.0026973432,0.016690534,0.022764571,0.02004391,0.00579149,0.00095005543],"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":[0.00019176127,0.00018506353,0.0029853475,0.00059984095,0.000036576403,0.00050916773,0.794097,0.00022315218,0.0013001867,0.07945242,0.012815475,0.10760406],"study_design_scores_gemma":[0.000040327202,0.000116886986,0.001561311,0.0008808577,0.000018358127,0.00028961358,0.7888572,0.00065013464,0.0007997746,0.0809584,0.12575631,0.00007077611],"about_ca_topic_score_codex":0.0019841148,"about_ca_topic_score_gemma":0.0056758607,"teacher_disagreement_score":0.06802639,"about_ca_system_score_codex":0.00353065,"about_ca_system_score_gemma":0.011512766,"threshold_uncertainty_score":0.35976225},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92670643,0.0012843724,0.011950137,0.0022785715,0.00018179255,0.009099655,0.0135901375,0.00020785532,0.034701016],"genre_scores_gemma":[0.93560624,0.00086184347,0.023400215,0.0006350103,0.000042038402,0.01721772,0.010289302,0.00006544739,0.011882165],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99589866,0.001291754,0.00041910142,0.0003263585,0.0016406277,0.00042353017],"domain_scores_gemma":[0.9852427,0.0038630792,0.0021568032,0.00076728826,0.0065657315,0.0014043651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072066896,0.00049191713,0.0007936096,0.0023157848,0.0015697754,0.0010030876,0.001152487,0.00063750497,0.005736969],"category_scores_gemma":[0.0151069425,0.00036109038,0.0008127603,0.0021347955,0.0012850263,0.00081265037,0.0021486168,0.0014235326,0.00059080136],"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":[0.0006357084,0.00062742824,0.798285,0.0015984878,0.0007845603,0.00026726688,0.023681669,0.0011720333,0.0028825996,0.0052446397,0.032403514,0.13241707],"study_design_scores_gemma":[0.00003950727,0.00010148315,0.98158824,0.0001478042,0.000032394568,0.00003281915,0.0029063516,0.0005156482,0.00020506787,0.00038412918,0.014013318,0.000033235032],"about_ca_topic_score_codex":0.298671,"about_ca_topic_score_gemma":0.4512639,"teacher_disagreement_score":0.701329,"about_ca_system_score_codex":0.007472715,"about_ca_system_score_gemma":0.010916214,"threshold_uncertainty_score":0.5938651},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011450686,0.052589934,0.07976538,0.7159052,0.004684874,0.00078324915,0.000084413776,0.00033380376,0.13440254],"genre_scores_gemma":[0.5554774,0.06102008,0.25556687,0.092682526,0.0042288983,0.0026629504,0.00015222872,0.00068880356,0.027520237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.84899646,0.11486975,0.005320712,0.0052025905,0.019800391,0.0058100563],"domain_scores_gemma":[0.7347842,0.19532247,0.0044332803,0.017357754,0.02895039,0.019151898],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17177688,0.0013209607,0.001508871,0.0066332626,0.012116996,0.026067652,0.0050308285,0.011878867,0.007939601],"category_scores_gemma":[0.120643765,0.0011026022,0.002210341,0.0044953185,0.077727206,0.024281835,0.019665167,0.017543525,0.001449881],"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":[0.00011658084,0.00021100021,0.0033675013,0.001670106,0.00006137394,0.00037292423,0.018234847,0.0012302035,0.00025166242,0.7355946,0.035272427,0.20361677],"study_design_scores_gemma":[0.00015403215,0.00023867263,0.004105805,0.0060842396,0.000053143725,0.00050195196,0.020590749,0.0028288125,0.00074618397,0.61391544,0.3505907,0.0001903021],"about_ca_topic_score_codex":0.06128724,"about_ca_topic_score_gemma":0.07917738,"teacher_disagreement_score":0.8282231,"about_ca_system_score_codex":0.05567558,"about_ca_system_score_gemma":0.12891887,"threshold_uncertainty_score":0.9084538},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07783029,0.0019248136,0.18011239,0.2720184,0.0077676144,0.01133818,0.00061256386,0.00289837,0.4454974],"genre_scores_gemma":[0.6240654,0.001215156,0.19584182,0.03228668,0.0009940565,0.003721082,0.00059137936,0.00071132754,0.14057308],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92499924,0.03990038,0.002768872,0.003022543,0.021907317,0.0074017146],"domain_scores_gemma":[0.80165523,0.03498592,0.0054776003,0.015390557,0.10587055,0.036620162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13149898,0.000490199,0.00054052914,0.0020882525,0.010227274,0.008753784,0.003591133,0.0029936244,0.01698925],"category_scores_gemma":[0.13267255,0.0004542421,0.00055922806,0.0009973025,0.0064186654,0.00453439,0.008561601,0.005893633,0.0037364673],"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":[0.00035021713,0.0012423145,0.015019411,0.00065231795,0.000040205716,0.00035111135,0.015274529,0.0017421816,0.002944021,0.11190782,0.34103945,0.5094364],"study_design_scores_gemma":[0.00018285247,0.00046554994,0.012689645,0.0009776552,0.000024415602,0.0001915994,0.00974568,0.0029500523,0.0042680767,0.021912863,0.94641423,0.00017724917],"about_ca_topic_score_codex":0.12828825,"about_ca_topic_score_gemma":0.22944479,"teacher_disagreement_score":0.9696437,"about_ca_system_score_codex":0.030356284,"about_ca_system_score_gemma":0.15302773,"threshold_uncertainty_score":0.69544137},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07961618,0.0033563501,0.18876052,0.38560024,0.0076488364,0.005264607,0.0005903177,0.0010069156,0.3281561],"genre_scores_gemma":[0.6231597,0.0016716989,0.26460937,0.022722758,0.0003394873,0.001461197,0.0004062864,0.0003475082,0.08528207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9289115,0.029905304,0.0040446483,0.0029417991,0.02719827,0.0069984165],"domain_scores_gemma":[0.88072926,0.017012928,0.0028671157,0.004883267,0.06566792,0.028839523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07909906,0.00054501294,0.0006330841,0.003957856,0.028821012,0.023976145,0.0037216377,0.0060484246,0.0061594187],"category_scores_gemma":[0.09960065,0.0007329146,0.00055876555,0.0027175313,0.021485249,0.007522305,0.013003032,0.009398586,0.0016661992],"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":[0.00011217682,0.00032134695,0.011398854,0.00047248392,0.000022575752,0.000818499,0.058035433,0.001784192,0.0015756907,0.54061997,0.18370771,0.20113106],"study_design_scores_gemma":[0.0000444678,0.00011118789,0.005701636,0.0014146629,0.000024286768,0.0003264412,0.039568592,0.003368593,0.0021957732,0.03769574,0.9093225,0.00022610412],"about_ca_topic_score_codex":0.64133954,"about_ca_topic_score_gemma":0.8198354,"teacher_disagreement_score":0.88221014,"about_ca_system_score_codex":0.11778988,"about_ca_system_score_gemma":0.40991592,"threshold_uncertainty_score":0.8546294},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81441903,0.0034053605,0.0022664198,0.05767208,0.0007281904,0.00088764436,0.00018655571,0.00006431926,0.120370455],"genre_scores_gemma":[0.9260659,0.0057114013,0.0058558495,0.0068453173,0.000110581735,0.00063379935,0.0001280816,0.00012014357,0.054528907],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9900857,0.0043047983,0.00044184012,0.00062969176,0.002871167,0.001666763],"domain_scores_gemma":[0.97889555,0.0042581395,0.0012046574,0.000918322,0.005644283,0.009079137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02505977,0.00031601515,0.0004793534,0.0008065654,0.008559217,0.0045201443,0.0011018914,0.0016401941,0.0069710044],"category_scores_gemma":[0.022307059,0.0005403452,0.00036217048,0.0013066013,0.0059808604,0.0037425978,0.007409636,0.004522505,0.0005019557],"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":[0.0008128946,0.0024793728,0.06485031,0.0012805609,0.00007002919,0.005088117,0.6245288,0.00063081714,0.0044827745,0.025179023,0.056024347,0.21457294],"study_design_scores_gemma":[0.00017733857,0.001252332,0.09953109,0.0017278348,0.000051316892,0.0020859602,0.33324662,0.00062683184,0.0012925585,0.0032243994,0.556626,0.0001576566],"about_ca_topic_score_codex":0.407992,"about_ca_topic_score_gemma":0.766743,"teacher_disagreement_score":0.407992,"about_ca_system_score_codex":0.021825299,"about_ca_system_score_gemma":0.07818974,"threshold_uncertainty_score":0.8112345},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011046914,0.009601616,0.1049345,0.8320427,0.0029987074,0.0009864899,0.00039035914,0.00043449228,0.037564136],"genre_scores_gemma":[0.5516031,0.008853294,0.2484738,0.15071516,0.0040700515,0.01526803,0.0005802973,0.001217122,0.019219192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.520369,0.3920216,0.0131854825,0.019413017,0.046842575,0.008168373],"domain_scores_gemma":[0.24667087,0.605014,0.015785886,0.062289927,0.051719565,0.01851972],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5397058,0.0013948618,0.0029588086,0.006932622,0.01102895,0.032277733,0.013405217,0.011887999,0.019520862],"category_scores_gemma":[0.4949599,0.0023270804,0.0011427548,0.005691072,0.049688496,0.030004641,0.016923496,0.019859483,0.0031373715],"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":[0.00034386956,0.0004446363,0.006089398,0.0032273964,0.000117626485,0.00009540875,0.027498197,0.0010501547,0.00039164472,0.5133172,0.06673736,0.38068703],"study_design_scores_gemma":[0.0007142995,0.00042539168,0.010413092,0.013486717,0.000059005342,0.00030993848,0.03349548,0.006221725,0.0009437331,0.5404777,0.39320284,0.00025021742],"about_ca_topic_score_codex":0.028973352,"about_ca_topic_score_gemma":0.032580607,"teacher_disagreement_score":0.4602942,"about_ca_system_score_codex":0.048051894,"about_ca_system_score_gemma":0.12609605,"threshold_uncertainty_score":0.5676247},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123026505,0.021921279,0.4809488,0.1886627,0.00071276026,0.0010106979,0.0003381374,0.00017686079,0.1832023],"genre_scores_gemma":[0.91773164,0.004290174,0.073180094,0.0016113595,0.00014963669,0.0011170118,0.000043634183,0.00009174742,0.0017846809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9131862,0.07477638,0.0020834743,0.0027492575,0.0046968497,0.00250774],"domain_scores_gemma":[0.8402103,0.14345202,0.0041219434,0.0043922127,0.0063056974,0.0015177308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.067587726,0.0009945717,0.0016997342,0.0097513385,0.014672435,0.025630767,0.00466983,0.006065571,0.005271486],"category_scores_gemma":[0.11949117,0.0013018139,0.0013914164,0.015455237,0.06818101,0.035820797,0.0141686825,0.005206436,0.00024085656],"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":[0.000039849667,0.000034892604,0.0028491677,0.000739656,0.000027095099,0.00022808452,0.061053142,0.001175047,0.000208875,0.8895181,0.00096019567,0.043165904],"study_design_scores_gemma":[0.000028687371,0.000082557126,0.0055653118,0.0027723734,0.00005889534,0.00037522818,0.20070207,0.0024443509,0.0007223944,0.72181296,0.06536542,0.00006976368],"about_ca_topic_score_codex":0.017626075,"about_ca_topic_score_gemma":0.028217122,"teacher_disagreement_score":0.067587726,"about_ca_system_score_codex":0.014485346,"about_ca_system_score_gemma":0.014889233,"threshold_uncertainty_score":0.35744232},"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":"other","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027617028,0.0053425585,0.20337304,0.18857095,0.020609198,0.11091623,0.008616119,0.0046718363,0.4302831],"genre_scores_gemma":[0.3855363,0.0034833823,0.25422266,0.04197252,0.0028401387,0.1969312,0.0041352813,0.002115181,0.10876333],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.39431658,0.46706507,0.0379694,0.0092420485,0.08178119,0.009625676],"domain_scores_gemma":[0.2712191,0.45666862,0.014787382,0.09910736,0.14846985,0.009747606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.52277935,0.0011049544,0.0015895338,0.009023038,0.0065883356,0.019773187,0.0038510696,0.0063241827,0.027866561],"category_scores_gemma":[0.70893776,0.001736277,0.0015507378,0.005831158,0.011018043,0.009962135,0.014114736,0.008255595,0.005677739],"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":[0.00080109347,0.00046172828,0.0026875797,0.005197686,0.00014474367,0.00048022723,0.07725885,0.001392056,0.0015992345,0.17747888,0.3432836,0.38921437],"study_design_scores_gemma":[0.0004066849,0.00041902822,0.006263347,0.009828952,0.000070561735,0.00010903965,0.01647762,0.0011335913,0.0039003326,0.033465162,0.92763346,0.000292187],"about_ca_topic_score_codex":0.013465184,"about_ca_topic_score_gemma":0.013739316,"teacher_disagreement_score":0.52277935,"about_ca_system_score_codex":0.028209245,"about_ca_system_score_gemma":0.1018779,"threshold_uncertainty_score":0.58849806},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24846151,0.016802201,0.12499471,0.14936428,0.0022551033,0.0003883398,0.00008416253,0.0002517841,0.45739794],"genre_scores_gemma":[0.9771706,0.0013644884,0.009196215,0.0028486683,0.00022377212,0.00022094605,0.000018551245,0.0000716056,0.00888516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.83487296,0.1267893,0.0030034448,0.0037604421,0.028893901,0.0026799487],"domain_scores_gemma":[0.8262708,0.11849468,0.011718093,0.0071323747,0.03223363,0.004150433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09235724,0.00063959573,0.0007005589,0.0038134288,0.009251542,0.020653231,0.00208896,0.0058409744,0.005186912],"category_scores_gemma":[0.19924481,0.00049792655,0.0005805267,0.0024675452,0.027454881,0.012555398,0.009754921,0.0061220755,0.0007159035],"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":[0.00028050758,0.00015912863,0.009232936,0.00057342526,0.00009183189,0.00064617075,0.13105834,0.0007400691,0.0015015176,0.75237054,0.007896001,0.095449485],"study_design_scores_gemma":[0.00019417796,0.00056104374,0.022416957,0.0054285135,0.00021271475,0.001588085,0.194404,0.0043164073,0.009192783,0.33835554,0.42306674,0.00026304793],"about_ca_topic_score_codex":0.012969678,"about_ca_topic_score_gemma":0.011325116,"teacher_disagreement_score":0.09235724,"about_ca_system_score_codex":0.0138099175,"about_ca_system_score_gemma":0.016879711,"threshold_uncertainty_score":0.4884376},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936335,0.00034985368,0.0001430181,0.00076555694,0.000011741916,0.000038034083,0.00014362157,0.000010962249,0.0049037603],"genre_scores_gemma":[0.9929549,0.0005126536,0.0003141593,0.00023299802,0.000007747028,0.000046571615,0.00012869386,0.0000097763905,0.0057926495],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9988269,0.0002692068,0.000027702974,0.000110689594,0.00024250122,0.0005228629],"domain_scores_gemma":[0.9932969,0.000911652,0.0009699577,0.00013351618,0.0017252286,0.002962611],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0012029536,0.0001849679,0.00019355428,0.0025273473,0.0030157133,0.0024050097,0.0015056381,0.0004872569,0.0032755611],"category_scores_gemma":[0.003932046,0.00028998358,0.00015996622,0.0040845205,0.0018772886,0.0006163618,0.0023715205,0.0009495988,0.000272679],"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":[0.00028905462,0.0003933205,0.8667283,0.00020829693,0.00004512515,0.00067812914,0.052134786,0.00064897916,0.005207041,0.0041058,0.0013277017,0.06823345],"study_design_scores_gemma":[0.0000063927946,0.00009000068,0.96058387,0.000071696304,0.000010438932,0.00008386194,0.031907037,0.0002770865,0.00034131747,0.00012169034,0.0064940522,0.000012604803],"about_ca_topic_score_codex":0.8175368,"about_ca_topic_score_gemma":0.9391691,"teacher_disagreement_score":0.9969843,"about_ca_system_score_codex":0.017495995,"about_ca_system_score_gemma":0.028787678,"threshold_uncertainty_score":0.36707556},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6403252,0.0033701966,0.15561184,0.02165411,0.0011488715,0.02328437,0.0030504984,0.0007760565,0.15077877],"genre_scores_gemma":[0.72334296,0.0015617866,0.2565323,0.00071304885,0.0000327281,0.0076220986,0.0021616055,0.00015116805,0.00788219],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94477475,0.027074726,0.0050019985,0.0016857685,0.018489456,0.0029733244],"domain_scores_gemma":[0.8274106,0.031284716,0.0052284026,0.00840042,0.12154295,0.006132863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09585789,0.0006448261,0.00061624753,0.0060374727,0.008010888,0.0058606747,0.0027948963,0.0009252451,0.0019131928],"category_scores_gemma":[0.15840276,0.0005146367,0.0007657913,0.0052374154,0.0041568475,0.0030818882,0.0065061185,0.0029719593,0.00043121944],"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":[0.00031177117,0.0009550885,0.090164654,0.0023604007,0.000063115964,0.0004313498,0.09642905,0.0036139318,0.006215713,0.06746478,0.02868323,0.703307],"study_design_scores_gemma":[0.00026292572,0.001176092,0.35496426,0.009158081,0.00018347788,0.0006637329,0.1910714,0.016963126,0.021776823,0.018803453,0.38452974,0.00044693574],"about_ca_topic_score_codex":0.63418305,"about_ca_topic_score_gemma":0.7605325,"teacher_disagreement_score":0.91959906,"about_ca_system_score_codex":0.08040093,"about_ca_system_score_gemma":0.22695234,"threshold_uncertainty_score":0.7359426},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018843682,0.9572105,0.0052482695,0.013087183,0.0014952247,0.00008659847,0.0010560685,0.00016120708,0.019770535],"genre_scores_gemma":[0.021652434,0.9436602,0.010342465,0.00058982236,0.0005064151,0.00007030659,0.0008516307,0.000095049356,0.022231732],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961343,0.0007421609,0.00021897223,0.00018821275,0.0024622704,0.0002541574],"domain_scores_gemma":[0.9903729,0.0041682078,0.0006186475,0.0002457546,0.003927981,0.00066645344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008784156,0.0022781054,0.0019681137,0.009485516,0.0023889348,0.0075911344,0.002758227,0.002346509,0.024664609],"category_scores_gemma":[0.009142931,0.0014886389,0.0011986975,0.012438707,0.0030772022,0.0038978504,0.0012808345,0.0032081858,0.008002286],"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":[0.00011065465,0.00006697771,0.0040335855,0.004313645,0.000113929884,0.00010180325,0.0015527161,0.0013598423,0.0004941022,0.0055362983,0.2661968,0.7161197],"study_design_scores_gemma":[0.00005046378,0.00013455942,0.029645849,0.011078298,0.00030978004,0.00051804725,0.0024856133,0.0013800319,0.0015545969,0.0067194845,0.9459822,0.00014116049],"about_ca_topic_score_codex":0.74218154,"about_ca_topic_score_gemma":0.8409395,"teacher_disagreement_score":0.74218154,"about_ca_system_score_codex":0.026636332,"about_ca_system_score_gemma":0.04088175,"threshold_uncertainty_score":0.5186736},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24833953,0.017111583,0.067074604,0.27088353,0.029021192,0.01677527,0.006458592,0.0046823234,0.33965337],"genre_scores_gemma":[0.7198902,0.010567459,0.0950061,0.048171975,0.0014548012,0.012790248,0.0038460577,0.0028637636,0.10540939],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8532752,0.078186095,0.017510865,0.0058596493,0.03974663,0.00542153],"domain_scores_gemma":[0.44547066,0.2558617,0.013441679,0.08616785,0.18400732,0.015050866],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22410792,0.00064960355,0.000932968,0.01958177,0.012517589,0.01427068,0.0035000525,0.0033697418,0.01448408],"category_scores_gemma":[0.3530005,0.0016159089,0.0009082625,0.013261708,0.007492369,0.009290343,0.01653213,0.0069532814,0.0034300587],"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":[0.00029271116,0.00076104945,0.032659736,0.0034570617,0.00011543364,0.0016970593,0.18778908,0.00022162212,0.0028942365,0.04554739,0.22691548,0.49764916],"study_design_scores_gemma":[0.0000522529,0.0004217993,0.046591297,0.0062206318,0.000089704474,0.0010060467,0.15170461,0.00048829115,0.0019804689,0.0032455274,0.7880013,0.00019807513],"about_ca_topic_score_codex":0.017335718,"about_ca_topic_score_gemma":0.017734988,"teacher_disagreement_score":0.98699695,"about_ca_system_score_codex":0.013003045,"about_ca_system_score_gemma":0.033629037,"threshold_uncertainty_score":0.9568131},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016572651,0.9258606,0.013852219,0.013252471,0.003614041,0.00017459237,0.0023605195,0.0007740554,0.038454212],"genre_scores_gemma":[0.0074897553,0.9446622,0.01721857,0.00081804575,0.0008129695,0.00016016276,0.0011506825,0.00022028576,0.027467374],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99736387,0.000560743,0.00039376062,0.00017982497,0.0013939711,0.00010780823],"domain_scores_gemma":[0.9903717,0.0048852297,0.00088533125,0.00039977304,0.0029700832,0.00048785142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006072469,0.002081115,0.0017833725,0.0048185457,0.0012855618,0.004193573,0.001822502,0.0018146788,0.026218195],"category_scores_gemma":[0.012013767,0.0018568442,0.0012064489,0.004977124,0.0016241211,0.0053409203,0.0012908513,0.003787438,0.029767418],"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":[0.000077148106,0.000059868114,0.0011330692,0.002356275,0.000041009596,0.00008099807,0.0006468698,0.00038197057,0.00039114826,0.0018948999,0.34167162,0.65126514],"study_design_scores_gemma":[0.00003993134,0.00017563725,0.009114374,0.009238119,0.00018709009,0.0013508025,0.0011992868,0.00030756675,0.0012306992,0.010261327,0.9667705,0.00012459594],"about_ca_topic_score_codex":0.023160195,"about_ca_topic_score_gemma":0.049668513,"teacher_disagreement_score":0.026218195,"about_ca_system_score_codex":0.0016525106,"about_ca_system_score_gemma":0.0065376265,"threshold_uncertainty_score":0.08770865},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119283,0.024935748,0.7122479,0.09147203,0.0036221463,0.0047931285,0.0020295826,0.0006457254,0.040970754],"genre_scores_gemma":[0.7155263,0.0063066576,0.24606818,0.017044146,0.0022088396,0.0109850215,0.00081137556,0.00021022382,0.0008392993],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.36012498,0.53739464,0.03646436,0.014408942,0.04819881,0.003408218],"domain_scores_gemma":[0.21962574,0.6347255,0.048503593,0.055466507,0.039228965,0.0024496599],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45365116,0.0016507753,0.0030141098,0.00931424,0.0028555237,0.012817273,0.003457566,0.004868898,0.001403721],"category_scores_gemma":[0.7531805,0.000970086,0.0021846064,0.018353235,0.017778907,0.02045443,0.006296465,0.005429358,0.0008109423],"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":[0.00034082984,0.00048084106,0.22020309,0.005926057,0.003290273,0.00010350061,0.028522098,0.006394861,0.0006679918,0.3168625,0.013205822,0.4040022],"study_design_scores_gemma":[0.000412396,0.0015452814,0.11605588,0.016952645,0.0011283467,0.00039480656,0.021998158,0.021542782,0.0021628551,0.71394897,0.10345724,0.00040076103],"about_ca_topic_score_codex":0.003033396,"about_ca_topic_score_gemma":0.0017031991,"teacher_disagreement_score":0.5463488,"about_ca_system_score_codex":0.0066115707,"about_ca_system_score_gemma":0.010549175,"threshold_uncertainty_score":0.6737454},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7363706,0.0022914258,0.06002602,0.028230364,0.00038727486,0.0012644528,0.00019100159,0.0005036423,0.17073514],"genre_scores_gemma":[0.8303685,0.002894177,0.09997033,0.0014055107,0.000051241543,0.00070630526,0.00018246088,0.00018730547,0.064234026],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99402195,0.0032602106,0.00017357669,0.0005319088,0.0013977526,0.00061456877],"domain_scores_gemma":[0.992004,0.0037175054,0.00070200354,0.0006580866,0.00091041415,0.0020080032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065251444,0.000533848,0.00035715496,0.0008598497,0.0061203786,0.01213496,0.0015180542,0.0019315281,0.004921474],"category_scores_gemma":[0.013315835,0.0004195453,0.00031631807,0.0006988851,0.005958803,0.0044839764,0.0064443243,0.0025502476,0.0016066227],"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":[0.000053432388,0.0008336018,0.014481861,0.0005112377,0.000023231261,0.0007191719,0.63663965,0.00049884967,0.0045879832,0.02917389,0.015315818,0.29716125],"study_design_scores_gemma":[0.00006540536,0.00046730175,0.023009002,0.0007154447,0.000049488073,0.00084130967,0.49897584,0.0010145414,0.0060201804,0.025381971,0.44336498,0.0000945481],"about_ca_topic_score_codex":0.03091821,"about_ca_topic_score_gemma":0.113883615,"teacher_disagreement_score":0.03091821,"about_ca_system_score_codex":0.0049893544,"about_ca_system_score_gemma":0.018988568,"threshold_uncertainty_score":0.06147647},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009603402,0.00012563184,0.9651693,0.0031456675,0.00006421066,0.0017389795,0.00034409686,0.0003303292,0.019478373],"genre_scores_gemma":[0.16202195,0.00018851968,0.8325685,0.00014128577,0.00001499952,0.002919939,0.00022580998,0.00007640878,0.0018425725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95645326,0.038123462,0.0009957644,0.001366571,0.0024573095,0.0006035994],"domain_scores_gemma":[0.925275,0.061666597,0.0023027016,0.005291001,0.004701562,0.0007631269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054440565,0.0014133105,0.0009123429,0.0076001524,0.0057928897,0.0081824865,0.002828105,0.0020424265,0.013523038],"category_scores_gemma":[0.07623443,0.0008961734,0.001643293,0.008722563,0.008116969,0.012006003,0.0077963704,0.0026444194,0.0008681473],"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":[0.00009988418,0.00019928001,0.0029698014,0.00088785856,0.000109909386,0.0004323146,0.0193293,0.025159553,0.0004455977,0.7879646,0.003943196,0.15845865],"study_design_scores_gemma":[0.000087321016,0.00012219572,0.00056796405,0.0006397751,0.00006245517,0.00022947382,0.01450076,0.055770207,0.0009986577,0.8849876,0.041978464,0.00005514315],"about_ca_topic_score_codex":0.00625913,"about_ca_topic_score_gemma":0.0070403153,"teacher_disagreement_score":0.054440565,"about_ca_system_score_codex":0.008496668,"about_ca_system_score_gemma":0.015018697,"threshold_uncertainty_score":0.28791273},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009652442,0.025549341,0.7513765,0.028387582,0.0033685258,0.00773007,0.0010569053,0.0004947994,0.1723838],"genre_scores_gemma":[0.20859618,0.017570887,0.71028924,0.011601385,0.0012965325,0.029806376,0.0005916181,0.0003651239,0.019882692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.42352256,0.49421805,0.016265988,0.009572513,0.054022152,0.0023988215],"domain_scores_gemma":[0.50255364,0.4174808,0.017052343,0.023137216,0.03778504,0.0019910128],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25571516,0.002907657,0.0031894164,0.012853506,0.0057178577,0.02023431,0.0042405804,0.005172084,0.0129309],"category_scores_gemma":[0.3076886,0.0014151488,0.0029573813,0.014745278,0.025949016,0.016671043,0.009737019,0.0075150966,0.0017812372],"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":[0.00024692845,0.00017308575,0.0019607511,0.010468518,0.0004937097,0.00015408652,0.02487006,0.0032985767,0.0008297141,0.7526621,0.009957809,0.19488472],"study_design_scores_gemma":[0.00023837962,0.0004729442,0.0030270724,0.013776151,0.0003515332,0.00025359206,0.022924833,0.0031284296,0.0022636724,0.65645504,0.29688174,0.00022649844],"about_ca_topic_score_codex":0.0075610084,"about_ca_topic_score_gemma":0.0090745855,"teacher_disagreement_score":0.25571516,"about_ca_system_score_codex":0.017566865,"about_ca_system_score_gemma":0.025197469,"threshold_uncertainty_score":0.9178357},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026105857,0.06304876,0.0053222636,0.7374593,0.159291,0.018423432,0.004458307,0.0008826816,0.008503595],"genre_scores_gemma":[0.03377141,0.04076151,0.07084904,0.69321114,0.0638487,0.08009492,0.004935976,0.00063943956,0.011887911],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.612263,0.15805987,0.15109918,0.009108026,0.06454036,0.0049295924],"domain_scores_gemma":[0.13538443,0.57419336,0.06723608,0.036923494,0.1662755,0.019987201],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34756264,0.0028493947,0.016559381,0.019898431,0.0063721146,0.012246269,0.0082132,0.049597032,0.0359607],"category_scores_gemma":[0.72571933,0.005237858,0.018623378,0.016448816,0.0077328524,0.019195326,0.008153114,0.02269163,0.010244215],"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":[0.0050576683,0.00027083172,0.0033928254,0.27416322,0.004304402,0.001179116,0.0016415585,0.00045039182,0.0021989022,0.0052924147,0.5848117,0.117236935],"study_design_scores_gemma":[0.013218328,0.0016958243,0.020934666,0.29953563,0.010732408,0.0015343057,0.0037069204,0.0019797336,0.0019198329,0.035761468,0.60737026,0.0016106506],"about_ca_topic_score_codex":0.010049607,"about_ca_topic_score_gemma":0.02228096,"teacher_disagreement_score":0.6524373,"about_ca_system_score_codex":0.01544593,"about_ca_system_score_gemma":0.053040273,"threshold_uncertainty_score":0.80457145},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8672195,0.003962612,0.0008661722,0.049388032,0.0008854609,0.0013188939,0.0007845122,0.00023657693,0.07533832],"genre_scores_gemma":[0.93218344,0.0015002609,0.0021671047,0.0031030565,0.000085075284,0.00068420795,0.00043113626,0.00005575639,0.059789877],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9960824,0.00059893314,0.000031427764,0.00020291531,0.00062942266,0.002454729],"domain_scores_gemma":[0.99568415,0.00013321538,0.00011441152,0.00005687548,0.00071744714,0.0032939364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029807733,0.0006088626,0.00043451082,0.0009070643,0.025046272,0.0031911328,0.0042558718,0.0013976928,0.004952855],"category_scores_gemma":[0.0031671936,0.0003925532,0.00043092764,0.0013941999,0.0040516932,0.0010693193,0.005574821,0.0028641773,0.000406177],"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":[0.0005164015,0.0052926606,0.06544342,0.00038141187,0.00008864789,0.00097096624,0.11786164,0.0013054445,0.0024079296,0.013865902,0.25825658,0.53360903],"study_design_scores_gemma":[0.00037092704,0.0019536421,0.47414643,0.0006893136,0.00014816487,0.00021567567,0.22897722,0.0008042409,0.0016628079,0.0019308428,0.2888828,0.00021788942],"about_ca_topic_score_codex":0.9772553,"about_ca_topic_score_gemma":0.99734336,"teacher_disagreement_score":0.09310904,"about_ca_system_score_codex":0.09310904,"about_ca_system_score_gemma":0.27690765,"threshold_uncertainty_score":0.67555654},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97137356,0.00035903664,0.0004411192,0.0012033294,0.0000456436,0.0026661563,0.00040553365,0.000018967876,0.023486534],"genre_scores_gemma":[0.98990893,0.00037924905,0.002161742,0.00029614015,0.000013154135,0.002874528,0.00042065524,0.000010344234,0.003935237],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98415333,0.008467404,0.0006267054,0.0009924279,0.0031875237,0.0025726294],"domain_scores_gemma":[0.9643312,0.012370389,0.004286917,0.001438683,0.009679156,0.007893741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020613724,0.00055439083,0.00064386934,0.0025650836,0.011689467,0.008247026,0.0029104091,0.0013833723,0.0067571015],"category_scores_gemma":[0.05163566,0.00046516207,0.00058197655,0.00353833,0.004966202,0.0041992217,0.0075079766,0.0017728996,0.00054353545],"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":[0.0026107922,0.004852219,0.44080347,0.0022022345,0.00032572326,0.0012034838,0.3367773,0.0046564755,0.00065715506,0.02076282,0.011552536,0.17359585],"study_design_scores_gemma":[0.00039535546,0.0019366795,0.20199582,0.0013217509,0.00021574128,0.000064213324,0.74598396,0.003455602,0.0006290905,0.0018361652,0.042079028,0.00008659953],"about_ca_topic_score_codex":0.75467306,"about_ca_topic_score_gemma":0.81822306,"teacher_disagreement_score":0.24532694,"about_ca_system_score_codex":0.09859973,"about_ca_system_score_gemma":0.094815545,"threshold_uncertainty_score":0.7153945},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06429817,0.004162093,0.12859733,0.11487432,0.007820316,0.029575098,0.0015346695,0.0027559702,0.64638203],"genre_scores_gemma":[0.42637864,0.0029151805,0.2535019,0.01824799,0.0019543758,0.015698815,0.0016929253,0.0015499782,0.27806023],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8717411,0.074409515,0.0071267383,0.0047641173,0.032296095,0.00966236],"domain_scores_gemma":[0.86963356,0.05012761,0.006437728,0.008299097,0.05456323,0.010938789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13529487,0.0007694616,0.0006048417,0.0052247383,0.011265043,0.025154244,0.0029679462,0.004597332,0.014082324],"category_scores_gemma":[0.1381194,0.0008591937,0.0006986607,0.003286252,0.009395425,0.007107518,0.0068075927,0.0057117646,0.0042020623],"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":[0.00019936779,0.0003863756,0.0075204843,0.0008744123,0.00006329324,0.0011534942,0.04975866,0.005724998,0.002297523,0.23147018,0.3922868,0.3082644],"study_design_scores_gemma":[0.00007177012,0.00016689871,0.00681316,0.0012686871,0.000031788597,0.00017510078,0.021777298,0.0014134897,0.0032258618,0.020504372,0.9442981,0.00025346485],"about_ca_topic_score_codex":0.056934524,"about_ca_topic_score_gemma":0.091273695,"teacher_disagreement_score":0.13529487,"about_ca_system_score_codex":0.045251403,"about_ca_system_score_gemma":0.122708485,"threshold_uncertainty_score":0.7155162},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088965625,0.0029750399,0.6038945,0.029786926,0.00027936205,0.0044391383,0.00010730229,0.00020281984,0.26934934],"genre_scores_gemma":[0.8633994,0.00042958785,0.1296843,0.00068535004,0.000046817466,0.0029395842,0.000029141518,0.00003777841,0.0027480226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6540979,0.30948108,0.0068262736,0.00694591,0.017787913,0.0048608375],"domain_scores_gemma":[0.8629884,0.09978261,0.008966747,0.008466688,0.016216477,0.003579053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16111016,0.0013803185,0.0014151353,0.009543944,0.0138736395,0.017901342,0.0036451553,0.00357075,0.0028369776],"category_scores_gemma":[0.088980414,0.0010945814,0.0012801412,0.0053198575,0.07171173,0.0139137525,0.013534754,0.004582234,0.00029750087],"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":[0.000046231562,0.00006229591,0.0013362692,0.00038598073,0.000047621477,0.00018328427,0.04369849,0.0024139492,0.0002878013,0.93430966,0.0007628554,0.016465502],"study_design_scores_gemma":[0.00011085106,0.00015201318,0.0014177451,0.0011858958,0.000046229212,0.00021892799,0.031699527,0.010525544,0.0006211898,0.9107194,0.043216176,0.00008642612],"about_ca_topic_score_codex":0.010864205,"about_ca_topic_score_gemma":0.009754018,"teacher_disagreement_score":0.16111016,"about_ca_system_score_codex":0.03071565,"about_ca_system_score_gemma":0.037339725,"threshold_uncertainty_score":0.8520422},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015041026,0.0022657502,0.0011205403,0.90967816,0.00395083,0.00011085164,0.00011091953,0.00019478831,0.06752711],"genre_scores_gemma":[0.3047845,0.012035775,0.0091279335,0.53819263,0.0055462485,0.000256302,0.00026396848,0.0004507348,0.12934196],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9915167,0.0033035392,0.00023056264,0.0003390349,0.0029447929,0.0016653424],"domain_scores_gemma":[0.97187334,0.0031328648,0.0016785922,0.00090825517,0.0056886123,0.016718233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058207293,0.00036189094,0.000549553,0.0011680174,0.011712279,0.008608236,0.0015282226,0.0067945863,0.031033836],"category_scores_gemma":[0.034345206,0.00034744715,0.00048126373,0.0013687706,0.0056572766,0.0065617,0.0024985643,0.0065002255,0.009725757],"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":[0.0000924222,0.00039636676,0.02125129,0.000275446,0.00003354558,0.0013541373,0.0058349855,0.000096146505,0.00049726764,0.005956747,0.79349,0.17072168],"study_design_scores_gemma":[0.000058278118,0.00049385364,0.034035176,0.0014802885,0.000053308988,0.002859465,0.03519627,0.00023841311,0.0006023663,0.0057188976,0.91908747,0.0001761484],"about_ca_topic_score_codex":0.051436946,"about_ca_topic_score_gemma":0.10474461,"teacher_disagreement_score":0.051436946,"about_ca_system_score_codex":0.007361922,"about_ca_system_score_gemma":0.018159045,"threshold_uncertainty_score":0.103818536},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018616492,0.0032259903,0.30290613,0.022728382,0.004414922,0.30606058,0.009207603,0.0016127836,0.3312271],"genre_scores_gemma":[0.07456951,0.0012552039,0.36492804,0.009042697,0.00072023744,0.46168166,0.003467372,0.000882631,0.08345266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.76147383,0.16794562,0.01958707,0.010731098,0.033166025,0.0070963716],"domain_scores_gemma":[0.8373322,0.08039025,0.0062169507,0.021802599,0.04950298,0.0047550015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21125619,0.0014124628,0.0012849487,0.008915477,0.0079875635,0.014033629,0.0040261517,0.005629785,0.039840125],"category_scores_gemma":[0.18358745,0.0018178187,0.0015909675,0.0062695337,0.010006091,0.0045866254,0.007607619,0.006319597,0.00983768],"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":[0.00099103,0.00069615076,0.0037754788,0.0034381389,0.00007490263,0.0006961325,0.04615064,0.0036089006,0.0025562765,0.49616715,0.15868172,0.28316346],"study_design_scores_gemma":[0.00029784875,0.00023808594,0.0033330482,0.0036573869,0.00003056639,0.00012628849,0.0070167235,0.0013806052,0.0029431514,0.031350918,0.949466,0.00015936053],"about_ca_topic_score_codex":0.014408849,"about_ca_topic_score_gemma":0.020149633,"teacher_disagreement_score":0.21125619,"about_ca_system_score_codex":0.023361325,"about_ca_system_score_gemma":0.07817187,"threshold_uncertainty_score":0.97266155},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018279789,0.007992523,0.0022223545,0.24878982,0.06871417,0.0005405681,0.01042874,0.0008007522,0.6586831],"genre_scores_gemma":[0.010144983,0.0044002347,0.0013052935,0.0157957,0.0024494545,0.00012593166,0.0018907008,0.00024567454,0.96364206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98545504,0.00077414955,0.00028757288,0.0012651741,0.009723712,0.0024944614],"domain_scores_gemma":[0.9343488,0.0016541434,0.0007912366,0.0011621555,0.04086179,0.021181861],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008050533,0.0011417625,0.0012224347,0.0026931546,0.008367387,0.009410416,0.0023226035,0.0057130186,0.2896616],"category_scores_gemma":[0.022739863,0.00062254875,0.0008073747,0.0028172226,0.0019050627,0.0023181692,0.0025651606,0.005590187,0.08821787],"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":[0.000025416286,0.000015650025,0.00029663756,0.00003822845,0.0000032577273,0.00003624972,0.00004293629,0.00003594146,0.00007670173,0.005623957,0.981443,0.012362074],"study_design_scores_gemma":[0.00001366667,0.000012160106,0.0007373899,0.00007008998,0.00000539478,0.000033292217,0.00015651283,0.000079125326,0.00008831699,0.0005828863,0.99820924,0.000011934442],"about_ca_topic_score_codex":0.7043745,"about_ca_topic_score_gemma":0.8771638,"teacher_disagreement_score":0.99194944,"about_ca_system_score_codex":0.043850448,"about_ca_system_score_gemma":0.22504814,"threshold_uncertainty_score":0.9690145},"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":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038731478,0.005977881,0.0025102366,0.38073012,0.046032023,0.00013638941,0.00049742707,0.0007637175,0.5594791],"genre_scores_gemma":[0.01569511,0.0010876822,0.0006697525,0.04134586,0.0016590054,0.000037850143,0.00011173665,0.00025446876,0.93913853],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99131876,0.0010519217,0.00019074992,0.0014153589,0.003386535,0.0026366918],"domain_scores_gemma":[0.9894805,0.0005166564,0.00019993733,0.00055997336,0.0025732773,0.006669553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004150361,0.0008274832,0.0009961217,0.001569221,0.023880893,0.016221367,0.0022242968,0.0066289874,0.18792285],"category_scores_gemma":[0.0102505665,0.00064289226,0.00078034523,0.0012747785,0.007505304,0.0068186666,0.010412474,0.016968718,0.053890016],"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":[0.000023103017,0.000026823442,0.0006405224,0.000029693734,0.0000042975294,0.00033846416,0.0019766781,0.000021121452,0.00018887676,0.038772684,0.92818475,0.02979288],"study_design_scores_gemma":[0.000002051587,0.000005144833,0.00024161572,0.00003163601,0.0000011015474,0.000106026055,0.0010866723,0.000013966926,0.000017314387,0.0006889733,0.9977969,0.000008682374],"about_ca_topic_score_codex":0.33856615,"about_ca_topic_score_gemma":0.54002917,"teacher_disagreement_score":0.33856615,"about_ca_system_score_codex":0.014641803,"about_ca_system_score_gemma":0.029629448,"threshold_uncertainty_score":0.67319095},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013221022,0.02423316,0.025207622,0.84643203,0.0015307867,0.0005108633,0.00018834764,0.00011045155,0.08856562],"genre_scores_gemma":[0.9040061,0.010433951,0.028408146,0.05015198,0.0019892114,0.0012034995,0.000093011105,0.000082931416,0.0036310994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76236254,0.20777202,0.005922934,0.0034698022,0.01545994,0.005012767],"domain_scores_gemma":[0.3828835,0.5139675,0.014001489,0.013901461,0.05791227,0.017333727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22009215,0.00085848174,0.0020982418,0.0051627746,0.009052132,0.029843837,0.004411399,0.007185534,0.013881078],"category_scores_gemma":[0.45212457,0.000506424,0.0009961278,0.006713599,0.05195165,0.032532357,0.010483689,0.009991826,0.0005924202],"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":[0.0002912541,0.00023434886,0.0069262492,0.0015067478,0.000053558564,0.00021368374,0.006108064,0.0016678988,0.00007431524,0.838269,0.026351603,0.11830342],"study_design_scores_gemma":[0.00016208149,0.00014383554,0.005118966,0.006967688,0.000086251915,0.0001326381,0.024100663,0.004333544,0.0003679164,0.8894744,0.06900509,0.0001068739],"about_ca_topic_score_codex":0.06002547,"about_ca_topic_score_gemma":0.062499866,"teacher_disagreement_score":0.22009215,"about_ca_system_score_codex":0.052256547,"about_ca_system_score_gemma":0.0799727,"threshold_uncertainty_score":0.9617652},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028106966,0.032511387,0.011649592,0.3264244,0.092737876,0.0017848437,0.009358979,0.0010002293,0.521722],"genre_scores_gemma":[0.056957338,0.03332823,0.028493026,0.0385714,0.007042641,0.001965009,0.01099315,0.0007604902,0.8218886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9689132,0.005829231,0.0014850929,0.0015893757,0.018903991,0.003279055],"domain_scores_gemma":[0.9305598,0.0031287125,0.0015712287,0.0024624125,0.046138052,0.016139781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031409264,0.0010651874,0.0014653633,0.004234948,0.0077383453,0.010308451,0.003013962,0.005413692,0.0907396],"category_scores_gemma":[0.039137013,0.00083198317,0.0010588892,0.0028896758,0.0043330654,0.0025250954,0.0068256063,0.0072625065,0.022900093],"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":[0.00003625028,0.000036618556,0.00049224956,0.00016378309,0.0000121983485,0.000026992799,0.00034707715,0.00008210044,0.0001297227,0.008086314,0.9430835,0.047503285],"study_design_scores_gemma":[0.0000046633263,0.0000069081634,0.0012904161,0.00018387132,0.0000029020662,0.000008886167,0.00029587004,0.000039397488,0.000031995038,0.0006925942,0.9974267,0.000015795988],"about_ca_topic_score_codex":0.6307645,"about_ca_topic_score_gemma":0.8093721,"teacher_disagreement_score":0.9681104,"about_ca_system_score_codex":0.03188959,"about_ca_system_score_gemma":0.19561224,"threshold_uncertainty_score":0.74282},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038470246,0.9980404,0.00015357793,0.00069789187,0.000057019268,0.000040770086,0.000011707658,0.0000031655547,0.00061085646],"genre_scores_gemma":[0.0057806834,0.99289024,0.00082005706,0.0002948622,0.000038713224,0.000090309564,0.0000177844,0.000003053569,0.00006433007],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98222476,0.010609715,0.0022431267,0.0006349525,0.004017948,0.00026946815],"domain_scores_gemma":[0.9276636,0.05907985,0.0039743898,0.0009275294,0.0076937545,0.0006608474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031654682,0.0010265572,0.0035503071,0.00798197,0.001218647,0.003617338,0.0019852123,0.0021149747,0.002135905],"category_scores_gemma":[0.077662855,0.0006736128,0.001312067,0.012061441,0.0024354558,0.0035050672,0.0019408034,0.0017513934,0.00046217078],"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":[0.00014118022,0.00014441041,0.0011953362,0.13212615,0.00027298377,0.00012727984,0.0013914752,0.00030726305,0.00014769212,0.0035516287,0.0075509623,0.8530436],"study_design_scores_gemma":[0.00016287783,0.0006747874,0.016162833,0.69796956,0.0021489656,0.0013992643,0.007334837,0.00046172156,0.00078422483,0.0067330217,0.2660354,0.00013248442],"about_ca_topic_score_codex":0.017045844,"about_ca_topic_score_gemma":0.030379813,"teacher_disagreement_score":0.96834534,"about_ca_system_score_codex":0.00836669,"about_ca_system_score_gemma":0.020153651,"threshold_uncertainty_score":0.16740799},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82414365,0.011062092,0.008215687,0.05212062,0.00060005276,0.00090761454,0.0055927793,0.00029870868,0.097058706],"genre_scores_gemma":[0.9701017,0.0024785937,0.0034370755,0.0030372916,0.000048990492,0.00030557218,0.0008014359,0.000043852102,0.019745458],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9892378,0.003471554,0.00063207827,0.0009150475,0.0039391266,0.0018044036],"domain_scores_gemma":[0.9472567,0.011414593,0.004066123,0.00082829816,0.029722763,0.0067115608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00936338,0.00036187802,0.0005371274,0.0022139268,0.00600905,0.005478035,0.0014193787,0.0010565625,0.01461039],"category_scores_gemma":[0.02587102,0.0003908534,0.00049331103,0.0048542167,0.0024988996,0.0019129909,0.0024399734,0.0018732721,0.0008654329],"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":[0.00051172177,0.00017948996,0.6025645,0.002447698,0.00024567597,0.0011429,0.092135794,0.0012958191,0.0032293238,0.013539244,0.06381424,0.21889357],"study_design_scores_gemma":[0.000024280464,0.00016539317,0.80099535,0.0015332355,0.00009278256,0.0002552695,0.0784777,0.00092411984,0.0010354504,0.00060972455,0.115776196,0.00011046936],"about_ca_topic_score_codex":0.9363706,"about_ca_topic_score_gemma":0.9514591,"teacher_disagreement_score":0.9363706,"about_ca_system_score_codex":0.07406249,"about_ca_system_score_gemma":0.10340915,"threshold_uncertainty_score":0.53736347},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021272855,0.06980778,0.025388991,0.34533104,0.008468244,0.0006425577,0.0020215071,0.0007734975,0.52629346],"genre_scores_gemma":[0.42039376,0.071833275,0.038522817,0.059107006,0.0031176286,0.0006186501,0.0013441639,0.0007373781,0.40432537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9693224,0.005007011,0.0012343263,0.002638843,0.017806632,0.0039907936],"domain_scores_gemma":[0.9480308,0.0062426683,0.0014745052,0.0015191826,0.037221454,0.0055114394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015055627,0.0006015971,0.00062583503,0.0051141223,0.011269187,0.015261536,0.0023237064,0.0040806374,0.022148054],"category_scores_gemma":[0.029305652,0.0006260453,0.0007196513,0.008130171,0.013004415,0.003037942,0.004153383,0.0060137114,0.002297268],"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":true,"study_design_scores_codex":[0.000118258184,0.000105317115,0.006733636,0.0014003344,0.00003529552,0.00038678525,0.010034367,0.0011940607,0.0014509021,0.41491398,0.29331183,0.27031532],"study_design_scores_gemma":[0.000013530372,0.000025881907,0.014204708,0.0016898197,0.000014322779,0.00013425916,0.00320021,0.0004790668,0.0004416393,0.008888154,0.9708407,0.00006760194],"about_ca_topic_score_codex":0.96441555,"about_ca_topic_score_gemma":0.97220224,"teacher_disagreement_score":0.8305526,"about_ca_system_score_codex":0.1694474,"about_ca_system_score_gemma":0.3081291,"threshold_uncertainty_score":0.9633233},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.896157,0.004903854,0.07722037,0.0025676156,0.00085169,0.0019253639,0.0014560975,0.00075104024,0.014166996],"genre_scores_gemma":[0.97779137,0.0001695992,0.019132927,0.000475804,0.00008253072,0.00086963025,0.00043484892,0.00020089031,0.00084242213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.50722843,0.37688854,0.034211084,0.027825925,0.051181443,0.002664583],"domain_scores_gemma":[0.084211424,0.7973049,0.046946935,0.050093524,0.020103931,0.0013393229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3075692,0.0012232442,0.0019453272,0.004067761,0.0024099387,0.0030705053,0.003489143,0.0021046314,0.0017821981],"category_scores_gemma":[0.654336,0.0011103648,0.0030871578,0.0047990573,0.0053040176,0.0035528147,0.004268879,0.00250008,0.00060329895],"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":[0.010017557,0.00060517364,0.87799066,0.00074892957,0.0067188595,0.0002510549,0.011039487,0.0033055525,0.0027347158,0.0023644636,0.0048349868,0.0793885],"study_design_scores_gemma":[0.00031836712,0.004281472,0.96641994,0.00039375172,0.002109097,0.00043080677,0.0026204342,0.009466684,0.006431779,0.0022492134,0.0050903196,0.00018820762],"about_ca_topic_score_codex":0.010496132,"about_ca_topic_score_gemma":0.009130489,"teacher_disagreement_score":0.3075692,"about_ca_system_score_codex":0.002641438,"about_ca_system_score_gemma":0.0017077944,"threshold_uncertainty_score":0.8538904},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52043253,0.30566972,0.0043596434,0.012137685,0.00053084205,0.0013418379,0.012325622,0.00008857769,0.14311355],"genre_scores_gemma":[0.9399821,0.049261283,0.0041548475,0.001540111,0.00006453215,0.00030135468,0.0026530493,0.000053091357,0.0019896203],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95816904,0.008182432,0.005928563,0.003444137,0.020963345,0.0033123603],"domain_scores_gemma":[0.78123486,0.09888213,0.015384026,0.009599569,0.089369945,0.005529428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045493856,0.0009575269,0.0017818918,0.036186144,0.008092065,0.010831515,0.0027079838,0.0011548008,0.003902235],"category_scores_gemma":[0.1356757,0.0006355249,0.0013905361,0.06894716,0.005173296,0.0028145288,0.0061129117,0.0015336922,0.00018554904],"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":[0.001356387,0.00032253674,0.49054775,0.030551573,0.0049617696,0.0010160081,0.13097098,0.00094756164,0.0014357686,0.047560364,0.008787749,0.28154156],"study_design_scores_gemma":[0.00008634689,0.00016721104,0.818222,0.018586013,0.002640721,0.00038710967,0.07944619,0.00030191286,0.0012879466,0.0024167893,0.076274246,0.00018355994],"about_ca_topic_score_codex":0.96755743,"about_ca_topic_score_gemma":0.97684026,"teacher_disagreement_score":0.921439,"about_ca_system_score_codex":0.078560986,"about_ca_system_score_gemma":0.11342783,"threshold_uncertainty_score":0.57000256},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01891878,0.024307808,0.38868153,0.36142734,0.0024945945,0.0009004703,0.00018856044,0.00034568907,0.20273525],"genre_scores_gemma":[0.5642834,0.026516518,0.37481955,0.021359654,0.0019905951,0.0016603383,0.0003586346,0.00020114104,0.008810181],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94005287,0.045216117,0.0032145784,0.0017727836,0.008369938,0.0013736556],"domain_scores_gemma":[0.67903644,0.2508772,0.0072430717,0.021487964,0.036868814,0.004486474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.099656515,0.0010291542,0.0012835219,0.009681543,0.0040868837,0.015034238,0.0034408122,0.0058081793,0.010018516],"category_scores_gemma":[0.17081341,0.0006412046,0.0009025412,0.0052150125,0.02590112,0.02371424,0.00838335,0.010055544,0.001766211],"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":[0.000012068872,0.0002844561,0.0015586365,0.0006785861,0.000021071744,0.000054084703,0.002817515,0.0014060993,0.00013058208,0.92635626,0.0068172263,0.05986344],"study_design_scores_gemma":[0.000042493833,0.000056507863,0.0012878443,0.0058557526,0.000019271964,0.000060908864,0.007437041,0.0053051007,0.0005385125,0.90943354,0.069933616,0.00002937895],"about_ca_topic_score_codex":0.005630156,"about_ca_topic_score_gemma":0.00628848,"teacher_disagreement_score":0.9003435,"about_ca_system_score_codex":0.015778843,"about_ca_system_score_gemma":0.038587928,"threshold_uncertainty_score":0.52704036},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23629655,0.0029420594,0.6708379,0.0049185366,0.0007334866,0.008720576,0.00032047965,0.0020767082,0.07315374],"genre_scores_gemma":[0.4950463,0.0017689265,0.49138403,0.0006189745,0.000116405834,0.0047247643,0.00038329925,0.00016763463,0.005789628],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9592884,0.03236577,0.0017210749,0.0009940296,0.0048736427,0.00075709244],"domain_scores_gemma":[0.9375666,0.044755228,0.0033046226,0.0037606284,0.007920486,0.0026925413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026890442,0.0011936778,0.00077309756,0.0025788906,0.001380669,0.0048468746,0.0025529005,0.0019617474,0.0060780407],"category_scores_gemma":[0.080367565,0.00046143166,0.0007090532,0.0016276877,0.0022165428,0.004209699,0.004755579,0.0018536734,0.0016355508],"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":[0.0004686106,0.0020641226,0.0121546425,0.0015374348,0.000043557116,0.00059604115,0.025223399,0.0064286804,0.008033272,0.01966838,0.0067953486,0.91698647],"study_design_scores_gemma":[0.00070101937,0.015029804,0.06754971,0.010782257,0.00016781864,0.0073458045,0.08304201,0.08509484,0.05175303,0.17765167,0.49963835,0.0012436939],"about_ca_topic_score_codex":0.00097049045,"about_ca_topic_score_gemma":0.0016347124,"teacher_disagreement_score":0.026890442,"about_ca_system_score_codex":0.0027169678,"about_ca_system_score_gemma":0.004003308,"threshold_uncertainty_score":0.14221197},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055935723,0.046345714,0.015929911,0.27181888,0.01157577,0.00031115246,0.001261009,0.0003482352,0.64681566],"genre_scores_gemma":[0.41667902,0.039235905,0.034222163,0.12661865,0.013151478,0.0014555589,0.0018532457,0.0008337856,0.36595026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93746907,0.029472658,0.002740012,0.003004391,0.024166081,0.0031477793],"domain_scores_gemma":[0.9534226,0.027821401,0.003557193,0.0031598664,0.010500869,0.0015379909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031007176,0.0011704686,0.00073348894,0.0037327893,0.0073456974,0.02729588,0.0024636583,0.010730024,0.01204792],"category_scores_gemma":[0.06047377,0.0005888509,0.00067512796,0.0043881433,0.025954736,0.008273659,0.009163031,0.009871202,0.0033299176],"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":[0.000032324122,0.00002388155,0.00043503856,0.00027883504,0.000010575606,0.00008744059,0.0034260438,0.00052699115,0.000085592306,0.77037096,0.17574507,0.04897727],"study_design_scores_gemma":[0.000008337739,0.000023080545,0.00065705884,0.0007792902,0.0000076059973,0.00008949205,0.001275353,0.00009699653,0.00035411204,0.03907253,0.95758235,0.000053861633],"about_ca_topic_score_codex":0.028452734,"about_ca_topic_score_gemma":0.02078819,"teacher_disagreement_score":0.031007176,"about_ca_system_score_codex":0.018837519,"about_ca_system_score_gemma":0.035048943,"threshold_uncertainty_score":0.16398352},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012093925,0.013682964,0.045581773,0.80757535,0.047606427,0.00022567721,0.0002965515,0.0017215483,0.071215846],"genre_scores_gemma":[0.21122706,0.0208286,0.056650583,0.6173424,0.015114219,0.0005508119,0.0005951262,0.0018184464,0.07587271],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92196286,0.037109096,0.0040683113,0.005049323,0.027220218,0.0045902063],"domain_scores_gemma":[0.7971109,0.08721467,0.0174752,0.02011605,0.05207078,0.026012324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038813513,0.0016986899,0.0012153705,0.0018581199,0.008430765,0.014380038,0.0043295096,0.009310989,0.0167791],"category_scores_gemma":[0.27910224,0.00077394856,0.0016377877,0.0013797993,0.016194953,0.022181869,0.011708112,0.019638484,0.012411552],"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":[0.000100561556,0.00012442161,0.004164863,0.00042573217,0.00010438036,0.0018497582,0.020551274,0.00036795397,0.00020563308,0.0236818,0.78109926,0.16732438],"study_design_scores_gemma":[0.000059511498,0.00014946329,0.001072204,0.0021973518,0.00006110607,0.004566483,0.03200482,0.00072896626,0.00055910175,0.11248851,0.8459711,0.00014140135],"about_ca_topic_score_codex":0.0037475226,"about_ca_topic_score_gemma":0.006428776,"teacher_disagreement_score":0.038813513,"about_ca_system_score_codex":0.006232121,"about_ca_system_score_gemma":0.014402676,"threshold_uncertainty_score":0.20526797},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012831299,0.005097257,0.8898376,0.027893372,0.0003105413,0.004000368,0.00049467385,0.0009238759,0.05861106],"genre_scores_gemma":[0.22093041,0.0019119123,0.76962465,0.0009773794,0.00012483033,0.003332134,0.00032825302,0.000055552624,0.0027147396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9402983,0.03968707,0.003702067,0.0030516766,0.011888603,0.0013723014],"domain_scores_gemma":[0.92708695,0.03751655,0.0052583558,0.0035149558,0.023787307,0.0028359562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05484173,0.0022617748,0.0019777205,0.015684793,0.002469552,0.010066376,0.004887673,0.004170597,0.0053647896],"category_scores_gemma":[0.083266295,0.0007276776,0.001999952,0.009626171,0.0069246585,0.011442672,0.005066645,0.0029073684,0.001202784],"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":[0.00014749424,0.0006961307,0.009604153,0.0013460399,0.00014483443,0.00012884948,0.0031479753,0.0118471505,0.00037452593,0.7543393,0.007837608,0.21038601],"study_design_scores_gemma":[0.00045491924,0.0010873427,0.010903323,0.005150763,0.0004550789,0.0004358873,0.0060199252,0.099594325,0.0021094938,0.81446415,0.059054196,0.00027065896],"about_ca_topic_score_codex":0.013716191,"about_ca_topic_score_gemma":0.011452169,"teacher_disagreement_score":0.05484173,"about_ca_system_score_codex":0.012295266,"about_ca_system_score_gemma":0.021388682,"threshold_uncertainty_score":0.29003423},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019682802,0.009086954,0.003441403,0.8022741,0.09716176,0.0014984071,0.0008423879,0.00041722108,0.08330945],"genre_scores_gemma":[0.05311761,0.02493523,0.028775224,0.29282048,0.04230891,0.0052266335,0.0066480413,0.0010875837,0.5450801],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.90632236,0.03086875,0.007073816,0.005070435,0.03421659,0.016448],"domain_scores_gemma":[0.7217222,0.009394987,0.0057147443,0.009801706,0.11509012,0.13827626],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11381973,0.0015004162,0.001473454,0.0030794044,0.008129925,0.018823855,0.004520904,0.013446416,0.04619631],"category_scores_gemma":[0.13180412,0.00091306947,0.0013603442,0.0032833468,0.0030514926,0.008996935,0.01357058,0.013629782,0.037554827],"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":[0.00006694174,0.000054368575,0.0004535403,0.00013058398,0.000010372724,0.000041472977,0.00023834774,0.000044172935,0.00013797285,0.009364856,0.95385087,0.03560649],"study_design_scores_gemma":[0.000037385526,0.00011207292,0.0016856637,0.00041010638,0.000008963751,0.00004475695,0.0005602858,0.000055919038,0.0001513997,0.0019602324,0.99495393,0.00001925516],"about_ca_topic_score_codex":0.009938511,"about_ca_topic_score_gemma":0.017132001,"teacher_disagreement_score":0.98288035,"about_ca_system_score_codex":0.017119657,"about_ca_system_score_gemma":0.14136225,"threshold_uncertainty_score":0.6019435},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24846217,0.32705778,0.05147551,0.15778086,0.0143919755,0.004313269,0.0054575293,0.0004229119,0.190638],"genre_scores_gemma":[0.96188813,0.020214098,0.0068985503,0.00317805,0.0020539158,0.0009569175,0.00045441568,0.000100944395,0.0042550173],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8189942,0.11643706,0.01833677,0.0031287186,0.041524496,0.0015787059],"domain_scores_gemma":[0.30526027,0.6124736,0.033901393,0.009398254,0.033489402,0.0054771295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13086447,0.00069962215,0.001946432,0.006414097,0.0010681694,0.008577522,0.002112412,0.0024922274,0.021758106],"category_scores_gemma":[0.552545,0.0003906085,0.002791922,0.01075939,0.0042933985,0.006408177,0.004783403,0.0027800114,0.0016456664],"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":[0.013443813,0.0011417689,0.13216348,0.04895117,0.007957137,0.00029064695,0.0042474465,0.0028114659,0.0009749055,0.056070197,0.025904706,0.7060433],"study_design_scores_gemma":[0.0030433144,0.01461165,0.50898904,0.07713795,0.026378514,0.0017708396,0.016970264,0.011528603,0.013250479,0.19363616,0.1318389,0.00084424845],"about_ca_topic_score_codex":0.0016129261,"about_ca_topic_score_gemma":0.0028389085,"teacher_disagreement_score":0.8691355,"about_ca_system_score_codex":0.004879294,"about_ca_system_score_gemma":0.006028531,"threshold_uncertainty_score":0.69208574},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029048212,0.2516394,0.18627007,0.29691812,0.018412726,0.009987321,0.0010152409,0.0005871279,0.20612182],"genre_scores_gemma":[0.47839564,0.09704169,0.31002557,0.054510362,0.0037347593,0.017691111,0.00050034904,0.00042705427,0.03767344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7332855,0.23162672,0.008993659,0.0051170606,0.01901477,0.00196232],"domain_scores_gemma":[0.80120635,0.14284602,0.0099387895,0.017997604,0.024463017,0.0035482687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18016222,0.0012873055,0.003234158,0.003865849,0.004246143,0.020490976,0.0029099667,0.004309713,0.009797356],"category_scores_gemma":[0.20219937,0.0008873072,0.0019349377,0.0036845938,0.014014139,0.016104272,0.005668169,0.0055618696,0.0017144335],"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":[0.0006632376,0.0005660016,0.0051950524,0.025697252,0.00088215247,0.000211551,0.03525829,0.00091324374,0.0014588716,0.2960286,0.042842727,0.59028304],"study_design_scores_gemma":[0.0009470119,0.0017941033,0.008238264,0.091168486,0.0015083146,0.00066543615,0.043466963,0.001842269,0.0031227695,0.23978679,0.6071467,0.0003129034],"about_ca_topic_score_codex":0.011826928,"about_ca_topic_score_gemma":0.014218261,"teacher_disagreement_score":0.18016222,"about_ca_system_score_codex":0.013417027,"about_ca_system_score_gemma":0.05044489,"threshold_uncertainty_score":0.9528003},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25492668,0.023157787,0.022226654,0.05449605,0.0010003195,0.0012700922,0.0028415513,0.00047494177,0.63960594],"genre_scores_gemma":[0.8699081,0.0217903,0.021574445,0.0028423173,0.0001691347,0.00075295096,0.0016207319,0.0001942313,0.081147924],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9864053,0.004596816,0.00048786934,0.0009251178,0.0056537353,0.0019310913],"domain_scores_gemma":[0.97338665,0.0071513997,0.0012551786,0.0010594934,0.015667738,0.0014795443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012559033,0.0005804592,0.0005962393,0.0037441505,0.006912546,0.010364982,0.0012506198,0.0012629806,0.0130165825],"category_scores_gemma":[0.024335543,0.00041722768,0.00075212127,0.008504984,0.004526364,0.004273346,0.0038683491,0.0032165255,0.0015213412],"study_design_candidate":"systematic_review","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":[0.00028076879,0.00034316303,0.09515726,0.004733338,0.00027442124,0.0007698287,0.07553476,0.008498106,0.003699716,0.28835818,0.044824615,0.4775258],"study_design_scores_gemma":[0.00005976719,0.00033025708,0.1729589,0.0069974493,0.0003161995,0.0003325329,0.10143521,0.0030545057,0.005702898,0.021295931,0.68728286,0.00023356905],"about_ca_topic_score_codex":0.62407005,"about_ca_topic_score_gemma":0.67976826,"teacher_disagreement_score":0.9518851,"about_ca_system_score_codex":0.048114892,"about_ca_system_score_gemma":0.10217374,"threshold_uncertainty_score":0.75628775},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3226478,0.0037347355,0.39184254,0.06681217,0.0050495416,0.0057110945,0.0012579581,0.0040716585,0.19887249],"genre_scores_gemma":[0.74364954,0.0013938402,0.21389742,0.004157888,0.0008048512,0.0022768455,0.0007724515,0.00047971072,0.03256745],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9678917,0.017757317,0.0019315341,0.0008473888,0.0108204335,0.0007516888],"domain_scores_gemma":[0.85479355,0.06613469,0.008493271,0.009318543,0.051479697,0.009780157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049607676,0.0006110796,0.0006412529,0.0021916453,0.0031422055,0.0068546887,0.0016076135,0.0027439024,0.005257941],"category_scores_gemma":[0.19461587,0.00050457177,0.0005213475,0.0008561625,0.0008548798,0.008957567,0.004780857,0.0023342296,0.0051207524],"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":[0.0016175292,0.0009324733,0.04365526,0.0010902657,0.00005844427,0.00045817753,0.010860888,0.0010434065,0.0064238724,0.008779505,0.050092965,0.87498707],"study_design_scores_gemma":[0.00070420816,0.0069069723,0.24871413,0.008909101,0.00057509984,0.013529152,0.045065,0.049215473,0.045381855,0.15489206,0.4250475,0.0010594872],"about_ca_topic_score_codex":0.0014030668,"about_ca_topic_score_gemma":0.004475432,"teacher_disagreement_score":0.049607676,"about_ca_system_score_codex":0.002081123,"about_ca_system_score_gemma":0.0060329875,"threshold_uncertainty_score":0.2623536},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023634145,0.0141672,0.23868874,0.3923158,0.0037867057,0.0009557395,0.00009844323,0.00047476817,0.32587844],"genre_scores_gemma":[0.8111094,0.004334113,0.13227876,0.03273885,0.0010381808,0.0031688581,0.00007091995,0.0004194123,0.014841493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6001475,0.3535772,0.006225415,0.013279921,0.021602154,0.0051678517],"domain_scores_gemma":[0.7994269,0.14002188,0.00860494,0.030193547,0.009960752,0.011791978],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20344757,0.0013614803,0.0024411795,0.0047019166,0.019493489,0.042831518,0.004306162,0.014864703,0.003882298],"category_scores_gemma":[0.1168547,0.0019980168,0.0018241509,0.0030027053,0.24567263,0.035396267,0.029039435,0.024958067,0.002001619],"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":[0.000027972752,0.000029772493,0.00030680295,0.00016402178,0.000019964744,0.00006531912,0.029652419,0.00015595746,0.00007729994,0.96057516,0.0020301123,0.006895227],"study_design_scores_gemma":[0.000037306054,0.000048649727,0.00014742369,0.0005528228,0.000008677662,0.000093939496,0.010333923,0.00031215165,0.00013924146,0.94810563,0.04018991,0.000030428142],"about_ca_topic_score_codex":0.0033136571,"about_ca_topic_score_gemma":0.003223601,"teacher_disagreement_score":0.20344757,"about_ca_system_score_codex":0.016175995,"about_ca_system_score_gemma":0.022523506,"threshold_uncertainty_score":0.982291},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016560346,0.97562575,0.00080177304,0.019585902,0.0017521521,0.00005073033,0.00004898708,0.000025553176,0.0019435001],"genre_scores_gemma":[0.004127252,0.98253274,0.002536948,0.008185773,0.0016076372,0.000111921996,0.00009614065,0.000061043145,0.00074053573],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9230305,0.035367656,0.011663113,0.004408984,0.023768561,0.0017612875],"domain_scores_gemma":[0.5659094,0.28996536,0.020173097,0.008470732,0.10855795,0.006923454],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13882571,0.0013679992,0.003918693,0.023110123,0.002434734,0.013789541,0.0062991274,0.0063408776,0.0046870694],"category_scores_gemma":[0.21770202,0.0017889207,0.0029161228,0.027508771,0.008545604,0.019277524,0.00725222,0.010784837,0.001791877],"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":[0.00011537094,0.00010100897,0.0009184924,0.044107635,0.00016984165,0.0001281306,0.0010486637,0.00039996768,0.0002787373,0.024395375,0.10112252,0.8272143],"study_design_scores_gemma":[0.000029418998,0.00009087053,0.0026961167,0.10168781,0.00014005562,0.00033095366,0.0007940838,0.00025636872,0.0002187712,0.0046122638,0.88908213,0.000061222774],"about_ca_topic_score_codex":0.010930102,"about_ca_topic_score_gemma":0.0242556,"teacher_disagreement_score":0.8611743,"about_ca_system_score_codex":0.024699895,"about_ca_system_score_gemma":0.05127047,"threshold_uncertainty_score":0.73418933},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03354306,0.041162934,0.6306914,0.15438513,0.003998639,0.053254407,0.011802985,0.0016160415,0.06954541],"genre_scores_gemma":[0.16114944,0.006474716,0.7693691,0.0079489555,0.0002849308,0.048853498,0.0028762014,0.00027880687,0.0027643372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.47584894,0.4183332,0.047163345,0.0053741727,0.05076118,0.0025191242],"domain_scores_gemma":[0.3862372,0.4297329,0.042649537,0.043042168,0.092445,0.005893224],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46726787,0.0017520997,0.0040511005,0.020939002,0.0040385956,0.016258787,0.0051641976,0.0067658797,0.0040084464],"category_scores_gemma":[0.54233545,0.0019305529,0.008949853,0.014684117,0.013231124,0.010972476,0.010973008,0.008567588,0.000712934],"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":[0.000999019,0.0004673439,0.01574076,0.04065092,0.0030523764,0.00018969389,0.008494598,0.015399812,0.00070254016,0.39918622,0.13226144,0.38285518],"study_design_scores_gemma":[0.0018565817,0.0022094739,0.048197545,0.14240561,0.004994042,0.0005442832,0.009214073,0.03820793,0.0038405354,0.43076456,0.31685618,0.00090919086],"about_ca_topic_score_codex":0.016846003,"about_ca_topic_score_gemma":0.018912347,"teacher_disagreement_score":0.5327321,"about_ca_system_score_codex":0.036478076,"about_ca_system_score_gemma":0.07636089,"threshold_uncertainty_score":0.6569536},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047039315,0.52646786,0.3210067,0.062409334,0.008324506,0.057900984,0.0016258198,0.0006327245,0.016928207],"genre_scores_gemma":[0.072005786,0.20694704,0.54182786,0.0105848145,0.0015009941,0.16480832,0.0010565104,0.00020169652,0.0010669832],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.3050629,0.50257325,0.12608169,0.010996293,0.053143088,0.0021428156],"domain_scores_gemma":[0.21169959,0.6923919,0.03268381,0.02831256,0.03351792,0.001394263],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5750985,0.004063656,0.011326417,0.0885369,0.0060685533,0.03081597,0.010459418,0.0147156315,0.004444985],"category_scores_gemma":[0.6637684,0.0041853213,0.01728223,0.053520363,0.028106384,0.03856281,0.019180415,0.011581981,0.00088973314],"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":[0.000293551,0.0001122058,0.0017629563,0.47074535,0.0042386376,0.000635194,0.028692013,0.0027891959,0.00073053694,0.2730056,0.010789257,0.20620544],"study_design_scores_gemma":[0.0004467868,0.00031316318,0.0014100928,0.7432826,0.005671483,0.00056977896,0.009773061,0.00212622,0.0006712331,0.13130145,0.10416187,0.00027231296],"about_ca_topic_score_codex":0.004588512,"about_ca_topic_score_gemma":0.008914071,"teacher_disagreement_score":0.4249015,"about_ca_system_score_codex":0.028957492,"about_ca_system_score_gemma":0.104218006,"threshold_uncertainty_score":0.5239792},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7041746,0.020153884,0.048600774,0.007934242,0.0012897265,0.00067135564,0.0019427451,0.0003463099,0.21488635],"genre_scores_gemma":[0.9916869,0.0014836248,0.00378593,0.00016556864,0.00013446201,0.00004140254,0.00025504507,0.000040243536,0.0024069252],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9681161,0.013254287,0.0017814224,0.0011736103,0.012817749,0.0028567715],"domain_scores_gemma":[0.7235584,0.22533095,0.011551406,0.007042601,0.02815237,0.0043641767],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.021147933,0.0013476631,0.0010725688,0.0049405512,0.0011738898,0.0066647697,0.0009088931,0.0011437045,0.011706258],"category_scores_gemma":[0.18170406,0.00035009382,0.0022548651,0.0036083881,0.0013912149,0.00426651,0.0022807796,0.0016827879,0.0010886074],"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":[0.0040984903,0.0015442354,0.22803015,0.001538771,0.0018517016,0.00069976755,0.00082301657,0.044210788,0.0023699396,0.05342791,0.007494605,0.6539107],"study_design_scores_gemma":[0.00041915846,0.004364696,0.69045866,0.0020139006,0.0037587993,0.002153206,0.0060004955,0.08040727,0.011617359,0.15698527,0.041396502,0.0004247083],"about_ca_topic_score_codex":0.006011235,"about_ca_topic_score_gemma":0.005445431,"teacher_disagreement_score":0.99505943,"about_ca_system_score_codex":0.0029422112,"about_ca_system_score_gemma":0.0042676954,"threshold_uncertainty_score":0.111842334},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030916375,0.4353784,0.041124288,0.18218519,0.010676665,0.0009188632,0.0036630586,0.0010960624,0.32186574],"genre_scores_gemma":[0.061797634,0.62696654,0.1054915,0.03930408,0.0017956543,0.0013923228,0.0021604963,0.0008793196,0.16021244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972133,0.0010716318,0.0002589615,0.00025929633,0.0011131173,0.00008371669],"domain_scores_gemma":[0.9817488,0.011730271,0.0009955,0.000686872,0.0040506017,0.0007879008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006858755,0.00086823286,0.0007106111,0.0043772548,0.0021584549,0.007085172,0.001604161,0.0022374187,0.024017714],"category_scores_gemma":[0.02407372,0.0008191031,0.00045799563,0.0065960772,0.004573202,0.0067509664,0.0018373338,0.0040048384,0.010984586],"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":[0.0000206972,0.000027635067,0.0006794244,0.0015875859,0.000013656535,0.000069611975,0.0033626377,0.00009628713,0.00017313907,0.019060696,0.6336322,0.34127638],"study_design_scores_gemma":[0.0000093277795,0.00001876534,0.0020192773,0.0037539077,0.000017348782,0.00013998349,0.0021591042,0.000059899357,0.00015207793,0.018092277,0.9735579,0.000020156094],"about_ca_topic_score_codex":0.015211826,"about_ca_topic_score_gemma":0.04463951,"teacher_disagreement_score":0.024017714,"about_ca_system_score_codex":0.0035164508,"about_ca_system_score_gemma":0.012290982,"threshold_uncertainty_score":0.0803473},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34213522,0.024660105,0.0046898318,0.04793945,0.00048780837,0.000173125,0.00022560796,0.000044672357,0.57964414],"genre_scores_gemma":[0.9880802,0.003906043,0.000714816,0.001489722,0.0000383336,0.000036123354,0.000041694148,0.000014908475,0.0056782756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.98653513,0.0056606843,0.00020614007,0.0006201202,0.0025863773,0.004391536],"domain_scores_gemma":[0.9856107,0.009052803,0.0009051982,0.000523847,0.0028443139,0.0010631355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013417678,0.00031057734,0.00062350236,0.0068741576,0.025035806,0.01661684,0.0018106514,0.0028278397,0.0052562677],"category_scores_gemma":[0.029044988,0.00031811962,0.0003208579,0.011731491,0.030360602,0.005145654,0.00435789,0.0035186852,0.00014721107],"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":[0.00012751891,0.000050087652,0.01454023,0.00041322515,0.000046430272,0.0007548087,0.18569987,0.0019309139,0.0005627375,0.7316654,0.0072916066,0.05691722],"study_design_scores_gemma":[0.0000353364,0.00007008555,0.06169062,0.001649823,0.00010068161,0.00019293131,0.4535472,0.00091047864,0.0009192724,0.068289176,0.4124929,0.00010150456],"about_ca_topic_score_codex":0.92858195,"about_ca_topic_score_gemma":0.95219904,"teacher_disagreement_score":0.8230828,"about_ca_system_score_codex":0.17691717,"about_ca_system_score_gemma":0.13670911,"threshold_uncertainty_score":0.9546594},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044386648,0.016791413,0.9250846,0.04090448,0.004766077,0.00037521112,0.00029464942,0.001960924,0.009378748],"genre_scores_gemma":[0.014680114,0.013337707,0.9468826,0.013449317,0.005735134,0.001664773,0.00027781096,0.001243055,0.0027295258],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7820652,0.17050195,0.013957615,0.0042258026,0.028385276,0.0008641647],"domain_scores_gemma":[0.44504523,0.49666652,0.010853232,0.021083787,0.024437193,0.0019141369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14477193,0.0040268516,0.0028494827,0.010690046,0.00260624,0.011531329,0.009469119,0.01391277,0.010129484],"category_scores_gemma":[0.5498069,0.0029444906,0.0023428346,0.010056033,0.017916841,0.024529636,0.008912091,0.02659306,0.010358756],"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":[0.00013002401,0.00015974828,0.000880165,0.0029871606,0.00030073276,0.00062174315,0.0076201046,0.0036428827,0.00071115285,0.3563386,0.30542517,0.3211825],"study_design_scores_gemma":[0.00010088904,0.000110209585,0.000522515,0.0029161293,0.000073063944,0.0008868931,0.0016337807,0.005663741,0.00097321236,0.71905833,0.26779965,0.00026152356],"about_ca_topic_score_codex":0.002864921,"about_ca_topic_score_gemma":0.0031648523,"teacher_disagreement_score":0.14477193,"about_ca_system_score_codex":0.002920556,"about_ca_system_score_gemma":0.0054484685,"threshold_uncertainty_score":0.7656363},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05197283,0.0029138068,0.62435585,0.19392516,0.0006485255,0.006433774,0.00016489634,0.0012101658,0.11837501],"genre_scores_gemma":[0.42365357,0.0014184872,0.5595375,0.0060731242,0.00012011158,0.0043222443,0.00007187576,0.00013893367,0.004664114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8871355,0.09892469,0.0013952599,0.0015226563,0.009629994,0.0013919387],"domain_scores_gemma":[0.91518396,0.056305356,0.0049117384,0.004142892,0.012587319,0.0068687242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.102684416,0.00094403874,0.00087419903,0.0056935064,0.004192205,0.016996842,0.00314784,0.005822201,0.0028235214],"category_scores_gemma":[0.07582124,0.0006760113,0.0007174569,0.0022760916,0.013655693,0.012991335,0.006454194,0.006858059,0.00076179026],"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":[0.00029582402,0.002274492,0.008538733,0.0010255117,0.00008762264,0.00017495698,0.0115995,0.010963574,0.00072294543,0.7524111,0.010572494,0.20133327],"study_design_scores_gemma":[0.0007776647,0.0030312603,0.008393702,0.004924347,0.00019573481,0.00057645974,0.020800533,0.123681195,0.0048934286,0.68591547,0.14648624,0.00032397828],"about_ca_topic_score_codex":0.008105778,"about_ca_topic_score_gemma":0.008846786,"teacher_disagreement_score":0.102684416,"about_ca_system_score_codex":0.015134438,"about_ca_system_score_gemma":0.04561533,"threshold_uncertainty_score":0.5430536},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021100449,0.92043227,0.00830798,0.017688971,0.0059288535,0.00023029806,0.00035553245,0.0004389122,0.04640623],"genre_scores_gemma":[0.007049678,0.8413529,0.029323518,0.01489899,0.0070209713,0.0011616404,0.0008729324,0.0005929625,0.097726345],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909088,0.0038249465,0.001036482,0.00039806866,0.0036273682,0.00020434566],"domain_scores_gemma":[0.97342867,0.016832188,0.001256685,0.001158536,0.0066650133,0.0006589019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077367686,0.0012375201,0.0018001179,0.007764437,0.00091155915,0.006826305,0.0018895377,0.002246169,0.017133262],"category_scores_gemma":[0.025458025,0.00081324915,0.0006466238,0.008315955,0.0025690931,0.004908689,0.0016208343,0.0029475777,0.014236217],"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":[0.000019708285,0.00003585931,0.00009015391,0.002674506,0.000017150947,0.00003349373,0.00032554526,0.00023310288,0.00016398444,0.011542242,0.6312128,0.35365155],"study_design_scores_gemma":[0.0000042337533,0.000014855248,0.00028584377,0.0030254272,0.000007594992,0.00008323726,0.00017720522,0.000075315445,0.000051991923,0.006576978,0.9896868,0.000010497303],"about_ca_topic_score_codex":0.0054513966,"about_ca_topic_score_gemma":0.010870248,"teacher_disagreement_score":0.017133262,"about_ca_system_score_codex":0.0045741964,"about_ca_system_score_gemma":0.008847493,"threshold_uncertainty_score":0.057316482},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004830592,0.010620751,0.60645914,0.3209286,0.0037325073,0.0081475,0.00026782966,0.0007318073,0.04428129],"genre_scores_gemma":[0.09553191,0.0040992517,0.86660177,0.012307863,0.0008039623,0.01675494,0.00020185942,0.0003303198,0.0033681358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3661595,0.5673512,0.018916024,0.017994171,0.02445427,0.005124774],"domain_scores_gemma":[0.37519062,0.49568757,0.022411166,0.05476446,0.038284387,0.013661718],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57787144,0.004544006,0.0065053054,0.023134405,0.019779474,0.049083408,0.01328574,0.022528445,0.009160836],"category_scores_gemma":[0.47648555,0.004206734,0.0061417525,0.014556091,0.069290474,0.076391265,0.03532277,0.01783521,0.0036438862],"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":[0.0004039467,0.00020212066,0.0018790679,0.0050977627,0.0005818247,0.00045692126,0.089209594,0.0026175547,0.00045764475,0.7439116,0.015738051,0.13944389],"study_design_scores_gemma":[0.00042388405,0.0002907804,0.00046416858,0.0067437273,0.00035771565,0.00024729795,0.025885418,0.005131047,0.0005203491,0.81956977,0.14014716,0.00021880862],"about_ca_topic_score_codex":0.012453412,"about_ca_topic_score_gemma":0.017488217,"teacher_disagreement_score":0.42212856,"about_ca_system_score_codex":0.041537292,"about_ca_system_score_gemma":0.13353458,"threshold_uncertainty_score":0.52055967},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55610955,0.01125931,0.18500903,0.025810083,0.00078406726,0.006658667,0.00064637914,0.00021524499,0.21350768],"genre_scores_gemma":[0.9089054,0.0035521826,0.07459771,0.0011465027,0.00011165042,0.0036703101,0.0003797244,0.000052273786,0.0075842612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.91155493,0.07308399,0.0029063805,0.0019883723,0.008336085,0.0021301974],"domain_scores_gemma":[0.7665394,0.20876619,0.004003285,0.006596324,0.013135414,0.00095937506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060237095,0.00063436,0.0010134112,0.0072483523,0.006627776,0.008287329,0.0030934482,0.0021325469,0.011352998],"category_scores_gemma":[0.11509279,0.0005686231,0.00081774767,0.009334709,0.005971221,0.010471991,0.0051727025,0.002305213,0.00073056074],"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":[0.00029148333,0.0026929525,0.044552665,0.0019031743,0.00022516097,0.0025544649,0.21243253,0.0040575326,0.00094150053,0.49736512,0.012260449,0.22072288],"study_design_scores_gemma":[0.00010183647,0.00057479227,0.04062124,0.0065802764,0.0001810851,0.0014416483,0.57342005,0.017073749,0.0027250685,0.24866356,0.108481936,0.00013482291],"about_ca_topic_score_codex":0.0057848054,"about_ca_topic_score_gemma":0.007603145,"teacher_disagreement_score":0.060237095,"about_ca_system_score_codex":0.01041882,"about_ca_system_score_gemma":0.004112858,"threshold_uncertainty_score":0.318568},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1029025,0.0015636327,0.49963441,0.17051417,0.0020474363,0.00083705684,0.000068154106,0.0018592334,0.22057346],"genre_scores_gemma":[0.8385572,0.00046804285,0.12851834,0.01685193,0.00031569807,0.0007509436,0.000057680903,0.00038364212,0.014096638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.94772106,0.036532238,0.0015945793,0.0037405866,0.008647246,0.0017642828],"domain_scores_gemma":[0.87137103,0.065353096,0.0063982,0.019093698,0.028607871,0.009176132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07910418,0.0004474728,0.00046601062,0.0024753897,0.0041765464,0.012123853,0.0019801247,0.003948609,0.00470713],"category_scores_gemma":[0.10786017,0.0006595159,0.0006228182,0.0010068867,0.028252194,0.016979404,0.015146924,0.0088588195,0.0013866937],"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":[0.00009413223,0.0004272937,0.019179236,0.0003211434,0.00006116434,0.00036066354,0.06946992,0.001112925,0.0032416675,0.6965797,0.028398296,0.18075386],"study_design_scores_gemma":[0.00005996494,0.00038616988,0.0060322164,0.00133722,0.00004012364,0.0007600681,0.032567944,0.00704607,0.0056684995,0.54759425,0.39834508,0.00016226737],"about_ca_topic_score_codex":0.0019534288,"about_ca_topic_score_gemma":0.002230284,"teacher_disagreement_score":0.07910418,"about_ca_system_score_codex":0.0075482773,"about_ca_system_score_gemma":0.014908393,"threshold_uncertainty_score":0.4183479},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20121856,0.016272875,0.018940553,0.19386318,0.001605259,0.0008985492,0.0013712272,0.00027585155,0.56555396],"genre_scores_gemma":[0.8552405,0.0050178166,0.0065916707,0.004496443,0.00016501296,0.0002634283,0.00024573732,0.00014146877,0.12783775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9745808,0.005700941,0.0010910123,0.0018904444,0.013219833,0.003516971],"domain_scores_gemma":[0.96213007,0.007051395,0.0024858231,0.0015267216,0.02007952,0.00672648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016867664,0.00043061146,0.0005920513,0.0025791472,0.01909062,0.01311366,0.001901253,0.0023067368,0.010126888],"category_scores_gemma":[0.03217503,0.00073489035,0.00046439804,0.003875886,0.016055243,0.005098028,0.006960044,0.0034714083,0.0008541828],"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":[0.0003567925,0.00014378785,0.04566199,0.0019465397,0.00010669703,0.0009593699,0.20451397,0.0016523842,0.0036944523,0.31645644,0.12528083,0.29922676],"study_design_scores_gemma":[0.000045365963,0.00014705808,0.10645348,0.0017177893,0.00006308431,0.0001855124,0.0802787,0.0008943394,0.0015017587,0.019568061,0.7889415,0.00020344337],"about_ca_topic_score_codex":0.95713776,"about_ca_topic_score_gemma":0.98182184,"teacher_disagreement_score":0.8093895,"about_ca_system_score_codex":0.1906105,"about_ca_system_score_gemma":0.32260457,"threshold_uncertainty_score":0.9387771},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98354256,0.00073496666,0.005611706,0.0014310703,0.00015318481,0.0012963855,0.000018648918,0.00007177382,0.0071397214],"genre_scores_gemma":[0.97895503,0.0008731627,0.017646413,0.00027902218,0.00003513807,0.0014686172,0.00002301786,0.000015453696,0.0007041226],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9832946,0.014609271,0.00028525325,0.00041600675,0.000888097,0.00050673645],"domain_scores_gemma":[0.98331696,0.008763317,0.0018944864,0.0012107854,0.0017652562,0.0030492018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016572423,0.00056902564,0.00038155136,0.0012279985,0.0060684443,0.0019169761,0.0013966186,0.000931742,0.0015695079],"category_scores_gemma":[0.039549828,0.00046051282,0.0002931852,0.00065910746,0.0025606735,0.0022595548,0.006017792,0.001420698,0.00023295432],"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":[0.0018349414,0.0111509655,0.031749304,0.001350504,0.00010659018,0.0012112792,0.3464849,0.0011064911,0.0060295174,0.0033142031,0.0032524015,0.59240896],"study_design_scores_gemma":[0.00153852,0.020913895,0.12684593,0.0052714213,0.0002199762,0.005230297,0.73892367,0.0056737936,0.014933946,0.009718915,0.070121944,0.00060771615],"about_ca_topic_score_codex":0.0042292853,"about_ca_topic_score_gemma":0.014132509,"teacher_disagreement_score":0.9957707,"about_ca_system_score_codex":0.0023250997,"about_ca_system_score_gemma":0.0072143525,"threshold_uncertainty_score":0.08764446},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99376184,0.00034682066,0.00025161513,0.0013960009,0.000016666874,0.00007306047,0.00005858208,0.0000055609967,0.004089909],"genre_scores_gemma":[0.99525744,0.00048818468,0.00035296832,0.0002461984,0.000009020304,0.00006788308,0.00005306024,0.000004642706,0.0035205893],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99564517,0.0013207316,0.00017434114,0.0002487493,0.0012293794,0.0013815933],"domain_scores_gemma":[0.984625,0.004940529,0.0022834896,0.0003514238,0.004171401,0.0036281443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004694855,0.00020559102,0.00037445012,0.00069671747,0.0042757294,0.0019453955,0.00091582973,0.00064828957,0.007356731],"category_scores_gemma":[0.013969202,0.00031606393,0.00026714258,0.00086814846,0.0019084585,0.0010818328,0.0021914886,0.0014517066,0.00036396098],"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":[0.00013662022,0.0004260558,0.60738295,0.0007083943,0.000059086164,0.001094705,0.3170212,0.00037836045,0.0021906171,0.0013584116,0.0028926863,0.066350915],"study_design_scores_gemma":[0.0000109473485,0.000244383,0.79448825,0.00032369595,0.000023617627,0.00015478859,0.19364323,0.000278855,0.00029870303,0.00014601811,0.010353095,0.0000344596],"about_ca_topic_score_codex":0.7655769,"about_ca_topic_score_gemma":0.88993204,"teacher_disagreement_score":0.2344231,"about_ca_system_score_codex":0.011804918,"about_ca_system_score_gemma":0.03553995,"threshold_uncertainty_score":0.47160733},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034307126,0.025344126,0.58905977,0.19976859,0.0022554696,0.006415056,0.0006303947,0.00036703836,0.14185244],"genre_scores_gemma":[0.57526326,0.008240607,0.38580248,0.009842915,0.00064337975,0.015393944,0.00026439098,0.000083713705,0.004465325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7750989,0.18767257,0.007509149,0.0051965863,0.021507738,0.0030150458],"domain_scores_gemma":[0.3811152,0.57740283,0.01073628,0.007195103,0.021906875,0.0016436748],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23509444,0.003819591,0.0032904875,0.011585157,0.0048403125,0.019828143,0.0073103937,0.013171157,0.014273297],"category_scores_gemma":[0.31650677,0.0018296046,0.0050687343,0.0064485576,0.037025876,0.022622636,0.0059061255,0.0094645135,0.0011065644],"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":[0.00017471184,0.00029749257,0.0010807343,0.0020379839,0.00028136958,0.00014899467,0.0033064776,0.0067274156,0.0000989919,0.96461326,0.0020097266,0.019222815],"study_design_scores_gemma":[0.0004197279,0.00034204798,0.00085754297,0.005712874,0.00030417243,0.00012651383,0.004489484,0.021352787,0.00058411376,0.9533779,0.012345634,0.000087115026],"about_ca_topic_score_codex":0.015042699,"about_ca_topic_score_gemma":0.009476488,"teacher_disagreement_score":0.23509444,"about_ca_system_score_codex":0.031124199,"about_ca_system_score_gemma":0.026350204,"threshold_uncertainty_score":0.9432647},"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":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037867256,0.0067683114,0.120490976,0.72681254,0.010855841,0.0013508026,0.00008717358,0.00044396557,0.09532309],"genre_scores_gemma":[0.70622206,0.0032271831,0.08602107,0.14954932,0.0029566633,0.0021444373,0.00012230674,0.00079957576,0.04895737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.37849542,0.42021713,0.026138619,0.018955084,0.13012125,0.026072457],"domain_scores_gemma":[0.31523255,0.312316,0.022289688,0.028464485,0.29361516,0.028082075],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48885494,0.0012252867,0.001800392,0.0055207233,0.037564702,0.029909818,0.008865093,0.015293403,0.0041241976],"category_scores_gemma":[0.5414956,0.0022429929,0.0013793265,0.0032368847,0.06143333,0.017380688,0.021504484,0.024933355,0.0014225831],"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":[0.00022932923,0.00014707111,0.0038446633,0.0008382746,0.000090107955,0.00078305334,0.28017703,0.0016939152,0.0016502426,0.42024964,0.16848896,0.121807694],"study_design_scores_gemma":[0.0001078398,0.0000892204,0.0013747647,0.0022815156,0.0000480918,0.00033184653,0.12703411,0.002269251,0.0018595953,0.103700586,0.7605997,0.00030350834],"about_ca_topic_score_codex":0.10266167,"about_ca_topic_score_gemma":0.13730755,"teacher_disagreement_score":0.51114506,"about_ca_system_score_codex":0.10347164,"about_ca_system_score_gemma":0.17327707,"threshold_uncertainty_score":0.7507428},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009754366,0.01768113,0.052966725,0.7968332,0.005877384,0.00038378776,0.00006647486,0.0003535209,0.116083406],"genre_scores_gemma":[0.7311483,0.020489402,0.09697567,0.11082451,0.003256051,0.0017256299,0.0001789975,0.0007132953,0.034688123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.5891609,0.35479483,0.0077073346,0.005246841,0.03643289,0.006657146],"domain_scores_gemma":[0.64193755,0.2759812,0.006638362,0.018264547,0.047406346,0.009772036],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2608644,0.0011022121,0.0010080712,0.0048757205,0.012463244,0.035262734,0.0058817435,0.009818867,0.0051238653],"category_scores_gemma":[0.28042197,0.0011899547,0.0012820868,0.0040090955,0.05968234,0.023293812,0.014963824,0.02137984,0.0012917215],"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":[0.00007207346,0.00016446928,0.001778779,0.0008952659,0.000045379755,0.00041157572,0.048885413,0.0018351804,0.00012707649,0.6811452,0.10792817,0.15671131],"study_design_scores_gemma":[0.00006107652,0.0001275918,0.0021104794,0.008573023,0.000031794232,0.0003783293,0.06383291,0.002125555,0.0009484065,0.3116655,0.6099091,0.00023625341],"about_ca_topic_score_codex":0.023261737,"about_ca_topic_score_gemma":0.023391424,"teacher_disagreement_score":0.2608644,"about_ca_system_score_codex":0.049722347,"about_ca_system_score_gemma":0.069443226,"threshold_uncertainty_score":0.9114858},"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":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007001019,0.8150608,0.0031242606,0.13614453,0.0066146874,0.000056564364,0.00034812652,0.00011665053,0.03783434],"genre_scores_gemma":[0.017081171,0.8605595,0.004829718,0.018646367,0.0041289856,0.00017358463,0.0007422275,0.00036164277,0.09347679],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99161506,0.0030321025,0.0007638241,0.0008594656,0.003196224,0.0005332041],"domain_scores_gemma":[0.9873037,0.0084893955,0.0009823355,0.00048065252,0.0018909147,0.0008530712],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011612616,0.0023468216,0.001753323,0.0032940218,0.0027632485,0.018496752,0.0021846532,0.0057604187,0.056826346],"category_scores_gemma":[0.01644819,0.0017385002,0.00087444147,0.008880437,0.00842077,0.023526348,0.0050784205,0.008153903,0.024506154],"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":[0.00004710425,0.00003892182,0.00043876417,0.0025289152,0.000019210618,0.00014186537,0.0052208668,0.00013973936,0.00028930543,0.02051575,0.7277826,0.242837],"study_design_scores_gemma":[0.000014521788,0.000015513153,0.00162503,0.0043223044,0.000020038806,0.00020621002,0.0050763353,0.00007681807,0.00027053678,0.02276285,0.9655686,0.000041179395],"about_ca_topic_score_codex":0.02715524,"about_ca_topic_score_gemma":0.05243597,"teacher_disagreement_score":0.9883874,"about_ca_system_score_codex":0.0075554,"about_ca_system_score_gemma":0.017424155,"threshold_uncertainty_score":0.19010311},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3663245,0.021626515,0.14938037,0.33976504,0.0014857166,0.00096884405,0.0002989897,0.00040706733,0.119742915],"genre_scores_gemma":[0.974924,0.0025066405,0.016221698,0.004624471,0.0002118358,0.0003092539,0.00013597138,0.00003831871,0.0010278454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9544366,0.032018714,0.0017380187,0.0030282561,0.0055659944,0.0032123802],"domain_scores_gemma":[0.96726704,0.020465989,0.002824227,0.0033562905,0.0029571503,0.003129338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0439086,0.0017985068,0.0019968601,0.005645441,0.0060404837,0.024303932,0.005589448,0.006409716,0.0032125956],"category_scores_gemma":[0.04657856,0.0013836984,0.0024157234,0.004699041,0.044079516,0.039798275,0.018955084,0.011140904,0.00047505167],"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":[0.00007740227,0.0001175981,0.0083691655,0.0005858839,0.00023211839,0.00062324567,0.3532679,0.0012617091,0.00031038662,0.59623915,0.0032156326,0.035699774],"study_design_scores_gemma":[0.00004476429,0.000119995326,0.003565903,0.0008973617,0.000105641724,0.0008132406,0.22622593,0.0070251487,0.00017329064,0.7428289,0.01807327,0.00012654827],"about_ca_topic_score_codex":0.00819114,"about_ca_topic_score_gemma":0.005210989,"teacher_disagreement_score":0.0439086,"about_ca_system_score_codex":0.014422073,"about_ca_system_score_gemma":0.01392728,"threshold_uncertainty_score":0.23221362},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011932409,0.027588187,0.86402494,0.011259458,0.002217601,0.04172118,0.001593722,0.0006745265,0.038988028],"genre_scores_gemma":[0.0480137,0.008824555,0.8604546,0.002707158,0.00027938103,0.07340119,0.00051193364,0.00027914107,0.0055282745],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.53042305,0.37717578,0.032769352,0.014900655,0.043131553,0.0015996321],"domain_scores_gemma":[0.5857795,0.314729,0.019757248,0.03144244,0.046259906,0.0020319961],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28252083,0.0037582403,0.0041423333,0.013415753,0.005317027,0.017570084,0.0054393113,0.0042504943,0.01910104],"category_scores_gemma":[0.3463305,0.0029044556,0.006027026,0.012541176,0.009880195,0.012892025,0.010551509,0.0070733703,0.0043002274],"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":[0.0009502381,0.0005002312,0.0056406017,0.05225697,0.0027719713,0.00026597094,0.05990768,0.0038520407,0.003614829,0.22640859,0.011848252,0.6319827],"study_design_scores_gemma":[0.0020039505,0.0019687745,0.011585396,0.080797166,0.0036085097,0.0007919797,0.03785442,0.009909719,0.013165517,0.38181126,0.4557538,0.0007495625],"about_ca_topic_score_codex":0.005257048,"about_ca_topic_score_gemma":0.009737203,"teacher_disagreement_score":0.71747917,"about_ca_system_score_codex":0.01564135,"about_ca_system_score_gemma":0.036342338,"threshold_uncertainty_score":0.8847796},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5834897,0.0027687473,0.10141404,0.037061024,0.00041437705,0.0004959056,0.00006322296,0.00008907885,0.27420384],"genre_scores_gemma":[0.99723333,0.000082822284,0.0016157196,0.00023310924,0.00003902555,0.00009871163,0.000004238954,0.0000111733125,0.0006818964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8769285,0.101250835,0.0022607415,0.003658403,0.012098236,0.0038033135],"domain_scores_gemma":[0.55035925,0.4133493,0.012169662,0.0063030967,0.012141475,0.0056771035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.100263886,0.0005997113,0.00071430305,0.0041186977,0.0067853094,0.010231847,0.0016775212,0.0026919714,0.0042384206],"category_scores_gemma":[0.25358143,0.0009625793,0.000527111,0.0017859176,0.03011424,0.011441135,0.0079740565,0.0036932952,0.0002446481],"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":[0.00035987952,0.00035357405,0.035591636,0.0004776075,0.00018241981,0.00046581333,0.27366948,0.0028223789,0.0008655744,0.5894498,0.0025844446,0.09317736],"study_design_scores_gemma":[0.00021852928,0.00030651563,0.024684897,0.0007858288,0.00013873474,0.00028849317,0.1261871,0.008866597,0.001629862,0.8153642,0.021385267,0.00014408737],"about_ca_topic_score_codex":0.0063091395,"about_ca_topic_score_gemma":0.004946845,"teacher_disagreement_score":0.100263886,"about_ca_system_score_codex":0.0053732437,"about_ca_system_score_gemma":0.005724425,"threshold_uncertainty_score":0},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011863782,0.0007745762,0.00009401893,0.9911344,0.007123713,0.000007877116,0.000009498446,0.0000062239837,0.0007310051],"genre_scores_gemma":[0.0013823488,0.00030144388,0.00015178989,0.9848067,0.012384407,0.000029805431,0.0000034187333,0.000011921279,0.0009281217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8438958,0.08591776,0.017157633,0.010213715,0.035874806,0.006940161],"domain_scores_gemma":[0.42998794,0.48278996,0.018334605,0.007695535,0.045896333,0.015295593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10827285,0.0018252349,0.0034358434,0.0020883847,0.014847013,0.017044727,0.0061502317,0.15358038,0.0053907256],"category_scores_gemma":[0.37011775,0.0021003755,0.0028174073,0.003255781,0.025668634,0.011948661,0.009851335,0.14343023,0.0040842663],"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":[0.000058537484,0.000027463402,0.00028616484,0.00022287815,0.000028142093,0.0005696959,0.0023499667,0.000050346138,0.00014335239,0.009153481,0.9806964,0.006413558],"study_design_scores_gemma":[0.00027743893,0.00014588486,0.002335241,0.0029512933,0.00010731034,0.0016202537,0.006871658,0.00045434307,0.00046291025,0.026632143,0.9579325,0.00020897917],"about_ca_topic_score_codex":0.009750675,"about_ca_topic_score_gemma":0.018737532,"teacher_disagreement_score":0.15358038,"about_ca_system_score_codex":0.015638297,"about_ca_system_score_gemma":0.017853295,"threshold_uncertainty_score":0.5726084},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05517223,0.0016762794,0.8372027,0.06982458,0.002998608,0.0013432953,0.0002945336,0.0010801256,0.03040759],"genre_scores_gemma":[0.25695482,0.00060090184,0.73378533,0.0036223882,0.00065584254,0.00089641503,0.00023659422,0.00018476973,0.0030629276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92225456,0.041915398,0.0048333528,0.0037358731,0.024905251,0.0023555972],"domain_scores_gemma":[0.72416496,0.19874986,0.009806251,0.015684174,0.044387434,0.007207265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08713598,0.0015370512,0.002916048,0.006696688,0.004783778,0.018262101,0.0037558277,0.0034863718,0.009546721],"category_scores_gemma":[0.2040172,0.0006548336,0.0026684704,0.0044162185,0.0081776,0.019073501,0.007500732,0.009334352,0.0006846485],"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":[0.00028645352,0.0011042382,0.009205229,0.0012694718,0.00038715266,0.00029902032,0.0035661124,0.013460868,0.0011257124,0.5690714,0.015663976,0.3845603],"study_design_scores_gemma":[0.00010127443,0.00027576386,0.0017394365,0.00041949016,0.00009003954,0.00014815973,0.0037435007,0.033353902,0.0015156002,0.94615656,0.012343502,0.00011275483],"about_ca_topic_score_codex":0.0036702221,"about_ca_topic_score_gemma":0.009112918,"teacher_disagreement_score":0.08713598,"about_ca_system_score_codex":0.00875769,"about_ca_system_score_gemma":0.02703435,"threshold_uncertainty_score":0.4608246},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006311462,0.00987296,0.14392485,0.63037205,0.0034831143,0.00074402615,0.00006235111,0.00018744558,0.20504183],"genre_scores_gemma":[0.7358721,0.006076299,0.14036028,0.08818028,0.0038838943,0.0041635013,0.000060618866,0.00040705773,0.020996025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43638754,0.48815,0.0075266217,0.01924803,0.03947902,0.009208781],"domain_scores_gemma":[0.5521003,0.3530542,0.01426022,0.04126886,0.028409185,0.010907163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38410926,0.0015802792,0.002539853,0.0054246793,0.020372022,0.037460733,0.005565479,0.020682137,0.00607849],"category_scores_gemma":[0.28712684,0.0014739732,0.002193286,0.004498021,0.14775026,0.05836201,0.02999454,0.03143195,0.0011317369],"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":[0.00002612646,0.000026728818,0.0003052581,0.00018585566,0.000025059571,0.000107909415,0.011262294,0.00031122295,0.000055486067,0.97175795,0.0055352114,0.010400836],"study_design_scores_gemma":[0.000039570124,0.00004198078,0.00022755687,0.0009409554,0.000012860869,0.00012095843,0.0059619765,0.0006141496,0.00013311546,0.8933764,0.098486125,0.000044307144],"about_ca_topic_score_codex":0.007304897,"about_ca_topic_score_gemma":0.005667371,"teacher_disagreement_score":0.38410926,"about_ca_system_score_codex":0.024871014,"about_ca_system_score_gemma":0.053899303,"threshold_uncertainty_score":0.75950295},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020752274,0.99576217,0.0010382334,0.0022830572,0.00017215153,0.000034374207,0.000023286913,0.000009943949,0.00046927275],"genre_scores_gemma":[0.0075230063,0.98698086,0.0038052676,0.0010681617,0.00032573423,0.000083618856,0.00003602519,0.000006557979,0.00017075564],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9660749,0.018024039,0.00391081,0.001245848,0.010291789,0.00045256453],"domain_scores_gemma":[0.8259943,0.14333947,0.007943577,0.001673349,0.019741425,0.0013079955],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057008572,0.0017273049,0.007977905,0.008853638,0.00059453264,0.004570164,0.0031008155,0.0039161923,0.0016529858],"category_scores_gemma":[0.09294871,0.00065896363,0.0016973974,0.00889714,0.0025767353,0.0030300668,0.0016101925,0.0035605666,0.00049358146],"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":[0.00013863923,0.000109333676,0.000891953,0.023610316,0.00046346366,0.000039443392,0.00012304867,0.0005697988,0.00010231462,0.0034649926,0.0068479427,0.96363884],"study_design_scores_gemma":[0.0006225034,0.0022994638,0.022224857,0.2877937,0.008809897,0.0018258264,0.0019341325,0.0053760787,0.0032758014,0.048449356,0.6170051,0.0003832354],"about_ca_topic_score_codex":0.008053652,"about_ca_topic_score_gemma":0.01309306,"teacher_disagreement_score":0.94299144,"about_ca_system_score_codex":0.004522971,"about_ca_system_score_gemma":0.012030367,"threshold_uncertainty_score":0.30149376},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070224434,0.012464735,0.15048695,0.12361622,0.00057763373,0.00032038288,0.00023214202,0.00011653291,0.64196104],"genre_scores_gemma":[0.9578674,0.0048535406,0.027105551,0.0016007903,0.0002541633,0.00026215077,0.00005955422,0.000033719803,0.007963127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99478215,0.0037484884,0.00012526984,0.0002792874,0.00071403803,0.0003508786],"domain_scores_gemma":[0.9890525,0.008641431,0.000685828,0.00040169185,0.0007105004,0.0005080585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006009924,0.00083191576,0.0006589781,0.0035132791,0.0041093733,0.009777536,0.0019103168,0.004025083,0.008558504],"category_scores_gemma":[0.007086477,0.0004717161,0.0013498372,0.004482776,0.021297397,0.013345477,0.006742706,0.0042813662,0.0005679828],"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":[0.0000058395594,0.000026884629,0.00041833188,0.000029380222,0.0000048631077,0.00007562846,0.0018235003,0.0017417644,0.00001746982,0.9921068,0.0004184512,0.0033311308],"study_design_scores_gemma":[0.000011288348,0.000020035473,0.00043699317,0.00013708838,0.000008051624,0.000102386395,0.003232242,0.012393056,0.00003405001,0.96751314,0.01609683,0.000014809584],"about_ca_topic_score_codex":0.011812497,"about_ca_topic_score_gemma":0.008884072,"teacher_disagreement_score":0.011812497,"about_ca_system_score_codex":0.00964291,"about_ca_system_score_gemma":0.008084314,"threshold_uncertainty_score":0.06996459},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033227038,0.012367793,0.3876245,0.05632688,0.0014285494,0.00079217646,0.00010589978,0.0002323455,0.5078948],"genre_scores_gemma":[0.8396615,0.0064736065,0.13712594,0.0051062866,0.00069233426,0.0014938099,0.000056800833,0.00011606337,0.009273636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89519393,0.0882131,0.001894604,0.001533064,0.012003043,0.0011622409],"domain_scores_gemma":[0.87870866,0.095393375,0.0044291504,0.0026019847,0.016731838,0.0021349604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055787537,0.0014297297,0.00067633606,0.0063516265,0.0025038992,0.011690442,0.0020554673,0.002256376,0.0046387604],"category_scores_gemma":[0.04516389,0.000405202,0.0006879491,0.0030869336,0.021786852,0.0069290344,0.0048894617,0.0047163004,0.0004888915],"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":[0.00005646988,0.00012469958,0.00083134166,0.0007046306,0.00003525531,0.00006443002,0.0057980022,0.0011029795,0.00017701137,0.9461059,0.0022538279,0.0427455],"study_design_scores_gemma":[0.00011655359,0.0001823889,0.0009389387,0.0023375077,0.00009069847,0.00015551917,0.00760585,0.0038278992,0.0015527264,0.9264856,0.056663904,0.00004248731],"about_ca_topic_score_codex":0.0022064869,"about_ca_topic_score_gemma":0.002390631,"teacher_disagreement_score":0.94421244,"about_ca_system_score_codex":0.014175431,"about_ca_system_score_gemma":0.011150274,"threshold_uncertainty_score":0.2950362},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1464546,0.004822688,0.03756988,0.2375067,0.0041586463,0.00018673127,0.00009201764,0.0004909221,0.5687179],"genre_scores_gemma":[0.91637903,0.0015769765,0.0049402933,0.01378504,0.00073912664,0.00008354187,0.00003955907,0.000101992424,0.062354334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98509085,0.009191758,0.00030702096,0.0009080846,0.003188209,0.001314211],"domain_scores_gemma":[0.9831079,0.0038534023,0.0023663677,0.0027282492,0.0030902706,0.0048538363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009997365,0.00024354472,0.00027006457,0.0006039655,0.0059228768,0.0063103987,0.000724272,0.0018413836,0.009231142],"category_scores_gemma":[0.015850857,0.0002461378,0.0003830401,0.0006509353,0.017692473,0.0034980343,0.006324503,0.005053717,0.0028811907],"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":[0.000067938745,0.0003792236,0.018056432,0.00027193685,0.00004813413,0.00035016003,0.14998001,0.0004041998,0.0024193507,0.57146317,0.08732973,0.16922978],"study_design_scores_gemma":[0.000022820308,0.00015320837,0.025476329,0.00058532413,0.000020927115,0.00057332596,0.058363438,0.00061455363,0.00094689935,0.17724058,0.7359395,0.000063002764],"about_ca_topic_score_codex":0.0036025573,"about_ca_topic_score_gemma":0.0054286732,"teacher_disagreement_score":0.009997365,"about_ca_system_score_codex":0.0026136693,"about_ca_system_score_gemma":0.011031728,"threshold_uncertainty_score":0.052871764},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25733215,0.010093235,0.6367826,0.007944568,0.0010111599,0.0050936816,0.002779241,0.0039520403,0.07501128],"genre_scores_gemma":[0.5618236,0.00238716,0.42803285,0.00054922013,0.0001346515,0.00228277,0.0011393327,0.00014219523,0.0035082423],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9257392,0.0428588,0.007605821,0.0010364732,0.021742757,0.001016949],"domain_scores_gemma":[0.83905303,0.11122002,0.008854401,0.0044031977,0.03453026,0.0019390114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059055794,0.0015579225,0.0017747056,0.012994143,0.0008926424,0.0073298877,0.0009346722,0.001437398,0.0023086106],"category_scores_gemma":[0.12612166,0.0004826413,0.0017254436,0.0062159672,0.0008147516,0.0056647086,0.0026602116,0.0015700982,0.0007201703],"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":[0.00057024666,0.001548864,0.056109622,0.0013349871,0.00060703367,0.00006316972,0.0010337839,0.007300574,0.0008708493,0.012422906,0.007352365,0.9107856],"study_design_scores_gemma":[0.0013301263,0.010131515,0.29183793,0.011933636,0.0057862997,0.0018228292,0.01287086,0.33387882,0.040123016,0.17339773,0.11577661,0.0011106369],"about_ca_topic_score_codex":0.0032673017,"about_ca_topic_score_gemma":0.0051469137,"teacher_disagreement_score":0.059055794,"about_ca_system_score_codex":0.0032324675,"about_ca_system_score_gemma":0.006426793,"threshold_uncertainty_score":0.3123206},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8136778,0.007536212,0.0017266781,0.12665619,0.00039724543,0.00042811115,0.00014262344,0.000039744074,0.049395423],"genre_scores_gemma":[0.9938642,0.0011793027,0.00075734424,0.0019000263,0.00002788832,0.000092777824,0.000017486034,0.000016599695,0.0021444587],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.80497414,0.1326224,0.006992801,0.0049709496,0.024548542,0.025891116],"domain_scores_gemma":[0.6838863,0.23345648,0.0125862835,0.006769463,0.03899401,0.02430752],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.14113827,0.0005235254,0.0013630722,0.0043121055,0.061895333,0.02951867,0.0047579,0.0062223743,0.0026847916],"category_scores_gemma":[0.22287695,0.0011195808,0.00079015805,0.0075620594,0.04060823,0.00653047,0.021001223,0.007995192,0.00020049005],"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":true,"study_design_scores_codex":[0.00013563067,0.000043033,0.015618455,0.00027531313,0.000040484018,0.0008294571,0.94895035,0.0003281763,0.00039013106,0.015634237,0.0027560103,0.014998652],"study_design_scores_gemma":[0.000039336526,0.000051874624,0.014031806,0.00071972824,0.00008085724,0.000113893075,0.92742556,0.0003305694,0.00064104557,0.004930804,0.051508415,0.00012615774],"about_ca_topic_score_codex":0.9538293,"about_ca_topic_score_gemma":0.96495813,"teacher_disagreement_score":0.9381047,"about_ca_system_score_codex":0.28626606,"about_ca_system_score_gemma":0.44505158,"threshold_uncertainty_score":0.8278302},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18520947,0.00036748804,0.7443963,0.0097043365,0.00023329732,0.0043781083,0.0001229999,0.0033576845,0.052230354],"genre_scores_gemma":[0.42734164,0.000214248,0.5653058,0.00039188235,0.000057714624,0.0012117347,0.000126595,0.00026120094,0.0050891247],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9275202,0.053062554,0.0023552093,0.002426617,0.012989397,0.0016458931],"domain_scores_gemma":[0.8961947,0.060261447,0.008063063,0.008031207,0.024029817,0.0034198281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06750033,0.000928104,0.00047091822,0.0035990279,0.0037639525,0.009393726,0.002779484,0.0023735724,0.0035666125],"category_scores_gemma":[0.09538903,0.0008150886,0.00061502063,0.0016780004,0.0032395197,0.0060419324,0.004539912,0.0019483856,0.0015984708],"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":[0.00021838765,0.0015293045,0.01700373,0.0011551781,0.00007002458,0.00062990154,0.1276309,0.003769768,0.018803693,0.037022706,0.012761859,0.7794045],"study_design_scores_gemma":[0.00041615852,0.0060626087,0.05269304,0.006574334,0.00029338914,0.0028825537,0.2101545,0.13502356,0.11477978,0.08032234,0.38977495,0.0010227638],"about_ca_topic_score_codex":0.0025068973,"about_ca_topic_score_gemma":0.003013637,"teacher_disagreement_score":0.06750033,"about_ca_system_score_codex":0.0035831002,"about_ca_system_score_gemma":0.013523075,"threshold_uncertainty_score":0.35698014},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48791447,0.020322556,0.07295597,0.23642468,0.00047345425,0.0005911633,0.0003752586,0.00033707242,0.18060538],"genre_scores_gemma":[0.98809797,0.001600552,0.00843717,0.000718839,0.00005562775,0.00006280186,0.000026475556,0.000014777269,0.0009859084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87019503,0.10343564,0.0047126417,0.0037808283,0.010522202,0.0073537417],"domain_scores_gemma":[0.5585784,0.35146752,0.024924079,0.019797144,0.031453453,0.013779478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10027676,0.0003764035,0.0009488152,0.011138813,0.014319453,0.026591497,0.002577911,0.0046244715,0.0042411983],"category_scores_gemma":[0.20199348,0.0008199692,0.00051253755,0.014122846,0.02849094,0.009278041,0.012608739,0.0052231625,0.00034422503],"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":[0.00015551722,0.00043540247,0.12488092,0.0016089096,0.0002312448,0.0005017477,0.14075762,0.008829632,0.00086119387,0.38967845,0.00880847,0.32325086],"study_design_scores_gemma":[0.00007569116,0.0002200155,0.15673265,0.006625234,0.00015763784,0.0003082625,0.19975784,0.01703427,0.0024196052,0.44053245,0.1758427,0.00029356516],"about_ca_topic_score_codex":0.09726483,"about_ca_topic_score_gemma":0.12054762,"teacher_disagreement_score":0.10027676,"about_ca_system_score_codex":0.039769284,"about_ca_system_score_gemma":0.1100433,"threshold_uncertainty_score":0.5303205},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02092104,0.22504973,0.0058919615,0.6085397,0.006071443,0.0001121098,0.002946901,0.00029108344,0.13017593],"genre_scores_gemma":[0.4806714,0.34083414,0.033846475,0.05726686,0.008936829,0.00019489332,0.0023387186,0.00020359369,0.0757071],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882045,0.0021829018,0.00033571047,0.00062341284,0.0064378357,0.002215664],"domain_scores_gemma":[0.9433199,0.010988421,0.0018662153,0.00081271876,0.03819633,0.00481638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024168925,0.0011074829,0.001462816,0.005870991,0.0051648687,0.008551451,0.0033482367,0.0037205704,0.019864177],"category_scores_gemma":[0.03340333,0.0002753978,0.0010853987,0.011375541,0.0055029504,0.0040411795,0.0019407406,0.0025484469,0.0011980194],"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":[0.0006484531,0.00013889928,0.023948194,0.0014279205,0.00014585716,0.00034256154,0.0007491822,0.0034159836,0.00052430667,0.1700258,0.23357296,0.5650599],"study_design_scores_gemma":[0.00014162503,0.00022027068,0.06633952,0.0028442012,0.00030677713,0.0004215267,0.004743711,0.0066255876,0.0011374314,0.083499946,0.8332173,0.00050212536],"about_ca_topic_score_codex":0.9666205,"about_ca_topic_score_gemma":0.9688816,"teacher_disagreement_score":0.09215211,"about_ca_system_score_codex":0.09215211,"about_ca_system_score_gemma":0.18612334,"threshold_uncertainty_score":0.6686135},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07921702,0.4096492,0.10899512,0.31018785,0.0032601105,0.0010570603,0.00063993636,0.00063221465,0.08636147],"genre_scores_gemma":[0.6845369,0.17776048,0.120116204,0.0108258175,0.0017893878,0.0010315423,0.00035309306,0.00030946534,0.0032771686],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8655325,0.0955029,0.008168658,0.007871283,0.020872857,0.002051767],"domain_scores_gemma":[0.57724047,0.3009056,0.011169597,0.016102297,0.089107886,0.0054741586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22516614,0.0010602818,0.0015368053,0.0056500845,0.0025065467,0.017681032,0.005872633,0.0042265775,0.0035333266],"category_scores_gemma":[0.21258889,0.00076305337,0.00079713436,0.0072587323,0.017718995,0.014531987,0.006398514,0.005650577,0.0006254647],"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":[0.00021122834,0.00036481395,0.00996774,0.0072819665,0.00013417158,0.00008576645,0.015860269,0.0035040565,0.0009033624,0.06478885,0.009562334,0.8873355],"study_design_scores_gemma":[0.00022354002,0.0018021837,0.044635378,0.06398495,0.00037174788,0.00090408686,0.10580448,0.0148990685,0.008651769,0.16835043,0.5894899,0.00088245],"about_ca_topic_score_codex":0.038606234,"about_ca_topic_score_gemma":0.040923912,"teacher_disagreement_score":0.9793124,"about_ca_system_score_codex":0.020687565,"about_ca_system_score_gemma":0.030010238,"threshold_uncertainty_score":0.9555081},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97899914,0.00051653694,0.0076707024,0.0006068525,0.000088626715,0.00015096054,0.00007467454,0.0002264985,0.011666039],"genre_scores_gemma":[0.99304163,0.00021939562,0.003531538,0.0002924579,0.00005892515,0.000116396746,0.000072635696,0.000033268436,0.0026337155],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98480487,0.008809924,0.0008399924,0.0012057526,0.0038565982,0.00048287355],"domain_scores_gemma":[0.9364461,0.040264692,0.011494274,0.0042840634,0.0057060327,0.0018048325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008440099,0.00043469554,0.00048154805,0.000944027,0.0007052584,0.0014669619,0.0005218601,0.0006155813,0.0038931891],"category_scores_gemma":[0.08114145,0.00028999327,0.00034762427,0.00035076682,0.00024320709,0.0007168155,0.0015855529,0.0006961948,0.00061013683],"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":[0.0023161185,0.0011019701,0.32881644,0.0011593802,0.00034485044,0.0005033454,0.04246681,0.0014015251,0.09408623,0.0010597827,0.005789736,0.52095383],"study_design_scores_gemma":[0.00021853366,0.0046877917,0.91923374,0.00038285952,0.00028703528,0.0009190649,0.019585762,0.0058467807,0.024698691,0.0019306975,0.021981329,0.00022769936],"about_ca_topic_score_codex":0.0010821265,"about_ca_topic_score_gemma":0.0015022005,"teacher_disagreement_score":0.008440099,"about_ca_system_score_codex":0.0007736942,"about_ca_system_score_gemma":0.0007495761,"threshold_uncertainty_score":0.04463601},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11599539,0.0026894554,0.588427,0.0051095122,0.0010878941,0.023586791,0.0024678197,0.0017018716,0.25893426],"genre_scores_gemma":[0.61134464,0.0010438096,0.34556186,0.0009485179,0.00027251066,0.019335754,0.0022567713,0.00057453377,0.018661682],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7672253,0.14153636,0.024926983,0.007395183,0.055506364,0.0034097661],"domain_scores_gemma":[0.5687214,0.18593384,0.024782034,0.039725438,0.17714758,0.0036897769],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21332447,0.0013086817,0.0011885896,0.011950475,0.0028216748,0.0063838335,0.0022281585,0.0011764617,0.0123301],"category_scores_gemma":[0.3802526,0.0003852777,0.001956029,0.0051832986,0.0021843049,0.0050754216,0.0063706296,0.001598445,0.0014008085],"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":[0.00079412677,0.00070268154,0.031576466,0.0026104078,0.0004174062,0.00016111677,0.010902294,0.007214093,0.0025903974,0.06722936,0.016040642,0.8597609],"study_design_scores_gemma":[0.0006422613,0.0055916575,0.13069762,0.009171301,0.001392572,0.0009218263,0.030674336,0.06936972,0.02370923,0.20781037,0.5192372,0.0007818705],"about_ca_topic_score_codex":0.0023948413,"about_ca_topic_score_gemma":0.0027611784,"teacher_disagreement_score":0.21332447,"about_ca_system_score_codex":0.005779904,"about_ca_system_score_gemma":0.009333748,"threshold_uncertainty_score":0.97011095},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061250255,0.015464228,0.0015725686,0.8977005,0.008630597,0.00013296207,0.00056142535,0.00009555077,0.069717094],"genre_scores_gemma":[0.37530917,0.045253396,0.010446616,0.20856139,0.008012884,0.00031335634,0.0009322811,0.00037945365,0.35079148],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9704751,0.0064345775,0.0006494861,0.0010981249,0.01790474,0.0034380083],"domain_scores_gemma":[0.8736762,0.013683528,0.0034052983,0.0026012736,0.060649242,0.04598451],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.035567272,0.00091484986,0.0011521275,0.0042463974,0.016858043,0.020299327,0.002228624,0.006146365,0.018849516],"category_scores_gemma":[0.068425156,0.00054641056,0.00044143174,0.005091111,0.017378945,0.0054623433,0.005620298,0.008702902,0.0027566957],"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":[0.000108385975,0.000082620136,0.007789002,0.00012603821,0.000020107618,0.000045267003,0.000770014,0.00028546725,0.00012919409,0.073102124,0.8557561,0.061785795],"study_design_scores_gemma":[0.00007996733,0.000061414496,0.024536783,0.0011678902,0.0000706863,0.00008334205,0.007530009,0.0010639182,0.000502326,0.04160681,0.92311984,0.00017686978],"about_ca_topic_score_codex":0.9018482,"about_ca_topic_score_gemma":0.96562326,"teacher_disagreement_score":0.9644327,"about_ca_system_score_codex":0.08883032,"about_ca_system_score_gemma":0.3264746,"threshold_uncertainty_score":0.6445121},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8667236,0.0062750042,0.023144802,0.011612994,0.0007294497,0.0041969526,0.0053502596,0.00030007144,0.0816669],"genre_scores_gemma":[0.9808421,0.0010448532,0.0075591146,0.00077245635,0.000058768208,0.0025601326,0.0022583106,0.00012373559,0.00478049],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.8339332,0.13773532,0.005515642,0.0031353103,0.015038593,0.0046419306],"domain_scores_gemma":[0.7458105,0.1450539,0.020446166,0.014581645,0.060015514,0.014092329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11422675,0.0005030816,0.00081062794,0.006356962,0.007540758,0.007975354,0.0024792454,0.0012655269,0.0044486397],"category_scores_gemma":[0.22704913,0.000636496,0.0005700048,0.014331176,0.006262408,0.0036480245,0.0072394125,0.002061302,0.00068726897],"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":[0.0012320103,0.00035517497,0.3384147,0.0010270616,0.00021244529,0.0004448441,0.5088618,0.00079677394,0.0004072433,0.0208118,0.022516247,0.10491989],"study_design_scores_gemma":[0.0001022716,0.00045372036,0.5351773,0.0012050235,0.00015046247,0.00014846807,0.40705228,0.0010020423,0.0006040574,0.0029857515,0.050994877,0.00012368917],"about_ca_topic_score_codex":0.53863895,"about_ca_topic_score_gemma":0.69982266,"teacher_disagreement_score":0.53863895,"about_ca_system_score_codex":0.036615115,"about_ca_system_score_gemma":0.034524687,"threshold_uncertainty_score":0.9281562},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012764091,0.062159926,0.59437543,0.025697647,0.006539298,0.006612499,0.023705857,0.03408156,0.24555147],"genre_scores_gemma":[0.0073361252,0.05926947,0.77890056,0.005496043,0.0014738768,0.015661435,0.01460385,0.008478409,0.10878026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.987276,0.00777457,0.0021402896,0.0004570534,0.0020132523,0.0003388139],"domain_scores_gemma":[0.95121425,0.03916166,0.0009140917,0.002406909,0.0054550907,0.0008480363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013940162,0.003493207,0.0028401506,0.0050040553,0.001975601,0.0072415653,0.0033513505,0.003575198,0.11957208],"category_scores_gemma":[0.02247617,0.0035900802,0.0023572776,0.0076571372,0.0046709604,0.0065027196,0.0037156683,0.0083960565,0.11116697],"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":[0.00005987441,0.00014063936,0.00026814154,0.0031452205,0.00004691317,0.00019826084,0.0039968444,0.0011090339,0.0009552232,0.030901972,0.6689892,0.2901887],"study_design_scores_gemma":[0.000020455616,0.000028345261,0.00032577393,0.00093842804,0.000012128131,0.00018026565,0.00064709707,0.00030985023,0.00025055232,0.015833203,0.981412,0.0000418931],"about_ca_topic_score_codex":0.007889103,"about_ca_topic_score_gemma":0.014561899,"teacher_disagreement_score":0.11957208,"about_ca_system_score_codex":0.002417267,"about_ca_system_score_gemma":0.010339344,"threshold_uncertainty_score":0.40000844},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83187836,0.0013039424,0.018886829,0.0074680145,0.000027714532,0.00015211888,0.0001293365,0.000053938566,0.1400998],"genre_scores_gemma":[0.9981254,0.00012653985,0.0013403636,0.000051440165,0.0000032508858,0.000025150925,0.000025004132,0.0000028249628,0.00030013613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903617,0.004234136,0.0005569273,0.00051606324,0.0022202667,0.002111042],"domain_scores_gemma":[0.9601122,0.022811536,0.0038582396,0.0021953867,0.007701904,0.0033207794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011760495,0.00033100837,0.000251636,0.0054334537,0.0031474584,0.0076675583,0.0010519155,0.0010782866,0.001955654],"category_scores_gemma":[0.032389373,0.00026762643,0.0003565613,0.0028981185,0.013836627,0.008487763,0.0061709597,0.0013783795,0.00010399176],"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":[0.000085377585,0.00016612693,0.16933325,0.00042282892,0.000068194546,0.00028454151,0.15818077,0.0053022667,0.0015419619,0.5604243,0.0025243019,0.10166609],"study_design_scores_gemma":[0.000028262468,0.00012419184,0.28397694,0.0011232314,0.000055996043,0.00032991258,0.3372654,0.0130932415,0.0016575905,0.29944205,0.06274616,0.00015701498],"about_ca_topic_score_codex":0.076252244,"about_ca_topic_score_gemma":0.05396079,"teacher_disagreement_score":0.076252244,"about_ca_system_score_codex":0.01782574,"about_ca_system_score_gemma":0.01767699,"threshold_uncertainty_score":0.15161681},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068214074,0.02634601,0.29803506,0.49936596,0.0019660634,0.00050793745,0.00014118782,0.00030510154,0.10511862],"genre_scores_gemma":[0.89176846,0.002990359,0.087538026,0.012831389,0.0012691717,0.0005706508,0.000027671782,0.00028681022,0.0027175243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5479843,0.38794556,0.007438884,0.009753195,0.043516107,0.0033619716],"domain_scores_gemma":[0.36181635,0.5716638,0.019092042,0.017951263,0.024981648,0.0044949143],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.410688,0.0014242112,0.003177085,0.012029239,0.011006556,0.038033877,0.004755534,0.0131118335,0.003500751],"category_scores_gemma":[0.53573954,0.0014036368,0.0009324108,0.0076027135,0.0907036,0.041658368,0.012471569,0.015788576,0.0005699133],"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":[0.00011319269,0.00008844188,0.003572472,0.000426373,0.00013626849,0.00007318411,0.011756906,0.0019037247,0.00022228203,0.89001685,0.00842538,0.08326493],"study_design_scores_gemma":[0.000045255107,0.000060787854,0.0014638386,0.00081462547,0.00003100769,0.0000711878,0.004647026,0.0058098687,0.00041109495,0.97459614,0.011966216,0.00008298824],"about_ca_topic_score_codex":0.008268528,"about_ca_topic_score_gemma":0.0091482885,"teacher_disagreement_score":0.98899347,"about_ca_system_score_codex":0.017868394,"about_ca_system_score_gemma":0.023084538,"threshold_uncertainty_score":0.72672665},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03440774,0.0372216,0.010578572,0.8470388,0.011341496,0.00004307124,0.00004619023,0.00013159678,0.05919103],"genre_scores_gemma":[0.73254687,0.033609003,0.012853353,0.15893115,0.0047512576,0.0001696619,0.0000388222,0.00069874607,0.05640113],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98715395,0.008901647,0.00036254025,0.0010241986,0.0019442049,0.00061344885],"domain_scores_gemma":[0.956795,0.03187426,0.0018890883,0.0019680604,0.004304341,0.0031692775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016245324,0.00037787037,0.00060104,0.0006701809,0.010039204,0.012706695,0.001202689,0.002942207,0.0029877154],"category_scores_gemma":[0.042510208,0.0005451296,0.0003324933,0.00072855153,0.035536233,0.014183576,0.004490181,0.021065064,0.0010353334],"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":[0.00010843918,0.000070924805,0.0010446127,0.0003224639,0.000039774248,0.00060962694,0.4551113,0.00014767726,0.00067907764,0.12491521,0.3548532,0.062097702],"study_design_scores_gemma":[0.000022405911,0.0000629828,0.0014848578,0.0016011035,0.000021547143,0.0009842074,0.22423966,0.00019777851,0.0006660715,0.051239517,0.71933985,0.00014000264],"about_ca_topic_score_codex":0.010903835,"about_ca_topic_score_gemma":0.017853662,"teacher_disagreement_score":0.016245324,"about_ca_system_score_codex":0.0039526937,"about_ca_system_score_gemma":0.004850648,"threshold_uncertainty_score":0.08591449},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03343506,0.0018217539,0.9149211,0.023046287,0.00043678813,0.0055765132,0.000065107,0.00030991767,0.020387486],"genre_scores_gemma":[0.23935577,0.0008830964,0.74114305,0.0023751622,0.00016217872,0.014927765,0.000031525407,0.00011129565,0.001010117],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.42926434,0.5067607,0.015612863,0.005836499,0.040627945,0.0018976865],"domain_scores_gemma":[0.3243181,0.57275754,0.027969617,0.041264206,0.031120446,0.0025700317],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37520546,0.002095821,0.0020695964,0.01255402,0.007656565,0.017666372,0.0038017537,0.0043889224,0.0038706705],"category_scores_gemma":[0.47038847,0.0018801849,0.0024983042,0.009013824,0.038148027,0.024125954,0.019243963,0.009382343,0.00066061306],"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":[0.00025131047,0.0008660225,0.012171636,0.0050677885,0.00058632815,0.00023404259,0.09756332,0.003311527,0.0025126473,0.35001925,0.006083333,0.52133274],"study_design_scores_gemma":[0.00049798016,0.0015423592,0.016579181,0.011232451,0.0007827072,0.0007969544,0.064365014,0.021816857,0.00805583,0.81516737,0.058418036,0.000745245],"about_ca_topic_score_codex":0.0015130033,"about_ca_topic_score_gemma":0.0045442325,"teacher_disagreement_score":0.62479454,"about_ca_system_score_codex":0.011199819,"about_ca_system_score_gemma":0.015296863,"threshold_uncertainty_score":0.7704829},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98800534,0.00014377323,0.0005664129,0.00067642477,0.000006081106,0.00020052843,0.0001664103,0.000033067463,0.010201979],"genre_scores_gemma":[0.9951427,0.00020417031,0.0009482201,0.000037835158,0.000002375787,0.00006581908,0.00016096061,0.000004886314,0.003433096],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987011,0.00026077736,0.000040344006,0.00009537981,0.00040411105,0.00049832027],"domain_scores_gemma":[0.99698955,0.00038577503,0.0002889433,0.00009624561,0.0011140739,0.0011254114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015548377,0.000120849756,0.00016131521,0.0006564091,0.0032771465,0.0011574819,0.00062934816,0.00020411963,0.0016052718],"category_scores_gemma":[0.0038058208,0.00016388764,0.00016130507,0.0012535547,0.0010237362,0.00041841457,0.0011315186,0.00029441714,0.00012826882],"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":[0.00066757906,0.0013097766,0.5256884,0.00049344444,0.00010280234,0.0013395314,0.06368567,0.016425764,0.00814468,0.0067727724,0.012252409,0.36311728],"study_design_scores_gemma":[0.00007905871,0.0005102932,0.8926546,0.00009317507,0.000050808685,0.00006534493,0.06227972,0.006081798,0.0019050831,0.0009491402,0.0352763,0.000054692897],"about_ca_topic_score_codex":0.9324593,"about_ca_topic_score_gemma":0.9776689,"teacher_disagreement_score":0.067540705,"about_ca_system_score_codex":0.042074688,"about_ca_system_score_gemma":0.049138248,"threshold_uncertainty_score":0.30527467},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80960864,0.0028598695,0.07203928,0.01510609,0.00032502934,0.003029101,0.00013793605,0.0004406898,0.096453324],"genre_scores_gemma":[0.97283924,0.000310072,0.02479965,0.00019727582,0.00005085006,0.0004609295,0.000043226653,0.000022123497,0.0012767031],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.85064226,0.127213,0.003156457,0.0022787594,0.014510912,0.0021986836],"domain_scores_gemma":[0.7788133,0.18165939,0.012753158,0.0058716913,0.014998929,0.0059035895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07498828,0.00067962136,0.00047959996,0.0022364873,0.0011032788,0.00901253,0.001903687,0.0018178411,0.0022166418],"category_scores_gemma":[0.16360277,0.0003225767,0.00032921546,0.0017541626,0.002930589,0.0049143145,0.004878218,0.0015269135,0.00032927166],"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":[0.0010963781,0.0038266664,0.0820741,0.001997646,0.0003566129,0.00041891908,0.016460186,0.020753253,0.0041080783,0.05417694,0.0087263165,0.8060049],"study_design_scores_gemma":[0.0020599756,0.032559916,0.17567818,0.006823749,0.0013686611,0.0015154539,0.08235654,0.23038778,0.11265933,0.2574317,0.09645343,0.0007053523],"about_ca_topic_score_codex":0.00080364087,"about_ca_topic_score_gemma":0.0009383543,"teacher_disagreement_score":0.07498828,"about_ca_system_score_codex":0.004327539,"about_ca_system_score_gemma":0.006311879,"threshold_uncertainty_score":0.3965807},"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":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41387278,0.0034210419,0.33062202,0.09829492,0.0015604511,0.019543448,0.00025792565,0.00088670204,0.13154079],"genre_scores_gemma":[0.8261065,0.0016991217,0.14556432,0.005333341,0.00023794935,0.011130272,0.00012506435,0.0004246285,0.00937891],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.41734225,0.54719996,0.010496218,0.004766799,0.015317305,0.0048774723],"domain_scores_gemma":[0.5949866,0.33969396,0.0090726,0.020021643,0.025156789,0.011068427],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35043517,0.0010006265,0.0013105733,0.003682723,0.017646851,0.016871642,0.0046696747,0.0062513254,0.0043317243],"category_scores_gemma":[0.39710388,0.001241921,0.0011683305,0.0027941894,0.029147003,0.014474743,0.023498695,0.010755615,0.0013028347],"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":[0.000106725616,0.00026762736,0.0017126665,0.00059026363,0.000027785285,0.0007620141,0.895867,0.00056251744,0.0013747272,0.03869783,0.00457188,0.055459015],"study_design_scores_gemma":[0.000081277474,0.00060547906,0.0014823243,0.0022196877,0.000047701295,0.00081436965,0.80025417,0.001764562,0.0028220823,0.053148806,0.1365808,0.00017882914],"about_ca_topic_score_codex":0.0026381952,"about_ca_topic_score_gemma":0.003365672,"teacher_disagreement_score":0.64956486,"about_ca_system_score_codex":0.010552167,"about_ca_system_score_gemma":0.026718942,"threshold_uncertainty_score":0.8010291},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6288518,0.0060695196,0.017994288,0.06238907,0.0006733207,0.00021849583,0.000091281574,0.000113427355,0.28359878],"genre_scores_gemma":[0.9448747,0.0029291513,0.0051659886,0.0019359556,0.00008631829,0.000096767006,0.000042774605,0.00005159248,0.044816837],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99001163,0.0065123523,0.0002189017,0.0004179697,0.0015091806,0.0013299559],"domain_scores_gemma":[0.9922416,0.0039082714,0.000453658,0.0003724841,0.0011736504,0.0018504048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010217843,0.00031531724,0.0003061453,0.0008875884,0.008121651,0.006978125,0.0007374564,0.0023335447,0.005849048],"category_scores_gemma":[0.009589314,0.00027288005,0.00024058577,0.0015686749,0.007841211,0.0050027426,0.005341206,0.0040784557,0.00070849154],"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":[0.0002289509,0.0005831137,0.011559572,0.00023778278,0.000009534091,0.0014994097,0.4103475,0.0018954575,0.0011808925,0.35421374,0.026743503,0.19150059],"study_design_scores_gemma":[0.00002947678,0.00028195788,0.0052634208,0.00026372366,0.0000058422133,0.0006561527,0.20610428,0.0009024674,0.00069190224,0.010773344,0.77497995,0.00004731342],"about_ca_topic_score_codex":0.03801473,"about_ca_topic_score_gemma":0.06011904,"teacher_disagreement_score":0.03801473,"about_ca_system_score_codex":0.009057558,"about_ca_system_score_gemma":0.012927097,"threshold_uncertainty_score":0.075586915},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019021282,0.9803507,0.0033766644,0.012198919,0.00045058547,0.000309073,0.0004976416,0.00003311093,0.0008812051],"genre_scores_gemma":[0.025063809,0.95566046,0.011994539,0.00540818,0.00037130283,0.00064971694,0.00047523316,0.00003367948,0.0003429902],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.95241016,0.016976917,0.0145466095,0.003323266,0.012010107,0.0007329798],"domain_scores_gemma":[0.66313106,0.26280856,0.027184375,0.009659354,0.03561612,0.0016004723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.068924606,0.0027088881,0.0077549173,0.03523083,0.002698715,0.011820236,0.0033300759,0.0045776283,0.0029539722],"category_scores_gemma":[0.16589348,0.0023353302,0.004164759,0.034249283,0.0057312082,0.01772322,0.0070626647,0.0053829057,0.00053246954],"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":[0.00019540163,0.00011991356,0.0037549098,0.34826308,0.00326205,0.00014923654,0.0046932567,0.0008165144,0.00070947374,0.009657667,0.013506349,0.61487216],"study_design_scores_gemma":[0.00007874479,0.00028462266,0.009542516,0.80724204,0.0075395317,0.00033323333,0.0079232,0.00046705833,0.00070514757,0.01786174,0.14783712,0.00018509467],"about_ca_topic_score_codex":0.022024933,"about_ca_topic_score_gemma":0.06387908,"teacher_disagreement_score":0.9310754,"about_ca_system_score_codex":0.010242137,"about_ca_system_score_gemma":0.05086936,"threshold_uncertainty_score":0.3645125},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2279489,0.0022450937,0.14315668,0.19376627,0.009341985,0.003202911,0.00011233307,0.0033261976,0.41689965],"genre_scores_gemma":[0.8273485,0.00077776826,0.09592788,0.022413472,0.0012651152,0.001782231,0.000062853636,0.0005186198,0.049903605],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.928192,0.04689859,0.004059466,0.001315328,0.01694284,0.0025917527],"domain_scores_gemma":[0.9073618,0.0389775,0.008430242,0.005974495,0.018413913,0.02084206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05355232,0.00044006165,0.00076320797,0.001161552,0.0051825168,0.0129218595,0.002172179,0.0037944934,0.01159493],"category_scores_gemma":[0.10006285,0.00038755502,0.0004521878,0.00059238635,0.006101722,0.007667326,0.010478282,0.0064197266,0.0035741616],"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":[0.0010261603,0.003586912,0.029378077,0.0012490938,0.00009222425,0.0013450368,0.023825996,0.00206715,0.004903742,0.14589266,0.16215868,0.6244743],"study_design_scores_gemma":[0.00069422374,0.0037342927,0.04828169,0.00412796,0.00025303586,0.0020448745,0.065180115,0.020239847,0.025109893,0.08010741,0.7491906,0.0010360824],"about_ca_topic_score_codex":0.0014666603,"about_ca_topic_score_gemma":0.00450404,"teacher_disagreement_score":0.05355232,"about_ca_system_score_codex":0.0044070263,"about_ca_system_score_gemma":0.012483813,"threshold_uncertainty_score":0.2832151},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6961843,0.028424835,0.017417498,0.12319455,0.00095049257,0.0020022243,0.0013323647,0.00016125829,0.1303325],"genre_scores_gemma":[0.95705354,0.008086235,0.011610059,0.0019344472,0.00007209613,0.0003573702,0.0002654965,0.000035059824,0.020585662],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9731217,0.012102086,0.0017910593,0.0011997027,0.008559146,0.003226352],"domain_scores_gemma":[0.9066897,0.024886949,0.0052398825,0.0014852778,0.05511643,0.006581791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029328855,0.00048659806,0.0006241365,0.0029125314,0.008832615,0.0060404236,0.001618448,0.0010657822,0.0036728545],"category_scores_gemma":[0.07459683,0.00040616788,0.00037186337,0.0050685657,0.0044952845,0.0025121039,0.002492237,0.0014530662,0.00037778015],"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":[0.00065463333,0.00020351475,0.34065285,0.0023698614,0.00016739454,0.0010852804,0.17213015,0.0030909027,0.0030148507,0.021811306,0.02953787,0.42528138],"study_design_scores_gemma":[0.00009873934,0.00039647368,0.59192085,0.0033539566,0.00014646449,0.00033292512,0.18228179,0.0026640282,0.0023887542,0.004214414,0.21190383,0.00029770588],"about_ca_topic_score_codex":0.97659636,"about_ca_topic_score_gemma":0.9899178,"teacher_disagreement_score":0.88592005,"about_ca_system_score_codex":0.114079975,"about_ca_system_score_gemma":0.18958241,"threshold_uncertainty_score":0.82771206},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26111582,0.03598369,0.14948939,0.108036384,0.0032499176,0.0010627059,0.00019594959,0.0003892228,0.44047692],"genre_scores_gemma":[0.9203533,0.0065008686,0.03573247,0.0031491388,0.00035201188,0.00035311523,0.00007852253,0.00011777065,0.033362933],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9286954,0.048673365,0.002965026,0.0023642655,0.014565699,0.00273637],"domain_scores_gemma":[0.9068082,0.05802177,0.0057202852,0.004357729,0.018397255,0.0066947546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049310535,0.0006822671,0.00094253157,0.0037440541,0.004670256,0.0153913265,0.0013415427,0.00290646,0.01005777],"category_scores_gemma":[0.058712356,0.00032268438,0.00083982956,0.0031879141,0.010728101,0.009079471,0.008093653,0.0044593043,0.001263658],"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":[0.00028674063,0.00049769616,0.012490083,0.00222623,0.00008347689,0.0005623414,0.08216207,0.0015523258,0.003305945,0.4398306,0.0103873415,0.4466152],"study_design_scores_gemma":[0.00007182523,0.0010212616,0.03875137,0.0059390217,0.000114080816,0.0011097929,0.11169972,0.0042153364,0.009535756,0.24546203,0.5817967,0.00028310795],"about_ca_topic_score_codex":0.0086771175,"about_ca_topic_score_gemma":0.01116879,"teacher_disagreement_score":0.049310535,"about_ca_system_score_codex":0.011872813,"about_ca_system_score_gemma":0.0261785,"threshold_uncertainty_score":0.26078218},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000164343,0.9239352,0.005950736,0.054325983,0.0041565048,0.00008015353,0.00021053113,0.00010133901,0.0110751465],"genre_scores_gemma":[0.006031297,0.9517374,0.013321505,0.015606026,0.00231885,0.00029089046,0.00023226136,0.0001223251,0.010339354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926912,0.0024621342,0.000945996,0.00039298402,0.003305474,0.0002022403],"domain_scores_gemma":[0.9631821,0.022029674,0.0019655528,0.0006514729,0.011124733,0.0010464084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018065495,0.0011783706,0.0011555761,0.006024815,0.0019277453,0.004019276,0.0024822154,0.005029096,0.010248041],"category_scores_gemma":[0.037605233,0.0009854002,0.0010104111,0.008307139,0.0037030776,0.007695567,0.0023177036,0.0073853126,0.007441012],"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":[0.000043432414,0.000018109882,0.00044919897,0.0039766203,0.000026468728,0.00007211618,0.0010569306,0.00020700102,0.00017256568,0.01196882,0.5962199,0.3857888],"study_design_scores_gemma":[0.000030650815,0.00007876341,0.0028813374,0.015827775,0.00007633372,0.00044953736,0.0007650466,0.00016880746,0.0005197318,0.023900943,0.9552452,0.00005585195],"about_ca_topic_score_codex":0.031648602,"about_ca_topic_score_gemma":0.058825154,"teacher_disagreement_score":0.031648602,"about_ca_system_score_codex":0.0058909515,"about_ca_system_score_gemma":0.016505273,"threshold_uncertainty_score":0.09554064},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45290017,0.006199101,0.0032081234,0.4124344,0.001307328,0.001988688,0.0021726075,0.00038467295,0.11940482],"genre_scores_gemma":[0.94734114,0.0017348683,0.003163867,0.01850896,0.0002841558,0.00071073143,0.0004636078,0.000041794716,0.027750885],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99035174,0.0045222994,0.00035584226,0.00041287852,0.0017797544,0.0025774979],"domain_scores_gemma":[0.98744196,0.003646062,0.0012064901,0.00054144586,0.0029568188,0.0042072088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017545654,0.00038306604,0.00041705987,0.0010067391,0.0016463302,0.0069662165,0.0013033026,0.0030560452,0.004717404],"category_scores_gemma":[0.028906316,0.00033459233,0.00044395868,0.0010723767,0.0035649426,0.003652313,0.004264487,0.003816103,0.0003259665],"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":[0.0022628887,0.0025906588,0.31267065,0.0036334773,0.0006897693,0.00258113,0.011326254,0.008682401,0.0075697564,0.21018037,0.10337544,0.33443713],"study_design_scores_gemma":[0.0009364732,0.002159704,0.43116486,0.0017279742,0.0003800311,0.00045267137,0.02353765,0.004252016,0.0076887193,0.016995076,0.5104262,0.0002786225],"about_ca_topic_score_codex":0.18598461,"about_ca_topic_score_gemma":0.15428087,"teacher_disagreement_score":0.18598461,"about_ca_system_score_codex":0.025703754,"about_ca_system_score_gemma":0.1087633,"threshold_uncertainty_score":0.36980414},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00448101,0.08445513,0.11144498,0.3109683,0.0105205,0.0017404042,0.0021285985,0.001080728,0.47318032],"genre_scores_gemma":[0.25997716,0.123506986,0.21622322,0.07889466,0.012299552,0.004690323,0.0043654894,0.0023223744,0.29772016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8385463,0.043368492,0.013763431,0.0074065547,0.08941179,0.0075035184],"domain_scores_gemma":[0.66994864,0.07358265,0.00935027,0.01953854,0.21991779,0.0076621296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1708321,0.0011377047,0.001510802,0.017924864,0.011207257,0.023901068,0.005849861,0.007421306,0.0058999723],"category_scores_gemma":[0.20294617,0.0019025701,0.0014039736,0.020786026,0.01951945,0.0068729115,0.0059042,0.015989305,0.001859508],"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":[0.00003120284,0.0000706906,0.0010461815,0.0005757432,0.00002667048,0.000058906753,0.0029043518,0.001602531,0.00030869202,0.7112929,0.14922467,0.13285744],"study_design_scores_gemma":[0.000009573116,0.000030375755,0.0028241032,0.0025403467,0.000021395626,0.000046071844,0.00088499504,0.0006134872,0.0004379679,0.042163223,0.95034266,0.000085852764],"about_ca_topic_score_codex":0.6719794,"about_ca_topic_score_gemma":0.62610275,"teacher_disagreement_score":0.6719794,"about_ca_system_score_codex":0.11552066,"about_ca_system_score_gemma":0.28782988,"threshold_uncertainty_score":0.9034573},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059869555,0.005555462,0.015738059,0.36330172,0.036441598,0.0005040666,0.00042825215,0.0011482118,0.5708957],"genre_scores_gemma":[0.17210335,0.0063400306,0.02262331,0.113463,0.014603189,0.00082560984,0.0008314673,0.0015209971,0.66768914],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94648176,0.020840168,0.0032147397,0.004670263,0.022076875,0.0027162135],"domain_scores_gemma":[0.89268875,0.030184854,0.0049978346,0.028158156,0.029394068,0.0145763755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028218932,0.000814721,0.0010527441,0.0034183708,0.0039027263,0.021903297,0.0028222746,0.00787144,0.17179397],"category_scores_gemma":[0.12452159,0.0007419417,0.0010447039,0.0035645035,0.005782472,0.017210849,0.0112942755,0.007987236,0.06055662],"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":[0.0001229906,0.0002602145,0.000906253,0.00050855,0.00003157338,0.00026349255,0.0029505237,0.00020719948,0.0006669506,0.10324658,0.5185415,0.37229407],"study_design_scores_gemma":[0.000045355784,0.00011862772,0.0007249739,0.00046395825,0.00001002918,0.00017450971,0.002543511,0.00019407127,0.00047660075,0.054702334,0.94052464,0.000021338505],"about_ca_topic_score_codex":0.0016839982,"about_ca_topic_score_gemma":0.0016742058,"teacher_disagreement_score":0.17179397,"about_ca_system_score_codex":0.006595337,"about_ca_system_score_gemma":0.0138024315,"threshold_uncertainty_score":0.5747081},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13206697,0.036545727,0.15744573,0.40732798,0.003437072,0.002118465,0.00018623263,0.00032689475,0.260545],"genre_scores_gemma":[0.9390294,0.0069682044,0.042207565,0.005804866,0.00060635654,0.0014376754,0.00005944644,0.00012435987,0.0037621595],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7662625,0.21665725,0.0032913692,0.0039892946,0.005865592,0.003934005],"domain_scores_gemma":[0.5726189,0.40169573,0.007450772,0.0067812493,0.0077133467,0.003739986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15683469,0.0018922737,0.002124576,0.011217555,0.017551385,0.041616924,0.004972361,0.008224075,0.004174175],"category_scores_gemma":[0.16472785,0.0011056989,0.0010590834,0.0074415547,0.13314885,0.055134255,0.017044868,0.010583358,0.00054551964],"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":[0.000037668837,0.000052343006,0.0006858072,0.00064817176,0.000030800227,0.0003453858,0.58683264,0.00027176077,0.00014089979,0.39146748,0.0027821336,0.016704945],"study_design_scores_gemma":[0.00004457823,0.000046426052,0.00033237095,0.0022309565,0.000023476387,0.00016982025,0.42011145,0.0008321605,0.00036277188,0.5306059,0.045193374,0.000046679015],"about_ca_topic_score_codex":0.004605616,"about_ca_topic_score_gemma":0.003880622,"teacher_disagreement_score":0.15683469,"about_ca_system_score_codex":0.018968832,"about_ca_system_score_gemma":0.023609476,"threshold_uncertainty_score":0.82943106},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083896354,0.0032783018,0.8340423,0.026891733,0.0009057815,0.0032433714,0.00016906057,0.0002762673,0.04729694],"genre_scores_gemma":[0.42196482,0.0013981091,0.5661652,0.00259961,0.000325612,0.005090534,0.00012720116,0.00007877804,0.0022501557],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.71053064,0.25988284,0.008518011,0.0051533654,0.012983363,0.0029317297],"domain_scores_gemma":[0.5003913,0.4342481,0.014194005,0.014448086,0.029013762,0.007704712],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18514965,0.0017481479,0.0021488992,0.010243418,0.0070507606,0.016412051,0.0047158212,0.0029601073,0.009293263],"category_scores_gemma":[0.30010316,0.0014869453,0.001558208,0.006283804,0.0035198978,0.009863124,0.019139068,0.0064871963,0.00092987693],"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":[0.00062588765,0.002286996,0.01874228,0.0052190544,0.0010542076,0.0005065024,0.06304387,0.013698827,0.0013361905,0.14925778,0.009878372,0.7343501],"study_design_scores_gemma":[0.0011293136,0.0014839969,0.017139973,0.011531835,0.00092100713,0.0007366037,0.07904616,0.08533692,0.0043993513,0.7267607,0.07108113,0.00043307326],"about_ca_topic_score_codex":0.0033875208,"about_ca_topic_score_gemma":0.0078106285,"teacher_disagreement_score":0.81485033,"about_ca_system_score_codex":0.00856018,"about_ca_system_score_gemma":0.03067243,"threshold_uncertainty_score":0.97917664},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095623214,0.98962116,0.002019227,0.001966982,0.00039835807,0.00006842449,0.000055131783,0.000019862306,0.00489454],"genre_scores_gemma":[0.008049755,0.9878169,0.002691254,0.00055314874,0.00020570283,0.00012167224,0.00007281925,0.0000118760845,0.00047693407],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98687965,0.006160551,0.002669234,0.0007319265,0.0032681176,0.00029059852],"domain_scores_gemma":[0.9126095,0.07110912,0.0038332676,0.001738885,0.01003186,0.00067736336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018790733,0.00096377137,0.0032914632,0.0133009525,0.0011178997,0.005517026,0.0015600601,0.002156009,0.0068840417],"category_scores_gemma":[0.05930339,0.00059390854,0.0011931026,0.02032941,0.0017743543,0.0061834157,0.0019225843,0.0014434913,0.0015423761],"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":[0.000071924565,0.00009402713,0.00070553,0.06813958,0.00019573886,0.00015322951,0.001493093,0.00038729602,0.00037091502,0.005670491,0.012805255,0.9099128],"study_design_scores_gemma":[0.000040429924,0.00036525904,0.009699894,0.30989188,0.0010481972,0.0012949496,0.0065193097,0.00051750254,0.0010586547,0.013218383,0.65624017,0.00010531727],"about_ca_topic_score_codex":0.0042713624,"about_ca_topic_score_gemma":0.009102548,"teacher_disagreement_score":0.018790733,"about_ca_system_score_codex":0.004478382,"about_ca_system_score_gemma":0.011794443,"threshold_uncertainty_score":0.09937608},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40921995,0.051794108,0.059439577,0.24922372,0.001161162,0.003372841,0.0015368792,0.0002766369,0.22397508],"genre_scores_gemma":[0.95331556,0.012456608,0.019723611,0.004421242,0.00020515989,0.0015071317,0.0005406068,0.000060768052,0.0077693034],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8809847,0.08419335,0.0056033456,0.004009684,0.019706756,0.0055021252],"domain_scores_gemma":[0.7310337,0.16380425,0.011038531,0.008004017,0.077472426,0.0086470805],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2100456,0.0004287617,0.0009061283,0.0034054094,0.0037483645,0.016486844,0.0020727601,0.0020139732,0.004755606],"category_scores_gemma":[0.15336399,0.00053400855,0.00032877605,0.009440592,0.0048588812,0.012104336,0.008160501,0.003727769,0.00064982206],"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":[0.001227547,0.00091867906,0.055201713,0.0038304438,0.00006102505,0.0003986543,0.02434105,0.0032580823,0.0010761018,0.24370964,0.015368619,0.6506085],"study_design_scores_gemma":[0.00041647616,0.0027881884,0.079931125,0.01239407,0.00013532516,0.001114826,0.14866057,0.013296645,0.009650909,0.21114357,0.5201675,0.000300801],"about_ca_topic_score_codex":0.007384159,"about_ca_topic_score_gemma":0.006853154,"teacher_disagreement_score":0.2100456,"about_ca_system_score_codex":0.016756052,"about_ca_system_score_gemma":0.030488249,"threshold_uncertainty_score":0.9741544},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92661566,0.0027081324,0.0023199192,0.007519873,0.00023142235,0.0002534387,0.0019147906,0.00010571013,0.058331076],"genre_scores_gemma":[0.9705432,0.000690609,0.0025120764,0.00032280982,0.000040303174,0.00019424073,0.0008217571,0.00004717678,0.024827816],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9846651,0.004544724,0.00074530224,0.0012216389,0.0071324916,0.0016908257],"domain_scores_gemma":[0.8962841,0.033448525,0.00960173,0.003130202,0.051493663,0.0060417354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017075343,0.00040246776,0.00051499245,0.0040211338,0.003600336,0.005938791,0.0012154788,0.0010802452,0.0055786897],"category_scores_gemma":[0.06749908,0.00038859565,0.00036430603,0.0052276165,0.0022618962,0.001793348,0.0018318213,0.0020729662,0.0009529391],"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":[0.0011562904,0.0003332515,0.47749037,0.000965939,0.0002034295,0.00072811975,0.09866889,0.002634961,0.0057477304,0.013904002,0.023445597,0.37472144],"study_design_scores_gemma":[0.000025181711,0.00017392357,0.90646183,0.0004019951,0.00003579896,0.00009556574,0.021395415,0.0008333671,0.0014133328,0.00065205514,0.06841014,0.00010140442],"about_ca_topic_score_codex":0.7367468,"about_ca_topic_score_gemma":0.8317933,"teacher_disagreement_score":0.95642,"about_ca_system_score_codex":0.043579984,"about_ca_system_score_gemma":0.035283145,"threshold_uncertainty_score":0.52960706},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021553796,0.77458304,0.00136166,0.2056287,0.004870724,0.000019507983,0.000056533016,0.000056010536,0.013208294],"genre_scores_gemma":[0.026080612,0.8516398,0.0056113396,0.041142665,0.01291861,0.00018339207,0.00015178224,0.00031712124,0.061954677],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99572206,0.0024482822,0.00023571083,0.00039373018,0.00096202805,0.00023807574],"domain_scores_gemma":[0.98133904,0.014751957,0.00058347813,0.00059679453,0.0018274202,0.0009012192],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0110107465,0.0019484292,0.0014382263,0.0036075003,0.0029326894,0.008593123,0.0017200918,0.0065208892,0.015153661],"category_scores_gemma":[0.021047778,0.0014591973,0.0006943144,0.0041288515,0.020728003,0.017163914,0.0032233237,0.010199571,0.0085113635],"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":[0.00002972884,0.000025875459,0.00032333395,0.001266098,0.00004962697,0.00008047966,0.0021746207,0.00021747418,0.00011815582,0.08238023,0.808342,0.10499242],"study_design_scores_gemma":[0.000022555088,0.0000258989,0.0011134339,0.0034087598,0.000020156758,0.00018096813,0.0025994368,0.00027665464,0.00008769334,0.23076487,0.7614646,0.000035013185],"about_ca_topic_score_codex":0.011375612,"about_ca_topic_score_gemma":0.025571574,"teacher_disagreement_score":0.98898923,"about_ca_system_score_codex":0.00448896,"about_ca_system_score_gemma":0.006464482,"threshold_uncertainty_score":0.058231115},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010274211,0.055204857,0.659018,0.060688216,0.0033116902,0.002668846,0.00019569285,0.0002801865,0.20835836],"genre_scores_gemma":[0.47531143,0.03542738,0.46265003,0.0116439415,0.0016478382,0.0055271597,0.00019964844,0.0003031834,0.0072893477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6221925,0.34015197,0.007971349,0.004127808,0.023161488,0.0023948704],"domain_scores_gemma":[0.5960803,0.35767066,0.0120324725,0.010835202,0.020655569,0.0027258547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19783479,0.0016954142,0.002258467,0.013436091,0.0056166,0.019426245,0.0038879614,0.004638157,0.006792222],"category_scores_gemma":[0.1978679,0.00082083856,0.0018117927,0.015153135,0.04189882,0.018280745,0.008173398,0.008133217,0.0010572341],"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":[0.000059494258,0.00008085795,0.0011985475,0.0029201426,0.000101289945,0.00007536653,0.00562389,0.0034968285,0.000079926984,0.8916586,0.004471207,0.09023384],"study_design_scores_gemma":[0.000066602464,0.0001457912,0.0009145045,0.009569376,0.00008768733,0.00012568706,0.0058999113,0.0054318435,0.00049306697,0.9137488,0.06342723,0.00008945067],"about_ca_topic_score_codex":0.0064839306,"about_ca_topic_score_gemma":0.005952217,"teacher_disagreement_score":0.19783479,"about_ca_system_score_codex":0.029717071,"about_ca_system_score_gemma":0.03859784,"threshold_uncertainty_score":0.9892125},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14580928,0.01593145,0.34065855,0.09418296,0.0005817396,0.0028068086,0.00020974485,0.00052020757,0.3992993],"genre_scores_gemma":[0.91314673,0.004007331,0.07818524,0.0014523022,0.000089480855,0.0005127036,0.00004352311,0.000019448262,0.002543337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92588145,0.065462984,0.0013048729,0.0005805253,0.005559944,0.0012102315],"domain_scores_gemma":[0.9468051,0.041522823,0.0032345478,0.0014234353,0.005011362,0.0020027466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056342144,0.00056525815,0.0007059893,0.002700732,0.0016909561,0.009153529,0.0009931433,0.0013911725,0.0031808065],"category_scores_gemma":[0.048768885,0.0002053618,0.00051543146,0.0018593718,0.005216806,0.0051380703,0.0046705795,0.0016441176,0.00026928243],"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":[0.00034294612,0.00087385235,0.0096678175,0.0021646365,0.00011033446,0.00014871953,0.0045488887,0.012355261,0.00085826806,0.6403917,0.010821733,0.31771585],"study_design_scores_gemma":[0.00069518614,0.0024785923,0.019040646,0.012594235,0.00045054313,0.0005422341,0.021268284,0.06841223,0.007942213,0.7217634,0.14452615,0.00028635643],"about_ca_topic_score_codex":0.0021072428,"about_ca_topic_score_gemma":0.0024843663,"teacher_disagreement_score":0.056342144,"about_ca_system_score_codex":0.005687425,"about_ca_system_score_gemma":0.014307735,"threshold_uncertainty_score":0.29796928},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050952435,0.010390025,0.7322032,0.06465534,0.0013466614,0.009933674,0.00033176556,0.0003701483,0.12981679],"genre_scores_gemma":[0.60956156,0.002215636,0.37483475,0.003916697,0.0002876163,0.007153122,0.000064514665,0.00008425187,0.0018818757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.38678676,0.5806772,0.0072533297,0.004384159,0.018857364,0.0020411832],"domain_scores_gemma":[0.3751899,0.5694263,0.015005752,0.014549373,0.023558978,0.002269646],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.37300056,0.0018533557,0.0028406316,0.0071444428,0.004275055,0.016333101,0.0037784884,0.0044758082,0.006227457],"category_scores_gemma":[0.41240168,0.0011059837,0.0018811603,0.0036373672,0.01624967,0.011772972,0.009119702,0.0068967543,0.00047428405],"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":[0.0013168248,0.0015886729,0.0114158215,0.008507739,0.001804088,0.00029511304,0.010505495,0.0669147,0.00059727207,0.62926006,0.006627094,0.26116714],"study_design_scores_gemma":[0.001801492,0.0032468985,0.007200122,0.01066285,0.0007197712,0.00027300618,0.009817599,0.11525274,0.0030891402,0.80321264,0.044338766,0.00038505546],"about_ca_topic_score_codex":0.007522498,"about_ca_topic_score_gemma":0.011880244,"teacher_disagreement_score":0.37300056,"about_ca_system_score_codex":0.025431296,"about_ca_system_score_gemma":0.034781013,"threshold_uncertainty_score":0.77320194},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061677594,0.0034175029,0.33833128,0.05150426,0.0006274938,0.003187099,0.00015287093,0.00073002384,0.54037184],"genre_scores_gemma":[0.5990266,0.0032116615,0.36559576,0.0037166567,0.00007593268,0.0028374537,0.00014912478,0.00015981475,0.025226945],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98682797,0.009144016,0.00036908413,0.0009295912,0.0018048261,0.0009245438],"domain_scores_gemma":[0.98821056,0.0073936004,0.0006948474,0.0008577025,0.0014842387,0.0013591548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017283015,0.0011925419,0.00046579304,0.00258635,0.0026677207,0.0070395023,0.0030372778,0.003096192,0.008934593],"category_scores_gemma":[0.02153869,0.0004166559,0.00063864706,0.0007800923,0.0071049435,0.005218279,0.0064175096,0.0019843434,0.0022090413],"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":[0.00008214499,0.0008623693,0.007539501,0.0016529028,0.000088764195,0.0006573746,0.05396657,0.004361473,0.0017470233,0.36937007,0.019135049,0.54053676],"study_design_scores_gemma":[0.00013588596,0.00079001114,0.0063641695,0.007555703,0.00010373766,0.00087125535,0.08781788,0.016331319,0.004718245,0.5257631,0.34941,0.00013878614],"about_ca_topic_score_codex":0.0032156878,"about_ca_topic_score_gemma":0.0039975927,"teacher_disagreement_score":0.017283015,"about_ca_system_score_codex":0.004884038,"about_ca_system_score_gemma":0.01508974,"threshold_uncertainty_score":0.09140235},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80983984,0.017477216,0.0007547582,0.01417929,0.00039558212,0.0010479385,0.005031527,0.00018183497,0.15109198],"genre_scores_gemma":[0.9755373,0.00540848,0.0008328998,0.0018603242,0.000049900882,0.00039973183,0.0022747503,0.00004947347,0.013587092],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9814217,0.002632043,0.0007352474,0.00071773614,0.007006616,0.0074867676],"domain_scores_gemma":[0.9675637,0.0039206897,0.0026325278,0.0007127056,0.016097886,0.009072383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048914948,0.00032812005,0.0009869975,0.0053355726,0.005310656,0.0045681796,0.0018814909,0.00094444177,0.0053435094],"category_scores_gemma":[0.024247678,0.00047939044,0.0006009392,0.012893772,0.002027196,0.0014257331,0.003729693,0.0018326995,0.00029891534],"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":[0.0037332426,0.0022075751,0.38461477,0.0046124505,0.0008003341,0.0013683037,0.03591019,0.006957947,0.0018634112,0.09680984,0.065535024,0.39558688],"study_design_scores_gemma":[0.00039303603,0.00039078938,0.9218441,0.0009753388,0.0001411232,0.00011797108,0.014772893,0.00050768384,0.0002756996,0.0005434174,0.05995858,0.0000792238],"about_ca_topic_score_codex":0.9897966,"about_ca_topic_score_gemma":0.9953976,"teacher_disagreement_score":0.12999713,"about_ca_system_score_codex":0.12999713,"about_ca_system_score_gemma":0.13962601,"threshold_uncertainty_score":0.94319963},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04345281,0.06469052,0.13015288,0.57821447,0.0040851603,0.0023129238,0.000420769,0.00035310246,0.17631733],"genre_scores_gemma":[0.8156778,0.018982332,0.1260065,0.030397303,0.0005241781,0.0015110091,0.00023600007,0.00032811143,0.006336661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8164898,0.101824485,0.010631408,0.007875972,0.04918565,0.013992646],"domain_scores_gemma":[0.7626232,0.06398183,0.007450372,0.005568599,0.14517605,0.015199918],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16551514,0.0013073487,0.0024590786,0.014829357,0.037112202,0.0365443,0.0073173973,0.0066731973,0.0020433753],"category_scores_gemma":[0.16151349,0.0010150219,0.0013399662,0.01449276,0.0729346,0.017485784,0.016663047,0.016301813,0.0003716185],"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":true,"study_design_scores_codex":[0.000116891184,0.00011805878,0.010594108,0.0030315581,0.00010922277,0.00046395246,0.1770221,0.0017652274,0.0011907322,0.63557136,0.033505533,0.13651133],"study_design_scores_gemma":[0.00009118948,0.00016221298,0.01969785,0.022299398,0.0003025282,0.00054636935,0.32550147,0.003810392,0.0018556896,0.19336951,0.4317728,0.0005906197],"about_ca_topic_score_codex":0.93756104,"about_ca_topic_score_gemma":0.9489504,"teacher_disagreement_score":0.8344849,"about_ca_system_score_codex":0.27071652,"about_ca_system_score_gemma":0.5470752,"threshold_uncertainty_score":0.8753382},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.310509,0.0028675487,0.040236685,0.108794816,0.00034735,0.0006891305,0.00007226004,0.00030779815,0.53617543],"genre_scores_gemma":[0.97520876,0.0005779939,0.007978215,0.002624129,0.00004526568,0.00016915849,0.0000121253,0.00011475324,0.013269668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.89419293,0.080885656,0.00110162,0.0020748524,0.013359313,0.008385685],"domain_scores_gemma":[0.9013883,0.07718405,0.0034073505,0.0046545966,0.009119047,0.004246599],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.075108916,0.00079563854,0.00086469925,0.0031419382,0.032689158,0.03302682,0.0037551317,0.008534928,0.004342149],"category_scores_gemma":[0.0624779,0.00072112697,0.0008868957,0.0033132776,0.0562201,0.011207045,0.010546647,0.013305315,0.0005061783],"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":[0.00009712376,0.00016650489,0.0027392418,0.00015049997,0.00001732002,0.004585906,0.3968565,0.0014422522,0.00047107082,0.5642857,0.007429224,0.021758681],"study_design_scores_gemma":[0.00015783998,0.00022816237,0.004181713,0.0013343276,0.00009082045,0.002409658,0.5062369,0.008259964,0.003150814,0.13028671,0.34346282,0.00020030848],"about_ca_topic_score_codex":0.26077476,"about_ca_topic_score_gemma":0.24701832,"teacher_disagreement_score":0.94064486,"about_ca_system_score_codex":0.059355155,"about_ca_system_score_gemma":0.046000455,"threshold_uncertainty_score":0.5185138},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08795315,0.03589273,0.106101625,0.10015045,0.008378028,0.0031151327,0.0011843758,0.00079437654,0.6564301],"genre_scores_gemma":[0.8289646,0.009664225,0.04473551,0.010848245,0.0016848583,0.0030970452,0.0006716126,0.00059599493,0.0997378],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87648165,0.08046201,0.0056636655,0.0053236783,0.028784335,0.003284675],"domain_scores_gemma":[0.8236334,0.10655151,0.011900341,0.018248392,0.03401867,0.0056476723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06821715,0.0008874147,0.0017702644,0.003919568,0.0039499816,0.013660979,0.0023962064,0.0029411817,0.041699447],"category_scores_gemma":[0.1908727,0.00041603262,0.001756983,0.0033511287,0.0071487804,0.011794449,0.008013248,0.00513967,0.00456583],"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":[0.0007537494,0.0006084352,0.009636879,0.0023672548,0.00027181234,0.00008547719,0.013702512,0.0012951831,0.0006112216,0.21914753,0.04143367,0.71008617],"study_design_scores_gemma":[0.00046275486,0.0022245217,0.032499254,0.0091139,0.0004188034,0.00028184004,0.01746328,0.003945807,0.0037566382,0.17465685,0.75496,0.00021634884],"about_ca_topic_score_codex":0.008724126,"about_ca_topic_score_gemma":0.009315178,"teacher_disagreement_score":0.06821715,"about_ca_system_score_codex":0.0132666705,"about_ca_system_score_gemma":0.0130644385,"threshold_uncertainty_score":0.36077106},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1165899,0.00052344595,0.04639606,0.014611915,0.0006661129,0.0014063489,0.00029653293,0.0011106827,0.818399],"genre_scores_gemma":[0.76891226,0.00043694643,0.033840686,0.0053510456,0.00012468065,0.0010716543,0.0005085396,0.00060330477,0.18915085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98088765,0.0053333645,0.0009106689,0.0020883821,0.006931259,0.0038485806],"domain_scores_gemma":[0.9696362,0.007813411,0.0014936842,0.0064340355,0.009439566,0.005183118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01973088,0.0009940525,0.00072111015,0.0016554899,0.0060415864,0.013696073,0.002166602,0.0036910307,0.08385977],"category_scores_gemma":[0.045197345,0.00053627585,0.0010813572,0.00096737064,0.0029741304,0.011617494,0.013129788,0.0035538261,0.02135025],"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":[0.00044316886,0.0027328474,0.018480493,0.00047974492,0.00009402122,0.0010632994,0.01669014,0.0012064109,0.005751114,0.46102297,0.06757823,0.4244576],"study_design_scores_gemma":[0.00022243641,0.0017028237,0.019476967,0.000902239,0.0001045686,0.001017252,0.035871956,0.004318959,0.00982556,0.19366728,0.7327115,0.00017848365],"about_ca_topic_score_codex":0.0046858108,"about_ca_topic_score_gemma":0.007490766,"teacher_disagreement_score":0.08385977,"about_ca_system_score_codex":0.0066024857,"about_ca_system_score_gemma":0.013767885,"threshold_uncertainty_score":0.28053886},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064128764,0.0029902128,0.8594982,0.01758174,0.00077174813,0.0014899602,0.0005701922,0.00050561945,0.052463572],"genre_scores_gemma":[0.4866986,0.00227063,0.49996126,0.0027403398,0.00027463742,0.004670847,0.0005224606,0.000117695374,0.0027434567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79922456,0.13950288,0.01081099,0.011798757,0.035936866,0.0027259856],"domain_scores_gemma":[0.7364173,0.13909146,0.024665508,0.032026492,0.06439362,0.0034056455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12904495,0.0010501967,0.0013805538,0.005572424,0.0024632437,0.007968769,0.0022867443,0.0037425251,0.0019502039],"category_scores_gemma":[0.25538138,0.0006870954,0.0006551579,0.005905854,0.006546078,0.016917355,0.013247183,0.005529729,0.0008727475],"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":[0.00016640409,0.00042706507,0.05150686,0.0017323539,0.00012743808,0.00008471746,0.028026538,0.0032806024,0.004387979,0.4711637,0.012317078,0.4267793],"study_design_scores_gemma":[0.00008981324,0.00088985526,0.05800097,0.0046851,0.00013651814,0.00033837513,0.027526962,0.018868204,0.010591007,0.7301467,0.14844984,0.00027667053],"about_ca_topic_score_codex":0.002586099,"about_ca_topic_score_gemma":0.0020700553,"teacher_disagreement_score":0.12904495,"about_ca_system_score_codex":0.0041024745,"about_ca_system_score_gemma":0.007649344,"threshold_uncertainty_score":0.68246305},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005128591,0.9927704,0.0007310025,0.0028655643,0.0008741528,0.00007460466,0.000042456508,0.000017068438,0.0021119504],"genre_scores_gemma":[0.01317201,0.98047286,0.0023859947,0.002322221,0.0006172649,0.00012279575,0.00008103072,0.0000040151785,0.000821743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924954,0.0032787253,0.0012855564,0.00054727093,0.0022048415,0.00018819886],"domain_scores_gemma":[0.98028153,0.013284094,0.0029628992,0.0005495462,0.002569898,0.00035189828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011946382,0.0008373237,0.0022070264,0.0041561075,0.00040479895,0.0021378908,0.0012488003,0.0019237979,0.004551218],"category_scores_gemma":[0.03717179,0.0003549163,0.0010840751,0.0036501035,0.0013166455,0.0027819143,0.0012643316,0.0018765186,0.0007910433],"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":[0.0000737614,0.0000414618,0.0005744126,0.017609045,0.00018214196,0.000029048952,0.00009254983,0.00008305249,0.000057205933,0.0013266214,0.00970198,0.9702287],"study_design_scores_gemma":[0.000563363,0.001052747,0.018505935,0.16785134,0.0029700694,0.0022475861,0.0008944855,0.0006449103,0.0012712992,0.01492292,0.78896093,0.000114402836],"about_ca_topic_score_codex":0.0016996898,"about_ca_topic_score_gemma":0.005682716,"teacher_disagreement_score":0.011946382,"about_ca_system_score_codex":0.0016598072,"about_ca_system_score_gemma":0.0051499913,"threshold_uncertainty_score":0.063179255},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96111757,0.003398145,0.0029180804,0.008384738,0.000031393163,0.000022500713,0.00011169611,0.000023645853,0.02399226],"genre_scores_gemma":[0.998276,0.0008697377,0.00046560145,0.00016199952,0.000031594387,0.000012651314,0.000033545624,0.000006540259,0.00014241977],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9352961,0.041284643,0.004364516,0.0025724368,0.013289587,0.0031927645],"domain_scores_gemma":[0.4351987,0.41211557,0.09783384,0.022814957,0.023338277,0.008698658],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028959945,0.0003103855,0.00055879034,0.008476022,0.0023632196,0.0070579317,0.0013403294,0.0015752863,0.005103831],"category_scores_gemma":[0.19293909,0.00060490106,0.0004374405,0.0110585885,0.01315538,0.008475112,0.0065090074,0.002756605,0.00037354912],"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":[0.00056954304,0.0007016485,0.7186745,0.0013024344,0.00026155703,0.00030163283,0.07340612,0.0008227781,0.0014196456,0.0460293,0.0013836947,0.15512715],"study_design_scores_gemma":[0.00004142294,0.0003014789,0.8767357,0.0009778421,0.0001067184,0.00043009318,0.09127908,0.0010481494,0.0009464239,0.012690382,0.015352573,0.0000901557],"about_ca_topic_score_codex":0.007919432,"about_ca_topic_score_gemma":0.011517477,"teacher_disagreement_score":0.97104007,"about_ca_system_score_codex":0.0042104106,"about_ca_system_score_gemma":0.004862611,"threshold_uncertainty_score":0.15315664},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937748,0.00008695667,0.0002078799,0.0001215133,0.0000032655944,0.000047950412,0.000016204833,0.0000037949467,0.005737504],"genre_scores_gemma":[0.99897134,0.000040893745,0.0001856863,0.0000328333,0.0000026357989,0.000037405014,0.0000105759145,0.0000016958797,0.0007169664],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99210006,0.004450553,0.00036799163,0.00032125128,0.0012292186,0.0015307942],"domain_scores_gemma":[0.93068355,0.05164348,0.005013694,0.0018369472,0.0034848645,0.0073376237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014766131,0.0002967519,0.00045635548,0.004486037,0.0045530912,0.007336809,0.0012131071,0.0011771842,0.007878089],"category_scores_gemma":[0.039076135,0.00029352363,0.0003245178,0.0027575896,0.0031475334,0.0035470508,0.0067963633,0.0013568953,0.0005460279],"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":[0.0023580506,0.012013917,0.7058178,0.00034213645,0.00011927161,0.0010935526,0.10627818,0.00068975514,0.002373236,0.020600723,0.0007969642,0.14751634],"study_design_scores_gemma":[0.000111720816,0.0025098007,0.654939,0.00027413227,0.00010040179,0.00035109144,0.32696104,0.0012922649,0.0024925906,0.004273213,0.006628608,0.00006605057],"about_ca_topic_score_codex":0.0024246327,"about_ca_topic_score_gemma":0.004779698,"teacher_disagreement_score":0.98523384,"about_ca_system_score_codex":0.0039126896,"about_ca_system_score_gemma":0.0070856684,"threshold_uncertainty_score":0.07809168},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021305146,0.0061735585,0.003143341,0.88366866,0.0011953657,0.0010589712,0.000400321,0.00014734671,0.08290732],"genre_scores_gemma":[0.59733236,0.01161908,0.042330228,0.28685457,0.0009275821,0.0020222305,0.000769832,0.00012265745,0.058021437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.945071,0.014157526,0.002100608,0.0020093338,0.017582001,0.019079506],"domain_scores_gemma":[0.87533695,0.040894765,0.0041799247,0.0017952926,0.044558417,0.033234734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054285765,0.00089433015,0.0009950114,0.008275287,0.024943125,0.022090672,0.0067334734,0.024141343,0.011464803],"category_scores_gemma":[0.11513779,0.00078969664,0.0013431342,0.008340806,0.009861452,0.009876007,0.008481217,0.009835951,0.0006870263],"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":[0.00022257022,0.0002768521,0.00755022,0.0014802257,0.000069835776,0.0008398651,0.014849764,0.0067046694,0.00074534555,0.56101096,0.30094847,0.105301306],"study_design_scores_gemma":[0.00035235382,0.00017988219,0.017625108,0.003999945,0.00012280596,0.00012507697,0.054855738,0.0077946545,0.000976712,0.07323944,0.840179,0.0005491381],"about_ca_topic_score_codex":0.9604881,"about_ca_topic_score_gemma":0.9701193,"teacher_disagreement_score":0.7864796,"about_ca_system_score_codex":0.2135204,"about_ca_system_score_gemma":0.6732974,"threshold_uncertainty_score":0.91220486},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013567056,0.15975255,0.04747781,0.57776874,0.017241498,0.00017226613,0.002433115,0.00066348194,0.19313385],"genre_scores_gemma":[0.22066833,0.32600397,0.063751675,0.21179967,0.015711254,0.0009156793,0.0032391145,0.002018556,0.1558917],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985872,0.0049268827,0.0017758483,0.00082231394,0.006183996,0.00041896533],"domain_scores_gemma":[0.91080976,0.057704385,0.0044348314,0.0036746764,0.02135377,0.0020225751],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02779282,0.00090307626,0.00074036245,0.004805044,0.003985282,0.014770515,0.0022399055,0.0055457763,0.013026939],"category_scores_gemma":[0.07128429,0.00082427746,0.00061794784,0.008597617,0.011741496,0.015092051,0.0049254214,0.01576214,0.008478205],"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":[0.00005770868,0.000018009145,0.000514319,0.0008851188,0.000036635232,0.00004812231,0.0011938226,0.00027458963,0.00023624212,0.3425532,0.5814877,0.07269453],"study_design_scores_gemma":[0.000022428883,0.000024557614,0.0013737215,0.0023533136,0.000066594985,0.00013634229,0.0008518148,0.000204437,0.0006574573,0.14852044,0.8457279,0.000060961393],"about_ca_topic_score_codex":0.027156381,"about_ca_topic_score_gemma":0.037109967,"teacher_disagreement_score":0.9722072,"about_ca_system_score_codex":0.005902717,"about_ca_system_score_gemma":0.021485278,"threshold_uncertainty_score":0.14698428},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8553621,0.0028668449,0.00096908613,0.0066707456,0.0003890249,0.00072726427,0.007851639,0.00025745734,0.12490583],"genre_scores_gemma":[0.95381886,0.0017579963,0.0010877339,0.0004925955,0.00006999501,0.00027229195,0.004293617,0.00004055964,0.03816629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99623907,0.00029318838,0.000085632855,0.00016570422,0.0016338783,0.001582538],"domain_scores_gemma":[0.98209816,0.00092380715,0.0007724165,0.00023046324,0.007028035,0.008947115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034114833,0.00041128884,0.00033092068,0.004930809,0.0026451855,0.001300696,0.0014073993,0.00046580675,0.012231201],"category_scores_gemma":[0.010043418,0.00030181475,0.00037919328,0.0057964255,0.0007587871,0.00048486778,0.0014774724,0.00072650384,0.00078175927],"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":[0.0010541658,0.0010654072,0.45999992,0.0018248605,0.000105927116,0.00027538362,0.015435088,0.004963055,0.0023065088,0.02404635,0.09167638,0.3972471],"study_design_scores_gemma":[0.000051909457,0.00022696094,0.89284015,0.00027768404,0.000019445286,0.000051968847,0.0042755753,0.0009219683,0.00070590636,0.00027574887,0.10033563,0.00001709549],"about_ca_topic_score_codex":0.90010375,"about_ca_topic_score_gemma":0.9559822,"teacher_disagreement_score":0.9469915,"about_ca_system_score_codex":0.053008486,"about_ca_system_score_gemma":0.11952368,"threshold_uncertainty_score":0.38460523},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0136521645,0.0032305396,0.3981984,0.2039597,0.0012244727,0.00037829505,0.00016845277,0.00027874607,0.37890926],"genre_scores_gemma":[0.85247535,0.0013770151,0.11158504,0.020687928,0.0007322215,0.00095668965,0.00006125707,0.00019944669,0.011925156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97480994,0.015729265,0.0008142212,0.0022890996,0.0047684326,0.0015889751],"domain_scores_gemma":[0.9263051,0.055013206,0.0029425968,0.007888793,0.004637339,0.003212917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039807834,0.0010791149,0.001746452,0.0037467286,0.005849578,0.011825824,0.0040159253,0.009404737,0.014469133],"category_scores_gemma":[0.059465878,0.0007744488,0.0018307694,0.002066644,0.059180375,0.022667103,0.009179029,0.014422048,0.0013624512],"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":[0.000012634228,0.000018985967,0.0001627664,0.000060770042,0.000010518428,0.000015956259,0.00029808097,0.0006925918,0.000023453731,0.99418396,0.0007855691,0.003734705],"study_design_scores_gemma":[0.000007696482,0.000015094941,0.00008233627,0.00008817746,0.000009239883,0.000022078575,0.00018018711,0.00094109704,0.00007463746,0.9928812,0.005690606,0.0000075260123],"about_ca_topic_score_codex":0.0041062795,"about_ca_topic_score_gemma":0.0052662273,"teacher_disagreement_score":0.039807834,"about_ca_system_score_codex":0.009138374,"about_ca_system_score_gemma":0.0128542995,"threshold_uncertainty_score":0.21052653},"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":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054298956,0.003965845,0.010828068,0.96035,0.0023731275,0.0002984233,0.000043045246,0.00009310204,0.0166186],"genre_scores_gemma":[0.5010082,0.009382629,0.088825084,0.37662435,0.0061386614,0.0050139865,0.00008852689,0.00080240227,0.012116214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27856824,0.6316417,0.021594314,0.009080901,0.051690046,0.0074248295],"domain_scores_gemma":[0.14910601,0.77607554,0.008158681,0.0110236835,0.047335047,0.008301123],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.59502614,0.001021566,0.0025110287,0.0038654397,0.014278121,0.03957076,0.0080017755,0.020924514,0.0052475613],"category_scores_gemma":[0.6618935,0.0018299705,0.0020327216,0.0040071653,0.06077994,0.037140373,0.017437518,0.03868965,0.0014527239],"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":[0.0002574074,0.00025980562,0.0022143687,0.001814513,0.00012249885,0.00071887276,0.117635585,0.0021556735,0.00032354737,0.51858604,0.2539023,0.102009445],"study_design_scores_gemma":[0.00023693212,0.0002549067,0.0016980586,0.008625879,0.00005147261,0.00063194666,0.12680684,0.0037823624,0.0009956168,0.39789212,0.45874923,0.0002745647],"about_ca_topic_score_codex":0.007999527,"about_ca_topic_score_gemma":0.007478223,"teacher_disagreement_score":0.59502614,"about_ca_system_score_codex":0.02578024,"about_ca_system_score_gemma":0.04382318,"threshold_uncertainty_score":0.4994049},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008257134,0.033092406,0.035661634,0.90295655,0.0044348896,0.00043508346,0.00010231699,0.00029502372,0.014764958],"genre_scores_gemma":[0.44436896,0.058111798,0.2538429,0.21293779,0.015291279,0.00212745,0.00045799548,0.0007471257,0.012114696],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85195273,0.11317332,0.005701212,0.004594557,0.018817062,0.0057610716],"domain_scores_gemma":[0.61348987,0.24334641,0.016842531,0.02169748,0.06818277,0.036440965],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27646622,0.001690643,0.002964834,0.0052988883,0.010110034,0.029830458,0.0063066445,0.011344716,0.00643184],"category_scores_gemma":[0.20621572,0.0009133705,0.0015453678,0.004532419,0.013494232,0.031822152,0.018181344,0.022486063,0.0019149473],"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":[0.0002169222,0.00040306835,0.003502657,0.003651713,0.00015100634,0.00033300917,0.004889515,0.0039203567,0.0012292339,0.092943855,0.12505147,0.7637072],"study_design_scores_gemma":[0.0002818547,0.000983003,0.012408846,0.0120766545,0.00013851964,0.0006932254,0.027778907,0.0077793347,0.0013643955,0.3518853,0.5841228,0.000487228],"about_ca_topic_score_codex":0.011841248,"about_ca_topic_score_gemma":0.024297781,"teacher_disagreement_score":0.72353375,"about_ca_system_score_codex":0.013936014,"about_ca_system_score_gemma":0.075017594,"threshold_uncertainty_score":0.89224595},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013611742,0.013600161,0.31525406,0.48327044,0.003947149,0.0018283144,0.00026006895,0.0011535456,0.16707462],"genre_scores_gemma":[0.3236467,0.0059560286,0.5967139,0.043791696,0.00076284504,0.0019389427,0.00023424735,0.00030006986,0.026655586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9256029,0.045301575,0.0054929503,0.003119341,0.016822794,0.0036603045],"domain_scores_gemma":[0.85431296,0.08604192,0.0049782703,0.010151085,0.032946724,0.011569136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13042666,0.0019599725,0.0017612057,0.0062745176,0.010726416,0.023602277,0.0041028373,0.010520312,0.00811545],"category_scores_gemma":[0.11979261,0.0013540315,0.0012560873,0.0029538625,0.040805012,0.025654446,0.009636141,0.01715313,0.0020794324],"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":[0.00011743323,0.00031485004,0.001856137,0.0005496984,0.00007166121,0.00009458126,0.0019625698,0.0014495621,0.00026028915,0.8365687,0.026632633,0.13012198],"study_design_scores_gemma":[0.000049095215,0.00007284992,0.00085259636,0.0010577311,0.000036532096,0.000034265715,0.0024978411,0.0015949785,0.0006565423,0.9523759,0.040705442,0.00006618325],"about_ca_topic_score_codex":0.01376494,"about_ca_topic_score_gemma":0.020766081,"teacher_disagreement_score":0.13042666,"about_ca_system_score_codex":0.01721957,"about_ca_system_score_gemma":0.074774265,"threshold_uncertainty_score":0.68977034},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68760246,0.00542339,0.001279222,0.13159722,0.0005767288,0.00014000037,0.00034265817,0.000053243148,0.172985],"genre_scores_gemma":[0.9772888,0.0006080592,0.00016573741,0.0021030807,0.000046082027,0.000023378972,0.00004172521,0.0000073367555,0.019715734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9965417,0.0007671206,0.00006661177,0.00023146806,0.00044124204,0.0019518716],"domain_scores_gemma":[0.9948631,0.0009008682,0.00065101037,0.00021333179,0.0007507854,0.0026209436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032848374,0.00022962425,0.00018355936,0.0007518987,0.020319464,0.005650521,0.0011990777,0.0031288124,0.008124755],"category_scores_gemma":[0.0044712275,0.00038211734,0.0002504242,0.001156722,0.015067333,0.0020465984,0.0058017923,0.0034337153,0.00021743742],"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":[0.00025059943,0.000078448145,0.049633406,0.00036961006,0.0000413343,0.0022392203,0.23178574,0.0021967762,0.0018995847,0.6028382,0.074662834,0.03400429],"study_design_scores_gemma":[0.000060496357,0.00012275405,0.13621287,0.0005449394,0.00004380785,0.00019716495,0.2316289,0.0009120845,0.0010576193,0.014076831,0.6150128,0.00012978364],"about_ca_topic_score_codex":0.90919936,"about_ca_topic_score_gemma":0.9613892,"teacher_disagreement_score":0.11497321,"about_ca_system_score_codex":0.11497321,"about_ca_system_score_gemma":0.07672909,"threshold_uncertainty_score":0.83419293},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99725336,0.000055047818,0.00028321156,0.0004902628,0.0000076085507,0.00016904561,0.00002109606,0.000005744901,0.001714621],"genre_scores_gemma":[0.99787533,0.00008061226,0.00091978203,0.00011662471,0.0000045020647,0.00026039014,0.000037937752,0.00000392528,0.00070089166],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98872185,0.008461838,0.00032041396,0.00037286963,0.0011736708,0.0009493833],"domain_scores_gemma":[0.97961134,0.010367025,0.0019106109,0.0010626558,0.0030864398,0.003961854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013762414,0.00031159105,0.00056636316,0.0017171148,0.005931494,0.0045386986,0.0013455643,0.0016535707,0.0036085527],"category_scores_gemma":[0.03865724,0.0003218582,0.00051473797,0.0024935151,0.0019116956,0.0030585695,0.006109471,0.0016555042,0.00071493466],"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":[0.0018770732,0.015808856,0.30145243,0.00046859658,0.00012718227,0.0014739037,0.35020024,0.000787763,0.0016542363,0.0024843523,0.0026299816,0.32103541],"study_design_scores_gemma":[0.00057045603,0.008679581,0.2561357,0.00043424318,0.00020776849,0.0007698778,0.71579385,0.003973273,0.0023992932,0.0028883526,0.008027828,0.00011975806],"about_ca_topic_score_codex":0.016236678,"about_ca_topic_score_gemma":0.027810993,"teacher_disagreement_score":0.016236678,"about_ca_system_score_codex":0.0047560395,"about_ca_system_score_gemma":0.016599264,"threshold_uncertainty_score":0.07278347},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12728845,0.024796387,0.017407846,0.23719688,0.0018542319,0.0006175029,0.00027122686,0.00026469285,0.5903028],"genre_scores_gemma":[0.93894017,0.012318186,0.015654627,0.008676007,0.00026730567,0.00017569265,0.000120022865,0.00015088708,0.023697134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.87040424,0.06674352,0.003536206,0.003643278,0.045927413,0.009745293],"domain_scores_gemma":[0.816703,0.09481774,0.00465567,0.0045852656,0.06610148,0.013136836],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09253305,0.00055005064,0.0010549673,0.005499267,0.02775499,0.024354352,0.0034082686,0.0034873427,0.004857157],"category_scores_gemma":[0.1252026,0.00057279767,0.0005773462,0.009955995,0.02187442,0.00622281,0.0067273085,0.006237126,0.00046216525],"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":[0.00027955693,0.00020886693,0.011648881,0.0009037015,0.000088932575,0.0006647203,0.12085008,0.0022680403,0.0008110615,0.40968627,0.09912063,0.35346922],"study_design_scores_gemma":[0.00008693124,0.0001821595,0.018235644,0.0015630876,0.00008567153,0.00025535823,0.091567956,0.0023890256,0.0014438996,0.06471133,0.8190959,0.00038297713],"about_ca_topic_score_codex":0.9346248,"about_ca_topic_score_gemma":0.96714836,"teacher_disagreement_score":0.90746695,"about_ca_system_score_codex":0.18534002,"about_ca_system_score_gemma":0.31775114,"threshold_uncertainty_score":0.9448901},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13565181,0.116132915,0.13820773,0.26572728,0.004585685,0.016351769,0.0037433913,0.0006238284,0.31897566],"genre_scores_gemma":[0.8645035,0.011866756,0.08169501,0.017842315,0.00052862085,0.013850117,0.0006342011,0.0001230819,0.008956412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.53870165,0.33630782,0.03243435,0.00806415,0.079731576,0.0047604465],"domain_scores_gemma":[0.6220814,0.29083693,0.019163815,0.008007532,0.054807827,0.005102465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38668382,0.0030399386,0.0034202733,0.0071063205,0.005614587,0.022715148,0.005211323,0.0074444152,0.0039261826],"category_scores_gemma":[0.35730544,0.001224726,0.0026441403,0.0053965426,0.015980748,0.008563033,0.005262507,0.008493889,0.00066777476],"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":[0.006490717,0.0014809308,0.03882112,0.030568605,0.0025987255,0.00052419025,0.024691546,0.012595274,0.00178477,0.44977987,0.050378487,0.38028577],"study_design_scores_gemma":[0.005333978,0.007864516,0.09691164,0.12492556,0.003783706,0.0011595179,0.023488306,0.031174932,0.013409887,0.23093642,0.4603339,0.0006775648],"about_ca_topic_score_codex":0.10367241,"about_ca_topic_score_gemma":0.073851064,"teacher_disagreement_score":0.38668382,"about_ca_system_score_codex":0.058028556,"about_ca_system_score_gemma":0.057306953,"threshold_uncertainty_score":0.75632805},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046504118,0.040729985,0.820844,0.037622515,0.0026331346,0.013295421,0.0004975312,0.0012115227,0.036661737],"genre_scores_gemma":[0.2427565,0.0040837815,0.73370564,0.0048085973,0.0007881772,0.012194094,0.00020906508,0.00026346854,0.0011906507],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23686475,0.45677504,0.14318661,0.0119165685,0.14707959,0.004177432],"domain_scores_gemma":[0.1791937,0.5459408,0.074692085,0.059188757,0.13632075,0.0046638153],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6274646,0.0016880553,0.004634359,0.027564334,0.005265151,0.022092517,0.0040804916,0.0047861733,0.0009751702],"category_scores_gemma":[0.7490197,0.0017611118,0.0022305653,0.018211652,0.01712969,0.019084051,0.012886953,0.005700875,0.000704599],"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":[0.00064105564,0.00042790105,0.047837917,0.012588411,0.0012896858,0.00028048764,0.023039734,0.0023634443,0.003514724,0.3348877,0.0069573433,0.5661715],"study_design_scores_gemma":[0.00089003687,0.0038620424,0.0864728,0.04646531,0.0021823517,0.0022622638,0.036653373,0.01834324,0.022083644,0.57935673,0.20030755,0.0011206621],"about_ca_topic_score_codex":0.0042891894,"about_ca_topic_score_gemma":0.003298286,"teacher_disagreement_score":0.3725354,"about_ca_system_score_codex":0.01732508,"about_ca_system_score_gemma":0.03728089,"threshold_uncertainty_score":0.4594025},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044954508,0.0010617063,0.9555759,0.0035221553,0.00036726243,0.0063881963,0.00054903305,0.002312003,0.025728332],"genre_scores_gemma":[0.060960572,0.00054980384,0.9281792,0.00034958695,0.00012824479,0.008108224,0.00028937365,0.00031920918,0.0011158743],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.57975996,0.34770653,0.028310927,0.0057741944,0.036660146,0.0017881923],"domain_scores_gemma":[0.33747485,0.5555155,0.022209913,0.035019938,0.04672412,0.003055727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.37963408,0.0036938235,0.0037270857,0.027491584,0.004755317,0.013061464,0.0032286996,0.0035037997,0.010195148],"category_scores_gemma":[0.5303242,0.0014460792,0.0039296993,0.014002976,0.007301831,0.017505916,0.011603938,0.006069284,0.0014251556],"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":[0.00047461633,0.0006815336,0.00576243,0.0061724293,0.0007461093,0.00023649269,0.010514852,0.010772445,0.0012306385,0.19065608,0.016303523,0.75644875],"study_design_scores_gemma":[0.000716824,0.0021405742,0.01161693,0.01246665,0.0012255049,0.0006295101,0.0075276457,0.052888196,0.005996759,0.6773503,0.22658709,0.0008540774],"about_ca_topic_score_codex":0.0030443957,"about_ca_topic_score_gemma":0.0028333676,"teacher_disagreement_score":0.37963408,"about_ca_system_score_codex":0.008520317,"about_ca_system_score_gemma":0.016434336,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3966953,0.19126153,0.0745983,0.031927485,0.008685132,0.087939486,0.0023126365,0.00069164624,0.20588847],"genre_scores_gemma":[0.83518267,0.031130424,0.08123299,0.0040538516,0.0006957993,0.039215624,0.00077499234,0.00010175008,0.0076119327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.63144755,0.33462244,0.006891261,0.0024996023,0.02117416,0.0033649683],"domain_scores_gemma":[0.72901815,0.18784386,0.018381577,0.007963769,0.047589105,0.009203479],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20201495,0.0008647495,0.0012985942,0.0044269217,0.0028892693,0.0040119374,0.0016603897,0.0014502372,0.0051499056],"category_scores_gemma":[0.27263612,0.0003579845,0.0009226552,0.006387186,0.0025176075,0.002490193,0.003581529,0.0017277087,0.00038887767],"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":[0.005762625,0.0047667916,0.025788255,0.01219497,0.0008027963,0.00011321149,0.005180986,0.0034536712,0.00034291076,0.016938448,0.013181185,0.9114742],"study_design_scores_gemma":[0.019823184,0.114856385,0.3422388,0.074918,0.0048369397,0.00073347724,0.033865888,0.01444695,0.011048718,0.037614044,0.34509325,0.00052442355],"about_ca_topic_score_codex":0.029957294,"about_ca_topic_score_gemma":0.044277813,"teacher_disagreement_score":0.20201495,"about_ca_system_score_codex":0.018630091,"about_ca_system_score_gemma":0.05045617,"threshold_uncertainty_score":0.9840576},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.642407,0.15719715,0.04307293,0.065980785,0.0058918986,0.057548724,0.0021216134,0.0005567171,0.02522325],"genre_scores_gemma":[0.81720877,0.038712416,0.1087674,0.0068531563,0.0015172445,0.023507673,0.0008827418,0.00007153936,0.002479106],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.881999,0.089052565,0.008576202,0.0020630246,0.016944846,0.0013643916],"domain_scores_gemma":[0.8507793,0.10173454,0.011005775,0.0043645985,0.02242534,0.009690458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08303539,0.0013073344,0.0029893208,0.0028284155,0.0021033129,0.0024885053,0.002475417,0.0024425536,0.0018205834],"category_scores_gemma":[0.11996806,0.000513137,0.0019037918,0.0019943472,0.0010441527,0.0024512794,0.0028236492,0.0032554592,0.0001613003],"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":[0.013024266,0.026352419,0.012384043,0.013456713,0.0025870483,0.00039738495,0.0043330607,0.0035963587,0.0014680078,0.0039828415,0.012237489,0.9061804],"study_design_scores_gemma":[0.06802923,0.33392778,0.31789497,0.06878789,0.01983709,0.0013503048,0.015708283,0.014716976,0.011054261,0.02081127,0.1268369,0.0010450499],"about_ca_topic_score_codex":0.006828235,"about_ca_topic_score_gemma":0.01653151,"teacher_disagreement_score":0.08303539,"about_ca_system_score_codex":0.005930462,"about_ca_system_score_gemma":0.025153656,"threshold_uncertainty_score":0.43913835},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90195024,0.00693381,0.0034332676,0.013011004,0.0010963299,0.0018473583,0.00021276686,0.00013094817,0.07138436],"genre_scores_gemma":[0.89784,0.009186224,0.011223021,0.007258175,0.0005374003,0.0014797421,0.00037657446,0.000021900121,0.07207695],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9994868,0.00019004873,0.000013156905,0.00002725329,0.000034818153,0.00024797855],"domain_scores_gemma":[0.99855095,0.00018869618,0.00016948735,0.00002601484,0.000104485465,0.0009602452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015580195,0.00037335668,0.00012220255,0.0004597113,0.0018340923,0.0009591458,0.000419099,0.0008963725,0.00985093],"category_scores_gemma":[0.0009302124,0.00023419566,0.0002262365,0.00019023239,0.00047694147,0.0004827427,0.0017441133,0.0007365205,0.00170932],"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":[0.00030152872,0.003952641,0.22183256,0.002390344,0.00005214383,0.0033501498,0.09684266,0.00045155975,0.021230577,0.0031111778,0.0380667,0.60841805],"study_design_scores_gemma":[0.00018475005,0.002315342,0.3867678,0.002451961,0.000058060275,0.0020100356,0.15313986,0.00039407893,0.003182512,0.0011973339,0.44824967,0.00004863778],"about_ca_topic_score_codex":0.0031734097,"about_ca_topic_score_gemma":0.011052197,"teacher_disagreement_score":0.00985093,"about_ca_system_score_codex":0.0005754645,"about_ca_system_score_gemma":0.003188055,"threshold_uncertainty_score":0.032954633},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002353317,0.006460057,0.005090519,0.9467883,0.007124344,0.00007486882,0.000058205453,0.00008813572,0.031962242],"genre_scores_gemma":[0.29485178,0.02889467,0.027935628,0.5768653,0.008326049,0.0013974524,0.00030742047,0.0014350372,0.0599867],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.88829297,0.09219533,0.0024936404,0.0026103982,0.010953016,0.0034546591],"domain_scores_gemma":[0.65687823,0.2924888,0.0053998525,0.012177171,0.019479778,0.013576211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10425604,0.0010154702,0.0012398934,0.0022488025,0.024980301,0.036649827,0.005000488,0.020926043,0.018836718],"category_scores_gemma":[0.24160258,0.0010583234,0.00112057,0.0038020532,0.04861346,0.056969583,0.02132435,0.027832758,0.007600789],"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":[0.000103916616,0.00014392803,0.00044638326,0.0010567136,0.00003602307,0.0012083728,0.16664766,0.00017172491,0.000118529,0.15543236,0.55756456,0.11706985],"study_design_scores_gemma":[0.00006563459,0.000092794086,0.0004019333,0.003516527,0.000031191517,0.0007438369,0.17756815,0.000293201,0.0003948424,0.20195368,0.61486715,0.000071048424],"about_ca_topic_score_codex":0.006006863,"about_ca_topic_score_gemma":0.008216192,"teacher_disagreement_score":0.10425604,"about_ca_system_score_codex":0.00964485,"about_ca_system_score_gemma":0.035867494,"threshold_uncertainty_score":0.55136526},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9623358,0.00018791639,0.018507125,0.0016568231,0.0000686693,0.011367913,0.00012557064,0.00006581386,0.0056843716],"genre_scores_gemma":[0.94511133,0.00013759629,0.043489713,0.00017366138,0.00003093132,0.010164023,0.00010485518,0.000014902648,0.00077294355],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6890462,0.2852272,0.0052378536,0.0035946716,0.009871443,0.0070225447],"domain_scores_gemma":[0.6052526,0.32967865,0.015684847,0.011269765,0.023925077,0.014188935],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22963327,0.0016622886,0.001407768,0.0024914937,0.008565608,0.0045086476,0.0030080602,0.0037790167,0.0024196233],"category_scores_gemma":[0.27070242,0.00091499236,0.001382667,0.00216579,0.004438487,0.0034132511,0.009023404,0.003450551,0.0003648277],"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":[0.032465693,0.06735912,0.10136604,0.0038026173,0.0011547377,0.0011188233,0.10126029,0.045775797,0.0033203699,0.018147215,0.0033265234,0.6209027],"study_design_scores_gemma":[0.046728726,0.2532551,0.16695634,0.005482086,0.004077279,0.00076321064,0.17851232,0.18800835,0.027818993,0.10152837,0.025617257,0.0012519949],"about_ca_topic_score_codex":0.012925052,"about_ca_topic_score_gemma":0.017795203,"teacher_disagreement_score":0.22963327,"about_ca_system_score_codex":0.011584962,"about_ca_system_score_gemma":0.0443467,"threshold_uncertainty_score":0.94999933},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017288454,0.0006112148,0.000056005214,0.9896712,0.00647742,0.000012298431,0.000049022787,0.000030226036,0.0029198441],"genre_scores_gemma":[0.001079189,0.0001967807,0.00010971155,0.98725593,0.0022445486,0.000025052548,0.000015378653,0.000017869212,0.009055452],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99706095,0.0008090403,0.00024365903,0.00053608237,0.00088456966,0.0004656638],"domain_scores_gemma":[0.99372923,0.0030293125,0.00034146785,0.00016370561,0.0012359399,0.0015002922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00510487,0.0009163927,0.0014282975,0.0006807434,0.005365189,0.004104597,0.0023303507,0.0546981,0.012449213],"category_scores_gemma":[0.02431774,0.00086407905,0.0011909459,0.00064500375,0.0027188524,0.00402385,0.0021124973,0.046696335,0.011373299],"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":[0.000030312576,0.000012570475,0.00018155243,0.000019453682,0.0000046899204,0.0003594834,0.00006865934,0.000022677837,0.000055537796,0.0008776807,0.9957224,0.0026449743],"study_design_scores_gemma":[0.00007318127,0.000055279434,0.0014610857,0.00027564907,0.000020164349,0.0009299315,0.00092116056,0.00035092188,0.00020961538,0.0052689966,0.9903666,0.00006748645],"about_ca_topic_score_codex":0.015860783,"about_ca_topic_score_gemma":0.03450146,"teacher_disagreement_score":0.0546981,"about_ca_system_score_codex":0.004231182,"about_ca_system_score_gemma":0.006009161,"threshold_uncertainty_score":0.04164672},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014803998,0.026159205,0.44052458,0.116026185,0.0039736405,0.0019635581,0.00068156153,0.00093612884,0.39493117],"genre_scores_gemma":[0.45803487,0.023370141,0.39927262,0.017996125,0.0025795894,0.005817711,0.0011214851,0.0016019896,0.09020555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7809864,0.16235197,0.0077450485,0.011322259,0.034699492,0.0028948213],"domain_scores_gemma":[0.7936053,0.13736719,0.0073698116,0.025899492,0.032187328,0.0035709033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.112626076,0.0022011956,0.0022436099,0.007395383,0.0072034188,0.034592252,0.0044249757,0.009833843,0.024660105],"category_scores_gemma":[0.12963764,0.0013814081,0.0031620401,0.0060570166,0.029686218,0.026914116,0.01206239,0.013268649,0.0065772193],"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":[0.00009688392,0.00008903058,0.0009960528,0.0020778882,0.00012155884,0.00010711889,0.010254382,0.0015710518,0.00090960186,0.9099973,0.008436988,0.06534216],"study_design_scores_gemma":[0.00011351545,0.0002616384,0.0019450233,0.0049339375,0.00017121338,0.00028330556,0.0100341905,0.0028528925,0.0024310993,0.43448257,0.5423477,0.00014295321],"about_ca_topic_score_codex":0.008790111,"about_ca_topic_score_gemma":0.008046871,"teacher_disagreement_score":0.8873739,"about_ca_system_score_codex":0.020757018,"about_ca_system_score_gemma":0.031573158,"threshold_uncertainty_score":0.59563076},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23644118,0.015689189,0.55077356,0.0124939345,0.0009814821,0.011784213,0.00077824807,0.0007871478,0.17027105],"genre_scores_gemma":[0.6529326,0.003987775,0.32317257,0.0011591597,0.00013287416,0.009278754,0.000299144,0.00017395847,0.008863188],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81777465,0.15166365,0.0067850994,0.0034163077,0.019434558,0.00092564453],"domain_scores_gemma":[0.7089795,0.25115347,0.006801121,0.013282219,0.018143563,0.0016400429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12857153,0.0015712072,0.0012555227,0.0029975849,0.0021814166,0.010001245,0.0017285264,0.0021615,0.0057309256],"category_scores_gemma":[0.21512115,0.0006638381,0.0011447913,0.002983365,0.0038399475,0.007886184,0.00499648,0.0028658884,0.0011504167],"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":[0.003293203,0.0015281506,0.002812741,0.005284553,0.000642707,0.00015629237,0.017043961,0.0060280133,0.0038679622,0.14235827,0.004090169,0.81289387],"study_design_scores_gemma":[0.005371388,0.02332473,0.018158205,0.019345962,0.0029667623,0.00080395857,0.038585488,0.06554839,0.05455503,0.6283366,0.14229812,0.00070536946],"about_ca_topic_score_codex":0.0011813579,"about_ca_topic_score_gemma":0.0015635332,"teacher_disagreement_score":0.12857153,"about_ca_system_score_codex":0.004947936,"about_ca_system_score_gemma":0.009386204,"threshold_uncertainty_score":0.67995936},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25236556,0.02227874,0.022863008,0.06835711,0.001559808,0.0017967669,0.00042407075,0.00079045264,0.62956446],"genre_scores_gemma":[0.88697284,0.011567136,0.023901427,0.0071000904,0.00038922668,0.00088569755,0.00048010188,0.00067447184,0.06802896],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.86783475,0.09384147,0.0033221005,0.0033797172,0.021038283,0.010583653],"domain_scores_gemma":[0.9057304,0.03804176,0.0023528382,0.005983589,0.028720353,0.019171143],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12441589,0.00079619297,0.0010101353,0.003101812,0.011493101,0.017532868,0.0034660941,0.0035693487,0.00911707],"category_scores_gemma":[0.06483799,0.00064098556,0.0006686727,0.006110033,0.0076875966,0.005926758,0.009161646,0.009480849,0.0020931163],"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":[0.00072253996,0.005232947,0.010586985,0.0011633667,0.00008096587,0.0019626506,0.23832211,0.0028459288,0.0016888712,0.12716727,0.1356118,0.47461453],"study_design_scores_gemma":[0.00014848368,0.001335245,0.0055947234,0.0011178163,0.0000442267,0.0005222415,0.08343735,0.0017766408,0.0033213806,0.0048645944,0.89766324,0.0001741485],"about_ca_topic_score_codex":0.036930174,"about_ca_topic_score_gemma":0.031728256,"teacher_disagreement_score":0.8755841,"about_ca_system_score_codex":0.028633473,"about_ca_system_score_gemma":0.047596753,"threshold_uncertainty_score":0.657982},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022212604,0.065653354,0.2956248,0.57232445,0.0053663575,0.003708324,0.00021421521,0.00028315294,0.03461276],"genre_scores_gemma":[0.65759355,0.020386834,0.25040588,0.049348395,0.005648718,0.013342623,0.0001231117,0.00036980867,0.0027811215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.14887722,0.7896465,0.023206243,0.005521296,0.03033341,0.0024153686],"domain_scores_gemma":[0.103888296,0.8220528,0.012962117,0.019893287,0.03737656,0.0038269197],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6878914,0.0014674105,0.0044495645,0.0064113867,0.00916967,0.027091319,0.007262372,0.009821366,0.0019401395],"category_scores_gemma":[0.67827845,0.0012446435,0.0016315161,0.006845554,0.062322035,0.021610841,0.017821265,0.016376097,0.00072892406],"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":[0.00042169218,0.0003897777,0.004659859,0.0068903137,0.00029669693,0.000412371,0.054889362,0.0043965187,0.0004924363,0.6812002,0.021613343,0.22433749],"study_design_scores_gemma":[0.00023708552,0.0002537223,0.0018286136,0.015455022,0.00008015678,0.0005661335,0.04621264,0.005005587,0.00093248877,0.8336228,0.09560683,0.00019888303],"about_ca_topic_score_codex":0.005869402,"about_ca_topic_score_gemma":0.0037212488,"teacher_disagreement_score":0.31210858,"about_ca_system_score_codex":0.01770986,"about_ca_system_score_gemma":0.046006843,"threshold_uncertainty_score":0.3848855},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0133533375,0.008021777,0.8072967,0.008026949,0.001066868,0.00016897802,0.0004874019,0.0007449782,0.16083293],"genre_scores_gemma":[0.6211451,0.008588551,0.33348596,0.0012699042,0.0012197058,0.00092162046,0.00078840455,0.00033818948,0.032242563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9880697,0.007395371,0.0009025784,0.00075800734,0.0024051617,0.0004690891],"domain_scores_gemma":[0.9795272,0.01354722,0.0021696645,0.0016587647,0.002409926,0.00068733597],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011002582,0.0017407112,0.0010010283,0.008908487,0.00101614,0.014049069,0.0013726366,0.0022095859,0.0065595494],"category_scores_gemma":[0.026007812,0.00060031516,0.00092591974,0.0072888397,0.011838336,0.018999986,0.0028362426,0.0032990873,0.0018327459],"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":[0.000002982368,0.000007304026,0.00009428852,0.000037082187,0.0000032225905,0.0000058686755,0.00016184867,0.00051622215,0.000038401828,0.9923511,0.0004294868,0.0063521117],"study_design_scores_gemma":[0.000006239116,0.000030211093,0.00016861083,0.00014545646,0.000018629153,0.00004737472,0.0003349171,0.003818474,0.00047560254,0.960517,0.034420755,0.000016667815],"about_ca_topic_score_codex":0.0006809524,"about_ca_topic_score_gemma":0.00040344772,"teacher_disagreement_score":0.9889974,"about_ca_system_score_codex":0.0032708955,"about_ca_system_score_gemma":0.0020343184,"threshold_uncertainty_score":0.058187902},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07423323,0.00047342974,0.7630015,0.02048534,0.00014034372,0.0007417176,0.0006431623,0.0011952195,0.13908611],"genre_scores_gemma":[0.27822414,0.00060813344,0.698626,0.0013255017,0.000031012096,0.00034339083,0.00049344404,0.00030977395,0.020038715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9964833,0.0020749692,0.0001533831,0.00017747858,0.00066609296,0.00044480246],"domain_scores_gemma":[0.9909087,0.007072363,0.00028397058,0.00032417284,0.0011724131,0.0002384172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003445295,0.0006718413,0.0003604024,0.0030591674,0.0042771176,0.005567923,0.0014669711,0.0026995467,0.0053322283],"category_scores_gemma":[0.008769098,0.00043484374,0.0011016221,0.0027536324,0.004366895,0.004373055,0.002487578,0.003079952,0.001063249],"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":[0.00029781333,0.00048592687,0.0066841687,0.0008679419,0.000034823453,0.0071780444,0.0457277,0.021502608,0.009692181,0.74296,0.020367047,0.1442018],"study_design_scores_gemma":[0.000121610035,0.0003385778,0.00548855,0.00119631,0.0001406644,0.0047005485,0.062052738,0.06935334,0.02172146,0.39945278,0.435175,0.0002585066],"about_ca_topic_score_codex":0.03826857,"about_ca_topic_score_gemma":0.047290213,"teacher_disagreement_score":0.03826857,"about_ca_system_score_codex":0.0048318217,"about_ca_system_score_gemma":0.0057884343,"threshold_uncertainty_score":0.07609165},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18564057,0.2739486,0.24879993,0.14622885,0.0032662766,0.014231073,0.0006435327,0.00019026248,0.12705083],"genre_scores_gemma":[0.8135375,0.058427587,0.11232997,0.0054613207,0.00042948136,0.008339843,0.00015902423,0.00006892533,0.0012462585],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.59912413,0.36241734,0.012709278,0.005915559,0.016152522,0.0036811423],"domain_scores_gemma":[0.40959904,0.5448314,0.014155095,0.012341709,0.016292004,0.0027806673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2891359,0.0014008798,0.0030204167,0.021021875,0.009839561,0.02006662,0.003518993,0.0052090073,0.003074911],"category_scores_gemma":[0.2777594,0.0012111737,0.0014220239,0.016404886,0.032280307,0.024167398,0.018713525,0.0043726857,0.00031215182],"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":[0.00013765265,0.00035291747,0.008158226,0.041161485,0.0004349039,0.0013988646,0.4673991,0.0012699711,0.0011325519,0.17370506,0.004620464,0.3002288],"study_design_scores_gemma":[0.00011910444,0.0005846697,0.006564172,0.10669857,0.00041033642,0.0011571273,0.5438666,0.0014259198,0.0018242612,0.18423615,0.15295666,0.00015643834],"about_ca_topic_score_codex":0.0030762907,"about_ca_topic_score_gemma":0.0041658822,"teacher_disagreement_score":0.2891359,"about_ca_system_score_codex":0.019366011,"about_ca_system_score_gemma":0.052370068,"threshold_uncertainty_score":0.87662196},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.797658,0.031657062,0.095930785,0.0045580524,0.0012215169,0.0016307952,0.002027848,0.00024784383,0.06506808],"genre_scores_gemma":[0.97333956,0.0031072497,0.020965567,0.0005290544,0.00025406395,0.00043381713,0.0005498764,0.00008827569,0.0007324924],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7354783,0.18943709,0.013489671,0.011103732,0.048931587,0.0015595782],"domain_scores_gemma":[0.18714167,0.6572934,0.048972808,0.05137894,0.052735727,0.002477536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28092933,0.0009126329,0.0011951409,0.0066418676,0.0013467708,0.004152265,0.003133726,0.0016680182,0.002065654],"category_scores_gemma":[0.5188504,0.00075482385,0.0026695062,0.00890469,0.0062307306,0.0047479435,0.0033802264,0.0018756408,0.00088096963],"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":[0.002398466,0.0011039858,0.70822674,0.0058530816,0.007585355,0.00010216832,0.0079572415,0.0037586847,0.000535763,0.009622407,0.002215206,0.2506409],"study_design_scores_gemma":[0.00028727716,0.004387881,0.94150877,0.0071068667,0.0027022357,0.00039250296,0.0041833357,0.00965141,0.0030435356,0.01453409,0.011979966,0.00022204117],"about_ca_topic_score_codex":0.0060603134,"about_ca_topic_score_gemma":0.008781861,"teacher_disagreement_score":0.28092933,"about_ca_system_score_codex":0.002209197,"about_ca_system_score_gemma":0.0029340212,"threshold_uncertainty_score":0.8867422},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05314898,0.21332465,0.54300445,0.06763005,0.01860938,0.03686228,0.0046522226,0.0012219468,0.061545953],"genre_scores_gemma":[0.4325749,0.05090488,0.43877837,0.004729606,0.0035151022,0.05724949,0.0009780071,0.0003164152,0.01095316],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.54460573,0.42003444,0.015662715,0.005696641,0.012680364,0.0013200501],"domain_scores_gemma":[0.5238394,0.41100475,0.012579988,0.03609635,0.01598155,0.00049798394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.31803006,0.0017285487,0.004646098,0.012286248,0.0028257794,0.011780607,0.0023340508,0.0024821244,0.007358361],"category_scores_gemma":[0.35957503,0.0018740472,0.0032233251,0.009570707,0.008441095,0.006716751,0.0051476853,0.002754075,0.00067205494],"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":[0.0018916806,0.00047455524,0.001911101,0.09714343,0.0041709496,0.00018860775,0.0327704,0.008692712,0.0013517003,0.3265237,0.019865358,0.5050158],"study_design_scores_gemma":[0.0023436374,0.001634658,0.0066257813,0.07820152,0.0061711236,0.00021382277,0.027068194,0.014463234,0.010650311,0.56954986,0.28261515,0.00046273565],"about_ca_topic_score_codex":0.003402378,"about_ca_topic_score_gemma":0.0051391553,"teacher_disagreement_score":0.31803006,"about_ca_system_score_codex":0.010806116,"about_ca_system_score_gemma":0.015965832,"threshold_uncertainty_score":0.84099036},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026657602,0.20891862,0.1378381,0.12621942,0.0063797617,0.00016105977,0.00048059545,0.00021904442,0.49312577],"genre_scores_gemma":[0.5789267,0.23801568,0.06359516,0.01582898,0.007837113,0.0007308999,0.00039156893,0.0004992825,0.094174646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924878,0.005250377,0.0002775961,0.0006146141,0.0009516007,0.00041809125],"domain_scores_gemma":[0.9790028,0.018295841,0.0006795994,0.000801615,0.00094685383,0.00027333596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006314457,0.0011723634,0.0009792728,0.005387554,0.0049268007,0.009976126,0.0012785632,0.004559508,0.010026905],"category_scores_gemma":[0.008750383,0.0006448836,0.0012434153,0.007292587,0.0197587,0.012985406,0.005073094,0.010620071,0.0013670797],"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":[0.000015297202,0.000023264596,0.00044114378,0.00027090666,0.000010217175,0.00010202828,0.012690785,0.00041755105,0.00013457128,0.958098,0.0043962975,0.023399882],"study_design_scores_gemma":[0.000008706107,0.00006149149,0.0018417301,0.0020898178,0.000017565231,0.00045691,0.011764146,0.0012121102,0.0006581348,0.34618273,0.6356531,0.000053651125],"about_ca_topic_score_codex":0.012646926,"about_ca_topic_score_gemma":0.01124559,"teacher_disagreement_score":0.012646926,"about_ca_system_score_codex":0.0076187183,"about_ca_system_score_gemma":0.0040531233,"threshold_uncertainty_score":0.055278003},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040746346,0.67814547,0.05267496,0.18302868,0.040501866,0.0028281629,0.0007128593,0.0007628379,0.0409377],"genre_scores_gemma":[0.0060771103,0.62676877,0.105996795,0.07423649,0.02634863,0.009125964,0.00094969297,0.0013082173,0.14918835],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97100925,0.01858747,0.0024817823,0.00063976593,0.006878404,0.00040341835],"domain_scores_gemma":[0.87000924,0.104600094,0.003957631,0.002502684,0.017094167,0.0018361455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027339129,0.0017685714,0.0036816874,0.009506344,0.0031505227,0.0073220334,0.0033358384,0.008106431,0.017790044],"category_scores_gemma":[0.06502741,0.0019597355,0.0011838615,0.010007998,0.006794805,0.0064746602,0.0028220639,0.008095641,0.012142227],"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":[0.000020532627,0.000045171804,0.000054531105,0.002999809,0.000026417745,0.00008800719,0.00070093485,0.00016535723,0.00031552886,0.009461859,0.86749524,0.11862657],"study_design_scores_gemma":[0.000015790634,0.000028126075,0.00016332683,0.0030474672,0.000019825397,0.00019963205,0.0002729461,0.00016314218,0.0001797673,0.007051427,0.98883027,0.000028189395],"about_ca_topic_score_codex":0.010413984,"about_ca_topic_score_gemma":0.04289638,"teacher_disagreement_score":0.027339129,"about_ca_system_score_codex":0.0060658017,"about_ca_system_score_gemma":0.020257061,"threshold_uncertainty_score":0.1445849},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8186346,0.0017141928,0.094240256,0.00656454,0.00018967736,0.0030631488,0.0002299195,0.00019229777,0.07517123],"genre_scores_gemma":[0.98274094,0.0002644606,0.014632012,0.00031674677,0.000030727024,0.0013288629,0.00007236111,0.000022028811,0.000591878],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.66450083,0.27621567,0.011482747,0.00444963,0.03858576,0.004765378],"domain_scores_gemma":[0.5297639,0.32791403,0.045685317,0.015456135,0.072087474,0.009093072],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19961834,0.0007223355,0.0006918487,0.0053752773,0.0033475792,0.005383664,0.001529637,0.0012065017,0.0027567965],"category_scores_gemma":[0.29190803,0.00036734852,0.00090692216,0.0032359445,0.0067654145,0.0054532737,0.0114008915,0.0018877023,0.0004754014],"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":[0.00038478308,0.0010593561,0.3337183,0.0032121178,0.00038550998,0.00036547697,0.18758343,0.0034275465,0.002959521,0.028522534,0.0049496214,0.4334317],"study_design_scores_gemma":[0.00018720227,0.0041056597,0.48288947,0.0078077116,0.0004132517,0.0014804265,0.27540156,0.014225676,0.012990241,0.088872366,0.11114161,0.0004848323],"about_ca_topic_score_codex":0.0014136402,"about_ca_topic_score_gemma":0.0014997305,"teacher_disagreement_score":0.80038166,"about_ca_system_score_codex":0.006642837,"about_ca_system_score_gemma":0.009788483,"threshold_uncertainty_score":0.9870131},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06223889,0.041547794,0.0030854605,0.69134617,0.009111976,0.00023446669,0.00020338636,0.000088845714,0.19214296],"genre_scores_gemma":[0.53889936,0.087041475,0.0117781805,0.2175198,0.0069871885,0.0005676496,0.00026758792,0.00010724049,0.13683152],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9875079,0.0070440825,0.00054332893,0.0007226094,0.0028610926,0.001321025],"domain_scores_gemma":[0.98460716,0.0070054135,0.00092672167,0.0013017198,0.0022147216,0.0039442256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018149542,0.00053427485,0.00074346864,0.0009679298,0.006587728,0.0069091404,0.0014445137,0.0033741344,0.01597388],"category_scores_gemma":[0.034200203,0.00028278123,0.00072746264,0.0008818477,0.008801677,0.0067624417,0.01220009,0.0070513277,0.0018411138],"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":[0.00014077748,0.00068488234,0.009213009,0.0024858967,0.00019398153,0.0017969537,0.2424029,0.0004133914,0.000844144,0.057612687,0.26301265,0.42119867],"study_design_scores_gemma":[0.00006322527,0.00035713,0.008221502,0.0043084985,0.00010793379,0.0013373379,0.15250777,0.0001496984,0.0004941153,0.050503813,0.7818674,0.00008157362],"about_ca_topic_score_codex":0.028105048,"about_ca_topic_score_gemma":0.060530897,"teacher_disagreement_score":0.028105048,"about_ca_system_score_codex":0.0052711335,"about_ca_system_score_gemma":0.015875185,"threshold_uncertainty_score":0.095985115},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5591231,0.0077997874,0.023486713,0.0713978,0.0009081622,0.0005444898,0.00008475702,0.00023552903,0.33641967],"genre_scores_gemma":[0.9812664,0.0009836999,0.005475551,0.0013325069,0.000070546506,0.0002150559,0.000023405431,0.000028920298,0.010604044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.96141946,0.027376054,0.000855835,0.0021215954,0.0045402455,0.0036868239],"domain_scores_gemma":[0.9695588,0.014917636,0.004016212,0.0022131763,0.0034160146,0.005878248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016243983,0.00037525376,0.00054478494,0.0024698607,0.01295889,0.011796655,0.0019274437,0.004146852,0.008471041],"category_scores_gemma":[0.032559857,0.00033750627,0.00061065436,0.0027416563,0.013079751,0.0077126236,0.013618972,0.0034676227,0.00077486766],"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":[0.00029864514,0.0005047451,0.017557139,0.0008466948,0.00006770698,0.005292214,0.39513677,0.0013815075,0.0010473948,0.39774615,0.015690446,0.16443051],"study_design_scores_gemma":[0.00007798325,0.0004811119,0.020483231,0.0014367157,0.000065632354,0.0038412367,0.38819203,0.0034177522,0.0015207817,0.08697326,0.4933672,0.0001431171],"about_ca_topic_score_codex":0.018884445,"about_ca_topic_score_gemma":0.02359901,"teacher_disagreement_score":0.018884445,"about_ca_system_score_codex":0.012249073,"about_ca_system_score_gemma":0.0126133505,"threshold_uncertainty_score":0.088873625},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12969656,0.0014614542,0.8172011,0.00175325,0.00065901864,0.02410405,0.0012573183,0.0016885523,0.022178823],"genre_scores_gemma":[0.1653454,0.0006533195,0.7977604,0.00018278215,0.00006858725,0.027586134,0.00049174327,0.00019804537,0.007713565],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84766394,0.11330019,0.01095753,0.004626022,0.021809783,0.0016425514],"domain_scores_gemma":[0.7691027,0.15846993,0.009142312,0.012759657,0.04905489,0.0014704955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11447071,0.0020238832,0.0017729965,0.0059614643,0.0020177423,0.004806688,0.0019899814,0.0016354705,0.00985441],"category_scores_gemma":[0.16420056,0.0010263362,0.0021572383,0.0039633447,0.0020606695,0.0039006264,0.002919755,0.0021365576,0.0016569337],"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":[0.0024668167,0.0012366207,0.015156228,0.005870706,0.00036710847,0.00017071184,0.02731342,0.0038663216,0.012848916,0.01636129,0.0075405403,0.90680134],"study_design_scores_gemma":[0.0044532963,0.016687246,0.18062648,0.015513496,0.0018038733,0.0014416365,0.066877015,0.11339152,0.17129773,0.06672886,0.35944137,0.0017374652],"about_ca_topic_score_codex":0.0037829697,"about_ca_topic_score_gemma":0.004829834,"teacher_disagreement_score":0.11447071,"about_ca_system_score_codex":0.0047582476,"about_ca_system_score_gemma":0.009367419,"threshold_uncertainty_score":0.60538626},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13710892,0.012376713,0.3178468,0.11810704,0.0015508602,0.019893227,0.0011006028,0.0011039957,0.39091185],"genre_scores_gemma":[0.6033776,0.0038555309,0.36865684,0.0062066047,0.00024615228,0.007448195,0.00060136203,0.00029360887,0.009314068],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6685637,0.24731743,0.023556702,0.007024946,0.038556945,0.014980193],"domain_scores_gemma":[0.7142226,0.21431717,0.011715862,0.00824701,0.038759258,0.012738077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32535785,0.0012409851,0.0016685353,0.007955745,0.007889148,0.030161753,0.0040976517,0.005733323,0.007356477],"category_scores_gemma":[0.2225522,0.0013492068,0.0013143709,0.0064152996,0.008355079,0.016727667,0.015156962,0.009443344,0.0026597842],"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":[0.00042781912,0.0007661021,0.016109072,0.002105422,0.00019105978,0.0013392254,0.043862566,0.013062488,0.0031903225,0.43651155,0.02311355,0.45932084],"study_design_scores_gemma":[0.00032722016,0.0009759981,0.027316691,0.010559116,0.00014539708,0.000997448,0.13108793,0.010250725,0.007425611,0.4904053,0.319677,0.0008315588],"about_ca_topic_score_codex":0.013176153,"about_ca_topic_score_gemma":0.021423902,"teacher_disagreement_score":0.32535785,"about_ca_system_score_codex":0.021922933,"about_ca_system_score_gemma":0.06101314,"threshold_uncertainty_score":0.8319539},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061313875,0.027242133,0.10600543,0.15016365,0.0015836402,0.00019628402,0.00015538526,0.00016818597,0.65317136],"genre_scores_gemma":[0.94023633,0.008390454,0.018686146,0.006193985,0.00069151074,0.00037093004,0.00011079978,0.0001447576,0.0251751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9607938,0.028105173,0.0013645092,0.0024510156,0.0060037207,0.0012818194],"domain_scores_gemma":[0.9228175,0.060549997,0.0037446674,0.004420583,0.0064907386,0.0019764877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027848788,0.00076987594,0.0007964354,0.004640639,0.0072592474,0.019122696,0.0019602552,0.0042974306,0.008808461],"category_scores_gemma":[0.05041009,0.00059301395,0.0011191261,0.0040478986,0.036387447,0.022093326,0.0068690265,0.0094131315,0.001117962],"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":[0.000017927354,0.000020873784,0.00072222203,0.00011716645,0.000011905928,0.000042572043,0.02804797,0.00012810787,0.00008334916,0.95526034,0.0019319766,0.013615611],"study_design_scores_gemma":[0.000027350794,0.000047489426,0.0031438714,0.0009056379,0.000029773215,0.00015825401,0.041724198,0.0011816816,0.00045802013,0.8030142,0.14925535,0.000054149616],"about_ca_topic_score_codex":0.00790517,"about_ca_topic_score_gemma":0.009859646,"teacher_disagreement_score":0.027848788,"about_ca_system_score_codex":0.01752711,"about_ca_system_score_gemma":0.015232041,"threshold_uncertainty_score":0.14728028},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55096465,0.013503256,0.011952331,0.14788783,0.00063208677,0.0002107794,0.00050170295,0.00035843364,0.2739888],"genre_scores_gemma":[0.9782348,0.0042731306,0.0028867365,0.004684103,0.0003138652,0.00009929197,0.000108350316,0.00006169907,0.009338035],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8840841,0.066083334,0.0054400805,0.0046094283,0.032241885,0.0075411974],"domain_scores_gemma":[0.65511453,0.24306709,0.04129116,0.020855157,0.028880177,0.010791825],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.057882737,0.00027732571,0.00057791243,0.0077364715,0.008410321,0.019297406,0.0021449286,0.0029389118,0.008789255],"category_scores_gemma":[0.17314568,0.00065950403,0.00067785376,0.009482456,0.01061004,0.012749173,0.007581614,0.0031310904,0.0015497316],"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":[0.00028227974,0.00038021206,0.12536055,0.0012461384,0.00017221252,0.0015424294,0.19423433,0.0007597159,0.0052263686,0.12372746,0.02698055,0.5200877],"study_design_scores_gemma":[0.00007184602,0.0003554251,0.090291426,0.0017197311,0.00015703244,0.0017242045,0.2408233,0.0016793167,0.00423576,0.042384736,0.61625135,0.00030592416],"about_ca_topic_score_codex":0.02320863,"about_ca_topic_score_gemma":0.030389287,"teacher_disagreement_score":0.9807026,"about_ca_system_score_codex":0.009300311,"about_ca_system_score_gemma":0.0144233825,"threshold_uncertainty_score":0.30611688},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24156342,0.0369783,0.17170669,0.01647691,0.0023145298,0.004937374,0.0037838854,0.0017281745,0.5205107],"genre_scores_gemma":[0.7444229,0.021797495,0.16033424,0.00193619,0.0006435838,0.0051369458,0.0025544646,0.0005785124,0.06259558],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92461395,0.039255325,0.0037692452,0.0035081597,0.027636511,0.0012167046],"domain_scores_gemma":[0.8412405,0.1070448,0.0071812645,0.009355672,0.0334245,0.0017531541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051069353,0.0013268737,0.0012911808,0.006886357,0.001449299,0.0130639905,0.0018520639,0.001921611,0.025491668],"category_scores_gemma":[0.10859532,0.0005180632,0.0016320406,0.006645849,0.0035537162,0.0086876,0.0034320578,0.0019337686,0.0042630616],"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":[0.0007128184,0.0009202173,0.020217383,0.0139607275,0.00070676213,0.00024291036,0.016979473,0.0040192995,0.0051949057,0.08628249,0.014926859,0.83583635],"study_design_scores_gemma":[0.00053739164,0.0044962093,0.0951386,0.021765517,0.0027137366,0.0009606885,0.04161315,0.00892395,0.03891184,0.10273843,0.68173236,0.0004681946],"about_ca_topic_score_codex":0.0040134066,"about_ca_topic_score_gemma":0.0045440258,"teacher_disagreement_score":0.051069353,"about_ca_system_score_codex":0.005642679,"about_ca_system_score_gemma":0.009747195,"threshold_uncertainty_score":0.27008379},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10856249,0.014416486,0.015289021,0.7163259,0.0012686581,0.00010981624,0.00011826184,0.00013280885,0.14377658],"genre_scores_gemma":[0.9738114,0.0024535381,0.0035936818,0.014430197,0.00066954666,0.0000722117,0.000024091705,0.00008997405,0.004855375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.95531774,0.034178972,0.0008689282,0.0017551627,0.0059642782,0.0019148635],"domain_scores_gemma":[0.811564,0.16148989,0.00604532,0.008886101,0.006921869,0.005092826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04879681,0.00046982736,0.00087856385,0.0034626615,0.006644605,0.015318649,0.0024200194,0.01005673,0.008175679],"category_scores_gemma":[0.1586927,0.0006076278,0.00044791237,0.001767119,0.060933013,0.023957958,0.012731599,0.011113242,0.00077007775],"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":[0.0003487066,0.0003572305,0.009719632,0.0004292596,0.00014232882,0.0020587558,0.12798364,0.0011663168,0.0004407176,0.6594705,0.039653353,0.15822951],"study_design_scores_gemma":[0.000107017455,0.00018396977,0.0050469,0.0010845857,0.000037478734,0.0017566032,0.05089942,0.0019895658,0.0007006381,0.83368343,0.10439441,0.00011593282],"about_ca_topic_score_codex":0.0056235255,"about_ca_topic_score_gemma":0.0044613136,"teacher_disagreement_score":0.04879681,"about_ca_system_score_codex":0.006790845,"about_ca_system_score_gemma":0.007059636,"threshold_uncertainty_score":0.25806534},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29429102,0.0119162565,0.0061492054,0.6334497,0.0012700589,0.000945524,0.000056590514,0.00013611553,0.05178562],"genre_scores_gemma":[0.9098993,0.00681314,0.014604263,0.05195502,0.00031887583,0.00096986047,0.0000536949,0.000094512,0.015291333],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.677376,0.25153118,0.011792313,0.0055761365,0.036375258,0.017349117],"domain_scores_gemma":[0.62800103,0.22446495,0.0121976845,0.014654963,0.067861535,0.052819803],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.2406818,0.0005233375,0.0011661702,0.0031841176,0.025366016,0.02978694,0.0067787636,0.011992465,0.0055189435],"category_scores_gemma":[0.22247188,0.0013264933,0.0012032436,0.0049668173,0.026364874,0.01628231,0.036272958,0.013634322,0.0007438365],"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":[0.00018415679,0.0012459145,0.0060256133,0.0018195239,0.00005980931,0.0014032943,0.7598527,0.000519471,0.0005288631,0.051975105,0.035721365,0.14066412],"study_design_scores_gemma":[0.00010101911,0.00044564964,0.014234772,0.0027400474,0.00004005686,0.00064161245,0.75780284,0.00083470024,0.000675408,0.017538477,0.20479034,0.00015502861],"about_ca_topic_score_codex":0.049666107,"about_ca_topic_score_gemma":0.05212962,"teacher_disagreement_score":0.97021306,"about_ca_system_score_codex":0.046189986,"about_ca_system_score_gemma":0.12226926,"threshold_uncertainty_score":0.93637455},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4569206,0.0039025422,0.0096831005,0.24344523,0.0011474263,0.0007791115,0.00092806737,0.00064150395,0.2825524],"genre_scores_gemma":[0.8894673,0.0021592039,0.0067602657,0.008034061,0.000069918955,0.00021159128,0.00022217695,0.00020112848,0.09287431],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938094,0.0017113634,0.0001911741,0.0005734668,0.0019028011,0.0018117728],"domain_scores_gemma":[0.9844647,0.0015897425,0.0010391708,0.0009087091,0.005580878,0.0064166626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004774298,0.00038495773,0.00036458817,0.0012785882,0.04037074,0.008081359,0.0027963,0.0025137963,0.007955105],"category_scores_gemma":[0.013517873,0.0010071117,0.00043978236,0.00277669,0.0128893,0.0049672225,0.0066116047,0.0026937118,0.0009170757],"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":[0.00016802156,0.00014668691,0.076519534,0.00051398907,0.00010568103,0.002635376,0.52331483,0.001487437,0.0026145135,0.040942222,0.18761617,0.16393559],"study_design_scores_gemma":[0.000046625733,0.000116455056,0.06871197,0.00047262368,0.000074493284,0.00028199478,0.25547397,0.0006478181,0.0005455713,0.00423132,0.6692493,0.00014790309],"about_ca_topic_score_codex":0.9878122,"about_ca_topic_score_gemma":0.9959525,"teacher_disagreement_score":0.8816494,"about_ca_system_score_codex":0.11835061,"about_ca_system_score_gemma":0.2704201,"threshold_uncertainty_score":0.8586978},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014987791,0.007042576,0.50849605,0.113437,0.0014768188,0.0014986225,0.00022467195,0.00030435828,0.35253212],"genre_scores_gemma":[0.69769883,0.0024114903,0.2791046,0.011042667,0.0007436352,0.0032733646,0.00006905258,0.00017083442,0.005485518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.667729,0.28043297,0.009072119,0.0073609715,0.030232316,0.005172703],"domain_scores_gemma":[0.638744,0.31976095,0.010560566,0.0181232,0.010844121,0.0019670823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16126618,0.0017638181,0.001942121,0.009971653,0.0055170413,0.016065897,0.0037460916,0.013627179,0.005432583],"category_scores_gemma":[0.30373907,0.0012513049,0.0035647952,0.004879046,0.06462908,0.0214306,0.010156787,0.011423939,0.00092026714],"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":[0.000028113876,0.000009077871,0.00012782557,0.0001370721,0.000025065596,0.00003807992,0.0010344525,0.0013264582,0.000018396237,0.99259263,0.0008324185,0.0038304017],"study_design_scores_gemma":[0.000046094192,0.000049549242,0.00015807713,0.00031613966,0.000030570864,0.00006316832,0.00036537586,0.0023635826,0.00019300109,0.9815965,0.014785184,0.000032774795],"about_ca_topic_score_codex":0.005865199,"about_ca_topic_score_gemma":0.0033553632,"teacher_disagreement_score":0.16126618,"about_ca_system_score_codex":0.014317031,"about_ca_system_score_gemma":0.011116036,"threshold_uncertainty_score":0.85286725},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016056309,0.019898772,0.43831772,0.38163128,0.0028649184,0.0010048377,0.00015150287,0.0006939076,0.13938072],"genre_scores_gemma":[0.6987083,0.011202709,0.25403365,0.021093518,0.0024640274,0.0024669827,0.00013890649,0.00045956558,0.009432264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6711181,0.26352954,0.013326546,0.01628143,0.031460144,0.004284191],"domain_scores_gemma":[0.53656864,0.3300967,0.030800333,0.061282586,0.035671834,0.0055799596],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2827663,0.0015269608,0.0018285094,0.009019854,0.007871662,0.035171557,0.0047656912,0.011958281,0.0031186307],"category_scores_gemma":[0.295375,0.0018617228,0.001272476,0.0075127534,0.091493025,0.038696628,0.021981945,0.014025416,0.0009980154],"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":[0.000032047978,0.00010878312,0.003155756,0.0007101118,0.00009200302,0.0000995066,0.032307144,0.0025170308,0.00041798502,0.81074864,0.0062950323,0.14351587],"study_design_scores_gemma":[0.000028137885,0.00004691032,0.0011951779,0.0014790009,0.000022931616,0.00006891814,0.008054013,0.0016661794,0.00047673163,0.89844227,0.08842392,0.00009581065],"about_ca_topic_score_codex":0.0063492553,"about_ca_topic_score_gemma":0.004905166,"teacher_disagreement_score":0.2827663,"about_ca_system_score_codex":0.014046143,"about_ca_system_score_gemma":0.053133138,"threshold_uncertainty_score":0.88447684},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03725586,0.012279271,0.7252148,0.04967627,0.0016538945,0.0033170115,0.0008964972,0.0005038577,0.16920252],"genre_scores_gemma":[0.5169561,0.008043255,0.43819916,0.006137646,0.0005870084,0.0056959437,0.000694575,0.00059801666,0.023088332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87169886,0.10745361,0.004458022,0.0061017647,0.009069239,0.0012185056],"domain_scores_gemma":[0.8803718,0.091026165,0.004228473,0.012495695,0.009956225,0.0019215473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.096440665,0.0013262477,0.0012890564,0.008700381,0.0075940695,0.023731943,0.0035655806,0.00341943,0.009113775],"category_scores_gemma":[0.104158,0.0010600439,0.001104977,0.009313316,0.037839327,0.02363142,0.016938448,0.007150382,0.0011592954],"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":[0.00003580546,0.00008247427,0.0026871008,0.0008263129,0.00004631521,0.00027311128,0.2411568,0.0003897295,0.0008727237,0.6611592,0.0039840536,0.088486455],"study_design_scores_gemma":[0.000038379414,0.00010740414,0.002613934,0.0031371529,0.000056927132,0.00048987713,0.18274009,0.001790303,0.0014881125,0.40805155,0.39941096,0.00007526001],"about_ca_topic_score_codex":0.007914132,"about_ca_topic_score_gemma":0.00789585,"teacher_disagreement_score":0.096440665,"about_ca_system_score_codex":0.014359521,"about_ca_system_score_gemma":0.02019077,"threshold_uncertainty_score":0.5100331},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5466221,0.008619864,0.08265789,0.07620462,0.00071587815,0.0015181707,0.000054464985,0.00024339218,0.2833637],"genre_scores_gemma":[0.9855182,0.0008479455,0.009908015,0.00063304463,0.00005026175,0.00059232727,0.000010130921,0.000013565309,0.0024264455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7794903,0.20900355,0.0015138648,0.0013652658,0.0052191247,0.0034078762],"domain_scores_gemma":[0.6830457,0.27888173,0.0090376595,0.0060445354,0.009991335,0.01299908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12564859,0.00038373398,0.0006862238,0.003030009,0.011993465,0.018357165,0.0021194639,0.0033827687,0.0051747616],"category_scores_gemma":[0.17484953,0.00046746415,0.0003127631,0.003423545,0.022495713,0.012075928,0.016968971,0.0038135792,0.00035696093],"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":[0.00033264238,0.0016131384,0.013739259,0.00077858526,0.000048869,0.0006572384,0.14708287,0.0037124038,0.00026610884,0.6782577,0.010680665,0.14283048],"study_design_scores_gemma":[0.00031725303,0.0007261592,0.005964408,0.0016841413,0.00003420753,0.00034509125,0.33641905,0.0074335025,0.0011116515,0.5543759,0.09150466,0.00008394744],"about_ca_topic_score_codex":0.0019983153,"about_ca_topic_score_gemma":0.003189683,"teacher_disagreement_score":0.12564859,"about_ca_system_score_codex":0.010398584,"about_ca_system_score_gemma":0.025252864,"threshold_uncertainty_score":0.6645012},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011397371,0.04191578,0.48853835,0.2120837,0.004523337,0.0013512343,0.000114064766,0.0005525623,0.23952349],"genre_scores_gemma":[0.65481865,0.015737018,0.29195583,0.019519318,0.0023848251,0.004506476,0.000068407324,0.00036420565,0.010645274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.45873955,0.48654014,0.014821034,0.01322739,0.022835111,0.003836682],"domain_scores_gemma":[0.534387,0.3945962,0.01127451,0.03503078,0.021369586,0.0033419686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34253052,0.0015258008,0.0031845686,0.010709114,0.011508159,0.034748256,0.006107853,0.012931271,0.003956072],"category_scores_gemma":[0.25238717,0.0012931586,0.0014606398,0.010415365,0.15206508,0.03228252,0.016892163,0.015623447,0.0010621389],"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":[0.00002822009,0.000036343085,0.00055034354,0.000721532,0.000039750284,0.00012283937,0.020832933,0.0006421516,0.00012285894,0.9327463,0.0045725033,0.039584205],"study_design_scores_gemma":[0.00003760223,0.000073604606,0.00042856098,0.0032908851,0.000023730632,0.00019074656,0.014684823,0.0014608759,0.0005287577,0.863371,0.11584186,0.00006755743],"about_ca_topic_score_codex":0.0047945734,"about_ca_topic_score_gemma":0.0036711604,"teacher_disagreement_score":0.34253052,"about_ca_system_score_codex":0.021828573,"about_ca_system_score_gemma":0.027937314,"threshold_uncertainty_score":0.81077695},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07481776,0.0073857903,0.43922716,0.08041549,0.0006592595,0.004797498,0.0004693532,0.00093039597,0.3912974],"genre_scores_gemma":[0.76412946,0.0019227411,0.21703957,0.00427318,0.00012573876,0.002068864,0.00014137512,0.0001871734,0.010111906],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.840982,0.121491,0.0034751035,0.0037283804,0.026141666,0.0041819285],"domain_scores_gemma":[0.8811569,0.05683735,0.0058691734,0.0068787644,0.044789832,0.004467917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13937679,0.0008133007,0.0008136886,0.0079120025,0.005194254,0.010816036,0.002562611,0.0012739822,0.0036130683],"category_scores_gemma":[0.09939618,0.00042419985,0.0004745936,0.004172122,0.014849733,0.0062524835,0.011013442,0.0028715325,0.00030314445],"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":[0.00018606934,0.00034301516,0.022383653,0.0012332582,0.000110012006,0.00013811383,0.030579425,0.004928321,0.0011914418,0.37043187,0.013122942,0.555352],"study_design_scores_gemma":[0.00031906477,0.0011404257,0.055934373,0.005716819,0.00027163228,0.00031927455,0.0806702,0.032504708,0.0149990935,0.3051062,0.50262076,0.00039743035],"about_ca_topic_score_codex":0.14516449,"about_ca_topic_score_gemma":0.22176486,"teacher_disagreement_score":0.86062324,"about_ca_system_score_codex":0.07248326,"about_ca_system_score_gemma":0.07787453,"threshold_uncertainty_score":0.7371037},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004114204,0.055987626,0.14384504,0.7184181,0.0059564766,0.0005496954,0.00003103897,0.00023189976,0.07086591],"genre_scores_gemma":[0.58970565,0.041915353,0.19414859,0.14696112,0.0089409035,0.0044060973,0.00007467626,0.0006638358,0.013183791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5601331,0.38849798,0.010774117,0.008191075,0.027894458,0.0045093084],"domain_scores_gemma":[0.5856812,0.33552265,0.0089923,0.03403752,0.027710719,0.008055558],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3271042,0.0017551951,0.004173931,0.009414955,0.014062099,0.047096685,0.006636934,0.0152758695,0.0046007982],"category_scores_gemma":[0.28594816,0.0010711249,0.0021776606,0.009106935,0.1333352,0.07546074,0.032631565,0.030008594,0.0009263376],"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":[0.000058936894,0.00006824936,0.0005406922,0.000556172,0.00006417742,0.00008577467,0.018762466,0.0004504121,0.000059196183,0.90221417,0.013344125,0.0637955],"study_design_scores_gemma":[0.00004456188,0.00007636595,0.000268363,0.0026752953,0.000033696437,0.00015748074,0.015856408,0.001122381,0.00020703868,0.8963106,0.083192244,0.000055462595],"about_ca_topic_score_codex":0.005559109,"about_ca_topic_score_gemma":0.004887207,"teacher_disagreement_score":0.6728958,"about_ca_system_score_codex":0.029862046,"about_ca_system_score_gemma":0.03743245,"threshold_uncertainty_score":0.8298003},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2802238,0.004052907,0.008964108,0.042685654,0.00023718893,0.00030347545,0.001043206,0.0002119737,0.66227776],"genre_scores_gemma":[0.9635566,0.0009621749,0.003366666,0.0005872202,0.000011964015,0.000030999254,0.00016580643,0.000022845821,0.031295773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904405,0.0011897605,0.00023317551,0.00043400985,0.004210686,0.0034918084],"domain_scores_gemma":[0.9889781,0.0020305703,0.00045972603,0.00040085704,0.0051088855,0.0030219636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005104686,0.00032222908,0.00033600282,0.0027437783,0.01293174,0.014262473,0.0012191463,0.0012152119,0.006094586],"category_scores_gemma":[0.011824449,0.00037219512,0.0004934848,0.0035724775,0.0049982895,0.002739007,0.0036915601,0.0024649994,0.00031561079],"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":[0.00024002549,0.000109259774,0.033011213,0.00018102668,0.0000781696,0.0011542608,0.018202638,0.0147605855,0.00077911525,0.7727107,0.03457633,0.1241968],"study_design_scores_gemma":[0.00006777652,0.00012001303,0.087435335,0.00066679314,0.000100600795,0.0002927199,0.05043083,0.016865509,0.001956741,0.119609706,0.72199374,0.0004603014],"about_ca_topic_score_codex":0.987253,"about_ca_topic_score_gemma":0.9923125,"teacher_disagreement_score":0.8322549,"about_ca_system_score_codex":0.16774511,"about_ca_system_score_gemma":0.27501953,"threshold_uncertainty_score":0.9652977},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037099443,0.0002722123,0.94180363,0.0055344254,0.00015705565,0.0074807582,0.0018207512,0.0007921819,0.005039594],"genre_scores_gemma":[0.22236942,0.00025068386,0.7642636,0.00073887454,0.00003183655,0.010666208,0.00078527845,0.00018635765,0.0007078012],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5217793,0.408122,0.025259808,0.009690493,0.032184206,0.0029641867],"domain_scores_gemma":[0.18912223,0.7241676,0.02581051,0.031658415,0.027839214,0.0014019656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34582078,0.0017887955,0.0024537093,0.011182374,0.0045330706,0.01567304,0.0062498325,0.0027014024,0.0040548868],"category_scores_gemma":[0.59778446,0.0023825637,0.002715724,0.012567487,0.0074963234,0.016100042,0.011071534,0.005335714,0.0007362847],"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":[0.0006714581,0.0009142739,0.04599443,0.009539931,0.0012691548,0.0004942492,0.18464725,0.008711541,0.0033451794,0.26767614,0.008246495,0.46848992],"study_design_scores_gemma":[0.000541476,0.0006811002,0.016503297,0.016738014,0.0013036747,0.00055099576,0.12257923,0.11077652,0.028311677,0.66406876,0.03706905,0.0008762919],"about_ca_topic_score_codex":0.008618762,"about_ca_topic_score_gemma":0.0074198656,"teacher_disagreement_score":0.34582078,"about_ca_system_score_codex":0.011294963,"about_ca_system_score_gemma":0.034375843,"threshold_uncertainty_score":0.8067194},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.948603,0.0008649025,0.012650855,0.010411099,0.00014568155,0.00045198243,0.000021360576,0.00018386549,0.026667317],"genre_scores_gemma":[0.99461824,0.0002148039,0.003357214,0.0006983005,0.0000591351,0.000199164,0.0000117521395,0.000023383825,0.00081798545],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.78100806,0.18757641,0.0047590504,0.0024813293,0.016573105,0.0076020546],"domain_scores_gemma":[0.73470676,0.2101716,0.024635408,0.010634522,0.0135920355,0.0062595815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08652134,0.0008055718,0.00094758475,0.0026385002,0.0071459888,0.010823206,0.0018331183,0.0033268633,0.0022085863],"category_scores_gemma":[0.27980137,0.00068632053,0.0010693978,0.0015145758,0.006990858,0.005445364,0.009671984,0.005279315,0.00032127756],"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":[0.0011806397,0.0015837519,0.07174745,0.0012225688,0.00033333944,0.005810428,0.57220954,0.004079384,0.005961954,0.028573962,0.01358641,0.29371056],"study_design_scores_gemma":[0.00046550186,0.0056484044,0.12476489,0.0034806957,0.00056264095,0.0061595184,0.6435657,0.016570166,0.011878895,0.07161893,0.1144569,0.0008277791],"about_ca_topic_score_codex":0.0021523149,"about_ca_topic_score_gemma":0.0040367334,"teacher_disagreement_score":0.08652134,"about_ca_system_score_codex":0.0059464676,"about_ca_system_score_gemma":0.0054370677,"threshold_uncertainty_score":0.45757407},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086995885,0.020664817,0.114342466,0.06161389,0.0032637604,0.00030398098,0.0003488208,0.00018198314,0.7905807],"genre_scores_gemma":[0.81985295,0.021129003,0.06647685,0.014386574,0.0062879333,0.0013229249,0.0005853139,0.00023303414,0.06972543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9876559,0.00740899,0.00073492544,0.00176618,0.001787156,0.00064688583],"domain_scores_gemma":[0.98773384,0.007572798,0.00077429647,0.0020549165,0.0013116061,0.00055256917],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.009524563,0.0010520808,0.0014405374,0.0045250026,0.0059791426,0.011195443,0.00199669,0.0050556744,0.009528802],"category_scores_gemma":[0.012683035,0.00037945365,0.0010700913,0.0026685314,0.047776353,0.008881906,0.0066487393,0.0052310345,0.0020941144],"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":[0.0000021380474,0.0000054129164,0.000060796083,0.00004441485,0.0000044351295,0.000024393188,0.0011679012,0.00008098769,0.000019329938,0.9941386,0.0014154305,0.0030360727],"study_design_scores_gemma":[0.0000047859016,0.0000056253334,0.0000615301,0.00012122774,0.0000026512078,0.000059678834,0.00067196187,0.0002116846,0.0000329691,0.9348657,0.06395752,0.0000047034964],"about_ca_topic_score_codex":0.0024658474,"about_ca_topic_score_gemma":0.0013131866,"teacher_disagreement_score":0.9940209,"about_ca_system_score_codex":0.007266282,"about_ca_system_score_gemma":0.0058711246,"threshold_uncertainty_score":0.052720845},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87706167,0.00059906556,0.00054025766,0.0141009,0.00025044917,0.0010312331,0.015719721,0.00021288796,0.09048391],"genre_scores_gemma":[0.9767347,0.00083606184,0.0010785788,0.0034996744,0.00012614571,0.0005663182,0.004003028,0.000027106955,0.013128366],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945539,0.00068174244,0.0004590567,0.00018786149,0.0030481692,0.0010691847],"domain_scores_gemma":[0.983273,0.0019148506,0.004088818,0.000439336,0.006246365,0.0040375283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004131268,0.00015013159,0.00020328815,0.0019572051,0.0013806137,0.0013547756,0.00052797515,0.0007008363,0.009782656],"category_scores_gemma":[0.019631634,0.00021695945,0.00035901237,0.002499778,0.0004241857,0.0011438684,0.0013087622,0.0007735803,0.0021308893],"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":[0.0003123908,0.00029485612,0.8394258,0.00018434979,0.000034339482,0.0001576059,0.0020937305,0.000100377314,0.00022870829,0.0002710084,0.10991137,0.046985384],"study_design_scores_gemma":[0.000029140443,0.000171698,0.97388613,0.00007978868,0.000021640104,0.00012469252,0.004289999,0.00013655605,0.00028789538,0.000051711642,0.020898178,0.000022616883],"about_ca_topic_score_codex":0.24613455,"about_ca_topic_score_gemma":0.34175742,"teacher_disagreement_score":0.7538655,"about_ca_system_score_codex":0.0037765454,"about_ca_system_score_gemma":0.008456899,"threshold_uncertainty_score":0.48940378},"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":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07000531,0.01949128,0.31379384,0.05304991,0.006329706,0.49913907,0.00079435343,0.0035955026,0.03380109],"genre_scores_gemma":[0.08939599,0.0086507555,0.7758764,0.003915067,0.0021580881,0.107266225,0.0010067346,0.00042431432,0.0113063445],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.65461874,0.24949008,0.045149975,0.006495569,0.039456084,0.0047895205],"domain_scores_gemma":[0.47096083,0.18703443,0.0679688,0.02500712,0.22019355,0.02883532],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4723147,0.0018960211,0.0031247472,0.021946674,0.010956559,0.013214071,0.008301732,0.005427649,0.005766594],"category_scores_gemma":[0.407835,0.002322756,0.0031727552,0.009037969,0.0037298754,0.011522055,0.0137032885,0.0065866765,0.0041516125],"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":[0.000925016,0.0020783616,0.004784726,0.0147336945,0.00040172433,0.002100886,0.06256222,0.0026893148,0.0070084026,0.00811961,0.059397597,0.83519846],"study_design_scores_gemma":[0.0020734123,0.00649598,0.030894002,0.029311907,0.0009976046,0.002814732,0.05814328,0.009600532,0.013647886,0.02613081,0.81801826,0.0018715827],"about_ca_topic_score_codex":0.0047461772,"about_ca_topic_score_gemma":0.012327696,"teacher_disagreement_score":0.4723147,"about_ca_system_score_codex":0.018364523,"about_ca_system_score_gemma":0.10022865,"threshold_uncertainty_score":0.6507299},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99885464,0.00034684478,0.00006743824,0.000076616605,0.000012559766,0.00024894168,0.00018552477,0.00000551366,0.0002020285],"genre_scores_gemma":[0.9988576,0.00020909264,0.00022135886,0.00012602033,0.000013935022,0.00022387656,0.00019740425,0.0000021634141,0.00014847971],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9861314,0.009914156,0.0010019352,0.0007719367,0.00112548,0.0010550107],"domain_scores_gemma":[0.9804386,0.0064078225,0.0062606423,0.0015861948,0.0022253906,0.0030813448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005910158,0.00070816284,0.0008212763,0.0009381558,0.00042609495,0.0011378884,0.0008665605,0.0014374398,0.0016108894],"category_scores_gemma":[0.024835594,0.00073247787,0.0010715935,0.0012280933,0.0009286773,0.0010624799,0.0018744754,0.00076237635,0.00020373675],"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":[0.06060647,0.013172311,0.81931615,0.002322704,0.0016978036,0.0015449903,0.005686597,0.0058078845,0.003970924,0.00027515608,0.001546022,0.08405292],"study_design_scores_gemma":[0.0020226745,0.03210117,0.96209913,0.000118645294,0.00023745076,0.00019907168,0.001304852,0.00089876243,0.00036045403,0.00002273226,0.00058512157,0.000049938648],"about_ca_topic_score_codex":0.06053487,"about_ca_topic_score_gemma":0.061400443,"teacher_disagreement_score":0.06053487,"about_ca_system_score_codex":0.0059496392,"about_ca_system_score_gemma":0.0030683253,"threshold_uncertainty_score":0.12036502},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25993904,0.007015065,0.030024944,0.12999567,0.00025928367,0.00071258994,0.0005472007,0.00012479708,0.57138133],"genre_scores_gemma":[0.9841027,0.001039821,0.009399471,0.00089959695,0.000025422705,0.00009948714,0.000034499943,0.000019428924,0.004379547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9465572,0.032941006,0.0011329144,0.0013613624,0.012173883,0.0058336104],"domain_scores_gemma":[0.93207854,0.047254357,0.0019485668,0.0023787399,0.013450734,0.0028890776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03529845,0.0008112639,0.0010133808,0.007089575,0.01757728,0.021001924,0.0026313022,0.0040552025,0.0022680503],"category_scores_gemma":[0.056417264,0.00032938027,0.0007258533,0.01346224,0.027610887,0.004843828,0.0075953747,0.0029102045,0.0001644424],"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":[0.000066194276,0.00005411008,0.0075470465,0.00017096664,0.00002554795,0.0007373165,0.017130375,0.0046908744,0.00023993112,0.94452786,0.004067292,0.020742496],"study_design_scores_gemma":[0.00017681009,0.00031011846,0.03284868,0.0022278947,0.0003172294,0.000752266,0.18610194,0.053641986,0.003224994,0.47864348,0.24134302,0.0004116721],"about_ca_topic_score_codex":0.9245374,"about_ca_topic_score_gemma":0.9412951,"teacher_disagreement_score":0.96470153,"about_ca_system_score_codex":0.15324818,"about_ca_system_score_gemma":0.14810835,"threshold_uncertainty_score":0.9821121},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029073428,0.011637059,0.22131133,0.3360745,0.008373706,0.0019256594,0.0021656335,0.001470447,0.38796824],"genre_scores_gemma":[0.69268924,0.020179389,0.2197573,0.036620546,0.0016765747,0.0029926735,0.0011624508,0.00090875337,0.024013089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.819006,0.14297545,0.0069969827,0.0021399714,0.026656238,0.0022252772],"domain_scores_gemma":[0.6446816,0.24549496,0.0064675612,0.01373955,0.08783863,0.0017777907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15634297,0.0007346299,0.0013015994,0.006424267,0.0025092904,0.017653706,0.002182998,0.0017882234,0.008775703],"category_scores_gemma":[0.30007192,0.0005081587,0.00067274575,0.0047393823,0.00950209,0.007992976,0.005105081,0.0055929846,0.0016132126],"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":[0.00014135781,0.00032591348,0.0024377631,0.0036428005,0.00014792981,0.00026975767,0.01692639,0.0055340314,0.0018908876,0.65800226,0.07408161,0.23659936],"study_design_scores_gemma":[0.00023092443,0.00032517553,0.006708131,0.026743736,0.00029881005,0.00012701044,0.042148974,0.008441988,0.011484318,0.33700117,0.5662746,0.00021527347],"about_ca_topic_score_codex":0.038294595,"about_ca_topic_score_gemma":0.027900442,"teacher_disagreement_score":0.15634297,"about_ca_system_score_codex":0.025862707,"about_ca_system_score_gemma":0.053100053,"threshold_uncertainty_score":0.8268305},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30856007,0.0034469573,0.021185841,0.31416744,0.00047728617,0.0010867766,0.00007367849,0.000056270597,0.35094565],"genre_scores_gemma":[0.98022753,0.00072966854,0.0046088863,0.0049712737,0.000052158273,0.00034902667,0.00002150376,0.0000089980185,0.00903088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9690636,0.019268963,0.0010422384,0.0011697405,0.0033709141,0.006084505],"domain_scores_gemma":[0.9605269,0.020698661,0.0016457516,0.0018334176,0.0045476602,0.010747642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05277859,0.00028526,0.00041491154,0.0015708557,0.018657044,0.026947903,0.0022023912,0.006259833,0.0043681497],"category_scores_gemma":[0.0452355,0.00029605135,0.0004187382,0.0020301214,0.015084235,0.010914124,0.018004976,0.0052582677,0.0002330885],"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":[0.000104452825,0.00043444714,0.020079784,0.00032688817,0.00001960289,0.0007287367,0.11406488,0.0011525024,0.00067971315,0.7693766,0.009146362,0.08388609],"study_design_scores_gemma":[0.00012601342,0.00033261345,0.02396511,0.0014898351,0.000049352366,0.00066429464,0.51019025,0.0024917962,0.0014964537,0.110038385,0.34907886,0.00007712043],"about_ca_topic_score_codex":0.040681574,"about_ca_topic_score_gemma":0.06453414,"teacher_disagreement_score":0.05277859,"about_ca_system_score_codex":0.019233448,"about_ca_system_score_gemma":0.054929,"threshold_uncertainty_score":0.2791232},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034607943,0.0027645722,0.5865698,0.051666316,0.00038426399,0.0013758817,0.00016738844,0.00033881047,0.322125],"genre_scores_gemma":[0.74998283,0.0025577422,0.21580753,0.002929761,0.0003523477,0.0029182879,0.00017640965,0.00011562884,0.025159534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9269082,0.057103723,0.0017230511,0.0040330836,0.0058276723,0.004404228],"domain_scores_gemma":[0.94734955,0.035428762,0.0040250504,0.0049891253,0.003916937,0.0042905463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046439316,0.0012122997,0.0013361203,0.007305416,0.013890637,0.0299187,0.0050775553,0.01153396,0.017266639],"category_scores_gemma":[0.054348003,0.0018266141,0.002720029,0.010312684,0.029770201,0.03610868,0.018635828,0.0052238163,0.0026080776],"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":[0.00003904188,0.00008813441,0.0012783034,0.00012373901,0.00004105833,0.0003528237,0.010612219,0.003974972,0.00010802284,0.97133887,0.00091909786,0.011123763],"study_design_scores_gemma":[0.00014062502,0.00017285053,0.00051834766,0.00034975252,0.000053909207,0.00028606332,0.0072355703,0.009540994,0.00019874473,0.9286472,0.052801076,0.000054874257],"about_ca_topic_score_codex":0.014697327,"about_ca_topic_score_gemma":0.008796288,"teacher_disagreement_score":0.046439316,"about_ca_system_score_codex":0.016388284,"about_ca_system_score_gemma":0.036270857,"threshold_uncertainty_score":0.24559754},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78869957,0.00089802337,0.07901367,0.0022754348,0.000043452896,0.005203094,0.00052473537,0.00019245848,0.12314956],"genre_scores_gemma":[0.95840865,0.00017694829,0.037748575,0.000163025,0.000007915629,0.00070362794,0.0002103607,0.00002515217,0.002555834],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95469826,0.027786234,0.00207818,0.0012489234,0.012747574,0.0014408343],"domain_scores_gemma":[0.8886131,0.07394994,0.0065137492,0.0039886576,0.025436735,0.001497695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07312925,0.00063986186,0.0005035359,0.0062074573,0.001644794,0.0043293266,0.0015715724,0.00080507336,0.002992021],"category_scores_gemma":[0.11741978,0.00019653144,0.0006924394,0.0034082395,0.0014735829,0.0033064112,0.0025414845,0.0007855162,0.00024950143],"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":[0.0032027452,0.0023667284,0.10844926,0.002260201,0.0006165189,0.00041458834,0.012860999,0.042564135,0.012977838,0.12382688,0.004559694,0.6859004],"study_design_scores_gemma":[0.0014327058,0.032166265,0.4648338,0.0027418444,0.0020752847,0.0010230439,0.04069731,0.24421677,0.041409016,0.08786424,0.08117663,0.00036311187],"about_ca_topic_score_codex":0.013593392,"about_ca_topic_score_gemma":0.012307137,"teacher_disagreement_score":0.07312925,"about_ca_system_score_codex":0.009014961,"about_ca_system_score_gemma":0.014457599,"threshold_uncertainty_score":0.3867491},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076592335,0.03469463,0.010492055,0.91957676,0.008503979,0.000051765663,0.00006220458,0.00013554982,0.025717102],"genre_scores_gemma":[0.08748709,0.044670336,0.060077213,0.7267524,0.02060534,0.0007539202,0.00018135717,0.0008193534,0.05865303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90250707,0.07113795,0.0037689814,0.0058055175,0.014416634,0.0023637982],"domain_scores_gemma":[0.86358273,0.09809355,0.004355283,0.012884621,0.015376595,0.005707244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0744662,0.0012394069,0.001814404,0.0037945386,0.012669725,0.03479474,0.0037995998,0.015233043,0.01131457],"category_scores_gemma":[0.11453647,0.0010104683,0.0016416297,0.004583868,0.08494021,0.04980837,0.012599107,0.03735276,0.005299456],"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":[0.000065950255,0.000040522344,0.0004972291,0.0007496781,0.000042382086,0.00015507692,0.02095825,0.0001142173,0.00039048513,0.6097786,0.33245772,0.034750015],"study_design_scores_gemma":[0.00001587915,0.000039053004,0.00029582944,0.0013613689,0.000014997188,0.00019918104,0.010926224,0.0001168239,0.00016917563,0.21628302,0.7705333,0.00004517022],"about_ca_topic_score_codex":0.0075649954,"about_ca_topic_score_gemma":0.013866863,"teacher_disagreement_score":0.9255338,"about_ca_system_score_codex":0.011374893,"about_ca_system_score_gemma":0.016719662,"threshold_uncertainty_score":0.39381963},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18969327,0.02881446,0.0012495203,0.68990046,0.000993545,0.00008741774,0.00172408,0.00014182348,0.087395504],"genre_scores_gemma":[0.9465375,0.011465254,0.002183036,0.027727244,0.00025363406,0.000039013474,0.000565534,0.000053881584,0.011174932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.98216724,0.0012555755,0.0006576095,0.0011843768,0.0079253875,0.006809751],"domain_scores_gemma":[0.9602449,0.0056283614,0.0027536093,0.0005308528,0.020498084,0.010344265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008787408,0.00028777527,0.00059031165,0.00478225,0.0144421775,0.011227317,0.0027082672,0.0037799717,0.0042858855],"category_scores_gemma":[0.023945758,0.0004954089,0.0006151954,0.012713374,0.0055769626,0.0031592683,0.0029229661,0.0061072567,0.00019788963],"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":[0.00041837795,0.00020263212,0.09440099,0.0008239286,0.00013445776,0.0008145435,0.011985245,0.0034450563,0.0014894741,0.54078156,0.16632603,0.17917782],"study_design_scores_gemma":[0.00018881555,0.000145099,0.39433986,0.0015720838,0.00017061806,0.00033405298,0.024417236,0.0076321713,0.0014195383,0.03188589,0.5374679,0.00042674408],"about_ca_topic_score_codex":0.9980938,"about_ca_topic_score_gemma":0.9985948,"teacher_disagreement_score":0.6344124,"about_ca_system_score_codex":0.36558762,"about_ca_system_score_gemma":0.46392375,"threshold_uncertainty_score":0.7358284},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060630843,0.013727752,0.2608605,0.42299217,0.0018762929,0.00079429446,0.00012581714,0.00026521372,0.23872715],"genre_scores_gemma":[0.90266097,0.002981714,0.07620222,0.007636959,0.0003636835,0.0010677914,0.00006596203,0.00029154256,0.008729178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.68190396,0.2908859,0.0031592331,0.005220538,0.014929382,0.003900976],"domain_scores_gemma":[0.5927063,0.36731043,0.0067076352,0.012628485,0.013773298,0.0068738535],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21285865,0.0013379654,0.0019579476,0.005378884,0.024142364,0.041200057,0.00622024,0.012537497,0.0061710766],"category_scores_gemma":[0.23478156,0.0014232628,0.0007971605,0.0040734927,0.10409184,0.038177695,0.028695235,0.014432869,0.0008267542],"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":[0.00005363447,0.0001348157,0.0008712578,0.00046829515,0.00002368906,0.00027338704,0.14245221,0.00056946045,0.00034144614,0.8071725,0.005611359,0.042027943],"study_design_scores_gemma":[0.000055050583,0.0001221692,0.0005106848,0.0019545422,0.000021775284,0.00024260936,0.09190573,0.0014484435,0.000873724,0.8034388,0.09935386,0.00007253571],"about_ca_topic_score_codex":0.004843929,"about_ca_topic_score_gemma":0.0060217804,"teacher_disagreement_score":0.21285865,"about_ca_system_score_codex":0.01323755,"about_ca_system_score_gemma":0.034811582,"threshold_uncertainty_score":0.9706854},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6865223,0.004036976,0.023730885,0.06949235,0.000442828,0.021597344,0.057691813,0.0025727993,0.13391265],"genre_scores_gemma":[0.86137426,0.0017579483,0.054020286,0.007016389,0.00012247264,0.009245379,0.015766736,0.00022162173,0.05047484],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9868961,0.0053048176,0.00087218307,0.0009021359,0.0038353044,0.0021893897],"domain_scores_gemma":[0.93492186,0.020034242,0.0043498673,0.005565226,0.020608176,0.014520682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027017036,0.00043443724,0.00050914875,0.0014610437,0.0035918376,0.0024797102,0.0035029976,0.0019039134,0.015936606],"category_scores_gemma":[0.056051683,0.000756542,0.0008778111,0.0022847936,0.0014066397,0.0016966083,0.00480488,0.0015780132,0.0012262459],"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":[0.011104462,0.0035479232,0.23626009,0.0027465648,0.0005354785,0.00069305726,0.0049954713,0.0075371545,0.003322488,0.020144837,0.22445516,0.48465726],"study_design_scores_gemma":[0.0072121173,0.0043223645,0.7446213,0.0014322286,0.00085438957,0.00041971172,0.0017209376,0.013029626,0.0033690112,0.0067221406,0.21609782,0.00019838335],"about_ca_topic_score_codex":0.8460731,"about_ca_topic_score_gemma":0.93641543,"teacher_disagreement_score":0.9535584,"about_ca_system_score_codex":0.046441622,"about_ca_system_score_gemma":0.31403175,"threshold_uncertainty_score":0.33695912},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.245385,0.0029961504,0.51786274,0.050268948,0.001185859,0.013543684,0.00025985527,0.0028512273,0.16564666],"genre_scores_gemma":[0.7825405,0.0008122145,0.20467478,0.001929347,0.000206484,0.0038062374,0.0001347103,0.0002297484,0.0056660795],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5438042,0.4126205,0.01206977,0.006616288,0.019326694,0.005562517],"domain_scores_gemma":[0.5103707,0.37025943,0.024402566,0.03401584,0.047931865,0.013019586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28600067,0.0010444506,0.0017793712,0.004360806,0.0065712305,0.017639142,0.0029521903,0.0033169389,0.010022684],"category_scores_gemma":[0.3300284,0.00097015296,0.000917877,0.003659431,0.0065132114,0.018802641,0.014755771,0.0032563538,0.002548755],"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":[0.002140456,0.0037979498,0.0276984,0.0036981686,0.00026422547,0.0017173612,0.13722304,0.0040320153,0.0076329997,0.04863327,0.018715901,0.7444463],"study_design_scores_gemma":[0.0035510845,0.008277378,0.03100457,0.017233444,0.0013971602,0.002193218,0.25442693,0.09716104,0.039754722,0.14559473,0.3983962,0.0010095454],"about_ca_topic_score_codex":0.0030671603,"about_ca_topic_score_gemma":0.0030354979,"teacher_disagreement_score":0.28600067,"about_ca_system_score_codex":0.009213918,"about_ca_system_score_gemma":0.03893637,"threshold_uncertainty_score":0.8804883},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49662986,0.0022077993,0.29766765,0.014047357,0.0013595067,0.09028029,0.009306033,0.0009205724,0.08758096],"genre_scores_gemma":[0.56311256,0.0012562175,0.15828238,0.006706944,0.0001783135,0.24155214,0.0025213098,0.0003007171,0.026089441],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.87499046,0.10706628,0.0044031236,0.0049092243,0.004143261,0.004487602],"domain_scores_gemma":[0.81993884,0.14776,0.008282501,0.0075116837,0.01395183,0.002555172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09525737,0.0018711087,0.0011209148,0.0050744126,0.009009349,0.0052219806,0.0029369271,0.0029632852,0.017857358],"category_scores_gemma":[0.09938196,0.0018071764,0.00082474103,0.004973302,0.0075679845,0.008346799,0.011880557,0.005607813,0.0057198266],"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":[0.0004015776,0.00037388655,0.0038155818,0.0025568448,0.000021707297,0.0006335821,0.8717329,0.0004989587,0.010935907,0.011445413,0.006992846,0.090590835],"study_design_scores_gemma":[0.00042880428,0.0006671808,0.006161223,0.0025589645,0.00004042762,0.0004268487,0.87747926,0.001664665,0.008979222,0.01796897,0.083453275,0.00017117144],"about_ca_topic_score_codex":0.0047824616,"about_ca_topic_score_gemma":0.0109544825,"teacher_disagreement_score":0.9047426,"about_ca_system_score_codex":0.012103577,"about_ca_system_score_gemma":0.012086149,"threshold_uncertainty_score":0.5037751},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011834435,0.035238933,0.058184292,0.43008476,0.0017796623,0.001050523,0.000093402086,0.00050644606,0.4612276],"genre_scores_gemma":[0.84543884,0.029880574,0.055964135,0.025274202,0.0008968983,0.0014564797,0.000060318638,0.00020135574,0.040827304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96822584,0.025051551,0.0005409927,0.0009878237,0.0028305256,0.0023633274],"domain_scores_gemma":[0.9805022,0.011345038,0.0012457841,0.0012613473,0.0018812187,0.0037643558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025682392,0.0010493711,0.0008403631,0.003932535,0.0072416575,0.020159451,0.0023487012,0.0058281487,0.009154943],"category_scores_gemma":[0.023941211,0.00046331147,0.00062059675,0.003923321,0.04958073,0.019979969,0.013888965,0.005861136,0.0011544637],"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":[0.000038042203,0.00014271984,0.0006185465,0.00056349277,0.000030948686,0.00011071319,0.01234595,0.0023057575,0.00012445218,0.8688074,0.036897,0.07801497],"study_design_scores_gemma":[0.000054549735,0.00013384527,0.00079484505,0.0013175618,0.000020249669,0.000087999484,0.016810475,0.0015924259,0.00034073432,0.74447405,0.23430942,0.000063775165],"about_ca_topic_score_codex":0.01605849,"about_ca_topic_score_gemma":0.022602245,"teacher_disagreement_score":0.025682392,"about_ca_system_score_codex":0.019392585,"about_ca_system_score_gemma":0.032042287,"threshold_uncertainty_score":0.14070374},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043800607,0.00068161084,0.5225273,0.002639999,0.0002593836,0.008286534,0.25441676,0.11466803,0.0527198],"genre_scores_gemma":[0.14881803,0.0006926847,0.6910317,0.0003670515,0.000071264774,0.008313675,0.13916273,0.0018582533,0.009684585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99385613,0.0018092991,0.0014054129,0.0005907185,0.0021574125,0.0001809828],"domain_scores_gemma":[0.9667341,0.0137750385,0.005249304,0.004792668,0.0076973382,0.0017514683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012474047,0.0012712011,0.0015187532,0.018579176,0.0012937523,0.0035270634,0.0016019433,0.0010056912,0.016231453],"category_scores_gemma":[0.030998953,0.0009798561,0.0006342216,0.014872777,0.00044872623,0.0054401937,0.002300016,0.0012571232,0.0050284136],"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":[0.0005819592,0.0008049827,0.028861782,0.0013053237,0.00032086103,0.0001190517,0.0022929779,0.016773969,0.0027309484,0.016983401,0.23304375,0.69618106],"study_design_scores_gemma":[0.00091024744,0.0016029878,0.15096271,0.0014481172,0.0011388451,0.0005408443,0.0030866766,0.2201822,0.022326047,0.030417642,0.56636536,0.0010183483],"about_ca_topic_score_codex":0.036371175,"about_ca_topic_score_gemma":0.030570878,"teacher_disagreement_score":0.036371175,"about_ca_system_score_codex":0.003971632,"about_ca_system_score_gemma":0.012259392,"threshold_uncertainty_score":0.07231891},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006737869,0.027870202,0.069005415,0.04823672,0.0067084916,0.010100291,0.0974838,0.006454194,0.7274031],"genre_scores_gemma":[0.052177414,0.037187006,0.40937343,0.02344778,0.0017945163,0.012523409,0.06469847,0.004557657,0.3942402],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9722989,0.0044274554,0.004475422,0.00070832734,0.01565088,0.002439032],"domain_scores_gemma":[0.9025644,0.011371663,0.0022601148,0.0018260585,0.079235464,0.0027422581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019096654,0.002261681,0.002225528,0.01708704,0.00488107,0.008696438,0.007060856,0.006189378,0.04091199],"category_scores_gemma":[0.07451423,0.0025413795,0.0041863625,0.022611752,0.0020598127,0.0025898716,0.002861296,0.0054707457,0.01262489],"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":[0.00005436881,0.00008402587,0.0015729713,0.00082383817,0.000060084385,0.0002018727,0.0003565007,0.004570881,0.00016338704,0.0205715,0.8948486,0.07669188],"study_design_scores_gemma":[0.00014618092,0.000034800472,0.012244424,0.002866704,0.00011931849,0.00021091607,0.00044437256,0.0033374988,0.0003113317,0.0104659265,0.96968085,0.00013771522],"about_ca_topic_score_codex":0.97280836,"about_ca_topic_score_gemma":0.9775728,"teacher_disagreement_score":0.93016636,"about_ca_system_score_codex":0.06983365,"about_ca_system_score_gemma":0.29492438,"threshold_uncertainty_score":0.50668097},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09310095,0.039734546,0.25951594,0.13341962,0.002284129,0.008479065,0.00078133366,0.00047813563,0.46220636],"genre_scores_gemma":[0.7922039,0.012171836,0.11598485,0.012292321,0.00041269272,0.009011833,0.00033284913,0.00024422593,0.05734549],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8890707,0.086417906,0.0030913975,0.0045755156,0.013617141,0.0032273508],"domain_scores_gemma":[0.8872564,0.075776346,0.0066940538,0.00936952,0.016188625,0.00471512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.087286666,0.0009125676,0.0012086804,0.0044359486,0.00493054,0.012331545,0.0029651541,0.0038340585,0.014934509],"category_scores_gemma":[0.1165582,0.000942863,0.0014787264,0.0038290264,0.01662119,0.0098474985,0.00681888,0.0063869953,0.0016252827],"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":[0.00021234727,0.00035745234,0.0052387686,0.0019686925,0.00011754922,0.000075793636,0.026364967,0.001382485,0.00039216122,0.8035994,0.007487276,0.15280312],"study_design_scores_gemma":[0.00040015907,0.0011564337,0.028575609,0.01235967,0.00035138318,0.00026259432,0.02767478,0.005332827,0.0035881181,0.5594424,0.36063376,0.0002222843],"about_ca_topic_score_codex":0.0398129,"about_ca_topic_score_gemma":0.048170332,"teacher_disagreement_score":0.087286666,"about_ca_system_score_codex":0.03956347,"about_ca_system_score_gemma":0.07443368,"threshold_uncertainty_score":0.46162152},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.121349975,0.004230488,0.7577131,0.07506187,0.00038069056,0.0025464431,0.00026982802,0.0005841139,0.03786358],"genre_scores_gemma":[0.6152948,0.002370447,0.3708593,0.002458752,0.00006277918,0.0045731757,0.00018457916,0.00022431236,0.0039718533],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.90414375,0.08846888,0.0026015653,0.001305334,0.0022850172,0.0011955309],"domain_scores_gemma":[0.85282445,0.12934953,0.0031979098,0.008897437,0.0045946483,0.0011361473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0791301,0.0014602246,0.00072261563,0.006003004,0.008303997,0.0149656255,0.0030784325,0.005857639,0.0031651799],"category_scores_gemma":[0.11268564,0.0015775603,0.00084458006,0.0047185193,0.025051873,0.031005215,0.008149043,0.004885767,0.0007241029],"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":[0.00005547746,0.00017414347,0.0044407053,0.0007414284,0.000031031122,0.00041078773,0.7280021,0.0006322473,0.0011849409,0.1790506,0.004746479,0.08053],"study_design_scores_gemma":[0.00006610272,0.000098128614,0.0030557094,0.004816497,0.00006434112,0.00069799786,0.7171649,0.004349453,0.0024556194,0.21382655,0.053270515,0.0001342206],"about_ca_topic_score_codex":0.007697606,"about_ca_topic_score_gemma":0.010897588,"teacher_disagreement_score":0.0791301,"about_ca_system_score_codex":0.0063975253,"about_ca_system_score_gemma":0.010095427,"threshold_uncertainty_score":0.418485},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82415545,0.003499553,0.017881026,0.007537831,0.00024258062,0.0018415382,0.00066125835,0.00024304909,0.14393772],"genre_scores_gemma":[0.95279616,0.0010310108,0.011971168,0.0003189968,0.000031872478,0.00047598514,0.00028626312,0.000044835535,0.033043608],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.980529,0.008013971,0.0006924236,0.0011996585,0.007562397,0.0020025128],"domain_scores_gemma":[0.9710183,0.009579357,0.0015936007,0.0009347381,0.014282601,0.0025913664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021462124,0.00081307406,0.00097261806,0.0028221135,0.005361071,0.007913893,0.001676845,0.001322647,0.008579627],"category_scores_gemma":[0.034072902,0.00027380962,0.0005813362,0.002968724,0.0032478306,0.0022867096,0.0028675867,0.0018998997,0.00090601516],"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":[0.0015046044,0.0015381594,0.11366684,0.0016083627,0.0003540541,0.00054402294,0.06722193,0.018543469,0.0066063525,0.05393539,0.015126673,0.71935004],"study_design_scores_gemma":[0.0002822987,0.00348228,0.54815894,0.0026737687,0.00052042445,0.00016511562,0.10922628,0.023541577,0.014646783,0.016185472,0.2806699,0.0004471402],"about_ca_topic_score_codex":0.7111696,"about_ca_topic_score_gemma":0.8091258,"teacher_disagreement_score":0.2888304,"about_ca_system_score_codex":0.04879398,"about_ca_system_score_gemma":0.05139231,"threshold_uncertainty_score":0.58106273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97543067,0.00075029995,0.00023950881,0.0059997183,0.000058866528,0.000043640594,0.00003887202,0.0000136537055,0.017424861],"genre_scores_gemma":[0.9989737,0.00014046933,0.000098972116,0.00028181548,0.000019883402,0.000011550291,0.000009526741,0.000002883533,0.00046126454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95882463,0.026391877,0.0010987783,0.0012275844,0.007929177,0.0045279763],"domain_scores_gemma":[0.79340506,0.12206089,0.05177184,0.0045958976,0.013322489,0.014843749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015544566,0.00035099348,0.00056978787,0.0020671997,0.00626965,0.0043294113,0.0024858685,0.0029349674,0.008369792],"category_scores_gemma":[0.08900027,0.00031086648,0.0008190383,0.0022757861,0.010379684,0.0041795224,0.0065295543,0.0035733294,0.00041886055],"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":[0.0010367484,0.0026212942,0.8557476,0.0004512914,0.00033789608,0.002145982,0.031837627,0.0018728937,0.00053875946,0.016528169,0.006690524,0.080191255],"study_design_scores_gemma":[0.00011656238,0.0014699309,0.852984,0.0004810859,0.0002305586,0.00042905507,0.12585677,0.0012947462,0.00083815306,0.007280823,0.008924002,0.00009443597],"about_ca_topic_score_codex":0.018783098,"about_ca_topic_score_gemma":0.039256074,"teacher_disagreement_score":0.018783098,"about_ca_system_score_codex":0.0067751296,"about_ca_system_score_gemma":0.0064474028,"threshold_uncertainty_score":0.082208514},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828075,0.00037212853,0.008296171,0.0028464766,0.00007119823,0.0010970206,0.00008698393,0.000025135438,0.004397353],"genre_scores_gemma":[0.9915211,0.00041524423,0.004702604,0.0007696755,0.000020763278,0.000950862,0.000040029754,0.000021967946,0.0015576968],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.894472,0.09567827,0.001544741,0.0019052462,0.0026225394,0.0037772206],"domain_scores_gemma":[0.86118495,0.11549512,0.005722998,0.0023124646,0.009820793,0.0054637208],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056250177,0.000871408,0.000993387,0.0030954445,0.017222315,0.006149689,0.0026099514,0.0034982187,0.0021197996],"category_scores_gemma":[0.10507646,0.0010431146,0.00042865297,0.0030225124,0.014648759,0.0045227115,0.0058538276,0.0044818823,0.00031915915],"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":[0.000062927145,0.000104327584,0.0019082787,0.000119074044,0.0000044654316,0.00079634925,0.9926843,0.000070336275,0.000581553,0.0013650743,0.00028231973,0.002021097],"study_design_scores_gemma":[0.000014162769,0.000121466524,0.0011168097,0.00015852363,0.0000048404295,0.0002853507,0.99090755,0.00024373192,0.00051875436,0.00046756846,0.006133094,0.000028148736],"about_ca_topic_score_codex":0.015170216,"about_ca_topic_score_gemma":0.021925915,"teacher_disagreement_score":0.94374985,"about_ca_system_score_codex":0.014677329,"about_ca_system_score_gemma":0.00860697,"threshold_uncertainty_score":0.2974829},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011576283,0.022367522,0.14083871,0.20954295,0.009328315,0.0051483875,0.0010569654,0.0018136665,0.59832716],"genre_scores_gemma":[0.108635984,0.023478711,0.552526,0.066230066,0.004166564,0.0071649672,0.0021047697,0.001059892,0.23463306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8885366,0.05839289,0.014738375,0.0016389079,0.032906197,0.0037870777],"domain_scores_gemma":[0.80295557,0.060279623,0.010626734,0.009188216,0.11170944,0.0052403877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07253798,0.00118388,0.0008991268,0.007981064,0.004697186,0.010164268,0.004376411,0.010222144,0.009881469],"category_scores_gemma":[0.15496008,0.0009260675,0.000753788,0.0064523257,0.0034485466,0.005515616,0.0036225892,0.0063497373,0.011868025],"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":[0.00004448911,0.00024959803,0.0021463297,0.0009653604,0.000013062022,0.00071725674,0.0060715643,0.0011711961,0.0012374212,0.15615748,0.56701905,0.2642073],"study_design_scores_gemma":[0.000026080705,0.00008002668,0.0016936229,0.0024651529,0.000012142843,0.0003819283,0.00295051,0.00046906178,0.00051253155,0.019103374,0.9722539,0.000051569423],"about_ca_topic_score_codex":0.010290545,"about_ca_topic_score_gemma":0.034305856,"teacher_disagreement_score":0.07253798,"about_ca_system_score_codex":0.004891722,"about_ca_system_score_gemma":0.03270497,"threshold_uncertainty_score":0.3836221},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97528756,0.00011147748,0.004596901,0.00050612085,0.000009059949,0.00023349898,0.000021402288,0.00005411039,0.019179875],"genre_scores_gemma":[0.99809223,0.00002706561,0.0013692247,0.000014905157,0.0000017368114,0.000029761497,0.000012684501,0.000002224339,0.00045015602],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946403,0.003238056,0.00013635655,0.0003524458,0.00063507713,0.0009977634],"domain_scores_gemma":[0.9934094,0.0014683198,0.001030146,0.00082845584,0.0010754168,0.0021882565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004358043,0.000219304,0.00015910143,0.0015067863,0.0026026443,0.003871463,0.00078014703,0.00060858356,0.0012543901],"category_scores_gemma":[0.011506603,0.00019629885,0.00024196,0.0005751802,0.00572693,0.0029456096,0.0039978717,0.00049850025,0.00022312769],"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":[0.0004167893,0.0034154966,0.327046,0.00052095973,0.00011126645,0.00080867705,0.1823816,0.012619295,0.0071627996,0.07619648,0.0036279429,0.38569272],"study_design_scores_gemma":[0.00028594572,0.00350167,0.51487815,0.00065761904,0.00007902273,0.00041342468,0.24774574,0.022925993,0.008187282,0.103192516,0.097966306,0.00016623526],"about_ca_topic_score_codex":0.011723284,"about_ca_topic_score_gemma":0.028916202,"teacher_disagreement_score":0.011723284,"about_ca_system_score_codex":0.0052422644,"about_ca_system_score_gemma":0.0074981726,"threshold_uncertainty_score":0.038035452},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76094687,0.01112,0.026564466,0.13837324,0.0017452204,0.00041627485,0.0010769428,0.0004495882,0.05930747],"genre_scores_gemma":[0.9752068,0.0025521433,0.012518527,0.007731953,0.000560076,0.00011297608,0.0002246442,0.00005991732,0.0010329535],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99119097,0.005473027,0.00066974363,0.00053632853,0.0015612957,0.00056866964],"domain_scores_gemma":[0.9113127,0.07329467,0.0048257075,0.0014565337,0.006251436,0.0028589217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016423017,0.00046583387,0.0011793385,0.0019617595,0.0008840317,0.0032458678,0.0008299569,0.004399988,0.005933831],"category_scores_gemma":[0.13972872,0.00026373094,0.0008245764,0.0012323644,0.0012733763,0.004052748,0.00070304924,0.0026573427,0.0017280434],"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":[0.0061824108,0.0017271268,0.14302012,0.0025995676,0.0013070357,0.00055973156,0.007062315,0.0033762637,0.002193441,0.0058703804,0.03008585,0.79601574],"study_design_scores_gemma":[0.0066155307,0.0057984726,0.42573732,0.010845016,0.007942252,0.0043894276,0.06501605,0.073403105,0.010592336,0.28806344,0.10067236,0.0009246419],"about_ca_topic_score_codex":0.0017669703,"about_ca_topic_score_gemma":0.004167576,"teacher_disagreement_score":0.016423017,"about_ca_system_score_codex":0.0011129328,"about_ca_system_score_gemma":0.0016357898,"threshold_uncertainty_score":0.08685428},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19512382,0.07698914,0.07992799,0.03341661,0.002945082,0.00059846806,0.001161545,0.00038255742,0.60945475],"genre_scores_gemma":[0.92401975,0.018199,0.027647495,0.0016768678,0.0008252042,0.00088873244,0.00074584695,0.00041619642,0.025580902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.96178514,0.022761596,0.0025350573,0.0036120377,0.007961139,0.0013450555],"domain_scores_gemma":[0.8767752,0.09225598,0.008369589,0.00949062,0.011051832,0.002056767],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.043377582,0.0007996911,0.0010794377,0.037541524,0.0066443034,0.027218465,0.0014198201,0.0022039602,0.008643729],"category_scores_gemma":[0.07199258,0.0006659137,0.00079152663,0.04724621,0.022099502,0.01986597,0.009084711,0.0035481402,0.00085317745],"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":[0.000077560675,0.000033668774,0.007725414,0.0013968174,0.00010255415,0.00036854765,0.18957552,0.0003055191,0.0007432866,0.6884911,0.006442464,0.104737595],"study_design_scores_gemma":[0.000035533736,0.0001467068,0.031562883,0.00647236,0.0002010976,0.00074440223,0.16212909,0.0009536348,0.002381776,0.16440077,0.6308597,0.00011202207],"about_ca_topic_score_codex":0.0043846946,"about_ca_topic_score_gemma":0.0041805147,"teacher_disagreement_score":0.9624585,"about_ca_system_score_codex":0.008747344,"about_ca_system_score_gemma":0.010768163,"threshold_uncertainty_score":0.22940528},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025452645,0.016500086,0.21039908,0.043549303,0.00087278296,0.000248157,0.00038167863,0.00035101775,0.70224524],"genre_scores_gemma":[0.9290632,0.0075003128,0.031354226,0.0016217269,0.00088422484,0.00045293922,0.00024274676,0.00014610082,0.028734531],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99028474,0.006381568,0.00024506997,0.00063136866,0.0017661679,0.000691071],"domain_scores_gemma":[0.99013317,0.0063221254,0.00079924834,0.0006302125,0.0014889059,0.0006264407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011161631,0.0014122112,0.00064006896,0.004061391,0.002117085,0.008571661,0.0019718572,0.0027772288,0.009189091],"category_scores_gemma":[0.014754585,0.0002961417,0.00095715123,0.0049121324,0.011986569,0.008956068,0.0033123076,0.003262941,0.0014561795],"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":[0.0000030651538,0.000011041391,0.00015853795,0.000013129895,0.000002984474,0.000006837206,0.00016320865,0.0030164423,0.0000044631342,0.99281704,0.0010699342,0.002733274],"study_design_scores_gemma":[0.00000752519,0.000023042481,0.00029361155,0.00006892006,0.000004289107,0.00001673991,0.0003439699,0.010140888,0.000023762957,0.96998614,0.01908159,0.000009588676],"about_ca_topic_score_codex":0.0068861283,"about_ca_topic_score_gemma":0.0039580893,"teacher_disagreement_score":0.9888384,"about_ca_system_score_codex":0.012347423,"about_ca_system_score_gemma":0.0048803384,"threshold_uncertainty_score":0.08958721},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9527079,0.0024272164,0.029621936,0.00040798867,0.000025754809,0.0015249925,0.0001421793,0.00006327751,0.013078674],"genre_scores_gemma":[0.98555124,0.0004081047,0.012458278,0.00006874457,0.0000050911804,0.00046527304,0.00011564356,0.000032770546,0.0008948744],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9202376,0.063063234,0.0043513114,0.0016262671,0.008702668,0.0020189928],"domain_scores_gemma":[0.5661487,0.38191277,0.009329598,0.008887236,0.0318068,0.0019149337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07237728,0.0006741517,0.0007788126,0.008694193,0.0018672548,0.0044468404,0.0018394846,0.0016778823,0.004266267],"category_scores_gemma":[0.22874193,0.00031697378,0.0010484288,0.0033171126,0.0014968878,0.0066439384,0.0034919525,0.0009560552,0.00046955424],"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":[0.0045742593,0.003982893,0.3122345,0.0030474083,0.0011962617,0.0018986167,0.11247794,0.0046221362,0.0043048034,0.025376568,0.0025289732,0.5237557],"study_design_scores_gemma":[0.0010906495,0.013331426,0.5261942,0.00706409,0.004737012,0.00645377,0.2626217,0.070883155,0.028905021,0.041864637,0.036197886,0.0006564897],"about_ca_topic_score_codex":0.0028600458,"about_ca_topic_score_gemma":0.003915768,"teacher_disagreement_score":0.07237728,"about_ca_system_score_codex":0.0050665685,"about_ca_system_score_gemma":0.0042618453,"threshold_uncertainty_score":0.3827722},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035226513,0.03957667,0.76743716,0.013952609,0.0007803257,0.0010165207,0.0005742381,0.0012079773,0.140228],"genre_scores_gemma":[0.5226774,0.0400559,0.4248938,0.0034038085,0.0010653174,0.0008762933,0.00031415987,0.0003700423,0.006343276],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92323,0.051439993,0.002899139,0.0018636198,0.019787902,0.0007792958],"domain_scores_gemma":[0.7350592,0.21859464,0.0075078737,0.012315254,0.024901945,0.0016210976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.080134064,0.0026633206,0.0027886238,0.011145138,0.0009692135,0.010194831,0.003285165,0.0036969837,0.0062638237],"category_scores_gemma":[0.12680358,0.00075144134,0.0022814677,0.008392639,0.0043247556,0.009673916,0.005525074,0.0040693954,0.001644765],"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":[0.00019360134,0.0005919367,0.010301244,0.0030987146,0.00048082045,0.00009797102,0.0007684728,0.029722212,0.0024073166,0.109102875,0.004603613,0.8386311],"study_design_scores_gemma":[0.00019967223,0.0010998806,0.02139963,0.0047434024,0.0008325212,0.00078492553,0.0019998485,0.16836303,0.010475999,0.6256812,0.1639706,0.00044925732],"about_ca_topic_score_codex":0.009529094,"about_ca_topic_score_gemma":0.00890466,"teacher_disagreement_score":0.91986597,"about_ca_system_score_codex":0.005096587,"about_ca_system_score_gemma":0.007743514,"threshold_uncertainty_score":0.4237945},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004110414,0.028425245,0.15845673,0.7758827,0.013979158,0.0008500377,0.00013882824,0.00027609162,0.017880818],"genre_scores_gemma":[0.3467751,0.0102502005,0.2010474,0.41043732,0.022590693,0.005869116,0.00006395529,0.00051274255,0.0024534592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.12137396,0.7528351,0.03066612,0.017833153,0.075127326,0.0021643387],"domain_scores_gemma":[0.03552245,0.92116725,0.013587585,0.01747164,0.011218207,0.0010328903],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8243429,0.003094659,0.010504271,0.010786887,0.007883517,0.022774119,0.012468774,0.041650247,0.0054912455],"category_scores_gemma":[0.8843158,0.0030952827,0.005676751,0.0067649437,0.1274338,0.04345642,0.020208092,0.059972893,0.002451534],"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":[0.0013608126,0.000073857605,0.0011234507,0.005010744,0.0011056261,0.00033728936,0.007882278,0.001605536,0.00027908734,0.9081871,0.02524885,0.047785487],"study_design_scores_gemma":[0.001207036,0.000265206,0.0003856258,0.008762814,0.00050450343,0.00025003057,0.0010031962,0.0052969195,0.0006444012,0.9380173,0.043485187,0.00017784929],"about_ca_topic_score_codex":0.0030257902,"about_ca_topic_score_gemma":0.002324478,"teacher_disagreement_score":0.1756571,"about_ca_system_score_codex":0.016659563,"about_ca_system_score_gemma":0.017878093,"threshold_uncertainty_score":0.21661651},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62890375,0.00022243982,0.31402376,0.003541286,0.00018933359,0.002062128,0.00048458765,0.0006269852,0.049945798],"genre_scores_gemma":[0.9533833,0.0000583481,0.038168147,0.00013177871,0.000025180096,0.0005750481,0.00008430877,0.000025669848,0.0075482503],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9922742,0.0048492905,0.00031255002,0.0010026417,0.0010673823,0.00049385766],"domain_scores_gemma":[0.9877742,0.007176015,0.0010565436,0.00077151303,0.0017359573,0.0014857382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007926389,0.0008397675,0.00084806466,0.0010582795,0.0021194154,0.0034073112,0.0015505318,0.0018485483,0.006021498],"category_scores_gemma":[0.014124613,0.00048082697,0.0006760043,0.00066029234,0.0022311043,0.0035093718,0.0025166494,0.0013500442,0.00080619],"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":[0.0021869717,0.0022810013,0.025415542,0.00031821194,0.00017425144,0.0009975134,0.008319088,0.67950314,0.0075805485,0.1982646,0.0056314194,0.06932767],"study_design_scores_gemma":[0.000269284,0.0009216774,0.0056801294,0.0000645652,0.00006794017,0.00010635879,0.0020679287,0.9345902,0.0014422376,0.04892838,0.005759916,0.00010129681],"about_ca_topic_score_codex":0.0128366845,"about_ca_topic_score_gemma":0.009436339,"teacher_disagreement_score":0.0128366845,"about_ca_system_score_codex":0.004491859,"about_ca_system_score_gemma":0.0025245887,"threshold_uncertainty_score":0.04191923},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008269026,0.019303538,0.00075546384,0.9642933,0.0076681203,0.000010052199,0.0000068203453,0.000011122145,0.0071247094],"genre_scores_gemma":[0.081466466,0.0453897,0.0025495852,0.8189036,0.015436091,0.000121130935,0.000025291267,0.00021093056,0.035897106],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.89687884,0.07444954,0.0038131562,0.0037095349,0.016653957,0.0044950396],"domain_scores_gemma":[0.87017816,0.083542906,0.003248955,0.0024325869,0.0236155,0.016981928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09419937,0.0006579602,0.0018722428,0.002343828,0.012439204,0.02158207,0.0016465223,0.015171719,0.004861577],"category_scores_gemma":[0.11931596,0.0008502112,0.0013561661,0.0024716589,0.026157,0.018428177,0.009645966,0.043706346,0.0017115746],"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":[0.000056113986,0.0001596456,0.00072846096,0.0004044189,0.000027789196,0.0007254373,0.04633964,0.00015015434,0.00022208437,0.1414363,0.7515459,0.058204077],"study_design_scores_gemma":[0.000015734797,0.00004968336,0.0005336078,0.0018587488,0.000011945097,0.00057810964,0.019811198,0.00016831838,0.00017587845,0.019596625,0.95712334,0.000076829514],"about_ca_topic_score_codex":0.009212085,"about_ca_topic_score_gemma":0.011180598,"teacher_disagreement_score":0.09419937,"about_ca_system_score_codex":0.025852272,"about_ca_system_score_gemma":0.021902556,"threshold_uncertainty_score":0.4981798},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47045776,0.014828602,0.12669301,0.018600488,0.0008824826,0.0023479047,0.00046734753,0.00049220695,0.3652303],"genre_scores_gemma":[0.8969352,0.004815199,0.071012676,0.0007063827,0.00014262459,0.0008587164,0.00026173503,0.000108983426,0.025158435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94205415,0.03624907,0.0027694115,0.002109963,0.015326267,0.0014911836],"domain_scores_gemma":[0.8973266,0.06050018,0.0051172804,0.005500844,0.028307403,0.0032477167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04246836,0.00091955496,0.00095425296,0.0055674296,0.0039457777,0.012009822,0.0015355912,0.0020458973,0.010213357],"category_scores_gemma":[0.10229762,0.00034323355,0.0009567259,0.004707043,0.0061047827,0.008617503,0.0060296,0.002692705,0.0014497822],"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":[0.00054641964,0.00074625446,0.022847362,0.0029464343,0.00018173299,0.0003946133,0.06326483,0.0055031334,0.0043967483,0.2186363,0.0092034945,0.67133266],"study_design_scores_gemma":[0.0002622277,0.003423646,0.08793595,0.010317473,0.00047817532,0.0009906983,0.15724522,0.020980831,0.030991431,0.17951494,0.5074019,0.00045757403],"about_ca_topic_score_codex":0.009754879,"about_ca_topic_score_gemma":0.013438082,"teacher_disagreement_score":0.04246836,"about_ca_system_score_codex":0.011375193,"about_ca_system_score_gemma":0.014380043,"threshold_uncertainty_score":0.2245968},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56916076,0.029275691,0.11735879,0.06631497,0.0015630819,0.004889378,0.00039483758,0.0006048563,0.21043764],"genre_scores_gemma":[0.89794713,0.010748197,0.07345337,0.0024615976,0.00026309525,0.0015840202,0.00016857327,0.000087276196,0.013286702],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92982316,0.0469928,0.0045568002,0.0016874542,0.015172228,0.0017674826],"domain_scores_gemma":[0.8623805,0.08459039,0.010236357,0.0035830012,0.03125496,0.007954837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0640751,0.0006616193,0.0009667036,0.005182753,0.0035504692,0.010894139,0.001128831,0.0020846853,0.0053502703],"category_scores_gemma":[0.12248482,0.00044924457,0.0009458952,0.002914795,0.0054144235,0.006255939,0.0057811043,0.0026447529,0.0012280003],"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":[0.00039420847,0.0007248104,0.047383033,0.0069299294,0.00019427165,0.00051957445,0.15539367,0.0011535627,0.006061739,0.033615567,0.009116085,0.73851365],"study_design_scores_gemma":[0.00018214817,0.0027932676,0.22257344,0.01881966,0.00046551987,0.0033889608,0.31090647,0.004931482,0.019912068,0.060696352,0.35467672,0.0006538952],"about_ca_topic_score_codex":0.0058742594,"about_ca_topic_score_gemma":0.008353989,"teacher_disagreement_score":0.0640751,"about_ca_system_score_codex":0.0075616166,"about_ca_system_score_gemma":0.028444914,"threshold_uncertainty_score":0.33886558},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029071532,0.056238636,0.0913754,0.38231888,0.0047655897,0.00026484893,0.00015459127,0.00024664818,0.4355639],"genre_scores_gemma":[0.9007149,0.026077794,0.023739547,0.020439401,0.0023521702,0.00063541223,0.00013311776,0.00040759565,0.025500135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9344445,0.048823915,0.0016800496,0.0032741716,0.0096294675,0.0021478757],"domain_scores_gemma":[0.9294394,0.053677566,0.0030745312,0.005279825,0.0069600237,0.0015686711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041587356,0.0012558121,0.0012946412,0.0057927663,0.005501497,0.028408902,0.0026782204,0.0062484853,0.010561865],"category_scores_gemma":[0.06462556,0.0005244736,0.0011002597,0.005412164,0.056030974,0.030972589,0.009177718,0.009683522,0.0014826497],"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":[0.00002885876,0.000030431984,0.00045969556,0.0003181069,0.000017910748,0.000032778353,0.007936232,0.00021187315,0.00008361835,0.97082764,0.0028534927,0.017199436],"study_design_scores_gemma":[0.000040237624,0.000093483664,0.0013698573,0.00256874,0.000043683067,0.00012637873,0.029633878,0.001204396,0.0006848422,0.80806535,0.1561284,0.000040845753],"about_ca_topic_score_codex":0.008667984,"about_ca_topic_score_gemma":0.0061498904,"teacher_disagreement_score":0.041587356,"about_ca_system_score_codex":0.021798324,"about_ca_system_score_gemma":0.019898687,"threshold_uncertainty_score":0.21993756},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028703792,0.031443227,0.12948732,0.7557825,0.004296477,0.00017103957,0.00008148189,0.00009459179,0.04993958],"genre_scores_gemma":[0.600411,0.059601583,0.1656495,0.1351837,0.0052904733,0.0008822662,0.00010511553,0.00042096002,0.03245543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9851586,0.009402429,0.00078141125,0.0012064297,0.0025950628,0.0008560507],"domain_scores_gemma":[0.92875683,0.055513192,0.001428797,0.001631273,0.010297895,0.0023720162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04231367,0.00064349885,0.0013161347,0.0015916214,0.005115688,0.01909363,0.0031753017,0.008850153,0.0034822412],"category_scores_gemma":[0.0550303,0.00065138214,0.0005254288,0.00225986,0.016671503,0.02545331,0.009224402,0.014203245,0.0008864787],"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":[0.0001061362,0.00024229592,0.0026458397,0.0010632419,0.00006338281,0.00040954075,0.08796736,0.0026231976,0.0010546437,0.73184806,0.067577034,0.1043993],"study_design_scores_gemma":[0.000037228532,0.00014700122,0.0025994861,0.0026357113,0.000094691604,0.0003142214,0.08296636,0.0049892287,0.0021913324,0.48152784,0.42223388,0.00026299636],"about_ca_topic_score_codex":0.01179546,"about_ca_topic_score_gemma":0.02135232,"teacher_disagreement_score":0.04231367,"about_ca_system_score_codex":0.0051341383,"about_ca_system_score_gemma":0.011043757,"threshold_uncertainty_score":0.22377872},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.319269,0.04211194,0.2662507,0.19376118,0.0015419901,0.0031530194,0.00022384721,0.00062883797,0.17305946],"genre_scores_gemma":[0.92608035,0.0029934333,0.061456565,0.005196373,0.0004664328,0.0010034536,0.000042647305,0.0000837696,0.0026770353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44485053,0.46138856,0.016381301,0.0048009334,0.06961619,0.0029624861],"domain_scores_gemma":[0.32437545,0.57279176,0.016076516,0.02438193,0.058632176,0.0037422322],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2961636,0.0012795152,0.0015989967,0.0030859988,0.0046506007,0.011597521,0.0027695785,0.0058318577,0.0032742568],"category_scores_gemma":[0.36571115,0.0009990371,0.0017464843,0.0033343562,0.00900353,0.01604059,0.012956744,0.005371577,0.0011298825],"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":[0.0029464012,0.0011253401,0.056521658,0.009004898,0.0006079179,0.0006884284,0.018100047,0.004945605,0.003916105,0.12140104,0.010375275,0.77036726],"study_design_scores_gemma":[0.0014498554,0.005956932,0.09320729,0.052117124,0.0034864575,0.008284329,0.07135799,0.06755213,0.034235872,0.45245144,0.20885123,0.0010493961],"about_ca_topic_score_codex":0.002859823,"about_ca_topic_score_gemma":0.0039798613,"teacher_disagreement_score":0.70383644,"about_ca_system_score_codex":0.005136479,"about_ca_system_score_gemma":0.010389182,"threshold_uncertainty_score":0.8679556},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018989965,0.0001570164,0.9613044,0.00068745686,0.00008330184,0.0019157925,0.0005085217,0.0008184149,0.015534986],"genre_scores_gemma":[0.09838486,0.00010752091,0.89745474,0.000084190586,0.000011379232,0.002569891,0.00031154277,0.00012219438,0.00095373776],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9725398,0.018683542,0.0015980289,0.0010221782,0.005680006,0.00047632866],"domain_scores_gemma":[0.9228941,0.040437464,0.007051401,0.0043652086,0.023994377,0.0012574648],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034804657,0.0014239325,0.00067624426,0.005121,0.0014334584,0.0036173228,0.0015596293,0.001140809,0.0050509297],"category_scores_gemma":[0.073782176,0.0007407424,0.0008319034,0.0032453602,0.001048645,0.004985571,0.0022283928,0.002219961,0.000969056],"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":[0.00065211894,0.0005331055,0.014181756,0.0019966555,0.00016117834,0.0003135066,0.011554842,0.056096744,0.013482883,0.14537644,0.012793837,0.74285686],"study_design_scores_gemma":[0.0007920281,0.004814674,0.034229487,0.0033920463,0.00031539603,0.00077759346,0.019357536,0.41464618,0.0698073,0.23119988,0.21956101,0.0011069241],"about_ca_topic_score_codex":0.004698495,"about_ca_topic_score_gemma":0.008434633,"teacher_disagreement_score":0.96519536,"about_ca_system_score_codex":0.0049057454,"about_ca_system_score_gemma":0.0069001154,"threshold_uncertainty_score":0.18406683},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9517677,0.0006242341,0.040522214,0.00031277988,0.00011284683,0.0038321002,0.00022399549,0.000049460374,0.002554669],"genre_scores_gemma":[0.9789355,0.00007814211,0.014014198,0.00020776046,0.000039371163,0.0056019863,0.00010130613,0.000025383766,0.0009964097],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.70310545,0.27396822,0.005395051,0.008285412,0.007138127,0.002107649],"domain_scores_gemma":[0.4360314,0.49866498,0.029280338,0.026435489,0.0076967594,0.0018910612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12029164,0.00071124325,0.0016622301,0.0016059825,0.0035682097,0.002446605,0.0019853672,0.0018337631,0.0061713806],"category_scores_gemma":[0.35382333,0.00087429315,0.0019464309,0.0019512465,0.003004873,0.004249552,0.002822711,0.0019646802,0.000570385],"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":[0.04866636,0.020786906,0.6469794,0.002820015,0.008045563,0.0005817973,0.0720697,0.00361163,0.002004597,0.03870946,0.0039193723,0.15180515],"study_design_scores_gemma":[0.01474219,0.0934525,0.6815305,0.0017739566,0.0072959694,0.0017556762,0.058512144,0.041361142,0.0060370513,0.07401206,0.01866988,0.00085704064],"about_ca_topic_score_codex":0.0025057683,"about_ca_topic_score_gemma":0.0024437981,"teacher_disagreement_score":0.12029164,"about_ca_system_score_codex":0.002127624,"about_ca_system_score_gemma":0.0038410274,"threshold_uncertainty_score":0.6361706},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86937976,0.00078254315,0.006385582,0.0275742,0.00023509563,0.0042548836,0.001868231,0.000044481978,0.08947524],"genre_scores_gemma":[0.9792749,0.00046415755,0.0039940714,0.0025256176,0.00002875827,0.002879767,0.00019972822,0.000034872057,0.010598132],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9418866,0.041442778,0.001166848,0.0016182184,0.007442155,0.0064434153],"domain_scores_gemma":[0.89800745,0.0741683,0.0045275334,0.001854131,0.01696538,0.0044772406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06693703,0.0004582834,0.00064942084,0.0021062193,0.022479696,0.0073324074,0.0025810846,0.002604176,0.005136642],"category_scores_gemma":[0.06490823,0.0007272716,0.00048721998,0.004204815,0.012539754,0.0023567663,0.007220393,0.0029108522,0.0003041629],"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":true,"study_design_scores_codex":[0.00021675674,0.00012938138,0.005283936,0.00057240133,0.00000996581,0.0005342475,0.96564376,0.0003025014,0.00096010644,0.00934085,0.0045885635,0.012417546],"study_design_scores_gemma":[0.000044459328,0.000092749346,0.007842672,0.00056933647,0.000015129412,0.000039798164,0.9460295,0.00026997278,0.0011465196,0.0017183555,0.04219718,0.000034336084],"about_ca_topic_score_codex":0.6914517,"about_ca_topic_score_gemma":0.83027244,"teacher_disagreement_score":0.8602649,"about_ca_system_score_codex":0.13973509,"about_ca_system_score_gemma":0.13095339,"threshold_uncertainty_score":0.9977854},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4325708,0.0026470511,0.3632582,0.006672709,0.00035872197,0.007075882,0.006767347,0.006198488,0.17445086],"genre_scores_gemma":[0.8206455,0.0010855318,0.17271441,0.0003065354,0.0000459121,0.001261934,0.0014606102,0.00015144155,0.0023281472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.963301,0.019579174,0.0027567858,0.001570284,0.011532848,0.0012599092],"domain_scores_gemma":[0.86468655,0.05630993,0.030488476,0.0075713457,0.038447406,0.0024962365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05813128,0.0015526925,0.00077392894,0.009569635,0.0012617115,0.007123193,0.0014895174,0.00049430516,0.0016759768],"category_scores_gemma":[0.11833154,0.00040093795,0.0005368164,0.008525653,0.0009858073,0.004599698,0.0030656953,0.0015844406,0.0004939375],"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":[0.00057195104,0.0013994392,0.19988959,0.0012941328,0.00024382795,0.000086659245,0.0053075785,0.021661269,0.0026883984,0.017068116,0.012689592,0.73709947],"study_design_scores_gemma":[0.00022960085,0.005013559,0.63776654,0.0048106443,0.0007745132,0.0002304555,0.0148402145,0.18303044,0.034007538,0.033828698,0.08462436,0.00084345136],"about_ca_topic_score_codex":0.05525202,"about_ca_topic_score_gemma":0.07204926,"teacher_disagreement_score":0.05813128,"about_ca_system_score_codex":0.00949736,"about_ca_system_score_gemma":0.018798599,"threshold_uncertainty_score":0.30743128},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013011251,0.000732362,0.19475931,0.70582306,0.014811836,0.0063634967,0.00028052425,0.0048318957,0.05938634],"genre_scores_gemma":[0.1512593,0.0023938315,0.46718496,0.225922,0.006611008,0.03687983,0.0005981469,0.0025958964,0.10655501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.940165,0.046409756,0.002077044,0.0017984562,0.0064081093,0.0031416975],"domain_scores_gemma":[0.7056028,0.19695812,0.012778338,0.013902498,0.048809707,0.02194849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08849362,0.00125978,0.0008034544,0.0029887424,0.013794872,0.009229947,0.0033236595,0.014466753,0.03555047],"category_scores_gemma":[0.27751,0.001973254,0.000828089,0.0014741304,0.007226723,0.012156167,0.008243365,0.020470513,0.05211447],"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":[0.00018419267,0.00061664963,0.0015955063,0.00048771466,0.00003203977,0.0011634199,0.040671565,0.00045325112,0.0041828286,0.016657216,0.7968721,0.13708349],"study_design_scores_gemma":[0.00028246685,0.00017887229,0.0016586409,0.0012075999,0.00003936459,0.0007868411,0.10453369,0.0029366808,0.0031806508,0.053001437,0.8318383,0.0003553882],"about_ca_topic_score_codex":0.0058789835,"about_ca_topic_score_gemma":0.011444334,"teacher_disagreement_score":0.91150635,"about_ca_system_score_codex":0.0031358611,"about_ca_system_score_gemma":0.013735129,"threshold_uncertainty_score":0.46800458},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09561433,0.004650143,0.28533685,0.16340256,0.0012464517,0.019777441,0.00085892103,0.0014391534,0.4276741],"genre_scores_gemma":[0.70009524,0.0015762532,0.25986788,0.0045678327,0.00030737865,0.00725451,0.00087409676,0.00022074065,0.025236195],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9593432,0.026996182,0.0012299784,0.0014940768,0.005663515,0.0052730744],"domain_scores_gemma":[0.9273653,0.020807197,0.0037497182,0.00246478,0.023839168,0.021773856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035415582,0.0010598227,0.000763468,0.0056887544,0.014169156,0.014519434,0.0045638797,0.0076410817,0.03283267],"category_scores_gemma":[0.100670785,0.0010138742,0.0011781197,0.004751764,0.0037484984,0.0100813545,0.008961415,0.006964405,0.0030075912],"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":[0.00035565544,0.003503864,0.025155583,0.0010815543,0.00014409616,0.001704336,0.006809134,0.027121916,0.0010162559,0.34450155,0.17706072,0.4115453],"study_design_scores_gemma":[0.00042404915,0.0011332348,0.022916881,0.002583122,0.00011619333,0.00074494234,0.042153962,0.0478591,0.0018148571,0.5959497,0.28399944,0.00030459967],"about_ca_topic_score_codex":0.057775334,"about_ca_topic_score_gemma":0.15781619,"teacher_disagreement_score":0.057775334,"about_ca_system_score_codex":0.023084732,"about_ca_system_score_gemma":0.117321245,"threshold_uncertainty_score":0.1872977},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043404666,0.002689343,0.9079314,0.010245725,0.00031614027,0.014196759,0.000512707,0.00033151443,0.059435878],"genre_scores_gemma":[0.14406797,0.0016838827,0.8266866,0.0012009413,0.00014994419,0.023850102,0.00032933327,0.00008281604,0.0019483872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.6743506,0.26269618,0.012835483,0.0057837297,0.041146945,0.0031870867],"domain_scores_gemma":[0.8447697,0.103163496,0.006928775,0.004974131,0.037802644,0.002361249],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18989246,0.0025662002,0.0025920973,0.012007904,0.004017579,0.010311944,0.0051958268,0.0038134886,0.004117018],"category_scores_gemma":[0.17048183,0.0011093635,0.0027710472,0.011534026,0.009790162,0.0106647145,0.007799503,0.004835932,0.0012102622],"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":[0.00012817522,0.00022681875,0.0022859445,0.0034009565,0.00021384844,0.00020122374,0.004232686,0.017961383,0.00019215888,0.831782,0.009661969,0.12971291],"study_design_scores_gemma":[0.00050347124,0.0017639246,0.0058025895,0.0067697377,0.0003860548,0.0006377986,0.007467823,0.11204548,0.0013660887,0.7587151,0.1042684,0.0002735366],"about_ca_topic_score_codex":0.017576743,"about_ca_topic_score_gemma":0.011752828,"teacher_disagreement_score":0.18989246,"about_ca_system_score_codex":0.027096374,"about_ca_system_score_gemma":0.05758935,"threshold_uncertainty_score":0.9990068},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85476387,0.0017551455,0.004042927,0.059103426,0.00024070167,0.000667766,0.00068539777,0.00024997382,0.078490734],"genre_scores_gemma":[0.97656745,0.0009366417,0.0033257983,0.0018567061,0.00003455784,0.00013713066,0.00020138167,0.00006458533,0.016875718],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9833754,0.0034639097,0.0008490424,0.0010098491,0.007160285,0.0041415724],"domain_scores_gemma":[0.95362747,0.006270978,0.0038181175,0.0022371826,0.020763656,0.013282626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011389209,0.0002415451,0.0003436689,0.002419171,0.011461895,0.007391268,0.0025706834,0.0018422657,0.0037396618],"category_scores_gemma":[0.040020365,0.00076334504,0.0003560932,0.0038820344,0.005240082,0.0036601035,0.0043883263,0.0018959481,0.0005177719],"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":[0.00037751373,0.00038333883,0.39231107,0.0005988698,0.00016405535,0.0015668768,0.17496392,0.0046306676,0.0031642409,0.015233489,0.052083775,0.35452214],"study_design_scores_gemma":[0.000112904505,0.0005109096,0.6050172,0.00083150784,0.00014947007,0.0003414046,0.16163085,0.0040384335,0.001509672,0.0036552572,0.22197357,0.00022878073],"about_ca_topic_score_codex":0.979507,"about_ca_topic_score_gemma":0.99216074,"teacher_disagreement_score":0.8879344,"about_ca_system_score_codex":0.11206561,"about_ca_system_score_gemma":0.238676,"threshold_uncertainty_score":0.81309676},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081995234,0.0093087945,0.2034837,0.31312332,0.0015699018,0.00018894498,0.000058901613,0.00024140102,0.39002985],"genre_scores_gemma":[0.9810776,0.0010965485,0.007609697,0.0043741926,0.00040665807,0.00010888719,0.000013357146,0.000102990714,0.0052099987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8701727,0.09493489,0.003978932,0.005716541,0.019578137,0.005618883],"domain_scores_gemma":[0.8436104,0.11010275,0.009491327,0.019517833,0.012472223,0.0048054974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08111893,0.0008960735,0.0014175996,0.005211034,0.015372694,0.028821247,0.003498413,0.009129091,0.0021990247],"category_scores_gemma":[0.11367591,0.0010604054,0.0009276651,0.00303208,0.2452627,0.039362125,0.026970733,0.014479921,0.0005518729],"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":[0.000012550697,0.0000132591495,0.00031463342,0.000045837845,0.000009480288,0.000114063354,0.062658735,0.00022032319,0.00007892353,0.92860574,0.0010857834,0.006840699],"study_design_scores_gemma":[0.000014477672,0.000020002943,0.00016019813,0.0002529032,0.000008309769,0.00010583766,0.015945805,0.00052728056,0.00018592119,0.95689267,0.025865043,0.000021621634],"about_ca_topic_score_codex":0.0101262,"about_ca_topic_score_gemma":0.005065297,"teacher_disagreement_score":0.08111893,"about_ca_system_score_codex":0.0148001695,"about_ca_system_score_gemma":0.027137397,"threshold_uncertainty_score":0.429003},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02106432,0.38931304,0.513674,0.051640097,0.0023417063,0.0037990436,0.0006462209,0.00054243574,0.016979037],"genre_scores_gemma":[0.35362452,0.113715954,0.5169954,0.004291197,0.0009058527,0.008948212,0.0003109965,0.00028589854,0.0009219352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"systematic_review","domain_scores_codex":[0.5007186,0.4259403,0.035439134,0.010086918,0.026410623,0.0014044363],"domain_scores_gemma":[0.31976914,0.61500895,0.018162018,0.030550215,0.015598778,0.0009108284],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40770683,0.0036907801,0.008467305,0.032562386,0.0047509186,0.033764064,0.008996603,0.0043530082,0.0031192626],"category_scores_gemma":[0.4468746,0.0031558732,0.007028542,0.03238084,0.029382965,0.053244945,0.014291947,0.008867054,0.0004687385],"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":[0.0003160036,0.00019321815,0.0072567696,0.0811257,0.0049223853,0.00053203217,0.06493234,0.0028891806,0.00089171005,0.573138,0.004213735,0.25958896],"study_design_scores_gemma":[0.00030036859,0.0002796042,0.0031472282,0.10300514,0.0061020763,0.00093685556,0.04801014,0.008253463,0.0018695049,0.7470316,0.08078625,0.00027772493],"about_ca_topic_score_codex":0.0042432393,"about_ca_topic_score_gemma":0.006485353,"teacher_disagreement_score":0.59229314,"about_ca_system_score_codex":0.019973565,"about_ca_system_score_gemma":0.025504641,"threshold_uncertainty_score":0.73040295},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007774075,0.09006819,0.087141916,0.6963973,0.0091395015,0.0030935258,0.00073069194,0.00043754512,0.10521726],"genre_scores_gemma":[0.7018377,0.05530583,0.14529559,0.06968587,0.008317306,0.011780006,0.00062886794,0.00030546647,0.0068433317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5179054,0.4376667,0.013447683,0.005042946,0.022533447,0.0034038783],"domain_scores_gemma":[0.18376282,0.7369837,0.0134116355,0.015345411,0.04593169,0.0045647766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34841308,0.0029713644,0.006076108,0.010812934,0.006256331,0.026509887,0.0068970546,0.015117353,0.023838468],"category_scores_gemma":[0.66347134,0.0010901947,0.0027381333,0.01682822,0.03192297,0.037642684,0.010877289,0.009222144,0.002351412],"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":[0.00088935136,0.00038803098,0.00222179,0.009355695,0.00034814168,0.00044869172,0.004393993,0.0042272354,0.000095909345,0.64677054,0.06249544,0.26836514],"study_design_scores_gemma":[0.0003823108,0.00019286256,0.0011953247,0.016534762,0.00021359242,0.00017233618,0.008403186,0.0076554646,0.00031107108,0.9227388,0.042081974,0.000118368574],"about_ca_topic_score_codex":0.011011935,"about_ca_topic_score_gemma":0.0051717334,"teacher_disagreement_score":0.34841308,"about_ca_system_score_codex":0.029121144,"about_ca_system_score_gemma":0.044795383,"threshold_uncertainty_score":0.8035227},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4876526,0.037896924,0.30224043,0.014553656,0.0021847496,0.0029660852,0.0003976052,0.0009528152,0.15115519],"genre_scores_gemma":[0.95339274,0.00314715,0.03760653,0.0003982829,0.00015417035,0.00047880696,0.000083761595,0.000038255996,0.00470033],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9339301,0.060141098,0.0014014582,0.0006246209,0.0034510014,0.00045165455],"domain_scores_gemma":[0.9371894,0.048982043,0.0041814484,0.001630723,0.0068647168,0.0011517332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03589217,0.00043578362,0.00044835082,0.0013330145,0.00062354904,0.0030958415,0.00059300713,0.00078940025,0.0035599235],"category_scores_gemma":[0.06829165,0.00019031894,0.00038213286,0.0008453292,0.0014279921,0.0018997823,0.0013962813,0.00094350096,0.00052343006],"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":[0.00435597,0.0017272193,0.011505323,0.0033264162,0.00025047315,0.0006754783,0.00626591,0.05308495,0.004820307,0.0716366,0.0184058,0.8239456],"study_design_scores_gemma":[0.003274831,0.021960149,0.05349191,0.01255002,0.0007146026,0.0034571595,0.02663531,0.23572254,0.055831738,0.22481158,0.36068213,0.00086806825],"about_ca_topic_score_codex":0.0010392042,"about_ca_topic_score_gemma":0.0009825756,"teacher_disagreement_score":0.9641078,"about_ca_system_score_codex":0.0016178663,"about_ca_system_score_gemma":0.0018206727,"threshold_uncertainty_score":0.1898182},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14048697,0.034814496,0.0064217052,0.5141421,0.0009518765,0.0006636094,0.0021672875,0.00022080024,0.30013114],"genre_scores_gemma":[0.9079056,0.022428473,0.014582084,0.0240183,0.00017376702,0.00026992837,0.00078313,0.00012415265,0.029714543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98311365,0.004148331,0.0007469507,0.0009804342,0.005475309,0.0055352505],"domain_scores_gemma":[0.9205151,0.034189336,0.0017472877,0.0021118687,0.030089678,0.011346725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021764973,0.0005776346,0.0009543065,0.0032982721,0.018175835,0.015156294,0.0039533656,0.004518113,0.007811139],"category_scores_gemma":[0.0526441,0.00063936994,0.0008758774,0.0077145067,0.010432837,0.0046749106,0.007086302,0.0061042644,0.00042706556],"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":[0.0005524063,0.00037718102,0.041609667,0.0022087486,0.0003087889,0.002657309,0.024413006,0.013776364,0.0006612923,0.5823292,0.104558036,0.22654808],"study_design_scores_gemma":[0.0005607948,0.00019485036,0.09829437,0.0069568395,0.00052048627,0.0004983571,0.05439557,0.018720912,0.0018150703,0.19695836,0.6204253,0.00065919134],"about_ca_topic_score_codex":0.99749315,"about_ca_topic_score_gemma":0.9979966,"teacher_disagreement_score":0.7039008,"about_ca_system_score_codex":0.2960992,"about_ca_system_score_gemma":0.61043376,"threshold_uncertainty_score":0.8164252},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704037,0.00015815174,0.0101499325,0.0017479961,0.00006705499,0.0055985185,0.00024573284,0.0005541466,0.011074701],"genre_scores_gemma":[0.97576094,0.00007236227,0.021793118,0.000115141585,0.000013063254,0.001656512,0.00015170408,0.000020662597,0.00041656187],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.91979444,0.062021654,0.0035232443,0.0013949614,0.0103634875,0.002902227],"domain_scores_gemma":[0.92377424,0.041517697,0.007168756,0.005629464,0.016871257,0.00503863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07009075,0.0005466741,0.0005458135,0.0022523638,0.0024203025,0.0030957123,0.0018394337,0.0006319718,0.0016420824],"category_scores_gemma":[0.09996334,0.0003256835,0.0006315019,0.001823209,0.0013278701,0.0015377458,0.0040520914,0.0014371277,0.0002557076],"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":[0.001348263,0.014141518,0.13938498,0.0010912112,0.00017797064,0.00027700607,0.017413609,0.007948492,0.0021685788,0.004926077,0.004456234,0.806666],"study_design_scores_gemma":[0.0026710662,0.0500378,0.7311596,0.002516299,0.00036946445,0.00039142268,0.06542458,0.06671458,0.022073952,0.011448969,0.046569698,0.000622583],"about_ca_topic_score_codex":0.014142836,"about_ca_topic_score_gemma":0.011792436,"teacher_disagreement_score":0.07009075,"about_ca_system_score_codex":0.0075130477,"about_ca_system_score_gemma":0.021667186,"threshold_uncertainty_score":0.37067974},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39883962,0.002407346,0.23929468,0.015934667,0.0016177176,0.002109351,0.00093369867,0.0019283456,0.33693457],"genre_scores_gemma":[0.7261022,0.0016907192,0.235129,0.0018000803,0.00022163443,0.0010731154,0.0009908183,0.0008874216,0.03210501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96073747,0.0174659,0.0028022635,0.0040102573,0.012130782,0.0028533014],"domain_scores_gemma":[0.9441596,0.008397616,0.002091748,0.017934492,0.025049428,0.0023670555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026810346,0.00065214926,0.0010341007,0.007388026,0.005281359,0.015384998,0.0032363278,0.0011543741,0.0067210537],"category_scores_gemma":[0.04450852,0.00045684536,0.0007412113,0.006914147,0.0053454638,0.009348746,0.012205838,0.0024569272,0.0024387224],"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":[0.0001428357,0.00022797518,0.03070894,0.00054311584,0.000040039118,0.00027246235,0.06518107,0.0017774997,0.0033006468,0.236849,0.020790579,0.6401658],"study_design_scores_gemma":[0.000056238616,0.00019910959,0.020028891,0.0013935649,0.0000926549,0.0004052001,0.15551592,0.010365527,0.0058295224,0.1388691,0.66706353,0.00018073272],"about_ca_topic_score_codex":0.016124178,"about_ca_topic_score_gemma":0.019223804,"teacher_disagreement_score":0.026810346,"about_ca_system_score_codex":0.010198267,"about_ca_system_score_gemma":0.009146568,"threshold_uncertainty_score":0.14178836},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5765656,0.035351142,0.09271273,0.046388004,0.000875413,0.0014941907,0.00012907675,0.00076576497,0.24571808],"genre_scores_gemma":[0.94840723,0.007199031,0.034959394,0.0013486275,0.00023204296,0.00026007663,0.00007712362,0.00008598062,0.0074305604],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.939179,0.05055147,0.0012450217,0.0012225225,0.0054856944,0.0023163848],"domain_scores_gemma":[0.8607813,0.103304036,0.0067024925,0.0056428583,0.015988303,0.007581068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07723539,0.0006067713,0.0007103115,0.0033256428,0.0032780154,0.007691665,0.002065184,0.0022022245,0.0028439644],"category_scores_gemma":[0.06696464,0.00023018081,0.00040064717,0.005418896,0.005030471,0.0051051294,0.0049878587,0.0017126952,0.0003414973],"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":[0.00034455818,0.0020523665,0.019664401,0.0014491979,0.00007982584,0.00022901646,0.01728509,0.0034525008,0.0011330278,0.0303974,0.0077763177,0.91613626],"study_design_scores_gemma":[0.00076488015,0.0067873313,0.119656436,0.003651336,0.00037291253,0.0017231677,0.08540117,0.01799092,0.023234708,0.120099366,0.6196957,0.00062203646],"about_ca_topic_score_codex":0.0068812747,"about_ca_topic_score_gemma":0.01057918,"teacher_disagreement_score":0.07723539,"about_ca_system_score_codex":0.005842151,"about_ca_system_score_gemma":0.009757993,"threshold_uncertainty_score":0.40846467},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04296228,0.04430625,0.06992962,0.051199775,0.0026115905,0.00033437568,0.0002332645,0.0003409967,0.7880818],"genre_scores_gemma":[0.9067696,0.01796104,0.019412603,0.0059241424,0.001268406,0.000359186,0.00018279866,0.0002093843,0.047912862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9694826,0.016542764,0.0017152313,0.0020242173,0.009029339,0.0012059393],"domain_scores_gemma":[0.9543013,0.018466301,0.0041268663,0.003221247,0.018517861,0.0013664368],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02384737,0.0006609487,0.00070171955,0.0044288067,0.0030397824,0.0135988165,0.0011184312,0.0012526559,0.0048345965],"category_scores_gemma":[0.045980755,0.00026633157,0.00046465264,0.003956595,0.015089988,0.0068849283,0.0050362903,0.0026366324,0.00096440746],"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":[0.00007345891,0.00010281936,0.005645331,0.0007370454,0.000028707092,0.00012042326,0.007165432,0.0008467087,0.000432552,0.68178743,0.020840032,0.28222007],"study_design_scores_gemma":[0.000055982826,0.00032472252,0.01880724,0.009207484,0.00010984964,0.00085726375,0.017231038,0.0035238012,0.0046791355,0.3831814,0.561885,0.00013711852],"about_ca_topic_score_codex":0.0035143844,"about_ca_topic_score_gemma":0.0028835395,"teacher_disagreement_score":0.97615266,"about_ca_system_score_codex":0.012942725,"about_ca_system_score_gemma":0.009247742,"threshold_uncertainty_score":0.12611848},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6907787,0.0061230413,0.08595903,0.06001897,0.00043623254,0.0050357063,0.00094768655,0.0007666831,0.14993408],"genre_scores_gemma":[0.96813554,0.001490533,0.02700149,0.0005601821,0.000058915808,0.0006360714,0.00031703938,0.000048941678,0.0017513847],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96893424,0.0153852645,0.0023801134,0.0011368068,0.007686725,0.0044769677],"domain_scores_gemma":[0.90029156,0.053724185,0.018436447,0.0033416292,0.015118821,0.009087376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03929587,0.0010214044,0.000627854,0.0029164376,0.0024092945,0.012346062,0.0017804854,0.0033049283,0.005244881],"category_scores_gemma":[0.11765391,0.00063273695,0.00046329643,0.0021518746,0.0027148034,0.008693023,0.005528696,0.003422709,0.0010328582],"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":[0.00056904694,0.0015827721,0.25953698,0.0017342791,0.00036291586,0.0004945493,0.0063430327,0.013487495,0.0025689383,0.08028764,0.0149148395,0.6181175],"study_design_scores_gemma":[0.00034383047,0.0048287064,0.504028,0.004445069,0.00072776724,0.00066512177,0.069900595,0.058129773,0.012425963,0.22722758,0.11685931,0.0004182904],"about_ca_topic_score_codex":0.005337886,"about_ca_topic_score_gemma":0.006502867,"teacher_disagreement_score":0.03929587,"about_ca_system_score_codex":0.0049627726,"about_ca_system_score_gemma":0.023570178,"threshold_uncertainty_score":0.20781887},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17078519,0.012234784,0.022102714,0.47170112,0.0024783826,0.00019285978,0.00009177939,0.000118564814,0.32029456],"genre_scores_gemma":[0.9710097,0.00094115664,0.0021471174,0.009197976,0.00010529829,0.00003846265,0.000008886023,0.000029615612,0.016521761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9784743,0.013889154,0.000557518,0.0010149232,0.0033124278,0.0027515849],"domain_scores_gemma":[0.9823225,0.010142375,0.0015866766,0.0012147039,0.0033796586,0.0013539697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016026614,0.00069659966,0.00047855632,0.0013584923,0.02131939,0.015866352,0.0019274811,0.007887308,0.002913886],"category_scores_gemma":[0.013885471,0.00044283562,0.0005650982,0.0012839008,0.09708379,0.009691749,0.010251572,0.0114592,0.00047019584],"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":[0.000030072431,0.00001294495,0.00090656255,0.000093048126,0.000008245396,0.00031099078,0.16485243,0.00023649943,0.0002804564,0.8160002,0.008981306,0.008287245],"study_design_scores_gemma":[0.00002183882,0.00004988079,0.0016607351,0.0008192605,0.000025655161,0.00050239975,0.28635645,0.00061258214,0.001299287,0.33726937,0.37127948,0.000103075734],"about_ca_topic_score_codex":0.19300821,"about_ca_topic_score_gemma":0.242727,"teacher_disagreement_score":0.19300821,"about_ca_system_score_codex":0.058475062,"about_ca_system_score_gemma":0.052387252,"threshold_uncertainty_score":0.42426825},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030917224,0.7099984,0.088750534,0.13092178,0.008393915,0.0060532438,0.0014352355,0.0002795635,0.023250075],"genre_scores_gemma":[0.6593482,0.15237729,0.15189251,0.01450859,0.004394987,0.013803951,0.000793258,0.00028778682,0.0025934433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.21073379,0.60964555,0.091101766,0.010230274,0.0763507,0.001937988],"domain_scores_gemma":[0.062542535,0.80582017,0.037723932,0.025754292,0.06680344,0.0013556068],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7032954,0.0022217194,0.0101396255,0.021693168,0.004235101,0.028260585,0.005445108,0.0074090958,0.0035615615],"category_scores_gemma":[0.85464853,0.0021002016,0.0067486996,0.018376026,0.0117534315,0.023480058,0.010298264,0.0088224765,0.00046482164],"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":[0.00265358,0.0002750657,0.022890871,0.26914507,0.020431822,0.00052539236,0.033266224,0.003103604,0.0022334743,0.11606353,0.017378658,0.51203275],"study_design_scores_gemma":[0.0016813447,0.0028059862,0.041353177,0.5314767,0.031234946,0.0020276613,0.01735292,0.014365974,0.0073121716,0.16232133,0.1871973,0.00087050337],"about_ca_topic_score_codex":0.012403704,"about_ca_topic_score_gemma":0.020193478,"teacher_disagreement_score":0.9720585,"about_ca_system_score_codex":0.027941503,"about_ca_system_score_gemma":0.04853296,"threshold_uncertainty_score":0.3658896},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99085253,0.0005808949,0.00011805756,0.0041259495,0.000016465832,0.000012609954,0.000009663548,0.0000027628291,0.0042810887],"genre_scores_gemma":[0.99935204,0.00017927022,0.0000543305,0.00019535687,0.000007236312,0.0000061802675,0.000004208909,0.0000010539214,0.00020036589],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9911048,0.004732949,0.00052464067,0.00028122257,0.0017746029,0.0015817798],"domain_scores_gemma":[0.9251578,0.04530802,0.00975489,0.0011684224,0.0074833464,0.01112759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016754473,0.00024008483,0.00038189377,0.0028036532,0.0037160888,0.006245315,0.00080573186,0.0019159875,0.0017574866],"category_scores_gemma":[0.044765864,0.00044825108,0.0005635432,0.0012471545,0.0060807434,0.002527531,0.0040341825,0.003317234,0.00016529382],"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":[0.0001702036,0.00069918635,0.7166794,0.0001751303,0.000066750334,0.00037774123,0.24261001,0.00019608276,0.00067102205,0.003898826,0.0014332985,0.033022344],"study_design_scores_gemma":[0.000030124897,0.00036571207,0.37124342,0.00038224235,0.0000581266,0.00046965698,0.61823255,0.0004310592,0.00067086617,0.0019295505,0.006126593,0.000060157734],"about_ca_topic_score_codex":0.00914338,"about_ca_topic_score_gemma":0.013195952,"teacher_disagreement_score":0.016754473,"about_ca_system_score_codex":0.003033408,"about_ca_system_score_gemma":0.0055054845,"threshold_uncertainty_score":0.08860719},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10204306,0.0024932479,0.7210494,0.011557415,0.00012592676,0.00572286,0.00056944496,0.00044707718,0.15599161],"genre_scores_gemma":[0.65238875,0.0011362067,0.337301,0.0005848158,0.00006178005,0.0032068251,0.00020218242,0.00014820193,0.004970299],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9382823,0.044175938,0.002384784,0.0018758915,0.010136758,0.0031442128],"domain_scores_gemma":[0.9215975,0.05941811,0.004555842,0.005139049,0.0076532844,0.0016362731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032816987,0.0010045642,0.0015842399,0.0055081323,0.003149693,0.0125521105,0.0018348546,0.0025712412,0.0097619435],"category_scores_gemma":[0.0643912,0.0010920714,0.0017414835,0.0041350224,0.009362314,0.008998844,0.0048189186,0.0032444056,0.000626025],"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":[0.00018729437,0.0004973119,0.012119801,0.0016783085,0.00018206664,0.0000981438,0.0028580548,0.015892755,0.0010444917,0.8607999,0.0014183049,0.10322356],"study_design_scores_gemma":[0.0002914126,0.00159856,0.028826164,0.0024201928,0.0007054368,0.00018976907,0.007905391,0.058582507,0.005646135,0.83288336,0.060803294,0.00014785236],"about_ca_topic_score_codex":0.0041817394,"about_ca_topic_score_gemma":0.0032340644,"teacher_disagreement_score":0.032816987,"about_ca_system_score_codex":0.01275613,"about_ca_system_score_gemma":0.016077178,"threshold_uncertainty_score":0.1735549},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81012917,0.0016949855,0.13200769,0.0061188764,0.00035939523,0.0020133366,0.00035470782,0.00039994944,0.046921868],"genre_scores_gemma":[0.9280803,0.0005952531,0.06797824,0.0006675047,0.00005644303,0.00093552645,0.00024713518,0.00011589866,0.0013237027],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96010375,0.026106382,0.0036350586,0.0014550416,0.0073990035,0.0013008752],"domain_scores_gemma":[0.88154715,0.07509971,0.0038117713,0.0106302025,0.026576303,0.0023348648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04772291,0.00037507244,0.00092353695,0.0056405654,0.0013163722,0.0038210861,0.0021069401,0.0010679221,0.0012612332],"category_scores_gemma":[0.10492878,0.00029324056,0.0010146478,0.004230163,0.002734946,0.003217091,0.003347729,0.0021266302,0.00031872193],"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":[0.0005597769,0.0017382896,0.31767988,0.0010578218,0.0005585349,0.00037325686,0.024306582,0.008222348,0.0065324083,0.021372339,0.00330258,0.6142963],"study_design_scores_gemma":[0.00020957369,0.0025914544,0.7597144,0.0022254912,0.000515697,0.0010595319,0.06251439,0.039137244,0.025309667,0.053074382,0.053177204,0.00047094308],"about_ca_topic_score_codex":0.008689892,"about_ca_topic_score_gemma":0.0096431235,"teacher_disagreement_score":0.04772291,"about_ca_system_score_codex":0.004025834,"about_ca_system_score_gemma":0.0066930475,"threshold_uncertainty_score":0.25238585},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029607983,0.08300997,0.07885069,0.44890952,0.0030093868,0.0003943366,0.00055011763,0.00043704233,0.35523096],"genre_scores_gemma":[0.84708726,0.019041358,0.057411388,0.01645312,0.00079492654,0.00092614,0.00028762245,0.00026465705,0.057733428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91218835,0.052523714,0.005549799,0.004570196,0.021302992,0.0038649628],"domain_scores_gemma":[0.9521206,0.028121006,0.0032998112,0.0036067832,0.011447118,0.0014046899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06809837,0.0011044098,0.0008063529,0.0039893365,0.0040788758,0.020095646,0.0016098653,0.004078235,0.0035195618],"category_scores_gemma":[0.07155782,0.0006632544,0.0005722269,0.0069792215,0.02916314,0.010480251,0.0039387094,0.008581631,0.0007030211],"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":[0.00003808828,0.000024304212,0.001513826,0.0002341359,0.000012937103,0.000054121458,0.005162454,0.0008972129,0.00025048,0.8862433,0.012096492,0.09347273],"study_design_scores_gemma":[0.000054931133,0.000058303274,0.007194199,0.0016129091,0.00001732102,0.00011193198,0.010102323,0.001524547,0.0012038483,0.22683972,0.751175,0.00010491357],"about_ca_topic_score_codex":0.44343823,"about_ca_topic_score_gemma":0.31765845,"teacher_disagreement_score":0.44343823,"about_ca_system_score_codex":0.08404935,"about_ca_system_score_gemma":0.072684094,"threshold_uncertainty_score":0.8817143},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014314688,0.0003554477,0.00011230479,0.9900379,0.008032449,0.000011815939,0.000036798276,0.000014775363,0.0012553358],"genre_scores_gemma":[0.0005086965,0.00008856034,0.00010976166,0.99227166,0.0050994945,0.000020296762,0.000007515698,0.000008644314,0.0018854415],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9792165,0.006062942,0.0023493788,0.002957997,0.0061844215,0.0032287987],"domain_scores_gemma":[0.9339898,0.04424862,0.0038294683,0.0014335959,0.009828012,0.006670526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022669084,0.0016383078,0.0032716482,0.0015905517,0.011785144,0.011542046,0.0067514908,0.1844863,0.009495206],"category_scores_gemma":[0.087519184,0.0024641156,0.0034679163,0.002209914,0.012844423,0.01068705,0.0054313485,0.1415372,0.009107967],"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":[0.00007985197,0.00003219067,0.0003689361,0.00006598977,0.000020373274,0.00034692153,0.00037491292,0.0000612007,0.00010116391,0.006216607,0.9888882,0.0034436479],"study_design_scores_gemma":[0.0002719989,0.00011404473,0.002923461,0.0010303187,0.000103028266,0.00052012026,0.0018849181,0.0007888893,0.00042633957,0.028727869,0.962965,0.00024395596],"about_ca_topic_score_codex":0.04351118,"about_ca_topic_score_gemma":0.079878286,"teacher_disagreement_score":0.1844863,"about_ca_system_score_codex":0.011677541,"about_ca_system_score_gemma":0.0181766,"threshold_uncertainty_score":0.119887054},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45349967,0.0118998615,0.46731755,0.0134949945,0.0052352925,0.015200652,0.0024689792,0.0019201575,0.028962769],"genre_scores_gemma":[0.6084043,0.0057557137,0.3351576,0.0045754462,0.0012970404,0.026983835,0.0020635477,0.0010213217,0.014741211],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.53083235,0.36093587,0.032888435,0.0111151645,0.061258417,0.0029697542],"domain_scores_gemma":[0.3296096,0.52703005,0.031200252,0.043218125,0.06702828,0.0019136216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23803614,0.0024876914,0.0022086946,0.0034191178,0.0021330796,0.0062578605,0.0030624587,0.002045571,0.0061534736],"category_scores_gemma":[0.4494284,0.0017301611,0.002752784,0.004533682,0.0045192945,0.007051542,0.0044481345,0.004165542,0.0036269787],"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":[0.0028826627,0.0013714968,0.124268875,0.012054047,0.0015302117,0.00043238024,0.056103658,0.003610456,0.017030494,0.016625518,0.013213616,0.75087655],"study_design_scores_gemma":[0.0009293293,0.010037245,0.53214794,0.010789554,0.0024570893,0.001444186,0.030484952,0.015444128,0.04290918,0.030547217,0.32165423,0.0011550133],"about_ca_topic_score_codex":0.0052969484,"about_ca_topic_score_gemma":0.006431758,"teacher_disagreement_score":0.76196384,"about_ca_system_score_codex":0.005535398,"about_ca_system_score_gemma":0.008461211,"threshold_uncertainty_score":0.93963706},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8265356,0.00043957206,0.006640053,0.007794786,0.00016925701,0.00056633767,0.00091462827,0.000102133214,0.1568376],"genre_scores_gemma":[0.97258556,0.00048679937,0.004015597,0.00042048938,0.000018139597,0.00026779927,0.0005587589,0.000013340154,0.021633642],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997851,0.0012159037,0.00011719471,0.00011183843,0.00026090702,0.00044328437],"domain_scores_gemma":[0.99670523,0.000578965,0.0003304651,0.00007177299,0.0005169001,0.0017968112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016528986,0.00040178042,0.00011056382,0.00065298827,0.0045140525,0.0028884204,0.00069031253,0.0015005586,0.010650597],"category_scores_gemma":[0.0023207655,0.00020658177,0.0003091033,0.0011027997,0.0012514181,0.002158192,0.0021797556,0.0012486647,0.0018024961],"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":[0.0016095347,0.0022322088,0.17030011,0.0021646598,0.00005831083,0.07731331,0.29905418,0.032303464,0.011436219,0.14345635,0.091698304,0.16837333],"study_design_scores_gemma":[0.000064042855,0.00086725585,0.06356028,0.00080749684,0.00001964746,0.006521525,0.62476444,0.011905292,0.004094455,0.01563337,0.27156326,0.00019889024],"about_ca_topic_score_codex":0.015118113,"about_ca_topic_score_gemma":0.021353332,"teacher_disagreement_score":0.015118113,"about_ca_system_score_codex":0.0038628022,"about_ca_system_score_gemma":0.0050464817,"threshold_uncertainty_score":0.03562981},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6668278,0.0063768923,0.015478761,0.10112042,0.0006188567,0.0009934079,0.00014622069,0.00022101567,0.20821664],"genre_scores_gemma":[0.98309416,0.00127344,0.0048844744,0.0018072772,0.0000219892,0.00008891344,0.000019713512,0.000042587522,0.008767392],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9388035,0.03926545,0.0012346947,0.0020851516,0.010990345,0.007620933],"domain_scores_gemma":[0.9263151,0.04225144,0.0020314674,0.0026957123,0.01798954,0.00871665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.067751594,0.00047742494,0.00063998817,0.002050484,0.03501148,0.011530667,0.0034504284,0.0038358434,0.005773933],"category_scores_gemma":[0.0847431,0.00078990625,0.00042992775,0.0026563914,0.017327882,0.004247147,0.008279722,0.004876209,0.0003687441],"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":[0.00017592307,0.00058498036,0.02019049,0.0005699767,0.000026837104,0.0016241863,0.7386363,0.0014529726,0.0014896697,0.11186147,0.017305769,0.10608131],"study_design_scores_gemma":[0.00014176762,0.00027873498,0.019242909,0.0008685421,0.000039826333,0.00046101317,0.55902725,0.0028139087,0.0026426816,0.009078208,0.40517905,0.00022609433],"about_ca_topic_score_codex":0.9538018,"about_ca_topic_score_gemma":0.9750923,"teacher_disagreement_score":0.8705019,"about_ca_system_score_codex":0.12949814,"about_ca_system_score_gemma":0.2315276,"threshold_uncertainty_score":0.9395791},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013009706,0.002422608,0.010169345,0.8904344,0.0054799397,0.000109516295,0.00009507212,0.00020198974,0.08978608],"genre_scores_gemma":[0.13898067,0.0066282633,0.045963775,0.584281,0.009786651,0.0021057336,0.00061208085,0.0010204306,0.21062145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93493843,0.031090396,0.0025407434,0.005640074,0.016587403,0.009203074],"domain_scores_gemma":[0.91677856,0.037275184,0.0024705578,0.009432974,0.01545569,0.018586988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10226369,0.0012940482,0.0016225568,0.0017059523,0.007305914,0.023737624,0.006854871,0.02637014,0.08525642],"category_scores_gemma":[0.12813736,0.0011008752,0.001254809,0.0022200097,0.012855484,0.03370756,0.020928215,0.033653237,0.017885461],"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":[0.000026466774,0.00013265711,0.00030095738,0.0003131057,0.00001888858,0.000109386034,0.0017852405,0.00043033363,0.00028182514,0.5601853,0.33993775,0.09647807],"study_design_scores_gemma":[0.00003771461,0.000062339415,0.0005266701,0.0007184981,0.000011504084,0.00010132475,0.003701456,0.0007128129,0.00021133768,0.21676847,0.77711374,0.000034071665],"about_ca_topic_score_codex":0.0059125433,"about_ca_topic_score_gemma":0.008397002,"teacher_disagreement_score":0.10226369,"about_ca_system_score_codex":0.010640055,"about_ca_system_score_gemma":0.063624464,"threshold_uncertainty_score":0.5408286},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4183476,0.004337855,0.30215058,0.023699358,0.00073464017,0.01146924,0.00034009112,0.00046063124,0.2384601],"genre_scores_gemma":[0.82648045,0.0023076572,0.13199931,0.0013531235,0.00009686578,0.0045256037,0.00011948203,0.000096829004,0.033020705],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.936292,0.052441757,0.0012997842,0.0016215569,0.006402089,0.0019428089],"domain_scores_gemma":[0.9681884,0.019246466,0.0021381695,0.0023819515,0.0060716546,0.0019733126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04748075,0.0011080918,0.0008869582,0.0025135907,0.005130447,0.0072005237,0.001452275,0.0019897209,0.0097287875],"category_scores_gemma":[0.033420373,0.0004257056,0.0011868417,0.0023379093,0.005821676,0.0048041157,0.0051926137,0.0022399588,0.00091266766],"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":[0.0012117438,0.0014941029,0.014972074,0.005327756,0.00030559007,0.000375558,0.12550274,0.0058573834,0.008284842,0.15570273,0.0076244716,0.67334104],"study_design_scores_gemma":[0.0012962116,0.010628949,0.073461734,0.009790592,0.00071075215,0.0007940761,0.25542533,0.015362566,0.03024582,0.17222482,0.4293825,0.0006766904],"about_ca_topic_score_codex":0.0104548,"about_ca_topic_score_gemma":0.0251157,"teacher_disagreement_score":0.04748075,"about_ca_system_score_codex":0.009446546,"about_ca_system_score_gemma":0.024250437,"threshold_uncertainty_score":0.2511052},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015828036,0.017389834,0.009583574,0.95582914,0.003970334,0.000019399113,0.000023153882,0.00021721261,0.0113845635],"genre_scores_gemma":[0.35900217,0.06003059,0.06012841,0.47604305,0.018629482,0.0002519538,0.00010346377,0.0012826595,0.02452826],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91039884,0.06833751,0.0028634348,0.0036848385,0.012454669,0.0022606766],"domain_scores_gemma":[0.8675676,0.0810836,0.006523168,0.011929173,0.023329427,0.009567072],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09025441,0.00092826324,0.0016663292,0.0025746063,0.0066479268,0.020595742,0.0036071148,0.010340696,0.006394656],"category_scores_gemma":[0.16724625,0.0007190919,0.0009078048,0.0027963105,0.028744575,0.04371119,0.008066321,0.021343937,0.004708578],"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":[0.00015391849,0.00017779846,0.0035758654,0.0020344425,0.00020929959,0.0004875659,0.025846189,0.00024145495,0.00057326135,0.2134222,0.34378946,0.40948856],"study_design_scores_gemma":[0.00006327709,0.0003359179,0.0019601067,0.0053312206,0.00009782553,0.0016915903,0.05677875,0.0008077236,0.00080527854,0.24515244,0.6867387,0.00023717067],"about_ca_topic_score_codex":0.0034880254,"about_ca_topic_score_gemma":0.004628639,"teacher_disagreement_score":0.9097456,"about_ca_system_score_codex":0.0044860416,"about_ca_system_score_gemma":0.0069642705,"threshold_uncertainty_score":0.47731668},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77537537,0.0009087945,0.0006538595,0.040408123,0.00008745758,0.00027304166,0.00008464771,0.00001547034,0.18219319],"genre_scores_gemma":[0.97538745,0.0003499648,0.00034889096,0.00087347266,0.000017970468,0.00003955319,0.000016569305,0.000006636442,0.022959447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9965424,0.0007415507,0.000044217664,0.0001306549,0.00036605974,0.0021751658],"domain_scores_gemma":[0.9962638,0.0011082926,0.00024044518,0.00015636506,0.0005636063,0.0016673722],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002446272,0.00026238337,0.00027427208,0.00069734297,0.026090916,0.00894379,0.0018067214,0.0037300827,0.0077987947],"category_scores_gemma":[0.004523078,0.0002841853,0.00033080616,0.001388957,0.01318344,0.002430929,0.0049936315,0.0024139187,0.00028356066],"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":[0.00059241627,0.0004350375,0.10148521,0.00051303185,0.00014196183,0.020573739,0.3248849,0.005194653,0.0026537157,0.4322315,0.04272898,0.06856488],"study_design_scores_gemma":[0.00012986502,0.0001284309,0.07968683,0.00047052006,0.00008352959,0.00089169753,0.65134865,0.0022512074,0.00089702965,0.016949752,0.24707419,0.000088337976],"about_ca_topic_score_codex":0.95478076,"about_ca_topic_score_gemma":0.989523,"teacher_disagreement_score":0.9910562,"about_ca_system_score_codex":0.07724406,"about_ca_system_score_gemma":0.1144975,"threshold_uncertainty_score":0.56044745},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012484357,0.1381969,0.48413348,0.24717398,0.06216224,0.0047906223,0.0005579486,0.0011848207,0.0605515],"genre_scores_gemma":[0.075005256,0.07846154,0.7353649,0.037126977,0.04444726,0.015457857,0.000270968,0.00091320375,0.0129520325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55394506,0.34892473,0.043124087,0.010266953,0.041131362,0.002607787],"domain_scores_gemma":[0.3345141,0.5423687,0.018458083,0.03174163,0.06662308,0.006294386],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2670245,0.0051313015,0.0050014895,0.04292992,0.0067849876,0.04356967,0.007703815,0.0105011,0.008854383],"category_scores_gemma":[0.3758414,0.0021757642,0.0035158424,0.01612336,0.069841005,0.024936762,0.013339193,0.026197294,0.0036465086],"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":[0.00010033343,0.000057496323,0.00021070648,0.01216845,0.00028857295,0.00040699265,0.018321153,0.0005999808,0.0005587454,0.77967376,0.069276705,0.11833711],"study_design_scores_gemma":[0.00009942328,0.00012286307,0.00031000946,0.018916816,0.00011968538,0.0007801802,0.010477694,0.001137868,0.00042242746,0.4973847,0.47008446,0.00014384657],"about_ca_topic_score_codex":0.0027744714,"about_ca_topic_score_gemma":0.0034964571,"teacher_disagreement_score":0.7329755,"about_ca_system_score_codex":0.01680204,"about_ca_system_score_gemma":0.03833774,"threshold_uncertainty_score":0.9038893},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07541661,0.074627616,0.056330994,0.4987356,0.009648097,0.00017928872,0.0006063206,0.00021423514,0.28424135],"genre_scores_gemma":[0.7356798,0.04829123,0.042561963,0.025640855,0.003219665,0.00029549914,0.00038462438,0.0004708662,0.14345546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910653,0.00474181,0.00033134106,0.0006640999,0.0024580508,0.00073930033],"domain_scores_gemma":[0.9855596,0.010081196,0.0006433928,0.000583353,0.0021848395,0.0009476938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008328918,0.00040129735,0.00078913773,0.0012252021,0.0026532072,0.015120365,0.0014744132,0.0036866197,0.022302972],"category_scores_gemma":[0.03916379,0.00036671557,0.00036518506,0.0013049043,0.0068295742,0.008321844,0.0037176835,0.0042540696,0.0030545914],"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":[0.0001503614,0.00032410517,0.0068061594,0.0012482358,0.0001008379,0.0015421659,0.03139593,0.00077335123,0.001187671,0.388548,0.14483297,0.42309025],"study_design_scores_gemma":[0.000023788461,0.00007327432,0.0033396666,0.0018137498,0.00006901068,0.0019894682,0.05579403,0.0008958167,0.00096275995,0.2584389,0.6765287,0.00007094476],"about_ca_topic_score_codex":0.020887615,"about_ca_topic_score_gemma":0.022423815,"teacher_disagreement_score":0.022302972,"about_ca_system_score_codex":0.0036875429,"about_ca_system_score_gemma":0.0075796978,"threshold_uncertainty_score":0.07461089},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5743333,0.057028968,0.014096531,0.038932,0.00028299988,0.00015148066,0.00017647099,0.00019183276,0.3148065],"genre_scores_gemma":[0.98903614,0.0032770385,0.001817755,0.0007396768,0.00005289467,0.00003127304,0.000032918804,0.000033199016,0.0049790223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9696508,0.022322398,0.0008906882,0.0010374276,0.0033410017,0.002757761],"domain_scores_gemma":[0.97305185,0.018533735,0.0041285516,0.00054584397,0.0018015841,0.0019384319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016366353,0.0003055496,0.00058819546,0.0043202187,0.0041769645,0.014665694,0.0005694314,0.0023873965,0.002987075],"category_scores_gemma":[0.0245152,0.00038543204,0.00035218333,0.006219079,0.011685513,0.00296895,0.0032183959,0.001900902,0.00026892836],"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":[0.00029508822,0.00029700354,0.03210975,0.0007955185,0.00015740245,0.00093656173,0.016443972,0.017737119,0.0014318207,0.69946915,0.006900477,0.22342621],"study_design_scores_gemma":[0.00018097542,0.0003433475,0.20979828,0.0021461756,0.00012817532,0.0008301794,0.03098326,0.009590842,0.003214349,0.2882807,0.4542285,0.00027526825],"about_ca_topic_score_codex":0.08274098,"about_ca_topic_score_gemma":0.077115394,"teacher_disagreement_score":0.08274098,"about_ca_system_score_codex":0.026289627,"about_ca_system_score_gemma":0.021293238,"threshold_uncertainty_score":0.19074547},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94972956,0.0015655711,0.024640061,0.013771305,0.00014133219,0.00025172753,0.000032200387,0.00007168434,0.009796622],"genre_scores_gemma":[0.9933751,0.00063220575,0.00328022,0.0012126582,0.000036957226,0.00019620247,0.000013501235,0.00004337673,0.0012097803],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.87284166,0.11379707,0.0030187934,0.0022929222,0.004312627,0.0037369134],"domain_scores_gemma":[0.7966037,0.17998949,0.005883359,0.0062032742,0.0078342995,0.0034858629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08672882,0.0005913949,0.0008718627,0.002746287,0.013862814,0.014772604,0.0028385185,0.0030104665,0.0008991846],"category_scores_gemma":[0.13736433,0.00069104607,0.00043615286,0.0018203798,0.02519884,0.012425126,0.010681641,0.0063696397,0.00019336633],"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":[0.00001793998,0.000043275424,0.0027836377,0.00004461904,0.000005696669,0.00024106796,0.9858084,0.000051660216,0.00017277893,0.0035820212,0.00040561176,0.006843299],"study_design_scores_gemma":[0.000005937142,0.000050090075,0.0013760014,0.00018290135,0.000008091887,0.00028265518,0.98695755,0.00025557962,0.000369424,0.0028261007,0.0076635256,0.00002220314],"about_ca_topic_score_codex":0.0070858127,"about_ca_topic_score_gemma":0.013347598,"teacher_disagreement_score":0.08672882,"about_ca_system_score_codex":0.006466675,"about_ca_system_score_gemma":0.006792373,"threshold_uncertainty_score":0.45867133},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5501835,0.007284823,0.0010627159,0.15683834,0.00017063509,0.00014787515,0.00037606314,0.000041835592,0.28389424],"genre_scores_gemma":[0.982941,0.0028294835,0.00046644022,0.0024927396,0.000043218904,0.000025920303,0.000053121137,0.00000892623,0.011139161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99575377,0.0008532266,0.00006732428,0.0001788431,0.0011447426,0.0020021065],"domain_scores_gemma":[0.996381,0.001111373,0.00030644741,0.00014532096,0.0011308443,0.0009250231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035072363,0.00018853715,0.00024071331,0.000976429,0.011287547,0.00727966,0.0008154382,0.0014526388,0.0035705313],"category_scores_gemma":[0.007409464,0.00016474843,0.0002277884,0.002485131,0.011807588,0.0015671791,0.0035205267,0.0014308324,0.0001162062],"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":[0.00033462056,0.00013522602,0.109555446,0.0007853215,0.00007788405,0.0017976188,0.092584334,0.008410159,0.0017595361,0.61155754,0.040795445,0.13220674],"study_design_scores_gemma":[0.00011638445,0.00015848162,0.29403725,0.000934055,0.0001280201,0.00018279592,0.17240962,0.0021015115,0.0019989877,0.049017567,0.4787893,0.00012596155],"about_ca_topic_score_codex":0.9792597,"about_ca_topic_score_gemma":0.99055356,"teacher_disagreement_score":0.86011654,"about_ca_system_score_codex":0.13988347,"about_ca_system_score_gemma":0.18516183,"threshold_uncertainty_score":0.99761325},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5100587,0.26152545,0.14679846,0.01704636,0.002019162,0.016176797,0.017529054,0.0006176547,0.028228393],"genre_scores_gemma":[0.9473459,0.008280066,0.038607277,0.00059424073,0.00015340057,0.0028719713,0.0016409014,0.00006315855,0.00044299205],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.43960133,0.41152018,0.07419215,0.008228734,0.06446396,0.0019936971],"domain_scores_gemma":[0.15041165,0.62325513,0.07561405,0.03555488,0.11309614,0.0020682563],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5048721,0.0014761714,0.0041373204,0.017162515,0.0020406109,0.006047614,0.0032084968,0.0012559766,0.0020456724],"category_scores_gemma":[0.7597043,0.0012081825,0.0076625496,0.02121109,0.0043308996,0.0030789066,0.0044749836,0.001610303,0.00010070939],"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":[0.005460544,0.0002303734,0.43553346,0.09497305,0.16559671,0.00020849016,0.010406988,0.0113388505,0.00069032813,0.011424673,0.0076184105,0.25651813],"study_design_scores_gemma":[0.0025601673,0.004591452,0.4858947,0.10997348,0.2720604,0.0006113741,0.010326589,0.025130406,0.0107287215,0.024888467,0.052492853,0.00074133376],"about_ca_topic_score_codex":0.0548638,"about_ca_topic_score_gemma":0.07341382,"teacher_disagreement_score":0.98390895,"about_ca_system_score_codex":0.016091041,"about_ca_system_score_gemma":0.02956002,"threshold_uncertainty_score":0.6105809},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037064403,0.008716696,0.080458,0.29141453,0.0045905667,0.0006888418,0.00014046054,0.00069291424,0.57623357],"genre_scores_gemma":[0.80286205,0.007259281,0.070279844,0.044943616,0.0016460269,0.000833829,0.00014847437,0.00049142574,0.07153548],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96125907,0.026569922,0.00078268046,0.0006899685,0.009547712,0.0011507024],"domain_scores_gemma":[0.97114795,0.015871169,0.0019379013,0.0015851504,0.0065478627,0.0029100112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026379578,0.00045256683,0.0003908026,0.0013149651,0.0026970266,0.009383282,0.00083369645,0.0019420155,0.012678456],"category_scores_gemma":[0.053693403,0.0001709181,0.00041622223,0.0007835563,0.009306877,0.006349445,0.0054171695,0.00429757,0.002443589],"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":[0.00017917165,0.00047471118,0.0053023584,0.00074658485,0.00007113524,0.00022397439,0.016021905,0.0005447131,0.0012812155,0.26014063,0.17947732,0.5355364],"study_design_scores_gemma":[0.00012002224,0.00041590497,0.008344005,0.0032542506,0.000088146335,0.00049179466,0.018157551,0.0016695339,0.004294001,0.30520532,0.6578252,0.00013424622],"about_ca_topic_score_codex":0.0025021846,"about_ca_topic_score_gemma":0.004461356,"teacher_disagreement_score":0.026379578,"about_ca_system_score_codex":0.004041915,"about_ca_system_score_gemma":0.0072815497,"threshold_uncertainty_score":0.13951015},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022603393,0.018483719,0.57897264,0.19568829,0.004907841,0.009582985,0.0016695316,0.001273419,0.16681816],"genre_scores_gemma":[0.13734786,0.006845772,0.82944447,0.008897645,0.00071844814,0.007894971,0.0014614392,0.0007295328,0.006659909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.63285,0.25692177,0.06095018,0.0039070933,0.041573774,0.0037972876],"domain_scores_gemma":[0.28048202,0.56574166,0.019944046,0.034104414,0.09499126,0.004736537],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.41358146,0.0016155912,0.0044938573,0.030492816,0.011738116,0.048429724,0.00855023,0.012938577,0.009877472],"category_scores_gemma":[0.59606487,0.002845869,0.002310924,0.019560324,0.024624297,0.05519924,0.016230585,0.012688954,0.0039729904],"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":[0.00008434359,0.00012108445,0.0011536975,0.0054479437,0.00006699212,0.0006832923,0.055857588,0.0015146489,0.0007047087,0.7503651,0.029333113,0.15466744],"study_design_scores_gemma":[0.00007564223,0.000106257176,0.0016480655,0.024983335,0.000112360496,0.0005897336,0.06294176,0.003254704,0.0010114191,0.52772015,0.3773259,0.0002306695],"about_ca_topic_score_codex":0.007763118,"about_ca_topic_score_gemma":0.008056445,"teacher_disagreement_score":0.41358146,"about_ca_system_score_codex":0.027687976,"about_ca_system_score_gemma":0.04777663,"threshold_uncertainty_score":0.7231585},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97167915,0.0010435439,0.015885,0.00024741236,0.0000156646,0.000103178136,0.000061030365,0.00005737385,0.010907709],"genre_scores_gemma":[0.99366826,0.00020952903,0.0053473716,0.000023332925,0.000008325364,0.00007382863,0.000019192024,0.00001679023,0.00063334225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9791215,0.013147866,0.0009114446,0.0017231344,0.004368428,0.00072761875],"domain_scores_gemma":[0.8201598,0.15127787,0.01192993,0.004858324,0.009788907,0.0019852207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01535337,0.0006320492,0.00068608514,0.0020427317,0.0010770048,0.0047002546,0.00060204335,0.0010522171,0.0026493552],"category_scores_gemma":[0.09120998,0.00040704117,0.0005494818,0.0015217469,0.0017950236,0.0025614554,0.002115765,0.0009920034,0.00032008765],"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":[0.0019912277,0.00081338215,0.6617587,0.0019943018,0.0006634797,0.0006674143,0.040222127,0.006942927,0.025267225,0.014628046,0.00043088378,0.24462026],"study_design_scores_gemma":[0.00006475302,0.001181399,0.95684355,0.00033479946,0.00028145756,0.00044289962,0.009894885,0.005963758,0.012758428,0.0054115374,0.006683033,0.00013953623],"about_ca_topic_score_codex":0.0033350664,"about_ca_topic_score_gemma":0.0049151867,"teacher_disagreement_score":0.01535337,"about_ca_system_score_codex":0.0020278408,"about_ca_system_score_gemma":0.0017225442,"threshold_uncertainty_score":0.08119732},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44391763,0.000814906,0.4618955,0.006309414,0.00012563667,0.0011432648,0.00042914157,0.00038015956,0.08498434],"genre_scores_gemma":[0.84426713,0.00016477218,0.1528562,0.00011793607,0.00000982949,0.00038468622,0.00009524322,0.00004596315,0.0020581307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.985715,0.011706592,0.00040891004,0.00039711845,0.0012109749,0.0005613363],"domain_scores_gemma":[0.93902487,0.050809994,0.0015281762,0.0040046335,0.0036847652,0.0009474972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018714687,0.00071984745,0.00048126996,0.0018114522,0.0017204916,0.006506319,0.0028445728,0.0016109055,0.0037883827],"category_scores_gemma":[0.043572713,0.0005500317,0.00075762643,0.0019767946,0.0020663922,0.0059864502,0.0045801997,0.0026108762,0.00038891792],"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":[0.0008597332,0.0010048214,0.025580382,0.00055822614,0.00024059178,0.0017558354,0.011374049,0.35659745,0.0017348465,0.44266784,0.004568864,0.1530573],"study_design_scores_gemma":[0.00015685832,0.0005407039,0.003042617,0.00041130892,0.00011724205,0.0005027313,0.007222646,0.81611675,0.0039293068,0.1448129,0.023024106,0.00012292298],"about_ca_topic_score_codex":0.006912949,"about_ca_topic_score_gemma":0.013683229,"teacher_disagreement_score":0.018714687,"about_ca_system_score_codex":0.0051819272,"about_ca_system_score_gemma":0.0044211037,"threshold_uncertainty_score":0.09897387},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9371962,0.0036202073,0.007930543,0.010908414,0.00021595044,0.00046518774,0.000568914,0.0000988056,0.038995694],"genre_scores_gemma":[0.98274255,0.0016793206,0.003286892,0.00047656405,0.00004143077,0.00032260208,0.000255666,0.000027269165,0.011167682],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9775083,0.008497688,0.0015604954,0.0013755093,0.007978969,0.0030789238],"domain_scores_gemma":[0.8880231,0.043716088,0.025491005,0.005073133,0.03002195,0.0076746875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018170422,0.00056108367,0.0007601793,0.004112659,0.005257442,0.0051858444,0.0018314351,0.001729156,0.010332189],"category_scores_gemma":[0.06534717,0.00053406274,0.00090916635,0.0043638363,0.004033886,0.0024579114,0.0039172526,0.0021840222,0.0012628002],"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":[0.00038508582,0.00036030702,0.7148458,0.0010268525,0.0001407387,0.0008114098,0.09378497,0.0010001053,0.0008884727,0.012888032,0.0042000213,0.16966817],"study_design_scores_gemma":[0.000045275847,0.00027523184,0.8536766,0.0010087861,0.0001131833,0.00043866373,0.09768757,0.0008748768,0.0012634142,0.0062754923,0.03823557,0.00010530204],"about_ca_topic_score_codex":0.16246752,"about_ca_topic_score_gemma":0.26943803,"teacher_disagreement_score":0.16246752,"about_ca_system_score_codex":0.0133930575,"about_ca_system_score_gemma":0.036854636,"threshold_uncertainty_score":0.32304376},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91764414,0.00034949256,0.0008891189,0.0032068915,0.000074828095,0.00090412266,0.0019175704,0.000055677454,0.07495817],"genre_scores_gemma":[0.7484741,0.0012577791,0.0033144036,0.0021741523,0.000028760933,0.0009886035,0.0010540183,0.000035401732,0.2426728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999567,0.00008059198,0.000011396021,0.000062639694,0.000079842495,0.000198458],"domain_scores_gemma":[0.9987129,0.00018972473,0.00007906542,0.000055454573,0.0004796336,0.0004832617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006274547,0.00033144985,0.00016634812,0.0009163355,0.008386344,0.0011455658,0.00057738164,0.00038435234,0.03178281],"category_scores_gemma":[0.0011461534,0.00032628395,0.000100928395,0.0015819857,0.00091591256,0.00045495213,0.0011945257,0.00079798285,0.0023329807],"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":[0.0004496847,0.0010464146,0.41986185,0.0011040659,0.000033284254,0.009696195,0.2646058,0.00103954,0.021045987,0.018102983,0.1223046,0.1407096],"study_design_scores_gemma":[0.000025660966,0.00025827045,0.32433787,0.00032952463,0.000014554206,0.0006081161,0.29866225,0.0005530938,0.002507478,0.00086170854,0.37180117,0.000040191393],"about_ca_topic_score_codex":0.5564128,"about_ca_topic_score_gemma":0.88786465,"teacher_disagreement_score":0.98968923,"about_ca_system_score_codex":0.010310796,"about_ca_system_score_gemma":0.019905385,"threshold_uncertainty_score":0.89239913},"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":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02849848,0.007925565,0.7666025,0.038118865,0.0007010561,0.008643433,0.00045881857,0.001570438,0.14748074],"genre_scores_gemma":[0.45395505,0.003428936,0.52030164,0.005066933,0.00017051946,0.011432551,0.0003262236,0.00029184655,0.0050262725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.38169858,0.5124876,0.017814392,0.010287222,0.07237459,0.005337592],"domain_scores_gemma":[0.57861227,0.3177066,0.021284906,0.024198692,0.05520077,0.0029967993],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3161006,0.0022961732,0.002901655,0.011509928,0.0039928164,0.018902222,0.004308831,0.0034068937,0.003447506],"category_scores_gemma":[0.3353768,0.0012150985,0.002458413,0.0109569775,0.014731334,0.022098111,0.012639086,0.005687449,0.00076448906],"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":[0.0006213226,0.0006574994,0.015330074,0.004415194,0.0007262473,0.0001505532,0.014457774,0.015325748,0.00075211487,0.48367324,0.015470883,0.44841942],"study_design_scores_gemma":[0.002020159,0.0059612887,0.028027814,0.017096888,0.0015562478,0.0005383991,0.016314425,0.11930293,0.008177857,0.59011394,0.21005034,0.00083979813],"about_ca_topic_score_codex":0.011610815,"about_ca_topic_score_gemma":0.008072362,"teacher_disagreement_score":0.3161006,"about_ca_system_score_codex":0.030427448,"about_ca_system_score_gemma":0.04259247,"threshold_uncertainty_score":0.8433697},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07121018,0.008702272,0.045934137,0.0708422,0.011021672,0.003940977,0.0005125756,0.0022059241,0.78563017],"genre_scores_gemma":[0.45329693,0.0051005213,0.05250187,0.011997761,0.0011345474,0.0031479914,0.00042644932,0.0004680267,0.47192594],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99558616,0.0028316781,0.00010135331,0.00026609135,0.00041636828,0.0007983536],"domain_scores_gemma":[0.9947772,0.0009522753,0.00019913165,0.00026140636,0.00036614636,0.0034437787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075057633,0.0009527067,0.00028899522,0.00094434683,0.009562036,0.0038722833,0.0017584187,0.0019030066,0.040443756],"category_scores_gemma":[0.005279708,0.0005495965,0.00048349472,0.00052621367,0.006069799,0.003109026,0.018995157,0.0032099674,0.0051440992],"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":[0.0001630569,0.00090461,0.0021305475,0.000986692,0.000015304162,0.0006508898,0.12542029,0.00028272785,0.002489053,0.04234062,0.39787903,0.42673725],"study_design_scores_gemma":[0.00004658022,0.0002641376,0.0031235118,0.00047927018,0.0000061089286,0.00054672785,0.045774933,0.00016676006,0.0004669463,0.0039984956,0.9451023,0.000024247103],"about_ca_topic_score_codex":0.007932964,"about_ca_topic_score_gemma":0.028006807,"teacher_disagreement_score":0.040443756,"about_ca_system_score_codex":0.0029977716,"about_ca_system_score_gemma":0.0112019265,"threshold_uncertainty_score":0.13529783},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033708002,0.00033044422,0.9438148,0.0021737982,0.000075306474,0.0016784632,0.0011502074,0.0010403068,0.016028674],"genre_scores_gemma":[0.3685908,0.00029731446,0.625058,0.00038304518,0.0000420458,0.0027638627,0.0013420319,0.000094459356,0.001428396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9748481,0.020847466,0.0008750318,0.00072296814,0.0021368645,0.0005694842],"domain_scores_gemma":[0.89049274,0.10021411,0.0030064862,0.0016385874,0.003935467,0.0007125571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024330584,0.0015273795,0.0010532371,0.003906354,0.0010320403,0.0055494327,0.0018374352,0.0012237623,0.007278892],"category_scores_gemma":[0.07704872,0.00083298347,0.0018988142,0.0024584841,0.0016302072,0.0044426695,0.0022921655,0.0019955025,0.0005763823],"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":[0.00060328376,0.00042965994,0.0050738016,0.00037751812,0.00023494907,0.00023082481,0.00054550846,0.7289297,0.00035610853,0.18863465,0.0024724163,0.07211155],"study_design_scores_gemma":[0.00015831152,0.00016399758,0.00024099305,0.00014361834,0.00009112019,0.000032732678,0.00015489044,0.85497457,0.00044817003,0.1414735,0.0020861193,0.00003193648],"about_ca_topic_score_codex":0.0125059765,"about_ca_topic_score_gemma":0.012481927,"teacher_disagreement_score":0.024330584,"about_ca_system_score_codex":0.0069660153,"about_ca_system_score_gemma":0.005950638,"threshold_uncertainty_score":0.12867397},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18348166,0.0015171691,0.08072403,0.45806506,0.0008000937,0.0018061136,0.00004894909,0.00020190749,0.27335486],"genre_scores_gemma":[0.9462334,0.00052008993,0.019527728,0.010682789,0.00022413289,0.0019037158,0.000017529112,0.00006741567,0.020823227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7658306,0.20258407,0.0030729587,0.005375951,0.008160079,0.014976433],"domain_scores_gemma":[0.7549552,0.20180416,0.008201863,0.010104477,0.008456943,0.016477462],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.17341971,0.0007798672,0.0006548648,0.003065914,0.066943765,0.031335197,0.003944322,0.031303275,0.0066280803],"category_scores_gemma":[0.15611103,0.0013965247,0.0012605673,0.0028937112,0.05527858,0.030776445,0.026029298,0.01640231,0.000983099],"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":[0.00005902143,0.00016555637,0.0013824622,0.000098696946,0.000013996854,0.0022838968,0.07362027,0.0014632392,0.0002755393,0.9023294,0.0048715533,0.0134363035],"study_design_scores_gemma":[0.00029646722,0.0003201049,0.0012518428,0.00071023114,0.000058781203,0.0014476125,0.16886555,0.006700686,0.0013343723,0.46014342,0.35864168,0.00022910391],"about_ca_topic_score_codex":0.0255147,"about_ca_topic_score_gemma":0.02764959,"teacher_disagreement_score":0.9686648,"about_ca_system_score_codex":0.034385078,"about_ca_system_score_gemma":0.09086075,"threshold_uncertainty_score":0.9171421},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008598701,0.5761912,0.20077942,0.08391711,0.025061,0.081606776,0.00607098,0.00068666483,0.017088182],"genre_scores_gemma":[0.049470156,0.30528408,0.53468376,0.018317468,0.0030404392,0.08449441,0.002408192,0.00034655415,0.0019548603],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.26509687,0.5796666,0.103078604,0.007941636,0.041886874,0.0023293921],"domain_scores_gemma":[0.08377583,0.78422683,0.030371442,0.022626463,0.07697625,0.0020231898],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57778805,0.0043112254,0.014803068,0.06851346,0.006514282,0.021979362,0.009511123,0.010650003,0.008451715],"category_scores_gemma":[0.7764085,0.004250369,0.008346179,0.04448532,0.01223127,0.024163468,0.011677238,0.00908117,0.0023731242],"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":[0.00033357623,0.00022160483,0.0023715864,0.5872911,0.0054670954,0.00072071987,0.030207131,0.0011744146,0.0013300925,0.03153147,0.030047959,0.30930325],"study_design_scores_gemma":[0.00033907,0.00031534224,0.0011557566,0.8337273,0.004283475,0.00023807165,0.019873064,0.0006533532,0.0014784558,0.033155646,0.10454444,0.00023609621],"about_ca_topic_score_codex":0.009594139,"about_ca_topic_score_gemma":0.018619183,"teacher_disagreement_score":0.42221195,"about_ca_system_score_codex":0.024340168,"about_ca_system_score_gemma":0.13564654,"threshold_uncertainty_score":0.52066255},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022602148,0.934748,0.0012850178,0.025480052,0.03262312,0.00039221864,0.00028976044,0.000094732255,0.0048611113],"genre_scores_gemma":[0.004822521,0.904866,0.006112355,0.038047135,0.032627456,0.0009392158,0.0005130776,0.00010322702,0.011969019],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9773401,0.01227643,0.003352354,0.0007429324,0.0059327385,0.00035536784],"domain_scores_gemma":[0.8719292,0.09948699,0.008156422,0.0016767657,0.016420322,0.002330162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016157784,0.0015587838,0.006221254,0.010158567,0.0007700763,0.0052744895,0.0020236117,0.005966431,0.02204685],"category_scores_gemma":[0.09702984,0.0010820826,0.0020078276,0.009798521,0.0022797394,0.003489209,0.0016803873,0.0048920885,0.0065498496],"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":[0.00020859524,0.00007052403,0.00020351843,0.06349305,0.0005694524,0.000093759685,0.00009707881,0.00021739303,0.00023205369,0.0015947714,0.75608456,0.17713517],"study_design_scores_gemma":[0.00057738455,0.0002581992,0.0025414445,0.12790854,0.0019672061,0.00069269823,0.00020386685,0.00031382186,0.0003048566,0.006335704,0.8588091,0.00008715624],"about_ca_topic_score_codex":0.003146817,"about_ca_topic_score_gemma":0.011094483,"teacher_disagreement_score":0.02204685,"about_ca_system_score_codex":0.004180163,"about_ca_system_score_gemma":0.008746107,"threshold_uncertainty_score":0.0854516},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9458601,0.0006843767,0.0024678868,0.011487865,0.00005664029,0.000108332766,0.00032192114,0.000068029825,0.03894492],"genre_scores_gemma":[0.99510646,0.0003816868,0.00069968915,0.00027582116,0.000008370534,0.000028556096,0.000069809656,0.000015604352,0.0034139224],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9864032,0.0034275234,0.00046816177,0.0014489385,0.00460416,0.00364795],"domain_scores_gemma":[0.97077787,0.012177424,0.0036524103,0.0013957331,0.0071672467,0.0048293592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0133641865,0.00034001662,0.000391956,0.0050780997,0.019027365,0.010367614,0.0019679253,0.0013130622,0.004188019],"category_scores_gemma":[0.03634841,0.0005422281,0.0004017008,0.007805272,0.0104535865,0.0028687844,0.0054199835,0.0024112137,0.00030763453],"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":[0.00013098976,0.000078642544,0.21543738,0.00015961828,0.000038233204,0.0002788409,0.63866967,0.001520748,0.0011018094,0.06582698,0.009680943,0.067076184],"study_design_scores_gemma":[0.000013710193,0.000039688184,0.2732849,0.00036361642,0.00003086468,0.00009607971,0.6133103,0.004179436,0.0005260566,0.009702497,0.09827829,0.0001745729],"about_ca_topic_score_codex":0.9737932,"about_ca_topic_score_gemma":0.9727744,"teacher_disagreement_score":0.8873507,"about_ca_system_score_codex":0.11264933,"about_ca_system_score_gemma":0.16029197,"threshold_uncertainty_score":0.8173319},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00783812,0.26851645,0.54857993,0.135933,0.005609617,0.0012544602,0.00030861428,0.00016063295,0.031799182],"genre_scores_gemma":[0.4890849,0.076476045,0.38167295,0.030617932,0.0074910694,0.010151755,0.000327281,0.000116729694,0.0040613837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.45107773,0.47001895,0.026291348,0.0076972204,0.042804472,0.0021102403],"domain_scores_gemma":[0.23294467,0.7344954,0.011069309,0.01162326,0.009120982,0.0007464401],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.36038327,0.003288066,0.00710595,0.0064019132,0.002726949,0.014400273,0.0046642707,0.013382338,0.0035020239],"category_scores_gemma":[0.5399421,0.0024517914,0.006515572,0.0034317286,0.02757816,0.0152492095,0.008362019,0.015855968,0.00059819623],"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":[0.00061597535,0.00009537252,0.0009515515,0.018472923,0.0020772573,0.000114624505,0.0026340494,0.010000432,0.00025976836,0.86132246,0.0047861533,0.09866952],"study_design_scores_gemma":[0.00049459573,0.00021765669,0.00084458356,0.009459181,0.0005755952,0.00017017774,0.00031773595,0.007939855,0.00032660028,0.9588233,0.0207451,0.00008559678],"about_ca_topic_score_codex":0.0044350117,"about_ca_topic_score_gemma":0.0041495743,"teacher_disagreement_score":0.36038327,"about_ca_system_score_codex":0.014183136,"about_ca_system_score_gemma":0.019064445,"threshold_uncertainty_score":0.7887613},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6233564,0.0040358603,0.14852555,0.11657243,0.0007099091,0.0005942828,0.00007237006,0.0008398237,0.10529347],"genre_scores_gemma":[0.96240985,0.000665097,0.027659293,0.0032380857,0.000051848783,0.00020364401,0.00003378511,0.0002324854,0.0055058063],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9500564,0.037571706,0.0014242386,0.0029032638,0.0052407826,0.002803702],"domain_scores_gemma":[0.92371196,0.048350506,0.0035110838,0.0073695313,0.0086442,0.008412626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05686505,0.0005055809,0.0006979892,0.004063216,0.011373386,0.020680234,0.0022788274,0.004866639,0.003107154],"category_scores_gemma":[0.072631165,0.0010947677,0.0005130688,0.0020782403,0.041910253,0.022651726,0.025137816,0.010794879,0.0008282591],"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":[0.000106043,0.0003249172,0.015008969,0.00037605374,0.000021425762,0.0008370548,0.6327965,0.00040852313,0.0033391123,0.19151796,0.00511819,0.15014525],"study_design_scores_gemma":[0.000021819542,0.00037524363,0.008220717,0.0012552903,0.000013260321,0.0016476428,0.5413043,0.0018760312,0.003845427,0.17690766,0.2643734,0.00015917327],"about_ca_topic_score_codex":0.0038209409,"about_ca_topic_score_gemma":0.0039802995,"teacher_disagreement_score":0.05686505,"about_ca_system_score_codex":0.010096176,"about_ca_system_score_gemma":0.019245403,"threshold_uncertainty_score":0.30073476},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073738367,0.766172,0.0027414928,0.13349137,0.05441245,0.0002796109,0.00061131374,0.00013888591,0.041415583],"genre_scores_gemma":[0.018506275,0.7435121,0.00668117,0.09266911,0.036348037,0.00056742184,0.0010872029,0.00022274801,0.10040602],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903279,0.003221466,0.00057300605,0.00045174273,0.005160078,0.00026576346],"domain_scores_gemma":[0.9333228,0.040110156,0.003079151,0.001041743,0.021499127,0.000947038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008196992,0.0007386401,0.0016714615,0.0055808276,0.0010124119,0.004440704,0.0022264926,0.005588147,0.01225078],"category_scores_gemma":[0.056659896,0.00049838907,0.00063381036,0.007255472,0.0022158183,0.0034358879,0.0009884886,0.0038007947,0.006100681],"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":[0.000015549776,0.000009630486,0.000093580886,0.00093782705,0.000025009544,0.000019025512,0.000052792584,0.00010373634,0.00005638503,0.0051513687,0.95695555,0.036579527],"study_design_scores_gemma":[0.00002193297,0.0000511797,0.0010050723,0.0032204608,0.00007281931,0.00013799134,0.00012389249,0.00015668635,0.00024625505,0.006153633,0.9887866,0.000023461738],"about_ca_topic_score_codex":0.007201887,"about_ca_topic_score_gemma":0.025040008,"teacher_disagreement_score":0.01225078,"about_ca_system_score_codex":0.0046599465,"about_ca_system_score_gemma":0.010679446,"threshold_uncertainty_score":0.0433504},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001578018,0.014189547,0.00063662155,0.08385305,0.9005133,0.000025703517,0.00002322168,0.000052666008,0.00069010636],"genre_scores_gemma":[0.000657533,0.011292117,0.0016167267,0.074780844,0.9074199,0.00014516743,0.000022381997,0.00010791044,0.0039573694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8705753,0.06013245,0.016495228,0.0051056333,0.045679633,0.00201173],"domain_scores_gemma":[0.3480879,0.5143399,0.012325973,0.011004459,0.101771496,0.012470254],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.1557811,0.004539761,0.008511488,0.010848694,0.0091475155,0.027400872,0.010316759,0.04184892,0.008653867],"category_scores_gemma":[0.34711054,0.0032308686,0.005449554,0.005569872,0.021974925,0.014735936,0.004727494,0.07493322,0.0075807017],"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":[0.000036066984,0.000013161572,0.000020743571,0.0011468665,0.000068504305,0.00006859249,0.00015739657,0.00004034868,0.00004387684,0.0030779934,0.98301184,0.012314605],"study_design_scores_gemma":[0.000105311876,0.000031248932,0.00018089436,0.0038145601,0.00016638344,0.0001722467,0.0002891249,0.00027160227,0.00013399536,0.010861501,0.9839092,0.00006394461],"about_ca_topic_score_codex":0.0050335145,"about_ca_topic_score_gemma":0.012832202,"teacher_disagreement_score":0.9908525,"about_ca_system_score_codex":0.012225688,"about_ca_system_score_gemma":0.014910165,"threshold_uncertainty_score":0.8238591},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029935243,0.0007761016,0.871553,0.011195491,0.00021951097,0.0069669955,0.00023952292,0.00011898012,0.07899517],"genre_scores_gemma":[0.54965854,0.00025971592,0.43607563,0.0007108762,0.000144375,0.012008344,0.000119557815,0.000053128497,0.0009698019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.50948113,0.42882356,0.016832136,0.0060575465,0.034971997,0.0038336916],"domain_scores_gemma":[0.5638793,0.35609242,0.029009813,0.016387176,0.032031152,0.0026001723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.36775017,0.0021336025,0.0020038881,0.016314343,0.008208381,0.012610477,0.0030825343,0.0034041135,0.004113114],"category_scores_gemma":[0.36053178,0.0010109291,0.0025961194,0.0063925805,0.03298356,0.010938004,0.009901284,0.004633101,0.00026983136],"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":[0.000118305456,0.00021047791,0.004066558,0.0009191658,0.00021018244,0.00015304345,0.01210965,0.008263263,0.00052365847,0.9271727,0.001023208,0.045229703],"study_design_scores_gemma":[0.00017188776,0.0004704977,0.004934634,0.0013016319,0.00016747149,0.00012157394,0.010611308,0.022386475,0.0014809316,0.9394794,0.018749353,0.00012472311],"about_ca_topic_score_codex":0.004340884,"about_ca_topic_score_gemma":0.004862678,"teacher_disagreement_score":0.36775017,"about_ca_system_score_codex":0.018244892,"about_ca_system_score_gemma":0.023639826,"threshold_uncertainty_score":0.7796766},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90931094,0.00020479131,0.053574182,0.0015994852,0.00006328464,0.009209494,0.00015808997,0.00028386698,0.025595834],"genre_scores_gemma":[0.94698405,0.000118422446,0.045427702,0.00009650179,0.00001641475,0.004171109,0.00007167104,0.000028856983,0.0030854316],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9087069,0.08033296,0.0013880499,0.002308623,0.003736463,0.0035268525],"domain_scores_gemma":[0.92208296,0.058894727,0.0033482334,0.0037763899,0.006588402,0.00530928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066260554,0.001033179,0.0007798608,0.0027566117,0.012033366,0.004775843,0.0026666792,0.0014884591,0.004345874],"category_scores_gemma":[0.06832276,0.00064208737,0.0006665457,0.0016724278,0.0042598485,0.0031603333,0.008315692,0.0018121671,0.0003824266],"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":[0.0050805523,0.017728528,0.05006637,0.0012631752,0.0001304041,0.0011840247,0.2155972,0.013714581,0.0045881853,0.022014562,0.0046962113,0.6639362],"study_design_scores_gemma":[0.0043016314,0.05740475,0.112870224,0.0028326092,0.00075285,0.0012166493,0.5351824,0.08332459,0.042013317,0.07334174,0.086136796,0.0006223995],"about_ca_topic_score_codex":0.012261783,"about_ca_topic_score_gemma":0.020323502,"teacher_disagreement_score":0.066260554,"about_ca_system_score_codex":0.008354831,"about_ca_system_score_gemma":0.033807945,"threshold_uncertainty_score":0.3504235},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99696237,0.00024211318,0.00006983514,0.0006950065,0.000002515469,0.000020855414,0.0005897366,0.000007708714,0.0014099252],"genre_scores_gemma":[0.9986928,0.00028207956,0.00016774297,0.000089197536,0.000006789114,0.000018421248,0.00032801443,0.00000251879,0.0004125493],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99606884,0.0010142114,0.00037809368,0.00030285248,0.001770278,0.00046576533],"domain_scores_gemma":[0.93343294,0.028113374,0.01910661,0.0014567025,0.011032021,0.006858347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047301017,0.0001786128,0.00033623708,0.0043243063,0.0014449582,0.0020167276,0.0007439914,0.0007849842,0.002997901],"category_scores_gemma":[0.033630177,0.0003576698,0.00019723146,0.0068465625,0.0008197583,0.00075119676,0.0009454799,0.0010477353,0.00036935962],"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":[0.000014772533,0.000032409644,0.9952742,0.000014216731,0.000016027161,0.000047783105,0.0013967647,0.000049880273,0.000098909324,0.000038372364,0.0003898064,0.002626882],"study_design_scores_gemma":[0.0000012124973,0.000012025138,0.9968874,0.0000118730095,0.000004925172,0.00003144914,0.0023433568,0.00016500943,0.000029002771,0.00001112064,0.0004968664,0.000005677961],"about_ca_topic_score_codex":0.5586818,"about_ca_topic_score_gemma":0.7497248,"teacher_disagreement_score":0.9952699,"about_ca_system_score_codex":0.00789465,"about_ca_system_score_gemma":0.00908214,"threshold_uncertainty_score":0.8878344},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2607274,0.06968929,0.44312492,0.1493303,0.005907123,0.018074468,0.0016525198,0.00069772714,0.050796293],"genre_scores_gemma":[0.8138507,0.008668195,0.14743055,0.013302271,0.0005914396,0.01440429,0.00020277953,0.0001684028,0.0013813172],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.110892646,0.8447934,0.0172627,0.0051192264,0.02033895,0.0015931325],"domain_scores_gemma":[0.017494343,0.9325496,0.017552383,0.014860805,0.01559195,0.001950845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.70476586,0.0010357877,0.002725138,0.017615212,0.010555927,0.031475052,0.0050584716,0.004966942,0.004298286],"category_scores_gemma":[0.836419,0.0019971963,0.0011466629,0.016322296,0.035698425,0.022596562,0.0157482,0.006455934,0.0007036294],"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":[0.0006476457,0.0003801841,0.050082922,0.018767225,0.00042548764,0.0005846398,0.6659735,0.00090333243,0.0021364861,0.06440751,0.005146754,0.19054437],"study_design_scores_gemma":[0.00027375293,0.0013745506,0.022433762,0.04611215,0.000337705,0.0020838731,0.7188229,0.0062583513,0.0037708634,0.11286052,0.08526483,0.00040682178],"about_ca_topic_score_codex":0.003349968,"about_ca_topic_score_gemma":0.0040093013,"teacher_disagreement_score":0.29523414,"about_ca_system_score_codex":0.013575962,"about_ca_system_score_gemma":0.033170898,"threshold_uncertainty_score":0.36407632},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35130233,0.055047087,0.012917058,0.51036364,0.0030260037,0.005215679,0.0033246197,0.00064004166,0.058163565],"genre_scores_gemma":[0.95135444,0.01186726,0.01155863,0.02003538,0.00095123,0.0014804805,0.00046674686,0.00014063175,0.002145179],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.66506207,0.2568642,0.01847975,0.0069459877,0.039079018,0.013568991],"domain_scores_gemma":[0.25839308,0.5503114,0.06483952,0.024368731,0.080763586,0.021323677],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26861843,0.00200068,0.0028430151,0.005503897,0.0034074297,0.020506892,0.004839527,0.016809864,0.017357372],"category_scores_gemma":[0.4510267,0.0009782447,0.004062666,0.013629788,0.010649035,0.018048566,0.010301555,0.008537797,0.0019309178],"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":[0.021225117,0.012842471,0.24706274,0.0238376,0.0033991341,0.0007935938,0.015599302,0.0051702913,0.0027967982,0.105325475,0.025713207,0.5362343],"study_design_scores_gemma":[0.006607697,0.017881323,0.3625317,0.03451329,0.011728966,0.0008010911,0.074061684,0.012713933,0.032234225,0.32711205,0.11900788,0.00080612686],"about_ca_topic_score_codex":0.011209303,"about_ca_topic_score_gemma":0.0065895068,"teacher_disagreement_score":0.9965926,"about_ca_system_score_codex":0.01994719,"about_ca_system_score_gemma":0.07313268,"threshold_uncertainty_score":0.90192366},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09581714,0.044281255,0.3288991,0.28292784,0.0032656556,0.0034511085,0.0006169322,0.00027124444,0.2404698],"genre_scores_gemma":[0.8317001,0.014066636,0.11672611,0.015104997,0.00058383145,0.004237069,0.00027524983,0.00022202366,0.017083943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7638117,0.177993,0.011724422,0.009248112,0.031553462,0.005669255],"domain_scores_gemma":[0.72946846,0.20986831,0.010862912,0.009775562,0.036206584,0.0038181713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15075262,0.0014791059,0.0022367588,0.0051569953,0.006268809,0.024242166,0.004353785,0.009302886,0.009931335],"category_scores_gemma":[0.17827265,0.0009412953,0.0018780025,0.0054348973,0.017493067,0.026304437,0.010733496,0.0097088795,0.0013674874],"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":[0.00031240218,0.00029061185,0.0060027745,0.011871758,0.00026924614,0.0005765051,0.08071028,0.0011541902,0.0025668822,0.6345112,0.007776795,0.25395733],"study_design_scores_gemma":[0.00015773745,0.0006944738,0.011653886,0.02910571,0.00050967344,0.00073046936,0.18285482,0.003140847,0.0074871965,0.46262622,0.3008208,0.00021816917],"about_ca_topic_score_codex":0.0068653515,"about_ca_topic_score_gemma":0.008967007,"teacher_disagreement_score":0.8492474,"about_ca_system_score_codex":0.015616942,"about_ca_system_score_gemma":0.03100961,"threshold_uncertainty_score":0.7972656},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8066461,0.0058390764,0.015379641,0.08169414,0.0006916593,0.0013576356,0.00015320638,0.00029841193,0.087940045],"genre_scores_gemma":[0.9869385,0.0006532748,0.005355344,0.0016352264,0.000081753285,0.00034672904,0.000050880175,0.000035768404,0.004902595],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94275856,0.04492181,0.00071044336,0.0009606635,0.0034445408,0.0072040623],"domain_scores_gemma":[0.883512,0.07138305,0.0038617507,0.0047781765,0.013969692,0.022495288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0524516,0.00058616337,0.000679463,0.0019808242,0.01803043,0.009852559,0.0045585753,0.0050855083,0.0073422566],"category_scores_gemma":[0.06368561,0.0005625785,0.0006327544,0.0028014025,0.006949539,0.005508182,0.011001735,0.005498716,0.0008571812],"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":[0.0029938396,0.008087628,0.06484467,0.0008788963,0.00024375782,0.0047198315,0.13100262,0.005827169,0.0012182541,0.03994467,0.03875809,0.70148057],"study_design_scores_gemma":[0.0019851853,0.006737182,0.18966903,0.0025925152,0.0002866629,0.0033689204,0.54640603,0.018035645,0.0024901605,0.083294,0.14454821,0.0005865824],"about_ca_topic_score_codex":0.06805528,"about_ca_topic_score_gemma":0.14668548,"teacher_disagreement_score":0.06805528,"about_ca_system_score_codex":0.020187177,"about_ca_system_score_gemma":0.055175446,"threshold_uncertainty_score":0.27739388},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008435748,0.12590571,0.23378061,0.45716593,0.07103414,0.08088153,0.0022353241,0.0023696518,0.018191388],"genre_scores_gemma":[0.052496057,0.044465523,0.71028423,0.050701275,0.01656592,0.12061919,0.00086487416,0.0007630303,0.003239978],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.031909242,0.67943823,0.22809581,0.0063218116,0.051969543,0.002265361],"domain_scores_gemma":[0.0131665,0.7833234,0.057302654,0.037339155,0.10507185,0.0037964315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90433776,0.0045203418,0.010499366,0.03432355,0.009860111,0.037180908,0.016741155,0.027923848,0.0067893625],"category_scores_gemma":[0.96756494,0.010032454,0.012374975,0.043318562,0.020672837,0.035948537,0.018078696,0.02082579,0.0069057513],"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":[0.002408994,0.00057099236,0.006647215,0.18321894,0.004390339,0.0009901588,0.048344467,0.0027827627,0.0021151034,0.05861673,0.11291815,0.5769961],"study_design_scores_gemma":[0.004732973,0.0024963005,0.016573852,0.3910271,0.0045718527,0.0019502079,0.026287574,0.0083169,0.003912607,0.13021715,0.40856972,0.0013437999],"about_ca_topic_score_codex":0.008962223,"about_ca_topic_score_gemma":0.015840076,"teacher_disagreement_score":0.095662236,"about_ca_system_score_codex":0.025679471,"about_ca_system_score_gemma":0.09147747,"threshold_uncertainty_score":0.18631846},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066153765,0.0077540474,0.8948092,0.0036957334,0.0007857816,0.009522395,0.0010213607,0.0003739795,0.015883718],"genre_scores_gemma":[0.21112706,0.0032826336,0.76206285,0.000856474,0.0002260302,0.017422127,0.00034275642,0.00019542266,0.0044846334],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79265183,0.16804767,0.008773947,0.0046348735,0.02493782,0.00095396873],"domain_scores_gemma":[0.6047507,0.3549119,0.012600492,0.011932232,0.01503854,0.00076617225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10553639,0.002625426,0.0033035902,0.003254763,0.0016806833,0.008159995,0.001889303,0.0031817772,0.010691166],"category_scores_gemma":[0.25579,0.0013043868,0.0042611086,0.0034031363,0.0044996673,0.006036222,0.0027860089,0.0045422423,0.0012245936],"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":[0.0039130347,0.002015851,0.019866366,0.027565185,0.0032300758,0.00042987455,0.021529265,0.01757156,0.015874712,0.10972882,0.0038362162,0.7744391],"study_design_scores_gemma":[0.0039763898,0.032867014,0.11551671,0.033923343,0.009187731,0.0016644575,0.028900227,0.13643138,0.086970754,0.36276242,0.18635863,0.0014410287],"about_ca_topic_score_codex":0.004757231,"about_ca_topic_score_gemma":0.0049299295,"teacher_disagreement_score":0.10553639,"about_ca_system_score_codex":0.004159004,"about_ca_system_score_gemma":0.010331613,"threshold_uncertainty_score":0.55813646},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55246943,0.0028126775,0.00082590827,0.009478251,0.00031440696,0.00034312435,0.29893312,0.0003536203,0.13446945],"genre_scores_gemma":[0.79621345,0.0019805061,0.0014287998,0.00070707826,0.000066992274,0.00014831424,0.07848098,0.000108207576,0.120865636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976749,0.00004532176,0.00005177754,0.00015135664,0.0014397315,0.0006370742],"domain_scores_gemma":[0.9929685,0.000109244225,0.0005352638,0.00014861494,0.004805403,0.0014329869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008693289,0.00026228733,0.00045554468,0.0019840884,0.004189823,0.002370872,0.0010109175,0.00048154022,0.0077135907],"category_scores_gemma":[0.003021669,0.00034238107,0.0003314764,0.005937184,0.00062049745,0.00075784343,0.0010103292,0.0006174142,0.0015429916],"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":[0.0004348291,0.00014830392,0.5215967,0.0005582709,0.00010805971,0.00034078056,0.0065162624,0.00088306825,0.0006109908,0.00448579,0.3914727,0.072844245],"study_design_scores_gemma":[0.00001477199,0.000017423412,0.9031709,0.00007097618,0.000027922226,0.000027694763,0.0029584907,0.00019482606,0.00018555751,0.0000752305,0.093238294,0.000017916998],"about_ca_topic_score_codex":0.9971643,"about_ca_topic_score_gemma":0.9994821,"teacher_disagreement_score":0.08204482,"about_ca_system_score_codex":0.08204482,"about_ca_system_score_gemma":0.097881585,"threshold_uncertainty_score":0.5952796},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963934,0.00007250836,0.000036906335,0.00023843219,0.000004634536,0.00012693324,0.000093467956,0.0000016652076,0.0030320233],"genre_scores_gemma":[0.9987827,0.00008368715,0.00010290368,0.00008955795,0.0000045987213,0.000050608203,0.00004462948,0.0000010019678,0.0008402339],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99603844,0.0014731179,0.00016525158,0.00016365922,0.0009610654,0.001198367],"domain_scores_gemma":[0.98858976,0.0037268067,0.0016685879,0.00037962562,0.0036753456,0.0019598815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003223595,0.00020141088,0.00033908334,0.0007245316,0.001998458,0.0014787285,0.0005011647,0.00043282637,0.0011535739],"category_scores_gemma":[0.009001868,0.00014771418,0.00033553675,0.0007989884,0.0010299487,0.00037988255,0.0016190183,0.00067984516,0.00011039548],"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":[0.0017194952,0.0033396445,0.91120976,0.0002591199,0.000118716576,0.001274645,0.01777286,0.0016517957,0.0022830265,0.0011017601,0.0013756421,0.057893593],"study_design_scores_gemma":[0.00005135279,0.0012726232,0.983343,0.00006047808,0.000041678195,0.000045050565,0.012770031,0.00036388822,0.0005021114,0.000050199957,0.0014884789,0.000011140773],"about_ca_topic_score_codex":0.6540481,"about_ca_topic_score_gemma":0.81792855,"teacher_disagreement_score":0.9843969,"about_ca_system_score_codex":0.015603139,"about_ca_system_score_gemma":0.018466232,"threshold_uncertainty_score":0.6959786},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56382483,0.007294389,0.0900044,0.118664525,0.0012486633,0.00059344573,0.0007969457,0.00016137351,0.21741147],"genre_scores_gemma":[0.9908049,0.0006642417,0.006178431,0.00063549436,0.00009508823,0.00019620647,0.00010162975,0.000054073247,0.0012699862],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66085833,0.31016287,0.006309039,0.0051056724,0.0141682755,0.0033958424],"domain_scores_gemma":[0.3454005,0.59289443,0.02203274,0.022348579,0.015506565,0.001817222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19942072,0.0010461281,0.0012384092,0.012185445,0.011320136,0.027594134,0.0043255542,0.004669566,0.0050117867],"category_scores_gemma":[0.38193792,0.0010588267,0.00074285717,0.011329376,0.08420649,0.034796935,0.014964389,0.0067015653,0.0004528014],"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":[0.0001644523,0.000041098847,0.003434183,0.00043980769,0.00004150668,0.00050473417,0.54806703,0.00077872735,0.00023640311,0.42484224,0.0019910051,0.019458741],"study_design_scores_gemma":[0.000046966983,0.00007793785,0.0036109986,0.0029558062,0.00004505014,0.0003319344,0.52951497,0.0032627303,0.0019286576,0.3640163,0.094116025,0.000092677685],"about_ca_topic_score_codex":0.0077964845,"about_ca_topic_score_gemma":0.0042908415,"teacher_disagreement_score":0.19942072,"about_ca_system_score_codex":0.020030169,"about_ca_system_score_gemma":0.010946781,"threshold_uncertainty_score":0.98725677},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53600955,0.027177792,0.014324053,0.21070817,0.0006967117,0.013488052,0.00096960797,0.00037162297,0.1962544],"genre_scores_gemma":[0.9428911,0.010033926,0.03004575,0.0048286123,0.000091483074,0.0030424427,0.00018655251,0.000057051675,0.008823041],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.91533923,0.05259617,0.004455037,0.002106342,0.01780813,0.0076950896],"domain_scores_gemma":[0.8447259,0.067410834,0.015193432,0.0072301715,0.036428105,0.029011583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07818745,0.00045705965,0.0007283242,0.004344803,0.013489352,0.00902589,0.003929298,0.0020132046,0.0044952803],"category_scores_gemma":[0.11266119,0.0012290891,0.0006329218,0.0074202553,0.010660499,0.0032978675,0.011421134,0.002444503,0.00029606745],"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":[0.0009242427,0.0012549644,0.11539114,0.010864366,0.0002893414,0.0023544186,0.27214652,0.0026930145,0.0040015173,0.03736209,0.04795397,0.5047644],"study_design_scores_gemma":[0.0012200433,0.00120033,0.36668658,0.011592031,0.00022228662,0.00037491397,0.14361456,0.0022094254,0.0020636232,0.017915012,0.45258707,0.00031419448],"about_ca_topic_score_codex":0.9244681,"about_ca_topic_score_gemma":0.97442186,"teacher_disagreement_score":0.19345161,"about_ca_system_score_codex":0.19345161,"about_ca_system_score_gemma":0.590367,"threshold_uncertainty_score":0.9354818},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80896664,0.0048804493,0.075385205,0.011186892,0.00050866714,0.0025304398,0.00032571252,0.0004466225,0.095769264],"genre_scores_gemma":[0.948005,0.0012316222,0.030439246,0.0004918503,0.000041857962,0.0010413252,0.00012726361,0.0001001539,0.018521687],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9497151,0.032493863,0.002043056,0.0023346224,0.011564137,0.001849289],"domain_scores_gemma":[0.883868,0.06715315,0.0060639917,0.005509884,0.032195054,0.005209914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059862174,0.0008120713,0.0011339303,0.0030050513,0.0048090178,0.008953016,0.0017834913,0.0017191168,0.007007109],"category_scores_gemma":[0.09238366,0.0004315443,0.00068308855,0.0030021116,0.006222799,0.004941761,0.004545786,0.0027215418,0.001096212],"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":[0.00066935277,0.0007513705,0.041179527,0.002230994,0.0001313405,0.0006796037,0.41301695,0.0015227782,0.00973158,0.05130227,0.0056566903,0.4731276],"study_design_scores_gemma":[0.00020213019,0.0027630492,0.21501778,0.0057062013,0.00026983506,0.00082081935,0.4043472,0.0071576172,0.023540255,0.028660089,0.31107327,0.00044179827],"about_ca_topic_score_codex":0.10717189,"about_ca_topic_score_gemma":0.11774938,"teacher_disagreement_score":0.10717189,"about_ca_system_score_codex":0.028317103,"about_ca_system_score_gemma":0.046437923,"threshold_uncertainty_score":0.31658524},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002305588,0.016621612,0.32883224,0.03409014,0.01834986,0.49597162,0.016198099,0.0089044105,0.0787265],"genre_scores_gemma":[0.0021279636,0.007824964,0.6488064,0.0033724857,0.0007229375,0.30871025,0.004199198,0.0008011573,0.023434572],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.78442293,0.12109166,0.058376163,0.0044212895,0.029597512,0.002090427],"domain_scores_gemma":[0.457445,0.14770861,0.023243025,0.034908805,0.32985097,0.006843539],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23671523,0.0033563823,0.005010781,0.025587436,0.0061343955,0.0048449473,0.007521294,0.0049738185,0.044229884],"category_scores_gemma":[0.32177514,0.0048752166,0.0055227005,0.021554966,0.004083099,0.004697166,0.004716052,0.011887596,0.041659337],"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":[0.00021656523,0.00030215687,0.00036714092,0.014427882,0.00015012054,0.00029679906,0.0033343104,0.0005677346,0.003120714,0.009416773,0.7063252,0.2614746],"study_design_scores_gemma":[0.0003898101,0.0002594717,0.0014885337,0.01384453,0.00013251697,0.00024938994,0.0012456045,0.0006555009,0.0013612926,0.0054099183,0.9747727,0.00019071819],"about_ca_topic_score_codex":0.010182154,"about_ca_topic_score_gemma":0.022989979,"teacher_disagreement_score":0.7632848,"about_ca_system_score_codex":0.007637185,"about_ca_system_score_gemma":0.06596962,"threshold_uncertainty_score":0.941266},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.114484936,0.018507281,0.1631706,0.04074434,0.0005727555,0.00047698367,0.00027876208,0.000554272,0.66121006],"genre_scores_gemma":[0.82855237,0.01308072,0.07306274,0.0032082875,0.00016470705,0.00053364475,0.00021300228,0.00029961232,0.080884844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9844171,0.008918615,0.00051473465,0.0016842175,0.0031650322,0.0013003856],"domain_scores_gemma":[0.9870293,0.0069231954,0.0012749685,0.0015145477,0.0023761713,0.0008817853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012891715,0.0012940759,0.0005949016,0.003422572,0.0045536533,0.015688393,0.0020806834,0.0038925074,0.013049863],"category_scores_gemma":[0.015653448,0.00060720806,0.0009266465,0.0032168296,0.010701782,0.008197333,0.005979522,0.004725962,0.0030721156],"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":[0.00010662569,0.00017648157,0.008353291,0.0012323296,0.00011419789,0.0003519571,0.029392917,0.0027854554,0.0025708645,0.74478287,0.004347632,0.20578532],"study_design_scores_gemma":[0.000051316776,0.00031864498,0.014136547,0.0030747799,0.0001601987,0.0005396031,0.04716903,0.0026210374,0.005878254,0.30022418,0.6257113,0.000115069444],"about_ca_topic_score_codex":0.010227332,"about_ca_topic_score_gemma":0.014654901,"teacher_disagreement_score":0.015688393,"about_ca_system_score_codex":0.0109138815,"about_ca_system_score_gemma":0.015292569,"threshold_uncertainty_score":0.07918608},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011660262,0.07371935,0.059885606,0.71189445,0.008755189,0.010599201,0.0020147269,0.0005922159,0.120879054],"genre_scores_gemma":[0.6265844,0.062304873,0.15924577,0.09050732,0.004668756,0.04422284,0.0012462583,0.00033873616,0.010881011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43743,0.5136371,0.01552967,0.0040821573,0.024475304,0.004845687],"domain_scores_gemma":[0.19606355,0.71348125,0.016679335,0.01441785,0.05197144,0.0073866034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.45408645,0.0033717009,0.00587556,0.0073505947,0.005036974,0.028149975,0.007697774,0.01594864,0.02746675],"category_scores_gemma":[0.69589037,0.0010737083,0.0023467722,0.012725505,0.014433255,0.02382317,0.0084104,0.00875962,0.0020570916],"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":[0.0022957942,0.0017014294,0.007585606,0.01691569,0.0006862576,0.00044697284,0.0038653219,0.008790869,0.00016014896,0.4755763,0.08701752,0.3949581],"study_design_scores_gemma":[0.0019204363,0.0017028002,0.0065513514,0.076454625,0.0010552261,0.00022695505,0.022606034,0.022477537,0.0010689613,0.7217121,0.1439165,0.00030742004],"about_ca_topic_score_codex":0.011902106,"about_ca_topic_score_gemma":0.009014539,"teacher_disagreement_score":0.45408645,"about_ca_system_score_codex":0.032236077,"about_ca_system_score_gemma":0.079622224,"threshold_uncertainty_score":0.6732086},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018828927,0.01560915,0.0024739774,0.887318,0.09043314,0.00010025224,0.00012153195,0.000116342555,0.0036392212],"genre_scores_gemma":[0.009893531,0.025422378,0.017960995,0.84895426,0.08256739,0.000550409,0.00019430195,0.00021823842,0.014238528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8142269,0.093074575,0.02590027,0.00664417,0.056432135,0.0037219177],"domain_scores_gemma":[0.23039523,0.39053836,0.018900208,0.048435442,0.27211797,0.039612755],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23875211,0.0015547349,0.0043682884,0.0031613444,0.0057150964,0.0151078515,0.007469699,0.023979718,0.019555135],"category_scores_gemma":[0.6180762,0.0011091707,0.0032808634,0.0033278181,0.014664695,0.021741599,0.006699933,0.032660354,0.018269286],"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":[0.00031131718,0.000101383055,0.0008211543,0.0047595273,0.00034344904,0.00015548433,0.00047157213,0.00012194124,0.00026269493,0.01732595,0.87509936,0.10022624],"study_design_scores_gemma":[0.00022084628,0.00024819595,0.0012204424,0.02152271,0.0004870167,0.00062524615,0.0029150345,0.00038919927,0.00048013014,0.062371805,0.9092604,0.0002590901],"about_ca_topic_score_codex":0.004409002,"about_ca_topic_score_gemma":0.010371201,"teacher_disagreement_score":0.7612479,"about_ca_system_score_codex":0.006247591,"about_ca_system_score_gemma":0.04122925,"threshold_uncertainty_score":0.9387542},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9641751,0.0027514766,0.0063128923,0.004094954,0.00008892372,0.0025026307,0.00011485327,0.00015717979,0.019801961],"genre_scores_gemma":[0.9831823,0.0013892356,0.0111438995,0.00028269086,0.00003160294,0.00091802294,0.00010844438,0.000016519392,0.0029271273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9864611,0.009227052,0.00063066307,0.00048166604,0.0017482986,0.0014512383],"domain_scores_gemma":[0.96216524,0.020147247,0.005243603,0.0014683142,0.005330995,0.005644648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0396255,0.00048347536,0.00031987138,0.0014170159,0.0016661453,0.0022730182,0.00085622247,0.000590013,0.0024526813],"category_scores_gemma":[0.056854904,0.00029903732,0.00032681786,0.00083312317,0.0015093315,0.0011219312,0.0033993735,0.0007575726,0.00033096864],"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":[0.0005443902,0.0019169536,0.10913112,0.0015696443,0.000031712705,0.0003859688,0.060977653,0.000560951,0.0024782182,0.001115395,0.0060715396,0.8152164],"study_design_scores_gemma":[0.00022009858,0.0047437446,0.88415426,0.004659829,0.00007881443,0.0010459932,0.042057093,0.0022069616,0.0057630865,0.0016716543,0.05323507,0.00016341588],"about_ca_topic_score_codex":0.012873341,"about_ca_topic_score_gemma":0.020231681,"teacher_disagreement_score":0.0396255,"about_ca_system_score_codex":0.007138154,"about_ca_system_score_gemma":0.013365236,"threshold_uncertainty_score":0.20956218},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008178153,0.10776946,0.2630899,0.55451035,0.006585613,0.0013745246,0.0003544737,0.0006124529,0.057525065],"genre_scores_gemma":[0.4621877,0.07241422,0.39490202,0.051250607,0.008398079,0.0063587907,0.00023572748,0.00045273337,0.003800199],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6143786,0.33592108,0.013819647,0.0035155928,0.029088836,0.0032763693],"domain_scores_gemma":[0.18585683,0.74346787,0.010437975,0.02107557,0.03487414,0.0042876415],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35224256,0.0033061176,0.0067472425,0.030623948,0.0079228,0.046662863,0.0070927944,0.011223835,0.015076941],"category_scores_gemma":[0.49937993,0.0022468807,0.0038687976,0.013057161,0.067514814,0.084324636,0.023451144,0.017216278,0.0018302229],"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":[0.00018049551,0.00018902801,0.0033267187,0.0069969287,0.00031041342,0.00018415642,0.008726928,0.0023081866,0.00011530436,0.76633537,0.020153299,0.19117317],"study_design_scores_gemma":[0.000087857,0.00012505159,0.0010921657,0.015064176,0.00014769132,0.00012179672,0.009821593,0.0030242219,0.00025171033,0.9247552,0.045376413,0.0001322275],"about_ca_topic_score_codex":0.0075864187,"about_ca_topic_score_gemma":0.010205195,"teacher_disagreement_score":0.35224256,"about_ca_system_score_codex":0.026557706,"about_ca_system_score_gemma":0.027439937,"threshold_uncertainty_score":0.79880023},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03208626,0.06374558,0.550171,0.23371367,0.004865833,0.00061523414,0.0001750692,0.0003329547,0.11429436],"genre_scores_gemma":[0.6839466,0.025437173,0.26174715,0.019043282,0.0021463241,0.001424246,0.00013153286,0.0002201721,0.005903459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92487776,0.065792255,0.0014500899,0.0020723548,0.004838395,0.00096920604],"domain_scores_gemma":[0.8056092,0.17444965,0.003065505,0.008267291,0.0058808126,0.0027276506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0644352,0.0016947913,0.0025156671,0.0077719237,0.0053659347,0.019642025,0.00358808,0.0072933403,0.0044673705],"category_scores_gemma":[0.073246315,0.0008927142,0.0013750199,0.004192245,0.07156443,0.030109186,0.008461147,0.008580377,0.0006690223],"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":[0.000029106495,0.00012672413,0.0013270947,0.0009882061,0.00012054048,0.00017380838,0.016642157,0.001036182,0.00019350841,0.94050175,0.005332084,0.033528846],"study_design_scores_gemma":[0.00002127032,0.000022622522,0.00020052967,0.00054655684,0.000021433692,0.000058843216,0.0066927588,0.0010048706,0.0001560177,0.9801413,0.01111474,0.000018873436],"about_ca_topic_score_codex":0.0022356662,"about_ca_topic_score_gemma":0.0029991216,"teacher_disagreement_score":0.0644352,"about_ca_system_score_codex":0.007228362,"about_ca_system_score_gemma":0.010306276,"threshold_uncertainty_score":0.34076995},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58483195,0.011307363,0.19248205,0.052320156,0.002160628,0.0014349947,0.004838145,0.0025428382,0.14808188],"genre_scores_gemma":[0.9116788,0.0019228944,0.07460235,0.0020681839,0.00040708738,0.00045507654,0.0016889436,0.00018345665,0.0069932835],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9485002,0.032147553,0.002793003,0.0024106062,0.01275002,0.0013985215],"domain_scores_gemma":[0.9135523,0.035881598,0.011136085,0.0115098,0.026408415,0.00151177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06202077,0.00046487592,0.00055578025,0.0044273334,0.0011821628,0.00497208,0.0010934361,0.0006447586,0.0028517328],"category_scores_gemma":[0.10432876,0.00040409318,0.0005847945,0.00691528,0.0013541062,0.0044490807,0.0028050428,0.002682807,0.0005472745],"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":[0.00028055214,0.00041140371,0.09628067,0.00039554914,0.00019637354,0.00007500396,0.0022684603,0.00944082,0.0012607034,0.13119254,0.057321616,0.70087636],"study_design_scores_gemma":[0.00012042501,0.002080473,0.35604542,0.0018767895,0.00024905938,0.0003760939,0.004250084,0.041193396,0.008660651,0.049453575,0.5353071,0.00038688304],"about_ca_topic_score_codex":0.015844157,"about_ca_topic_score_gemma":0.010985704,"teacher_disagreement_score":0.06202077,"about_ca_system_score_codex":0.0052621053,"about_ca_system_score_gemma":0.0065990775,"threshold_uncertainty_score":0.32800108},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029092615,0.0026396455,0.78865635,0.11855148,0.0009607204,0.0012405713,0.000096071984,0.00034706647,0.08459885],"genre_scores_gemma":[0.2712866,0.0021305142,0.6895554,0.021316571,0.0010140915,0.008652979,0.00015951655,0.00039176774,0.005492499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.653598,0.23668715,0.023369972,0.01930781,0.061435148,0.0056018946],"domain_scores_gemma":[0.6968179,0.21434493,0.010473255,0.04115148,0.031270288,0.0059421356],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3024054,0.002648088,0.005341647,0.009153823,0.01660413,0.03869847,0.013435098,0.029608075,0.007384952],"category_scores_gemma":[0.23804352,0.0026459417,0.006060009,0.007560718,0.14169532,0.054811884,0.028114997,0.035474144,0.0031853241],"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":[0.000009428871,0.000021035194,0.00005940397,0.000103843326,0.000012538738,0.000019961071,0.002033072,0.00023596987,0.00002057937,0.99409544,0.00091309566,0.0024756247],"study_design_scores_gemma":[0.000050206123,0.00002049205,0.000053584536,0.00029001915,0.00000860828,0.00004477476,0.0007774134,0.000804695,0.00008450032,0.98587996,0.011966064,0.00001973255],"about_ca_topic_score_codex":0.0044825273,"about_ca_topic_score_gemma":0.0028709907,"teacher_disagreement_score":0.3024054,"about_ca_system_score_codex":0.019950347,"about_ca_system_score_gemma":0.027325708,"threshold_uncertainty_score":0.86025834},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87213904,0.0009525173,0.0023417983,0.020423166,0.00006799839,0.000633793,0.0009851787,0.00011971342,0.10233682],"genre_scores_gemma":[0.9969813,0.00016471083,0.0006205928,0.00028988486,0.0000062983927,0.00008567787,0.0001021061,0.000009200957,0.0017402116],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9336766,0.02732248,0.0035900648,0.0030524645,0.015145535,0.017212847],"domain_scores_gemma":[0.75264823,0.110485554,0.015484533,0.021223636,0.06704269,0.033115342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051144246,0.00022615885,0.00063160097,0.0051195184,0.014555783,0.012447515,0.0034082653,0.0014878028,0.005645623],"category_scores_gemma":[0.13572139,0.0007382678,0.0004644266,0.009059171,0.012354385,0.003687613,0.01131815,0.0020366868,0.0004214425],"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":[0.00050833577,0.00036828063,0.343196,0.0011335752,0.00016089616,0.0010428806,0.37479085,0.0045999833,0.0029080017,0.13257883,0.016975226,0.12173712],"study_design_scores_gemma":[0.00014208765,0.00026012142,0.2724062,0.0016295053,0.000130483,0.00045444374,0.4232513,0.0067902403,0.001737475,0.029908717,0.26301074,0.00027878903],"about_ca_topic_score_codex":0.8681263,"about_ca_topic_score_gemma":0.89101636,"teacher_disagreement_score":0.94885576,"about_ca_system_score_codex":0.12661001,"about_ca_system_score_gemma":0.3186712,"threshold_uncertainty_score":0.9186242},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50163674,0.0026069777,0.14050646,0.024032868,0.0003367495,0.001205484,0.0003078865,0.0009386883,0.32842824],"genre_scores_gemma":[0.9360065,0.000536068,0.032392245,0.0005660131,0.000036650337,0.000425403,0.00011701194,0.00014246553,0.029777808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.97135407,0.0153077105,0.0012023429,0.0025314884,0.008130383,0.0014740253],"domain_scores_gemma":[0.9209445,0.035018988,0.006506329,0.007196824,0.026415862,0.003917505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02702066,0.000939,0.0009688631,0.0032882097,0.005930535,0.012055222,0.0019772255,0.0018452766,0.013836282],"category_scores_gemma":[0.07887491,0.0005583157,0.00068281416,0.002712394,0.008540062,0.0055626584,0.0055577997,0.0026133372,0.0015801762],"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":[0.000776414,0.000373952,0.074208274,0.0015087695,0.000341284,0.0007488632,0.12752482,0.00876045,0.006816365,0.38395518,0.01606347,0.37892222],"study_design_scores_gemma":[0.00025064131,0.0013703234,0.19071424,0.004349321,0.0008903795,0.0010222865,0.10470945,0.07031448,0.017037837,0.23589386,0.37282202,0.00062520744],"about_ca_topic_score_codex":0.14678186,"about_ca_topic_score_gemma":0.16909419,"teacher_disagreement_score":0.9746946,"about_ca_system_score_codex":0.0253054,"about_ca_system_score_gemma":0.033586495,"threshold_uncertainty_score":0.29185498},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8529402,0.00095795834,0.05857592,0.018697828,0.0004256541,0.016649771,0.00045924875,0.0019204131,0.049372975],"genre_scores_gemma":[0.95529664,0.0001814114,0.03275485,0.0012245859,0.00006793526,0.0060958285,0.00029150027,0.00009773744,0.003989413],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9212608,0.0580131,0.0021492788,0.0044095623,0.0042385566,0.009928823],"domain_scores_gemma":[0.7700112,0.12484077,0.010302751,0.016051311,0.02537529,0.053418603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10459871,0.0010690856,0.0011910138,0.003558317,0.007891338,0.0120311715,0.008009607,0.0035974514,0.02364628],"category_scores_gemma":[0.13385291,0.0023466307,0.0009639583,0.0014296331,0.0047586965,0.013244635,0.025197431,0.005777225,0.0026728394],"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":[0.0069015427,0.04422926,0.20683576,0.0027855795,0.00056533626,0.001509381,0.037918795,0.026948435,0.009121499,0.026445892,0.040962495,0.5957761],"study_design_scores_gemma":[0.006843905,0.016384935,0.37322918,0.010030634,0.000733767,0.001349375,0.11291013,0.21311957,0.03544565,0.0780456,0.15058547,0.0013217572],"about_ca_topic_score_codex":0.015469731,"about_ca_topic_score_gemma":0.034675002,"teacher_disagreement_score":0.10459871,"about_ca_system_score_codex":0.016125433,"about_ca_system_score_gemma":0.07578313,"threshold_uncertainty_score":0.5531775},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7776065,0.0011213898,0.109903626,0.018594999,0.0003192757,0.0014477097,0.000032841,0.00020202337,0.09077168],"genre_scores_gemma":[0.97530705,0.0002283457,0.022511195,0.00020601359,0.000025304253,0.00024711707,0.000010717837,0.00001603029,0.0014482541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.84527534,0.14093885,0.0019543066,0.0013521694,0.006173182,0.004306186],"domain_scores_gemma":[0.8582171,0.111021705,0.009018799,0.0067895013,0.007082435,0.007870464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09079977,0.00064966973,0.0007974751,0.0016991155,0.00889505,0.010395076,0.002831722,0.004432528,0.005312374],"category_scores_gemma":[0.12565906,0.00048678755,0.00055321533,0.0012872185,0.009120305,0.010535329,0.009473324,0.0037794812,0.00084173994],"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":[0.0014438346,0.0030780574,0.03165616,0.0023187757,0.00027866324,0.0062188315,0.19470875,0.015538986,0.008367832,0.37592,0.009023195,0.35144705],"study_design_scores_gemma":[0.0004437462,0.005284543,0.015123327,0.0022329085,0.0003283597,0.002336927,0.34910616,0.061651085,0.022194093,0.42574623,0.11517697,0.00037568292],"about_ca_topic_score_codex":0.0010599595,"about_ca_topic_score_gemma":0.0020157823,"teacher_disagreement_score":0.09079977,"about_ca_system_score_codex":0.0028682305,"about_ca_system_score_gemma":0.0059419144,"threshold_uncertainty_score":0.48020083},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73047775,0.028340135,0.02732011,0.087235525,0.0009748562,0.0009213707,0.00011213968,0.0001145915,0.1245035],"genre_scores_gemma":[0.98054403,0.0067835134,0.0073596532,0.0013539082,0.00008277925,0.0002701828,0.000022995757,0.000007471356,0.0035755998],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9881258,0.0097277,0.00021487886,0.0003556964,0.00071755407,0.00085836375],"domain_scores_gemma":[0.9906669,0.0060701524,0.0010308243,0.00044423103,0.0006768655,0.0011110299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008667291,0.00046614348,0.00045238528,0.0008844252,0.0018862572,0.0021009273,0.00087124243,0.001987798,0.005226134],"category_scores_gemma":[0.01896134,0.00016612303,0.000488806,0.00060210703,0.0045084613,0.0018151174,0.002410949,0.0016426765,0.00038650344],"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":[0.0008315971,0.0034202673,0.04947674,0.0045792353,0.0002842118,0.0013352592,0.15538372,0.0029537221,0.0017963559,0.13159536,0.005453323,0.6428902],"study_design_scores_gemma":[0.0008829184,0.0096441535,0.16297881,0.019762399,0.0010222717,0.0032253154,0.43687677,0.0054638786,0.004760172,0.13583787,0.21929835,0.00024711926],"about_ca_topic_score_codex":0.007602246,"about_ca_topic_score_gemma":0.015103793,"teacher_disagreement_score":0.008667291,"about_ca_system_score_codex":0.002212161,"about_ca_system_score_gemma":0.010711676,"threshold_uncertainty_score":0.04583758},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06546339,0.005580786,0.07765759,0.1448788,0.00070087716,0.0003501623,0.00029914573,0.00046575704,0.7046035],"genre_scores_gemma":[0.97530615,0.001348594,0.009455623,0.0033876873,0.00010083174,0.00012166481,0.000052507243,0.00009515153,0.010131853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9469776,0.022206908,0.0012924029,0.0032334037,0.020665733,0.0056239706],"domain_scores_gemma":[0.9369613,0.023990642,0.004948615,0.005756052,0.022088367,0.0062549794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030891482,0.00061507925,0.00066364266,0.0048443703,0.009287342,0.019652367,0.0023656625,0.001922729,0.0034265025],"category_scores_gemma":[0.06683926,0.00029507582,0.0003704613,0.0061299587,0.040943768,0.0083797835,0.009644399,0.005127126,0.00035289433],"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":[0.000027692293,0.000035461908,0.008805757,0.00016082336,0.000018715611,0.000084566294,0.01797047,0.0009850394,0.00020907915,0.9084269,0.006563095,0.056712396],"study_design_scores_gemma":[0.000034554017,0.00007798224,0.02677508,0.0011766861,0.000055173055,0.00014478843,0.035854064,0.0037406369,0.0011217267,0.67364556,0.257222,0.00015176953],"about_ca_topic_score_codex":0.7432911,"about_ca_topic_score_gemma":0.7307203,"teacher_disagreement_score":0.7432911,"about_ca_system_score_codex":0.09353679,"about_ca_system_score_gemma":0.14481358,"threshold_uncertainty_score":0.67866004},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36891326,0.010600713,0.096905336,0.48443285,0.0043673,0.0018756996,0.00019029857,0.00020674757,0.032507665],"genre_scores_gemma":[0.9188807,0.005132992,0.03794066,0.031064887,0.00090936304,0.0023588545,0.000046802696,0.00028441072,0.0033812386],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5434182,0.418528,0.008432685,0.005865908,0.017078508,0.0066767163],"domain_scores_gemma":[0.45311794,0.49997276,0.013556557,0.011382408,0.016610872,0.0053594317],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3093373,0.0018096872,0.0027163478,0.0038629852,0.0332379,0.03193589,0.01050842,0.020030137,0.0014412572],"category_scores_gemma":[0.3826426,0.0025738864,0.0021991564,0.004727072,0.10928961,0.028852073,0.03141216,0.036897272,0.0005302381],"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":[0.00003074311,0.000023838866,0.00034459922,0.00027620187,0.000010484086,0.0010311761,0.9821468,0.00012437705,0.00017261245,0.010823847,0.0010870392,0.003928311],"study_design_scores_gemma":[0.00002178431,0.00004898316,0.00025805354,0.0010191646,0.000014182907,0.001190028,0.95862687,0.00037963464,0.0003458791,0.015555848,0.022474464,0.000065155684],"about_ca_topic_score_codex":0.0072553586,"about_ca_topic_score_gemma":0.010970825,"teacher_disagreement_score":0.69066274,"about_ca_system_score_codex":0.017328264,"about_ca_system_score_gemma":0.018868929,"threshold_uncertainty_score":0.8517101},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014329175,0.9669631,0.000489521,0.00556422,0.0005367205,0.001652615,0.0053783115,0.000028357308,0.0050578797],"genre_scores_gemma":[0.12030287,0.8643721,0.006165561,0.003260989,0.00017689307,0.0020313826,0.001983931,0.00002266456,0.0016836851],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9515566,0.0120409895,0.012420369,0.0022375786,0.01914053,0.0026038492],"domain_scores_gemma":[0.8195991,0.05895192,0.02217287,0.0028277661,0.09222186,0.004226466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044833913,0.0013257496,0.004922319,0.052193318,0.0050743767,0.008122327,0.0028067785,0.0019333839,0.0027984842],"category_scores_gemma":[0.14658754,0.0011696779,0.002179934,0.13186803,0.003068114,0.0026577206,0.0026397414,0.0013949628,0.00026126878],"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":[0.00096330896,0.00011332773,0.024951428,0.462648,0.0040652263,0.0007873093,0.01395223,0.00078554417,0.0008617462,0.0034326278,0.053023897,0.43441525],"study_design_scores_gemma":[0.00054037524,0.0003561547,0.17064163,0.58523005,0.02215761,0.0005788922,0.015443421,0.0002312358,0.0009461116,0.0010972413,0.2025299,0.000247282],"about_ca_topic_score_codex":0.87857574,"about_ca_topic_score_gemma":0.9702312,"teacher_disagreement_score":0.90243804,"about_ca_system_score_codex":0.097561955,"about_ca_system_score_gemma":0.4509753,"threshold_uncertainty_score":0.7078649},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7071873,0.0062510576,0.093136586,0.09236219,0.005955673,0.0035751727,0.000366549,0.0003785486,0.09078695],"genre_scores_gemma":[0.9373006,0.0024207602,0.026906833,0.006349824,0.0004211732,0.0016395842,0.000108422464,0.00018599372,0.024666857],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.85492486,0.13200727,0.0021937655,0.0024609459,0.0052725365,0.0031406383],"domain_scores_gemma":[0.8716952,0.10462382,0.0031965582,0.006680717,0.0108430935,0.0029605653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06497761,0.0011638247,0.0011573469,0.0029923054,0.013113869,0.011610219,0.0032473214,0.005701659,0.001972483],"category_scores_gemma":[0.12270652,0.0008276559,0.0012480286,0.0018217231,0.020740204,0.0056086616,0.008431679,0.0077982927,0.0006876355],"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":[0.00013332708,0.00024350127,0.00086459616,0.00030235547,0.00001752539,0.0015265521,0.9457401,0.00036327235,0.0014070536,0.021588827,0.007313683,0.020499269],"study_design_scores_gemma":[0.00005153036,0.00040812773,0.00079011533,0.001026375,0.000029647526,0.0012108402,0.76223665,0.0013400831,0.0040837787,0.008905352,0.21983245,0.00008501886],"about_ca_topic_score_codex":0.0025249778,"about_ca_topic_score_gemma":0.0032091194,"teacher_disagreement_score":0.06497761,"about_ca_system_score_codex":0.008557905,"about_ca_system_score_gemma":0.009568618,"threshold_uncertainty_score":0.34363854},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5934908,0.020679079,0.01010112,0.1443781,0.0012689909,0.00015678428,0.000069719,0.00003818257,0.22981724],"genre_scores_gemma":[0.9907183,0.0028176757,0.0013830279,0.0034228459,0.00012172591,0.000044632045,0.000008515324,0.000026929263,0.0014563322],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97209126,0.023330541,0.0005714811,0.0010587304,0.0015016894,0.0014462079],"domain_scores_gemma":[0.9618655,0.027319558,0.0027963808,0.0018952865,0.001710556,0.004412726],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02298079,0.0004454655,0.00084087974,0.002451148,0.015773801,0.017731348,0.0009823322,0.0025282719,0.004460331],"category_scores_gemma":[0.023704473,0.00052981824,0.00035413442,0.0032582702,0.030665353,0.012686612,0.018386964,0.006108394,0.00033549164],"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":[0.00006316436,0.000032629476,0.009695012,0.00032502232,0.000024517483,0.0010557829,0.87280554,0.000059905964,0.0007891165,0.09363628,0.0021671918,0.019345816],"study_design_scores_gemma":[0.000012567373,0.00006593442,0.008968227,0.0011655372,0.000020626212,0.00078965834,0.8943809,0.000061465726,0.0003969767,0.026313737,0.06778766,0.00003673998],"about_ca_topic_score_codex":0.005655225,"about_ca_topic_score_gemma":0.012758058,"teacher_disagreement_score":0.9770192,"about_ca_system_score_codex":0.0044034105,"about_ca_system_score_gemma":0.00777004,"threshold_uncertainty_score":0.12153548},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14069268,0.2171744,0.2139037,0.28454116,0.008625108,0.0017580839,0.0012290365,0.00056380586,0.13151208],"genre_scores_gemma":[0.9288931,0.013372257,0.040563304,0.0125349015,0.0022365672,0.0012660321,0.0002969689,0.00018817016,0.00064868113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.21329382,0.62209463,0.051167805,0.013633848,0.09583285,0.0039769993],"domain_scores_gemma":[0.071455926,0.8244242,0.04321363,0.024262654,0.034096293,0.002547249],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52377,0.00185709,0.0053121373,0.022469051,0.0056337076,0.025494363,0.0050307596,0.010169312,0.002633051],"category_scores_gemma":[0.8515333,0.0021686722,0.0037368683,0.014330476,0.046161134,0.036339577,0.009387719,0.010070787,0.0008635753],"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":[0.0021840748,0.0004163203,0.03317363,0.01643217,0.0063291183,0.0005519332,0.051958244,0.0034692585,0.00072628463,0.50113124,0.020996233,0.36263153],"study_design_scores_gemma":[0.0006303364,0.00044681778,0.012721209,0.018737458,0.0013638346,0.00044817402,0.014241929,0.0031861004,0.0016557575,0.91176003,0.03436797,0.00044039206],"about_ca_topic_score_codex":0.0046575675,"about_ca_topic_score_gemma":0.0051678387,"teacher_disagreement_score":0.47623003,"about_ca_system_score_codex":0.015915113,"about_ca_system_score_gemma":0.015994484,"threshold_uncertainty_score":0.58727646},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70113015,0.0020931605,0.009106846,0.0075357123,0.00010687286,0.001836099,0.0007506967,0.00021537048,0.2772251],"genre_scores_gemma":[0.96862566,0.0010777132,0.010018278,0.00019550993,0.000007574051,0.00016422126,0.00034318134,0.00001998094,0.019547783],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99325573,0.0012097422,0.00030393066,0.00028970416,0.0028492035,0.0020916427],"domain_scores_gemma":[0.98936146,0.0019699878,0.0011597732,0.00035035048,0.004599975,0.002558531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058957674,0.0004040385,0.00023464134,0.006318878,0.011506094,0.009293952,0.0014931102,0.0008684761,0.0045755296],"category_scores_gemma":[0.014300735,0.00040251113,0.00035955457,0.008276152,0.0032942726,0.001995434,0.0032511884,0.0013197215,0.00044997124],"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":[0.00023676635,0.00046099818,0.14599153,0.0007824214,0.000045828438,0.0021250497,0.08772332,0.010226079,0.003274221,0.22228709,0.029162548,0.49768424],"study_design_scores_gemma":[0.00005018169,0.00030153093,0.3081764,0.00073734985,0.00005956956,0.00055386557,0.20786326,0.008108796,0.0041933553,0.023212798,0.44645512,0.00028780953],"about_ca_topic_score_codex":0.9509011,"about_ca_topic_score_gemma":0.97384804,"teacher_disagreement_score":0.88316256,"about_ca_system_score_codex":0.116837434,"about_ca_system_score_gemma":0.3177309,"threshold_uncertainty_score":0.8477189},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068879807,0.0012782012,0.96084684,0.002315934,0.00049086503,0.0013641298,0.0003495731,0.0044641225,0.022002306],"genre_scores_gemma":[0.15555578,0.0015398321,0.824492,0.0013057012,0.0002902474,0.0022501145,0.0011863158,0.00066125934,0.012718793],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9544673,0.023594322,0.0038198046,0.003816957,0.013618068,0.00068361725],"domain_scores_gemma":[0.9213396,0.03896092,0.002110332,0.008005866,0.028655306,0.00092798524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03544516,0.0020374611,0.0022536917,0.0041971426,0.0020200538,0.010440213,0.0032380526,0.0035369615,0.015955491],"category_scores_gemma":[0.08173043,0.0012266238,0.0019410363,0.0031189243,0.002662705,0.0075640786,0.004141564,0.0030393258,0.0064575276],"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":[0.0013608611,0.00044655823,0.0057908096,0.004015818,0.0006808074,0.00065088854,0.005229815,0.025092669,0.019070227,0.09309808,0.03426096,0.8103025],"study_design_scores_gemma":[0.0005913211,0.0016475657,0.009913091,0.0042472803,0.0009792465,0.0014870747,0.0039430866,0.30025274,0.045677636,0.21873689,0.41192687,0.0005972772],"about_ca_topic_score_codex":0.006635101,"about_ca_topic_score_gemma":0.0057839304,"teacher_disagreement_score":0.03544516,"about_ca_system_score_codex":0.003663477,"about_ca_system_score_gemma":0.005417547,"threshold_uncertainty_score":0.18745422},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60641986,0.0047478876,0.09634733,0.04648876,0.0027803755,0.049442124,0.0077644163,0.0024001447,0.18360908],"genre_scores_gemma":[0.759698,0.0018797888,0.19277374,0.004639509,0.00041683982,0.022955054,0.0045583937,0.00014467131,0.012933985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8955538,0.076028034,0.005574121,0.0017527769,0.018155364,0.0029358012],"domain_scores_gemma":[0.88692164,0.045732357,0.0089025535,0.0043096845,0.04688205,0.007251687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12299204,0.00080230826,0.0004973251,0.0030543169,0.002339252,0.00451434,0.0023438928,0.0014635572,0.013644445],"category_scores_gemma":[0.14958797,0.00035459825,0.00075055566,0.0016645399,0.0008894861,0.002333509,0.0030184458,0.00130618,0.0024465607],"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":[0.0020083569,0.003320907,0.083973974,0.0016221894,0.0001734527,0.00013265778,0.004493016,0.01409093,0.0010598942,0.015361204,0.06970559,0.80405796],"study_design_scores_gemma":[0.0025359213,0.04801086,0.22355182,0.009811617,0.0012691674,0.00046140555,0.036719143,0.09450313,0.015049487,0.020879425,0.5465422,0.000665803],"about_ca_topic_score_codex":0.009974629,"about_ca_topic_score_gemma":0.01351142,"teacher_disagreement_score":0.12299204,"about_ca_system_score_codex":0.013469575,"about_ca_system_score_gemma":0.024758672,"threshold_uncertainty_score":0.65045184},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00061311416,0.8406866,0.004435097,0.089250244,0.0073125134,0.00045892812,0.0005885177,0.00011209949,0.056542926],"genre_scores_gemma":[0.026257182,0.8390501,0.017920861,0.07265397,0.003712862,0.0018389169,0.00079796027,0.000051376453,0.03771682],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9875465,0.0073003587,0.0012229823,0.0008280611,0.0025910384,0.0005111942],"domain_scores_gemma":[0.9901972,0.0059375484,0.0010603925,0.0003270648,0.002032224,0.000445669],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008466149,0.0013318717,0.0023046976,0.003432803,0.0022368694,0.006941336,0.002176643,0.006427606,0.034172338],"category_scores_gemma":[0.026075818,0.0008535026,0.0009366789,0.006949917,0.002095169,0.010525362,0.0033415123,0.0026258957,0.010877053],"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":[0.00013639093,0.00004655139,0.0009737335,0.033481255,0.00030033517,0.00039800297,0.001786676,0.000363041,0.00037037718,0.13808978,0.28519788,0.5388559],"study_design_scores_gemma":[0.00004467892,0.00003147977,0.0005920139,0.014638588,0.00008843997,0.00040163472,0.0013277767,0.00007387006,0.00010296777,0.029618442,0.9530605,0.000019495781],"about_ca_topic_score_codex":0.004759808,"about_ca_topic_score_gemma":0.0075379466,"teacher_disagreement_score":0.9915339,"about_ca_system_score_codex":0.003281245,"about_ca_system_score_gemma":0.009031739,"threshold_uncertainty_score":0.114317834},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93358403,0.0007700679,0.008717068,0.0015546078,0.00007924016,0.0005072744,0.00018720182,0.00006345067,0.05453714],"genre_scores_gemma":[0.9713902,0.0005121852,0.0053252536,0.00012298001,0.000019984513,0.00025874795,0.00015250676,0.000025511412,0.022192582],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914922,0.0030200183,0.00054846774,0.0007189081,0.0027626136,0.0014579291],"domain_scores_gemma":[0.96908396,0.015166944,0.0029456252,0.0015445112,0.0074721132,0.0037868056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010195563,0.0004733313,0.00041537735,0.0025444261,0.003191406,0.006464929,0.0010541219,0.0013093525,0.013760396],"category_scores_gemma":[0.034746267,0.00036876326,0.00057009317,0.0014624344,0.0029161922,0.0038351004,0.0042368206,0.0019121843,0.0022865064],"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":[0.0010812763,0.0011312681,0.24816382,0.0010620699,0.00010578713,0.0011974153,0.29450598,0.0016729528,0.011309148,0.034116086,0.0029811496,0.40267313],"study_design_scores_gemma":[0.00007857284,0.0016517156,0.60776764,0.00089153857,0.000117707736,0.0006296347,0.2742728,0.0022659698,0.015059383,0.013737652,0.08329697,0.00023037288],"about_ca_topic_score_codex":0.022292478,"about_ca_topic_score_gemma":0.033236958,"teacher_disagreement_score":0.022292478,"about_ca_system_score_codex":0.0064906306,"about_ca_system_score_gemma":0.010039584,"threshold_uncertainty_score":0.05391997},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2717613,0.10168471,0.0037596766,0.457207,0.0012416592,0.00021574095,0.0021631287,0.00027116295,0.16169567],"genre_scores_gemma":[0.9516801,0.02635349,0.0032630104,0.0048327325,0.0003279131,0.00006183894,0.00035975504,0.000027282525,0.013093971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99204284,0.0010645962,0.0003086818,0.00031938433,0.0038897237,0.0023748656],"domain_scores_gemma":[0.9794667,0.0031042832,0.0028223945,0.00047493287,0.009089166,0.0050425394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00645571,0.00025769763,0.00037139995,0.002113836,0.00676962,0.006110403,0.0012416992,0.0011119387,0.0023434667],"category_scores_gemma":[0.012720145,0.00026387154,0.0004345033,0.0060993657,0.0059825387,0.0026332177,0.0022734595,0.0014777249,0.0001571113],"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":[0.0003229046,0.00015442594,0.266992,0.0031377603,0.00011874636,0.0006014184,0.024598412,0.0029851082,0.0009698433,0.15345526,0.0756313,0.4710328],"study_design_scores_gemma":[0.000057479054,0.0001280707,0.55830985,0.001389566,0.00010623085,0.00019708564,0.020560922,0.0019242114,0.0005164368,0.016903209,0.39973903,0.00016800445],"about_ca_topic_score_codex":0.98922324,"about_ca_topic_score_gemma":0.9949352,"teacher_disagreement_score":0.8176763,"about_ca_system_score_codex":0.1823237,"about_ca_system_score_gemma":0.29503986,"threshold_uncertainty_score":0.94838864},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09221153,0.0024257305,0.6746214,0.073979154,0.0023231767,0.0013734351,0.00029965973,0.001126257,0.15163967],"genre_scores_gemma":[0.8616789,0.00096396933,0.12944146,0.0019664718,0.0006381311,0.000983318,0.00010931748,0.00023766857,0.003980828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5601743,0.36616987,0.00970088,0.005340076,0.054548074,0.0040667523],"domain_scores_gemma":[0.38365763,0.45590827,0.04896079,0.04298695,0.06314822,0.005338111],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2501988,0.0023667894,0.0014657624,0.009304908,0.005556213,0.021944625,0.0040563834,0.004386266,0.0055424636],"category_scores_gemma":[0.5074871,0.0006854335,0.0012228453,0.008964634,0.016085077,0.028039984,0.013885073,0.009504279,0.0011425066],"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":[0.0005304755,0.0007259019,0.04637861,0.0018470956,0.00046230372,0.0002591189,0.035092894,0.004942377,0.0017746462,0.46061566,0.017620811,0.4297501],"study_design_scores_gemma":[0.00016646976,0.00091365795,0.02325374,0.0035608304,0.00038853384,0.00041741438,0.033372905,0.045193527,0.015555608,0.80254936,0.074191846,0.0004361568],"about_ca_topic_score_codex":0.0018711194,"about_ca_topic_score_gemma":0.0014415523,"teacher_disagreement_score":0.74980116,"about_ca_system_score_codex":0.007487682,"about_ca_system_score_gemma":0.011894471,"threshold_uncertainty_score":0.9246384},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035001755,0.0099783605,0.8459606,0.04171013,0.0019100782,0.0070136534,0.00057338754,0.00054695597,0.057305127],"genre_scores_gemma":[0.4960785,0.00492896,0.47401094,0.0061350586,0.00077175203,0.014874641,0.0003934087,0.00030430112,0.002502428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.37876797,0.50916964,0.03893474,0.014017188,0.05560078,0.003509804],"domain_scores_gemma":[0.17696795,0.6743445,0.028556425,0.0347926,0.08355184,0.0017866805],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5230787,0.0009196325,0.0022120136,0.009978246,0.00463382,0.0126040485,0.0030769578,0.003434371,0.0037481454],"category_scores_gemma":[0.7133928,0.0014596483,0.0019053221,0.008945811,0.025984993,0.020003693,0.011337673,0.0049246317,0.00103038],"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":[0.00023622396,0.0001184614,0.014287521,0.010696747,0.00031217924,0.0004923119,0.24312748,0.0023332008,0.0021510366,0.5054209,0.010110419,0.21071342],"study_design_scores_gemma":[0.00011910643,0.0002626788,0.008595438,0.019179974,0.00019789329,0.0008221326,0.06879234,0.0062811384,0.0029099514,0.7753266,0.11718399,0.00032886481],"about_ca_topic_score_codex":0.004930538,"about_ca_topic_score_gemma":0.002878062,"teacher_disagreement_score":0.47692132,"about_ca_system_score_codex":0.010559781,"about_ca_system_score_gemma":0.023750622,"threshold_uncertainty_score":0.5881289},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29186472,0.017297368,0.02284439,0.25351968,0.0018090106,0.00065766554,0.00015689424,0.00016228452,0.41168794],"genre_scores_gemma":[0.9500912,0.0061226096,0.007885099,0.01813547,0.00017371812,0.00023458712,0.000046014873,0.00015355986,0.017157711],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.908236,0.061894394,0.0014596177,0.0027443592,0.011956174,0.013709389],"domain_scores_gemma":[0.89010143,0.06221988,0.004596379,0.0035909147,0.021321084,0.018170217],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08579384,0.0011013316,0.0006756525,0.004972318,0.03447238,0.027050817,0.0034956213,0.0047084196,0.0030439487],"category_scores_gemma":[0.06832769,0.00086032547,0.00054374145,0.006357224,0.0571436,0.009157219,0.017974347,0.014473765,0.0003183405],"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":[0.00005234224,0.00008282633,0.0061626635,0.00020825278,0.000016414251,0.0005389366,0.8322605,0.00017002803,0.0005497467,0.1222017,0.00799725,0.029759381],"study_design_scores_gemma":[0.000015351952,0.000055844288,0.0034803832,0.00077678513,0.000018781984,0.00013369534,0.82115954,0.00017445094,0.00035909,0.012281598,0.16145332,0.00009114813],"about_ca_topic_score_codex":0.51266587,"about_ca_topic_score_gemma":0.6741901,"teacher_disagreement_score":0.91420615,"about_ca_system_score_codex":0.07520182,"about_ca_system_score_gemma":0.15326296,"threshold_uncertainty_score":0.9804083},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99076545,0.0009411457,0.0013016863,0.0010427478,0.000051197585,0.00032113196,0.000040933937,0.000010742678,0.0055249515],"genre_scores_gemma":[0.99035585,0.0012421032,0.0047078133,0.00014873594,0.000019801842,0.000290008,0.000082545375,0.000006126263,0.0031469718],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9885056,0.0076662772,0.00050661527,0.00042496968,0.0018892748,0.001007202],"domain_scores_gemma":[0.9859692,0.0050640227,0.0021389637,0.0005140802,0.0036721425,0.0026416301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013666339,0.00043772793,0.00066032,0.0014030554,0.0027706968,0.0023835397,0.00087662425,0.0007985343,0.00470025],"category_scores_gemma":[0.023905825,0.00022249208,0.0005949649,0.001019974,0.0015910616,0.0012823597,0.0034526326,0.00094962603,0.00048514406],"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":[0.0025013904,0.0025821042,0.23506144,0.0016431662,0.00021708242,0.0010045335,0.14714865,0.0011891415,0.004328966,0.0028279019,0.0020325875,0.59946305],"study_design_scores_gemma":[0.00031199044,0.02014909,0.4961681,0.0022918205,0.0005776697,0.0014743226,0.42339844,0.0024660903,0.009269498,0.0024541188,0.04128912,0.00014982562],"about_ca_topic_score_codex":0.007793269,"about_ca_topic_score_gemma":0.020775888,"teacher_disagreement_score":0.013666339,"about_ca_system_score_codex":0.004608373,"about_ca_system_score_gemma":0.010004721,"threshold_uncertainty_score":0.0722754},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006770666,0.022126036,0.77834237,0.09402347,0.0032874558,0.03311828,0.00052798283,0.0007436331,0.06106008],"genre_scores_gemma":[0.14681081,0.012004738,0.7792578,0.014045605,0.0017634525,0.042219136,0.00023435084,0.0003157178,0.0033482965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.28081235,0.67067474,0.0132991485,0.0045767473,0.028929781,0.0017072217],"domain_scores_gemma":[0.41975188,0.49943382,0.013604388,0.02615441,0.031415455,0.009640151],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5263081,0.0028683178,0.007395701,0.014757517,0.0070838034,0.033904098,0.0062304437,0.009584855,0.006026469],"category_scores_gemma":[0.41776168,0.0019625598,0.0017464628,0.012779138,0.029059332,0.02630508,0.014769503,0.008867976,0.002117081],"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":[0.00049338536,0.0011358295,0.0019459625,0.016850824,0.00071295677,0.00036940878,0.026920857,0.0026453482,0.0011272392,0.65732926,0.034110337,0.2563586],"study_design_scores_gemma":[0.0011361741,0.0016657229,0.0014713552,0.025726765,0.0004642932,0.00046718627,0.040346093,0.006556222,0.0020236103,0.74358016,0.17628668,0.00027570996],"about_ca_topic_score_codex":0.001561854,"about_ca_topic_score_gemma":0.0020219185,"teacher_disagreement_score":0.5263081,"about_ca_system_score_codex":0.016029749,"about_ca_system_score_gemma":0.05274491,"threshold_uncertainty_score":0.5841465},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8509575,0.005380791,0.009064365,0.032166567,0.00018020523,0.00046882554,0.0005398823,0.00008437894,0.101157635],"genre_scores_gemma":[0.95581836,0.0025171372,0.0041173655,0.0017300296,0.00003159803,0.00025480147,0.00024235796,0.00003622027,0.035252042],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.978848,0.009182512,0.0010636065,0.0015317297,0.0061939443,0.003180276],"domain_scores_gemma":[0.8995534,0.038469326,0.0063289395,0.003705588,0.038503762,0.013439028],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027726196,0.00030738214,0.00060994376,0.003946325,0.01371343,0.009379418,0.0013907412,0.0017844755,0.010953128],"category_scores_gemma":[0.046908528,0.0005703208,0.0005016716,0.005345568,0.005555372,0.0034021905,0.0043848795,0.0027919062,0.0012641997],"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":[0.0004333442,0.0004735292,0.26602104,0.0013370165,0.00019789998,0.0006926356,0.39834112,0.0010542835,0.0067406576,0.065806136,0.017472552,0.24142984],"study_design_scores_gemma":[0.00004186978,0.000288277,0.5465612,0.001217393,0.00010714073,0.0001653613,0.25345793,0.0010066967,0.0026095682,0.0037467529,0.19061041,0.00018745389],"about_ca_topic_score_codex":0.7304434,"about_ca_topic_score_gemma":0.855333,"teacher_disagreement_score":0.9722738,"about_ca_system_score_codex":0.063488156,"about_ca_system_score_gemma":0.08217706,"threshold_uncertainty_score":0.54228806},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20631279,0.014836271,0.13977888,0.25621262,0.0009405166,0.0010021094,0.000094859344,0.00025319844,0.3805687],"genre_scores_gemma":[0.9842821,0.0013443906,0.007287067,0.0019704138,0.000099814344,0.00021379716,0.000011934911,0.000031604843,0.0047589475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.85881764,0.12278798,0.002088786,0.0020483728,0.0074142413,0.0068429573],"domain_scores_gemma":[0.90766597,0.069103055,0.0028513754,0.0021704535,0.010505226,0.0077039427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08030852,0.0006304934,0.0007336159,0.0046968763,0.010917285,0.023937969,0.00335233,0.005304297,0.0042674886],"category_scores_gemma":[0.044608302,0.0008165097,0.00070990814,0.0021693108,0.050920192,0.012504658,0.018927027,0.009807965,0.00032195242],"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":[0.000056279634,0.00030508862,0.0034651724,0.0005318354,0.00002888897,0.0005954774,0.18856013,0.0030968082,0.00039379267,0.7692883,0.0057323445,0.027945945],"study_design_scores_gemma":[0.000106905914,0.00020816093,0.0039957464,0.0021804138,0.000041600095,0.00051067275,0.44362208,0.008921295,0.0032201908,0.32346386,0.21356863,0.00016038946],"about_ca_topic_score_codex":0.019322168,"about_ca_topic_score_gemma":0.016837154,"teacher_disagreement_score":0.98067784,"about_ca_system_score_codex":0.036547028,"about_ca_system_score_gemma":0.049982563,"threshold_uncertainty_score":0.42471713},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005944031,0.045866482,0.42661086,0.49001426,0.00454776,0.0030316361,0.00023837354,0.00040004795,0.023346554],"genre_scores_gemma":[0.22087756,0.019469554,0.688532,0.056789517,0.002238032,0.009718457,0.00028558576,0.00035721943,0.00173209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.38596827,0.47650623,0.0368845,0.012077136,0.084698655,0.003865279],"domain_scores_gemma":[0.093531035,0.81195825,0.012566281,0.026263174,0.052769825,0.0029114229],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7093204,0.003338019,0.011049779,0.018128056,0.006242353,0.034778666,0.014798819,0.020857604,0.005633152],"category_scores_gemma":[0.755809,0.003597219,0.005564645,0.010140999,0.053368337,0.050387163,0.019303992,0.041862708,0.0016817125],"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":[0.0002916491,0.0003736715,0.0014694607,0.011839301,0.00080756156,0.00014119702,0.008957516,0.003707259,0.00021478682,0.82492435,0.0088014575,0.13847171],"study_design_scores_gemma":[0.00048433206,0.00030816876,0.00048708235,0.024020977,0.00029787613,0.000072758114,0.0034087112,0.008307198,0.00081186666,0.93023306,0.03142024,0.00014783336],"about_ca_topic_score_codex":0.005641839,"about_ca_topic_score_gemma":0.0038871567,"teacher_disagreement_score":0.29067957,"about_ca_system_score_codex":0.029953213,"about_ca_system_score_gemma":0.048209228,"threshold_uncertainty_score":0.3584597},"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":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024867669,0.045052726,0.35125214,0.2843098,0.0066535403,0.00048699457,0.00023469534,0.0003789619,0.2867635],"genre_scores_gemma":[0.7748417,0.021747442,0.16936159,0.019254979,0.0034803355,0.001592961,0.0000974293,0.00039471738,0.009228777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86449695,0.12069848,0.003295177,0.002102846,0.008175475,0.0012310651],"domain_scores_gemma":[0.8759598,0.106104076,0.0040124576,0.008290613,0.0042278855,0.0014052661],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.086740136,0.0015006871,0.0017626993,0.00729964,0.005929714,0.020701442,0.0025004141,0.00878206,0.0030820903],"category_scores_gemma":[0.09209235,0.0011135356,0.0013023887,0.0064436165,0.1347357,0.03665569,0.009585054,0.010332077,0.00076708954],"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":[0.000018132334,0.000008868002,0.00005191091,0.00016135884,0.000007831719,0.00007070784,0.01258163,0.00011091756,0.00008771548,0.9831571,0.0009751556,0.0027685948],"study_design_scores_gemma":[0.0000563368,0.000046699723,0.00015425266,0.00075459684,0.000018849561,0.00033352786,0.0101954695,0.0006344917,0.00023734765,0.9116407,0.07589392,0.000033668446],"about_ca_topic_score_codex":0.0016886974,"about_ca_topic_score_gemma":0.0010021538,"teacher_disagreement_score":0.91325986,"about_ca_system_score_codex":0.007114884,"about_ca_system_score_gemma":0.0092093395,"threshold_uncertainty_score":0.45873117},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029045137,0.05025032,0.0026713717,0.823109,0.110260144,0.00013881625,0.00028983795,0.00031338746,0.012676691],"genre_scores_gemma":[0.03794142,0.1477574,0.023652343,0.4909506,0.24527784,0.0021024884,0.001525805,0.0027480132,0.04804404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.69302815,0.1556561,0.03690808,0.015336194,0.09137211,0.007699346],"domain_scores_gemma":[0.4010722,0.1765282,0.042854734,0.03460495,0.29006216,0.054877836],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25717202,0.0031441269,0.0056287334,0.020267436,0.007011245,0.067759365,0.0070028203,0.019856399,0.02409178],"category_scores_gemma":[0.6760027,0.0016746209,0.0025320854,0.017888973,0.024903957,0.05266767,0.0103160385,0.027440935,0.035622876],"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":[0.000098828685,0.000029254908,0.0013480701,0.0013691339,0.00012490353,0.00004172929,0.0010749223,0.000102917096,0.00010336869,0.03394592,0.86781436,0.093946524],"study_design_scores_gemma":[0.00005464465,0.00008973195,0.0019151433,0.0076038553,0.00008026653,0.00012654111,0.0022672259,0.00026451494,0.00013200287,0.04547452,0.9418602,0.00013144911],"about_ca_topic_score_codex":0.008272834,"about_ca_topic_score_gemma":0.0062036556,"teacher_disagreement_score":0.742828,"about_ca_system_score_codex":0.020423507,"about_ca_system_score_gemma":0.026461273,"threshold_uncertainty_score":0.91603917},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6364671,0.006849935,0.13644233,0.090509325,0.00060764374,0.018154472,0.0007895393,0.0009102747,0.10926935],"genre_scores_gemma":[0.908693,0.0012121486,0.078648336,0.002547321,0.000041184154,0.0074020918,0.0001572403,0.0001430015,0.0011557637],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6458943,0.30763093,0.0060295663,0.005089664,0.031259075,0.004096499],"domain_scores_gemma":[0.6565549,0.2525021,0.011980007,0.020792916,0.048973493,0.009196609],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22956291,0.0005588687,0.00094450294,0.001986407,0.00526387,0.012742716,0.0058926716,0.0014220983,0.002268333],"category_scores_gemma":[0.28265795,0.0008637753,0.0007102546,0.0022112792,0.010797339,0.004714685,0.0055228444,0.0029418964,0.0003014386],"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":[0.0018839114,0.005119499,0.07469917,0.01056891,0.00091654505,0.00044980898,0.10678534,0.03687728,0.0015715418,0.1323151,0.024259314,0.60455364],"study_design_scores_gemma":[0.006060078,0.014283016,0.22509368,0.033911496,0.0008795446,0.0009050409,0.2479905,0.0912575,0.0061897165,0.12326989,0.24895123,0.00120825],"about_ca_topic_score_codex":0.1644582,"about_ca_topic_score_gemma":0.2655474,"teacher_disagreement_score":0.94966084,"about_ca_system_score_codex":0.050339136,"about_ca_system_score_gemma":0.114925206,"threshold_uncertainty_score":0.9500861},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73672324,0.001455828,0.060722508,0.015084211,0.00022562547,0.004143653,0.00015620483,0.000093392366,0.18139526],"genre_scores_gemma":[0.97966343,0.00029764068,0.014433541,0.00043717652,0.00002559697,0.0009946594,0.000052832944,0.00002447365,0.0040706373],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.811268,0.16431403,0.0023836722,0.0033514337,0.014267527,0.0044154627],"domain_scores_gemma":[0.73410904,0.22736537,0.006223354,0.0075475345,0.020354155,0.004400579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1281474,0.00057276705,0.00091949845,0.0029977232,0.014798708,0.012610448,0.003649987,0.0031680942,0.005001995],"category_scores_gemma":[0.1208099,0.0006323969,0.00049386243,0.0031079473,0.018196315,0.0069587394,0.012129507,0.002639307,0.00038330824],"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":[0.000563303,0.0022359344,0.013564428,0.001417874,0.00008074058,0.0022112099,0.6709596,0.0038907074,0.0017507015,0.10086173,0.008490657,0.19397314],"study_design_scores_gemma":[0.0002673776,0.0011507781,0.00992014,0.0011645132,0.00003988562,0.00045036725,0.81805193,0.0074051144,0.0022344124,0.07507968,0.08410201,0.00013386557],"about_ca_topic_score_codex":0.01693185,"about_ca_topic_score_gemma":0.024563346,"teacher_disagreement_score":0.1281474,"about_ca_system_score_codex":0.017153928,"about_ca_system_score_gemma":0.021406904,"threshold_uncertainty_score":0.67771626},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23732586,0.46151116,0.0018953676,0.115538135,0.001081892,0.0006683714,0.003321668,0.000055917713,0.1786015],"genre_scores_gemma":[0.81390613,0.16537854,0.002100633,0.01419289,0.00019872439,0.00022129047,0.00070174824,0.00004345413,0.0032566176],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9583017,0.011099839,0.0027943193,0.0014597138,0.02204976,0.0042947563],"domain_scores_gemma":[0.7452007,0.14678973,0.011618984,0.0032406761,0.08407771,0.009072204],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037186857,0.0004784081,0.0012257122,0.0058484687,0.005859644,0.0064701685,0.002112034,0.0018461788,0.0046423324],"category_scores_gemma":[0.13058266,0.00052310264,0.00057663536,0.01895968,0.005109488,0.0020552217,0.0026503305,0.0026039246,0.00022043144],"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":[0.0029811095,0.0008668469,0.14526775,0.039717123,0.00086886674,0.0011062631,0.042270586,0.0029857075,0.0006002257,0.07128014,0.06979103,0.62226427],"study_design_scores_gemma":[0.0008609173,0.0007447791,0.50244564,0.09504126,0.0014698041,0.00070634513,0.06819153,0.0014668929,0.0017488212,0.0080270525,0.31896695,0.000330018],"about_ca_topic_score_codex":0.98161936,"about_ca_topic_score_gemma":0.99026525,"teacher_disagreement_score":0.96281314,"about_ca_system_score_codex":0.14297064,"about_ca_system_score_gemma":0.26855624,"threshold_uncertainty_score":0.99403256},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6525841,0.011675687,0.09765738,0.032571636,0.0013741585,0.00260717,0.0017485217,0.0009733321,0.1988081],"genre_scores_gemma":[0.980208,0.00082292024,0.015289698,0.001068897,0.00023652686,0.00045796228,0.00025161804,0.00020106383,0.0014634359],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.551963,0.3362945,0.02914376,0.0058917915,0.071886055,0.0048209587],"domain_scores_gemma":[0.11367509,0.68174887,0.04339569,0.05258529,0.104721405,0.0038737147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3834028,0.0009292508,0.0018022234,0.013832001,0.003197204,0.011562012,0.0029401125,0.0024515209,0.0033419158],"category_scores_gemma":[0.7234866,0.0008613089,0.001973193,0.0085854605,0.00728339,0.008902586,0.006318773,0.0030608869,0.000520031],"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":[0.00295326,0.0009556173,0.28968522,0.003883431,0.0015061394,0.0002614162,0.037338924,0.0024057196,0.0010022159,0.036742862,0.020170651,0.6030945],"study_design_scores_gemma":[0.001487851,0.0042680893,0.56677514,0.039346263,0.005929078,0.0018989712,0.080048196,0.074873835,0.029022617,0.10538934,0.089570895,0.001389729],"about_ca_topic_score_codex":0.0054610227,"about_ca_topic_score_gemma":0.0055771745,"teacher_disagreement_score":0.3834028,"about_ca_system_score_codex":0.006681332,"about_ca_system_score_gemma":0.010994235,"threshold_uncertainty_score":0.7603741},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6436949,0.008957406,0.12297208,0.046422604,0.0034366352,0.015575558,0.0011125193,0.00035729748,0.15747094],"genre_scores_gemma":[0.92392623,0.0015938804,0.04802833,0.002613299,0.00022254507,0.015735094,0.00016444284,0.000080947815,0.0076351627],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.86103916,0.12113568,0.0037870381,0.0037627418,0.007663047,0.0026122364],"domain_scores_gemma":[0.9282714,0.050084744,0.0042427434,0.0068745753,0.0067278673,0.0037986704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0540735,0.0010414892,0.0016299784,0.0015428793,0.004231841,0.005447032,0.0026168434,0.0028490585,0.012869114],"category_scores_gemma":[0.102593064,0.000683069,0.001860565,0.0018237941,0.0059849494,0.0052026045,0.010439838,0.0040866937,0.0013652107],"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":[0.0111338245,0.0052557564,0.016370758,0.013134868,0.0014002216,0.00058491767,0.10900555,0.0048760157,0.0021413628,0.14957346,0.017295856,0.66922736],"study_design_scores_gemma":[0.012508045,0.08188849,0.07201072,0.01875442,0.0031544098,0.0015545388,0.2149304,0.00945082,0.012982813,0.2316188,0.3405472,0.00059939525],"about_ca_topic_score_codex":0.0030414115,"about_ca_topic_score_gemma":0.0038958404,"teacher_disagreement_score":0.0540735,"about_ca_system_score_codex":0.0051063164,"about_ca_system_score_gemma":0.01411254,"threshold_uncertainty_score":0.2859714},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00711156,0.00020321546,0.9453391,0.000963445,0.00031175173,0.0059829475,0.00063282053,0.0005342365,0.038920928],"genre_scores_gemma":[0.061658025,0.00017076069,0.91283685,0.0002512664,0.000063313615,0.016809078,0.00044335081,0.00032251983,0.007444848],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8707089,0.09604144,0.008519234,0.009061929,0.014349238,0.0013192858],"domain_scores_gemma":[0.8829531,0.06641935,0.004977448,0.01471382,0.0296535,0.0012827228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069573626,0.0014923605,0.0012226688,0.008029932,0.0039070887,0.010311433,0.002786169,0.0017814755,0.023193695],"category_scores_gemma":[0.15073581,0.0010192241,0.0015083776,0.0068026553,0.0041712266,0.0080764,0.0072990702,0.0034116697,0.003351172],"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":[0.00038477714,0.00025149735,0.0029141265,0.0016551182,0.00014594175,0.00021036727,0.0267929,0.004322817,0.0033873164,0.43147826,0.015792899,0.5126641],"study_design_scores_gemma":[0.0004987163,0.0008429159,0.0054448624,0.0024429413,0.00021989952,0.00082820404,0.024840578,0.07299381,0.009699829,0.3805006,0.50134367,0.0003438703],"about_ca_topic_score_codex":0.0027998271,"about_ca_topic_score_gemma":0.0033972354,"teacher_disagreement_score":0.069573626,"about_ca_system_score_codex":0.008372096,"about_ca_system_score_gemma":0.010421578,"threshold_uncertainty_score":0.3679449},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931623,0.00007658886,0.0015122021,0.0014918608,0.000007702669,0.000108525506,0.000013151507,0.000008089985,0.0036196013],"genre_scores_gemma":[0.99937075,0.000018045965,0.0003618797,0.00009866703,0.000003313223,0.000040167863,0.00000547169,0.0000024881745,0.00009915735],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.92928785,0.05771068,0.0026886356,0.0020549651,0.0040384494,0.004219407],"domain_scores_gemma":[0.61209494,0.2910415,0.059386615,0.012916729,0.0130831525,0.0114771295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07467737,0.00024680447,0.00038483573,0.0021193912,0.0037729375,0.004325684,0.0011591541,0.0016693907,0.0026617884],"category_scores_gemma":[0.2637075,0.00037993325,0.0005195259,0.0014104036,0.0044095605,0.0031199637,0.003627358,0.00273629,0.00019543138],"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":[0.00051833433,0.000787188,0.89938945,0.00013714506,0.00019172466,0.00037263686,0.058240205,0.0009266774,0.0006921054,0.0037934647,0.00071097765,0.03424011],"study_design_scores_gemma":[0.00007919337,0.0010500943,0.8421735,0.00028839306,0.00010894916,0.0005362863,0.13679917,0.005676328,0.0011791616,0.0073021576,0.0047179717,0.000088800196],"about_ca_topic_score_codex":0.0041796234,"about_ca_topic_score_gemma":0.0057636914,"teacher_disagreement_score":0.07467737,"about_ca_system_score_codex":0.003641659,"about_ca_system_score_gemma":0.0055066384,"threshold_uncertainty_score":0.39493638},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018143919,0.9574817,0.001407063,0.01526682,0.010181812,0.00012650719,0.0005481725,0.00011570035,0.014690858],"genre_scores_gemma":[0.0009987593,0.9487721,0.0031627903,0.0063074245,0.003040789,0.00019650106,0.0008919328,0.000097497614,0.03653238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827504,0.00028219345,0.00017155526,0.00018505179,0.0010126429,0.00007356241],"domain_scores_gemma":[0.994306,0.0027985624,0.0003914259,0.000104653795,0.0021589037,0.00024043565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020897146,0.0014941222,0.0026048534,0.0065272073,0.0008944149,0.003272995,0.0017481104,0.0019950077,0.031916354],"category_scores_gemma":[0.007034331,0.00084872183,0.0009098892,0.010659463,0.0010829257,0.00391187,0.0013154516,0.0034838512,0.027830997],"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":[0.000017291926,0.000020723199,0.00008271078,0.0033813552,0.000021982152,0.000051704224,0.00012971209,0.00007344125,0.00011909614,0.0010638942,0.77711755,0.21792044],"study_design_scores_gemma":[0.000007188517,0.000016301563,0.00040299783,0.0040757116,0.000017396951,0.0003004472,0.00009233563,0.000029753293,0.000056809018,0.0008383919,0.99414885,0.000013855609],"about_ca_topic_score_codex":0.0063806735,"about_ca_topic_score_gemma":0.014803054,"teacher_disagreement_score":0.031916354,"about_ca_system_score_codex":0.0020956905,"about_ca_system_score_gemma":0.0049035978,"threshold_uncertainty_score":0.10677081},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009599631,0.0007347889,0.00010250319,0.9828584,0.015699562,0.00001558989,0.000066122484,0.000020300577,0.00040686585],"genre_scores_gemma":[0.0009894534,0.00042537702,0.00031655893,0.9771262,0.020300189,0.000046355377,0.000022021562,0.000015829726,0.0007579868],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95547915,0.019779602,0.006987761,0.0037456332,0.011909764,0.0020980204],"domain_scores_gemma":[0.77961975,0.16489291,0.008338055,0.003651224,0.0367003,0.0067978175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03900968,0.0017432169,0.0037375216,0.0024547111,0.006770155,0.00575305,0.008166972,0.10952678,0.0066194395],"category_scores_gemma":[0.21366759,0.0019043167,0.0028605966,0.0031539553,0.0077583995,0.008566232,0.0027037517,0.07755043,0.011064874],"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":[0.00007516603,0.000016233467,0.00021337588,0.00017795064,0.000021596696,0.000436551,0.00025746538,0.0000424119,0.00010095738,0.0017328562,0.992808,0.0041174195],"study_design_scores_gemma":[0.00030152008,0.000127672,0.0014317724,0.0023970017,0.00013396867,0.0025368778,0.0010717795,0.0009239079,0.00059087685,0.018185293,0.9721051,0.00019420279],"about_ca_topic_score_codex":0.013501984,"about_ca_topic_score_gemma":0.015480317,"teacher_disagreement_score":0.9609903,"about_ca_system_score_codex":0.011711672,"about_ca_system_score_gemma":0.013173507,"threshold_uncertainty_score":0.20630533},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045459915,0.007083567,0.7290207,0.0051811435,0.0016688522,0.012133917,0.0131834075,0.0053670397,0.18090151],"genre_scores_gemma":[0.1731644,0.0045206062,0.73979175,0.0006984465,0.0004180357,0.016028684,0.006151681,0.001698301,0.057528187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8661551,0.0675054,0.015865598,0.00780047,0.04088766,0.0017858868],"domain_scores_gemma":[0.75541943,0.11300481,0.011851468,0.030251905,0.08786011,0.0016122712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08089267,0.0018661007,0.0019785743,0.017958403,0.003681981,0.01997836,0.003119636,0.001979581,0.027349928],"category_scores_gemma":[0.20209576,0.001202469,0.001768201,0.01850552,0.0039199833,0.0075404113,0.004045673,0.0027336485,0.0069649727],"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":[0.0005673489,0.00034358475,0.00987388,0.0073957443,0.00032049208,0.00021798615,0.021788225,0.0041032867,0.0036890719,0.09301552,0.03284458,0.8258403],"study_design_scores_gemma":[0.00035128003,0.00066254876,0.029779496,0.011206552,0.0006072221,0.00041642474,0.020094834,0.018508157,0.025071794,0.06572944,0.8270133,0.00055894745],"about_ca_topic_score_codex":0.021123812,"about_ca_topic_score_gemma":0.021428226,"teacher_disagreement_score":0.08089267,"about_ca_system_score_codex":0.009480258,"about_ca_system_score_gemma":0.020115914,"threshold_uncertainty_score":0.42780644},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45781884,0.0037175312,0.25051436,0.117419235,0.00050225604,0.000482949,0.000058684036,0.00007466116,0.16941154],"genre_scores_gemma":[0.97863436,0.00050417753,0.018015878,0.0009793446,0.000042314387,0.00016121045,0.000010218416,0.000023775367,0.0016286952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9528259,0.039721906,0.00097566465,0.0014885879,0.0035168421,0.0014710595],"domain_scores_gemma":[0.94787633,0.041101564,0.0032911284,0.0031907167,0.0030439938,0.0014962557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052211422,0.00050854974,0.0007294369,0.0044842553,0.009204794,0.018042248,0.0019164974,0.0029911604,0.0018266592],"category_scores_gemma":[0.044733115,0.00042611078,0.0005563285,0.0024981997,0.0886293,0.014129985,0.013440681,0.006333944,0.00022039485],"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":[0.000024686191,0.000044325694,0.0010771565,0.00009656724,0.000010406609,0.00009525397,0.16019858,0.00042738748,0.00029310753,0.82691044,0.00038853113,0.010433511],"study_design_scores_gemma":[0.000020432924,0.000047062127,0.0008746855,0.00029564401,0.000012180095,0.00010604057,0.12827943,0.0024329545,0.00064431323,0.8498511,0.017404644,0.000031467433],"about_ca_topic_score_codex":0.0038093333,"about_ca_topic_score_gemma":0.004137819,"teacher_disagreement_score":0.052211422,"about_ca_system_score_codex":0.010698879,"about_ca_system_score_gemma":0.01796717,"threshold_uncertainty_score":0.2761237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007884784,0.00021425422,0.000045946603,0.9906653,0.008318603,0.0000068521017,0.000017842696,0.000007062151,0.0006453513],"genre_scores_gemma":[0.0006061511,0.000097349875,0.000109035216,0.98963124,0.008305905,0.000027165976,0.0000054223397,0.000010879906,0.0012069893],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9569931,0.017703358,0.0037809813,0.005117036,0.0116046555,0.0048008235],"domain_scores_gemma":[0.826029,0.13035817,0.006179223,0.003108543,0.020245682,0.014079358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041774224,0.001362134,0.003928529,0.0023826961,0.016948646,0.012282128,0.009530945,0.18186386,0.0144822765],"category_scores_gemma":[0.16857752,0.0024113227,0.0037077935,0.0026126949,0.015924951,0.011050076,0.007677778,0.14489506,0.008974713],"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":[0.000048510155,0.000022266257,0.00020473346,0.00010654952,0.000019764624,0.00036105447,0.00052692066,0.000044636836,0.000075810356,0.0049537653,0.990647,0.0029888437],"study_design_scores_gemma":[0.0002733095,0.000065759574,0.0011902938,0.0017288913,0.00012682853,0.00077821885,0.0034708953,0.0006398744,0.00033316037,0.03436756,0.9568009,0.00022426898],"about_ca_topic_score_codex":0.045822956,"about_ca_topic_score_gemma":0.084471755,"teacher_disagreement_score":0.18186386,"about_ca_system_score_codex":0.018417977,"about_ca_system_score_gemma":0.036314428,"threshold_uncertainty_score":0.22092587},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795306,0.0014494183,0.0013010442,0.0040096375,0.00009468345,0.00019597082,0.00021236716,0.000030933134,0.013175324],"genre_scores_gemma":[0.9729739,0.0013559469,0.0025378054,0.0006236094,0.000029025849,0.0002941364,0.00024340735,0.000018937297,0.02192328],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966839,0.000918601,0.00013197544,0.00019147963,0.0012129941,0.00086109526],"domain_scores_gemma":[0.98224026,0.00361704,0.0016023011,0.000375886,0.009082213,0.003082227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064588245,0.00039877513,0.0004077717,0.0015044679,0.004324384,0.002744945,0.0009304287,0.00073737616,0.0042177546],"category_scores_gemma":[0.011595777,0.00024611127,0.00033477324,0.0018967387,0.0018066475,0.00094015844,0.0016323342,0.0015233452,0.0006106828],"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":[0.00031584577,0.00063378934,0.49983507,0.0007004612,0.000083993036,0.00050880434,0.21059912,0.0005950097,0.0046374705,0.0018705402,0.012584053,0.26763588],"study_design_scores_gemma":[0.000011973119,0.0003917295,0.87142,0.0003291233,0.000022911161,0.00009977223,0.100937404,0.00036428092,0.0012906459,0.00019100183,0.02485647,0.00008476286],"about_ca_topic_score_codex":0.80845994,"about_ca_topic_score_gemma":0.9187544,"teacher_disagreement_score":0.19154006,"about_ca_system_score_codex":0.01839317,"about_ca_system_score_gemma":0.030854387,"threshold_uncertainty_score":0.3853361},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9763222,0.0007361619,0.0011072345,0.01373042,0.000109032146,0.00027352342,0.00009195483,0.000031426483,0.00759808],"genre_scores_gemma":[0.9900712,0.00066518004,0.0015393281,0.0012610403,0.00004102311,0.0002635822,0.00006769001,0.000012952543,0.006078],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9806096,0.012367536,0.0008942824,0.0006754297,0.0027577155,0.0026954443],"domain_scores_gemma":[0.89962643,0.045737863,0.009117312,0.0029660077,0.014820849,0.027731458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.049801983,0.00025787903,0.00040645606,0.0016984022,0.0061979573,0.0050887857,0.0009381312,0.001325182,0.007922171],"category_scores_gemma":[0.069157794,0.0004132588,0.0005477309,0.0008698435,0.00303747,0.002163592,0.0046230885,0.0022766527,0.0007785551],"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":[0.00048831484,0.00082156307,0.51157224,0.0004519487,0.00008307097,0.0006823564,0.33286998,0.00036477053,0.002463924,0.0075176666,0.00928918,0.13339505],"study_design_scores_gemma":[0.00007655413,0.0015687208,0.5196617,0.0007463688,0.000043455562,0.0004908601,0.40072277,0.0006757074,0.00094395754,0.0017552678,0.07317923,0.00013537404],"about_ca_topic_score_codex":0.050861035,"about_ca_topic_score_gemma":0.05228929,"teacher_disagreement_score":0.9940256,"about_ca_system_score_codex":0.0059744087,"about_ca_system_score_gemma":0.028159197,"threshold_uncertainty_score":0.26338124},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99469817,0.0001394873,0.00024976768,0.0017717348,0.000113688235,0.00014220345,0.000011463581,0.000014169491,0.0028592127],"genre_scores_gemma":[0.99363744,0.00024862296,0.0013150236,0.0003862893,0.000047404978,0.00009989256,0.000020335827,0.000008127836,0.0042368285],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99638915,0.0014125886,0.00008862684,0.00024332956,0.00057293737,0.0012934103],"domain_scores_gemma":[0.98186815,0.0008197921,0.00038432996,0.00023883945,0.0009084029,0.015780402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004956981,0.00030587253,0.00029667636,0.00044269484,0.0058639986,0.0020233325,0.0017771992,0.0011407547,0.005863423],"category_scores_gemma":[0.008149181,0.00042507745,0.0002811859,0.0002643031,0.0011972415,0.0012863973,0.0060286317,0.0022232526,0.0006203224],"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":[0.0014490212,0.072896466,0.27631134,0.00024394388,0.000067313995,0.0056860363,0.08038676,0.00069649395,0.0052988566,0.0017518876,0.018576743,0.5366352],"study_design_scores_gemma":[0.0012536112,0.037333786,0.42696103,0.0007995712,0.000163294,0.0095593855,0.4503248,0.004257328,0.0073244185,0.00283686,0.05894326,0.00024262878],"about_ca_topic_score_codex":0.008995923,"about_ca_topic_score_gemma":0.047463015,"teacher_disagreement_score":0.008995923,"about_ca_system_score_codex":0.0026056601,"about_ca_system_score_gemma":0.013345155,"threshold_uncertainty_score":0.026215315},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012402756,0.004850009,0.9496247,0.006718708,0.0015418346,0.011315406,0.00037695057,0.00071394164,0.012455627],"genre_scores_gemma":[0.027472502,0.0024026434,0.950711,0.0009454374,0.00020454064,0.015869884,0.00006682169,0.00018774287,0.0021394044],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8411312,0.14220694,0.004983342,0.0029893622,0.007964953,0.0007241263],"domain_scores_gemma":[0.8252816,0.15203017,0.004821182,0.005938877,0.01058796,0.0013401352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.088304564,0.001724789,0.001100222,0.003935598,0.0046923175,0.004782284,0.0023010776,0.0022102946,0.004492874],"category_scores_gemma":[0.091485016,0.0015274835,0.0010570276,0.00443014,0.011086115,0.004570314,0.0047138077,0.0044420976,0.0014795617],"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":[0.00042797285,0.00048463405,0.001815286,0.0091669485,0.000099097786,0.00055854284,0.3676323,0.001730606,0.017239368,0.095911756,0.014641626,0.4902919],"study_design_scores_gemma":[0.0005715394,0.0016597837,0.0038491683,0.018270602,0.00014141237,0.0029376491,0.11929049,0.008730753,0.023085227,0.23116897,0.58938664,0.0009077244],"about_ca_topic_score_codex":0.0016741977,"about_ca_topic_score_gemma":0.0032225165,"teacher_disagreement_score":0.088304564,"about_ca_system_score_codex":0.0036202334,"about_ca_system_score_gemma":0.0054339073,"threshold_uncertainty_score":0.46700478},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073106296,0.028242817,0.005920232,0.9071005,0.016135398,0.00005427205,0.000052984717,0.00008391891,0.041678794],"genre_scores_gemma":[0.13513982,0.15542313,0.07003165,0.38557193,0.06253102,0.0009056284,0.00060474535,0.0004566179,0.18933542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94402486,0.03095425,0.0026124127,0.0017709759,0.017788427,0.002849032],"domain_scores_gemma":[0.8367263,0.065120935,0.0059061763,0.0054267035,0.063339144,0.023480782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08235093,0.00045984806,0.00077961787,0.0027566655,0.0036921129,0.017418401,0.0014114253,0.007814776,0.009785045],"category_scores_gemma":[0.083763644,0.0004867261,0.00075231545,0.0024682917,0.00592852,0.009478055,0.0057261786,0.015417405,0.0027541642],"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":[0.00005967045,0.0001367935,0.0014560191,0.00028822743,0.000017420558,0.00006274784,0.0005736451,0.00026053638,0.00020686488,0.2130001,0.6665818,0.11735629],"study_design_scores_gemma":[0.000017629036,0.000039429277,0.0009895654,0.00063043,0.000009932887,0.00006570239,0.0006068162,0.00039269918,0.00012245114,0.03485003,0.9622445,0.0000307763],"about_ca_topic_score_codex":0.007620287,"about_ca_topic_score_gemma":0.013074901,"teacher_disagreement_score":0.08235093,"about_ca_system_score_codex":0.010287704,"about_ca_system_score_gemma":0.05143477,"threshold_uncertainty_score":0.43551856},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7882025,0.002231623,0.028248938,0.018086502,0.00011304784,0.0006938156,0.00045769126,0.00026869038,0.16169725],"genre_scores_gemma":[0.9922545,0.00018253637,0.002622929,0.00012925954,0.0000075554103,0.00006499628,0.000047936363,0.000020736194,0.0046694125],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97088057,0.016108764,0.0011857402,0.0016228011,0.0075884587,0.0026137198],"domain_scores_gemma":[0.9170936,0.031808224,0.007218821,0.003119481,0.037440933,0.0033190255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023535332,0.00052657444,0.0005646427,0.004034071,0.008679768,0.012753825,0.0011260535,0.0010266429,0.003699195],"category_scores_gemma":[0.050010007,0.00047905647,0.0004841709,0.0053510214,0.011329922,0.003502881,0.0037693044,0.002029029,0.00024330383],"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":[0.00027136935,0.00015620838,0.22452381,0.0009802283,0.00031389206,0.0007953357,0.37353277,0.0092446115,0.0034332955,0.15995055,0.007446525,0.21935138],"study_design_scores_gemma":[0.000052713232,0.00039598774,0.5925986,0.0011766851,0.00023901975,0.00017634164,0.24611282,0.01124145,0.002423296,0.019332837,0.12594782,0.00030237588],"about_ca_topic_score_codex":0.8530528,"about_ca_topic_score_gemma":0.83286077,"teacher_disagreement_score":0.9028565,"about_ca_system_score_codex":0.09714349,"about_ca_system_score_gemma":0.086317725,"threshold_uncertainty_score":0.7048287},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4672841,0.015256994,0.09375114,0.02089859,0.00038974013,0.00059990183,0.0001636035,0.00020322093,0.4014527],"genre_scores_gemma":[0.98567086,0.002346379,0.007278406,0.00054520956,0.00008606803,0.000296269,0.000026716592,0.000045078345,0.0037050121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91364133,0.059187386,0.0028884315,0.0048589613,0.016816143,0.0026077093],"domain_scores_gemma":[0.8256159,0.13898864,0.010076373,0.009400407,0.01281961,0.0030990709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06099656,0.00065825187,0.0008324177,0.00593378,0.003996184,0.016065113,0.0015899901,0.001515419,0.00669882],"category_scores_gemma":[0.09265173,0.0005627161,0.0007012706,0.0042814193,0.020273937,0.009922505,0.013999841,0.0023275353,0.00045629262],"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":[0.00020719541,0.0004251917,0.069831036,0.0019522329,0.0003700261,0.00037059627,0.17160043,0.0014377946,0.0014815647,0.48005772,0.002004276,0.270262],"study_design_scores_gemma":[0.00009772871,0.00068036787,0.18238398,0.0043697646,0.00030574392,0.00067548343,0.19752397,0.0030735051,0.0032392791,0.470579,0.13688014,0.00019106198],"about_ca_topic_score_codex":0.0036379271,"about_ca_topic_score_gemma":0.005790169,"teacher_disagreement_score":0.06099656,"about_ca_system_score_codex":0.008105042,"about_ca_system_score_gemma":0.013841624,"threshold_uncertainty_score":0.3225845},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0983326,0.018882055,0.3412369,0.30042115,0.0016708452,0.0019339933,0.0000670235,0.00014167282,0.23731373],"genre_scores_gemma":[0.94488907,0.0025823081,0.044630416,0.0036754066,0.0002919383,0.00091636064,0.0000131855795,0.0000532627,0.0029481521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7553987,0.21400574,0.0047267308,0.0049787317,0.016574673,0.0043153805],"domain_scores_gemma":[0.6947962,0.27248624,0.009657795,0.009481447,0.010049526,0.0035288224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17820369,0.0009752236,0.0013478224,0.0057972535,0.01540491,0.025658652,0.0031435844,0.007066301,0.0026253262],"category_scores_gemma":[0.15626729,0.0008135266,0.0008467783,0.0040158643,0.118422896,0.025773462,0.018267203,0.010014355,0.00015424789],"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":[0.00003520462,0.000048764472,0.0005022213,0.00034386857,0.00002265627,0.00020891122,0.061298415,0.0009140056,0.00011570704,0.91793716,0.0012238728,0.017349234],"study_design_scores_gemma":[0.00003349171,0.000054872184,0.00037793015,0.000853592,0.000013636602,0.0001401305,0.033532124,0.0010153848,0.0003858795,0.9343658,0.029190764,0.00003632091],"about_ca_topic_score_codex":0.0032006283,"about_ca_topic_score_gemma":0.0036153537,"teacher_disagreement_score":0.17820369,"about_ca_system_score_codex":0.017770458,"about_ca_system_score_gemma":0.021755563,"threshold_uncertainty_score":0.9424424},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023906403,0.018053362,0.00860727,0.8382012,0.0623446,0.00068639923,0.00019668415,0.00018031857,0.07149106],"genre_scores_gemma":[0.025117729,0.010036354,0.012148212,0.8445891,0.066881336,0.002660348,0.00020584543,0.0005803626,0.03778063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.40690145,0.3980728,0.04778742,0.022918008,0.11128228,0.013038034],"domain_scores_gemma":[0.2378167,0.56971717,0.016244633,0.063607715,0.100063145,0.012550564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.42046943,0.002706085,0.0064277737,0.008311171,0.014298269,0.04605095,0.013416005,0.06456641,0.043720737],"category_scores_gemma":[0.71387094,0.0019991752,0.005445906,0.0086832475,0.05484586,0.048288625,0.020113094,0.04973005,0.011595958],"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":[0.00007976253,0.000063171414,0.0002450992,0.001563,0.00010084785,0.0001792066,0.0016379287,0.00012498008,0.000041111325,0.35988587,0.57711375,0.05896531],"study_design_scores_gemma":[0.000073498326,0.000029542825,0.0001437335,0.006118959,0.00006151402,0.00028875083,0.0012649863,0.0002182936,0.00009884323,0.14021084,0.8514387,0.000052333486],"about_ca_topic_score_codex":0.007088883,"about_ca_topic_score_gemma":0.004805258,"teacher_disagreement_score":0.42046943,"about_ca_system_score_codex":0.025589647,"about_ca_system_score_gemma":0.060262796,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012468694,0.0069510406,0.86633265,0.039660245,0.00034110842,0.00464399,0.00035222768,0.00040323893,0.068846814],"genre_scores_gemma":[0.24532843,0.0022439333,0.7409336,0.0021372335,0.00013534365,0.007300219,0.00019340987,0.00010954882,0.0016182094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5754796,0.37740567,0.01459867,0.00610842,0.021615827,0.0047917953],"domain_scores_gemma":[0.55871826,0.36790317,0.016020365,0.022944754,0.030291267,0.0041222745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3932894,0.0033844572,0.0051880316,0.022925155,0.007913848,0.036278676,0.00807224,0.010393492,0.005701813],"category_scores_gemma":[0.27374813,0.0019447383,0.003503525,0.013841,0.038207684,0.02794675,0.015787859,0.010699354,0.0007298402],"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":[0.00004229904,0.0001586976,0.00084010296,0.0011022176,0.000090222806,0.000051009196,0.0038979691,0.0073241894,0.00017133106,0.95587194,0.0010423397,0.029407531],"study_design_scores_gemma":[0.000114507515,0.00017996188,0.00071483164,0.0039534434,0.00009260173,0.000040121893,0.0062822667,0.009573683,0.00066860125,0.959644,0.018665906,0.00007006644],"about_ca_topic_score_codex":0.0120386835,"about_ca_topic_score_gemma":0.009454791,"teacher_disagreement_score":0.3932894,"about_ca_system_score_codex":0.042247888,"about_ca_system_score_gemma":0.06585893,"threshold_uncertainty_score":0.7481822},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7006844,0.015074155,0.06358186,0.12891085,0.0008894254,0.0016971331,0.00007061623,0.00028018767,0.088811316],"genre_scores_gemma":[0.9765454,0.0015722616,0.016410526,0.002410612,0.00011367406,0.0003140995,0.000018019155,0.00003836092,0.0025770408],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8211798,0.1454848,0.004231362,0.0031349477,0.02038508,0.0055839308],"domain_scores_gemma":[0.737013,0.19529074,0.013880778,0.007295248,0.032490604,0.014029594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.111812375,0.00031606815,0.00058579445,0.0017116284,0.008224795,0.011854612,0.0019961256,0.0020709124,0.0016372552],"category_scores_gemma":[0.15501483,0.00038252486,0.00034057998,0.001432364,0.015493615,0.004196774,0.007877385,0.0038202675,0.00031059215],"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":[0.00025012787,0.00064959767,0.04007102,0.0014394154,0.00007427037,0.000897556,0.29294893,0.001875122,0.0014796123,0.052836087,0.014619765,0.59285843],"study_design_scores_gemma":[0.00015939477,0.0011291885,0.05722724,0.004140433,0.00004140428,0.0013853484,0.64851916,0.0032785297,0.0024819588,0.09401588,0.1873632,0.00025824193],"about_ca_topic_score_codex":0.019816611,"about_ca_topic_score_gemma":0.023102552,"teacher_disagreement_score":0.111812375,"about_ca_system_score_codex":0.015628617,"about_ca_system_score_gemma":0.056542918,"threshold_uncertainty_score":0.5913274},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002186212,0.824883,0.024620576,0.13433929,0.005506083,0.00031552473,0.000022605238,0.00004668279,0.008079968],"genre_scores_gemma":[0.09362945,0.8263291,0.044168413,0.023450263,0.009324557,0.0015443017,0.000066933986,0.00015284141,0.0013340954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.4722924,0.45993826,0.0218858,0.004672527,0.039149836,0.0020611428],"domain_scores_gemma":[0.24528414,0.70243454,0.011047052,0.0064584133,0.033565518,0.0012103654],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4075321,0.0021247964,0.0052391076,0.024131697,0.0085959025,0.032495722,0.0076586343,0.014033739,0.0008883122],"category_scores_gemma":[0.5251456,0.00170402,0.0015735922,0.021013312,0.06728119,0.035731316,0.009607165,0.013359899,0.0008619681],"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":[0.00009251255,0.000088806875,0.0016008556,0.03117544,0.0002861845,0.0011162614,0.10988391,0.00095242384,0.00044664144,0.46305606,0.02748341,0.36381748],"study_design_scores_gemma":[0.00007150171,0.00012302105,0.0018228199,0.13232724,0.00027751471,0.0011704142,0.12527972,0.001607797,0.0009615576,0.36702988,0.36917198,0.00015643242],"about_ca_topic_score_codex":0.0097870175,"about_ca_topic_score_gemma":0.01336022,"teacher_disagreement_score":0.5924679,"about_ca_system_score_codex":0.023148559,"about_ca_system_score_gemma":0.03835126,"threshold_uncertainty_score":0.7306184},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023017518,0.9747999,0.003801208,0.011495027,0.0009747452,0.000055055963,0.0000998537,0.00005387233,0.0084900865],"genre_scores_gemma":[0.0050473046,0.98130655,0.0059317597,0.0013590817,0.00048985414,0.00009053055,0.000119846605,0.000043126718,0.0056118616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99127215,0.0033349085,0.00074988365,0.0005978956,0.0037451354,0.00029999547],"domain_scores_gemma":[0.96311826,0.025351435,0.002342094,0.00076707976,0.0073871035,0.0010340167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015169417,0.0018356773,0.0018789289,0.010925671,0.0028273747,0.0071149077,0.0031236429,0.004120903,0.011968392],"category_scores_gemma":[0.025424201,0.0017120888,0.0013246237,0.014384606,0.0045738555,0.009525184,0.0024340684,0.0046186387,0.0069516944],"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":[0.000056742396,0.00005199105,0.0008640486,0.0066327774,0.000068346686,0.000113040245,0.0024425255,0.00032854656,0.00028913756,0.012099181,0.25333914,0.7237145],"study_design_scores_gemma":[0.000022625121,0.00008269961,0.0036144159,0.01368118,0.00016073041,0.00050007366,0.0017558255,0.00023918427,0.0006725817,0.016574875,0.9626134,0.00008235481],"about_ca_topic_score_codex":0.08353952,"about_ca_topic_score_gemma":0.16940965,"teacher_disagreement_score":0.08353952,"about_ca_system_score_codex":0.008552647,"about_ca_system_score_gemma":0.017033234,"threshold_uncertainty_score":0.16610652},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14753586,0.0551276,0.0023431866,0.66139156,0.0017000361,0.00048874825,0.0025416452,0.000083605715,0.12878779],"genre_scores_gemma":[0.90055627,0.013852568,0.003003745,0.054781985,0.0004945832,0.00017297117,0.00053533097,0.000038549468,0.026564032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9562239,0.0050424687,0.002522289,0.0020725555,0.022680417,0.0114584025],"domain_scores_gemma":[0.92133045,0.03476045,0.0036458625,0.0012908798,0.030344514,0.008627836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044789523,0.00049297395,0.0011270059,0.0069685294,0.02500289,0.019196218,0.0046841963,0.009640583,0.004109537],"category_scores_gemma":[0.09192791,0.0012106057,0.0008579449,0.010693158,0.01281883,0.0034474635,0.007290959,0.009689149,0.00014886573],"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":[0.00045136854,0.0001691763,0.030570019,0.0014310365,0.00031086683,0.0012182228,0.019310342,0.0052698967,0.00097121106,0.71193945,0.11198217,0.11637632],"study_design_scores_gemma":[0.0003345023,0.00016947831,0.16311218,0.0029838826,0.0005081695,0.0002144516,0.022832558,0.0044037607,0.0029045094,0.055321705,0.7468025,0.00041228108],"about_ca_topic_score_codex":0.99677074,"about_ca_topic_score_gemma":0.9973041,"teacher_disagreement_score":0.45860484,"about_ca_system_score_codex":0.45860484,"about_ca_system_score_gemma":0.5997215,"threshold_uncertainty_score":0.62794167},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012875005,0.013632534,0.66642296,0.11940192,0.0013166448,0.0031956935,0.00025990655,0.0006280973,0.18226719],"genre_scores_gemma":[0.27337098,0.007511776,0.7002377,0.004709861,0.0003930926,0.0044727973,0.00015959927,0.00023679029,0.008907422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9201315,0.06624804,0.0022877466,0.0024726156,0.0075780535,0.0012820606],"domain_scores_gemma":[0.8994044,0.08239544,0.0026963349,0.007833119,0.004324407,0.0033464122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06803323,0.0017485706,0.0026431018,0.00886382,0.008069438,0.028189855,0.0048941714,0.009400678,0.0075244564],"category_scores_gemma":[0.06977091,0.0015922346,0.0014375349,0.0053828466,0.06905914,0.03898201,0.0135844955,0.0069624074,0.001581967],"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":[0.000013779975,0.000035440986,0.00036198966,0.00040668476,0.000014646788,0.0001162482,0.012422569,0.00044456392,0.000095667034,0.96252286,0.0026209205,0.020944595],"study_design_scores_gemma":[0.000029687053,0.00004572392,0.0001198925,0.0010648537,0.000009206439,0.00016326307,0.015100974,0.0014128925,0.000113872455,0.937923,0.043992933,0.00002376992],"about_ca_topic_score_codex":0.002668175,"about_ca_topic_score_gemma":0.0030056285,"teacher_disagreement_score":0.06803323,"about_ca_system_score_codex":0.010592844,"about_ca_system_score_gemma":0.018849904,"threshold_uncertainty_score":0.35979843},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54040045,0.0025002745,0.43382758,0.0022416152,0.00054149685,0.0006156869,0.00016587155,0.00042869092,0.019278366],"genre_scores_gemma":[0.9172783,0.00031563477,0.08005909,0.00047420483,0.00008820368,0.00022754527,0.00007978743,0.000055989793,0.0014212312],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96643674,0.023243569,0.0015798656,0.0030230607,0.0053720884,0.00034476185],"domain_scores_gemma":[0.7216542,0.21316339,0.027024295,0.017993568,0.018895466,0.0012690844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.061581496,0.00055288477,0.00050559145,0.00096035015,0.0005530058,0.001906455,0.00086214516,0.0009785374,0.0013482776],"category_scores_gemma":[0.27051517,0.00031527635,0.0004483481,0.00070295174,0.0013481881,0.00257225,0.0011603493,0.00156197,0.00033637107],"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":[0.0018853915,0.00081809534,0.2819172,0.0010474651,0.00078312255,0.00046759084,0.032509997,0.010291572,0.04749984,0.018659033,0.0049155806,0.59920514],"study_design_scores_gemma":[0.00035103364,0.0041553075,0.7308371,0.0011866948,0.0005070663,0.0026303583,0.0049639526,0.12878348,0.055373434,0.045464437,0.025251891,0.0004952479],"about_ca_topic_score_codex":0.0024637817,"about_ca_topic_score_gemma":0.003105307,"teacher_disagreement_score":0.061581496,"about_ca_system_score_codex":0.0013700391,"about_ca_system_score_gemma":0.00097283727,"threshold_uncertainty_score":0.32567793},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21881084,0.08955612,0.017170984,0.5349047,0.0033521012,0.00036310434,0.0004790361,0.00023937042,0.13512379],"genre_scores_gemma":[0.864489,0.03151172,0.015421501,0.033397187,0.0012841192,0.00035604084,0.00040315284,0.00011754165,0.053019717],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96060544,0.016134957,0.0029853445,0.003722267,0.012597534,0.0039543575],"domain_scores_gemma":[0.7488516,0.15426783,0.018275449,0.007512381,0.060025785,0.011066917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.076886214,0.00043030985,0.0008488562,0.0043714195,0.00494424,0.008053816,0.0013303169,0.0053847716,0.0064519104],"category_scores_gemma":[0.12586413,0.0005568927,0.00060831243,0.0047569354,0.00727344,0.0057879435,0.0060189553,0.007271591,0.0006457256],"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":[0.0004014534,0.00020997984,0.059177473,0.002429603,0.00012417401,0.0007679623,0.03790284,0.0016264608,0.0041198484,0.36962873,0.053380266,0.47023126],"study_design_scores_gemma":[0.00007386632,0.0005562244,0.13656422,0.007215109,0.00009935128,0.00087221473,0.01872015,0.0012496366,0.0034449927,0.021330787,0.80973184,0.00014162378],"about_ca_topic_score_codex":0.100877024,"about_ca_topic_score_gemma":0.112124726,"teacher_disagreement_score":0.100877024,"about_ca_system_score_codex":0.021725291,"about_ca_system_score_gemma":0.07734795,"threshold_uncertainty_score":0.406618},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004777343,0.9900237,0.004630267,0.0013928316,0.0001246994,0.00008682388,0.00004137179,0.000021585312,0.0032009257],"genre_scores_gemma":[0.004475451,0.9858359,0.0084714405,0.00036325038,0.000104492865,0.00013960147,0.000049776667,0.000008064836,0.0005519197],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9840216,0.006817177,0.0022889562,0.001060002,0.005532226,0.00028009873],"domain_scores_gemma":[0.9723352,0.020951614,0.0022793333,0.00055054046,0.0036236271,0.00025979674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021907205,0.0014796434,0.0028947406,0.012137258,0.00090062775,0.0031157874,0.0026493312,0.003461497,0.002169643],"category_scores_gemma":[0.030525612,0.00091712293,0.00095813663,0.0086085005,0.0029573052,0.0043039382,0.001413083,0.0024883458,0.0019569444],"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":[0.000037847054,0.00008148002,0.0006089337,0.015399179,0.000080545884,0.000083579245,0.00035670528,0.00052738795,0.000461776,0.012567928,0.0055805272,0.96421415],"study_design_scores_gemma":[0.0000612068,0.0007755058,0.014114042,0.06387187,0.0004060543,0.002533539,0.0018198822,0.001021303,0.0033810185,0.029456701,0.8823453,0.00021350605],"about_ca_topic_score_codex":0.006249243,"about_ca_topic_score_gemma":0.009620618,"teacher_disagreement_score":0.9780928,"about_ca_system_score_codex":0.0039696842,"about_ca_system_score_gemma":0.0066107195,"threshold_uncertainty_score":0.11585778},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071448027,0.0011473516,0.92384565,0.0041861725,0.0003296195,0.0036385586,0.0004352779,0.0008000658,0.058472533],"genre_scores_gemma":[0.2260898,0.0013535673,0.7579619,0.0007846472,0.00024685886,0.008554532,0.0005679262,0.00044933773,0.0039914325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6667181,0.27741677,0.010400525,0.0074346466,0.03407228,0.0039576883],"domain_scores_gemma":[0.6047398,0.31994292,0.014417935,0.022383625,0.035514895,0.0030008792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19090745,0.0036673518,0.0032145155,0.021391341,0.005064007,0.012978594,0.0049339524,0.003295998,0.011089493],"category_scores_gemma":[0.29873714,0.0015358435,0.004464129,0.017858671,0.013978583,0.013015957,0.015522866,0.0053552184,0.001847885],"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":[0.0003083694,0.0003523819,0.005052297,0.002855855,0.00044245485,0.00025332088,0.010625223,0.024713328,0.0003561834,0.63095874,0.006163663,0.31791815],"study_design_scores_gemma":[0.00019863395,0.0002985232,0.0019534687,0.0014916442,0.00017089954,0.00017527277,0.003610638,0.038749386,0.0013046905,0.9166563,0.035253223,0.00013728392],"about_ca_topic_score_codex":0.005633098,"about_ca_topic_score_gemma":0.0038716432,"teacher_disagreement_score":0.19090745,"about_ca_system_score_codex":0.013402027,"about_ca_system_score_gemma":0.022422764,"threshold_uncertainty_score":0.99775517},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82412237,0.007942061,0.029258758,0.012161166,0.0005597861,0.0070340014,0.007853434,0.0025304977,0.10853792],"genre_scores_gemma":[0.9528651,0.002477253,0.030360676,0.00041586478,0.000031607015,0.00074565073,0.0015497982,0.00012674133,0.01142736],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9889414,0.002826474,0.00081576523,0.0007640929,0.0053995727,0.0012527615],"domain_scores_gemma":[0.9425539,0.008590992,0.0019764875,0.0017691187,0.039877575,0.005232017],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013904988,0.0005386876,0.00066753017,0.003892792,0.003719432,0.003077951,0.0018029965,0.0004772357,0.0033290882],"category_scores_gemma":[0.0346649,0.0006220286,0.0004522266,0.0056025106,0.00095658045,0.0011288971,0.0025342589,0.0011685721,0.00053009734],"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":[0.000978038,0.00083550107,0.21477263,0.0011829651,0.00017108767,0.00062261237,0.009035869,0.0057961927,0.0026522733,0.006700957,0.039901506,0.7173505],"study_design_scores_gemma":[0.0002717431,0.0004513204,0.90593964,0.0008389924,0.00008743498,0.00021634545,0.0069318577,0.013274492,0.0022099523,0.001549265,0.06801017,0.00021871016],"about_ca_topic_score_codex":0.98908347,"about_ca_topic_score_gemma":0.9954456,"teacher_disagreement_score":0.986095,"about_ca_system_score_codex":0.06414459,"about_ca_system_score_gemma":0.18572712,"threshold_uncertainty_score":0.46540374},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018124003,0.98832625,0.006373845,0.0010692903,0.00049028464,0.0003497235,0.000050753224,0.00002655005,0.003132095],"genre_scores_gemma":[0.005248141,0.98297,0.009909185,0.0003903514,0.00019379215,0.00085236644,0.00007379635,0.000018203342,0.000344125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94840735,0.03347314,0.0048701568,0.0026803315,0.009947302,0.00062181894],"domain_scores_gemma":[0.89375067,0.09113469,0.0038958907,0.002601662,0.008086847,0.00053022016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037758935,0.0016454456,0.0036562087,0.010318945,0.0014984773,0.005270563,0.004421463,0.0033277993,0.0055915127],"category_scores_gemma":[0.0692103,0.0012328001,0.0029199047,0.013508249,0.004579897,0.0054316814,0.004873898,0.0034416853,0.0011879705],"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":[0.0000697869,0.00013051917,0.00031732273,0.14132434,0.00043282175,0.00015793122,0.0014948699,0.0011786787,0.00031139352,0.04243523,0.011682065,0.80046505],"study_design_scores_gemma":[0.00006427465,0.00020816055,0.0014845857,0.22191493,0.00059774425,0.00065578654,0.0012295999,0.00092025875,0.00070783455,0.031730812,0.74037284,0.00011311417],"about_ca_topic_score_codex":0.003699547,"about_ca_topic_score_gemma":0.003624696,"teacher_disagreement_score":0.037758935,"about_ca_system_score_codex":0.004746148,"about_ca_system_score_gemma":0.015497665,"threshold_uncertainty_score":0.1996907},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99191487,0.0001750487,0.0046205083,0.00034957274,0.000014854086,0.00004209326,0.00024069518,0.000042714317,0.002599678],"genre_scores_gemma":[0.99850535,0.00006547357,0.0008900284,0.000009573977,0.000005071311,0.000010345365,0.0001694447,0.0000020729915,0.00034254306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993994,0.0001603514,0.00003302446,0.00008420506,0.00015893186,0.00016410062],"domain_scores_gemma":[0.9968918,0.0016647438,0.00050013233,0.00010312737,0.00056538975,0.00027488646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016699616,0.000412475,0.0004607875,0.0011904065,0.00033580634,0.0014365776,0.0006589426,0.00069735723,0.0022684885],"category_scores_gemma":[0.0050466135,0.00014148028,0.00046791733,0.0008275581,0.0002719681,0.00068123837,0.00054243667,0.00055491395,0.00022054264],"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":[0.0005259588,0.0008611971,0.57862705,0.00017926948,0.00022607564,0.00046400807,0.00027462142,0.35648152,0.001227831,0.0025258726,0.0025075595,0.0560991],"study_design_scores_gemma":[0.000030446405,0.00047114628,0.21675523,0.0000379504,0.00008036844,0.000063821,0.00052743615,0.7798631,0.0006406446,0.0009425716,0.000567394,0.000019893343],"about_ca_topic_score_codex":0.023450539,"about_ca_topic_score_gemma":0.017454453,"teacher_disagreement_score":0.023450539,"about_ca_system_score_codex":0.0016903195,"about_ca_system_score_gemma":0.001603203,"threshold_uncertainty_score":0.046628118},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22763017,0.04269992,0.31061116,0.30668023,0.005900509,0.0025004903,0.0019008394,0.0007386967,0.10133796],"genre_scores_gemma":[0.8979217,0.003875135,0.07664495,0.011961976,0.0018426534,0.002151925,0.000481168,0.00027288587,0.004847648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27401266,0.52997786,0.044746216,0.04351461,0.10207318,0.0056755003],"domain_scores_gemma":[0.033004984,0.8493159,0.027287988,0.047000725,0.041379932,0.002010593],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6575541,0.0013882132,0.003653535,0.012637128,0.00790086,0.02264893,0.008038468,0.00620666,0.0067604627],"category_scores_gemma":[0.8514972,0.0018766329,0.0030023656,0.010565557,0.03701661,0.023714423,0.014062834,0.007586254,0.0014099294],"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":[0.001654566,0.00052421005,0.19272684,0.008096628,0.003440033,0.00052662427,0.052706573,0.005836642,0.0010561735,0.4102694,0.013120777,0.31004146],"study_design_scores_gemma":[0.0007209008,0.0016731331,0.15802675,0.013624373,0.0010310328,0.0012840133,0.030456426,0.02025998,0.0044483347,0.6702942,0.097566485,0.0006143516],"about_ca_topic_score_codex":0.02471924,"about_ca_topic_score_gemma":0.015871,"teacher_disagreement_score":0.3424459,"about_ca_system_score_codex":0.019090053,"about_ca_system_score_gemma":0.026426557,"threshold_uncertainty_score":0.42229682},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009697262,0.07542092,0.4865546,0.27765727,0.004902406,0.0006179437,0.00016729595,0.00040079126,0.14458148],"genre_scores_gemma":[0.54335433,0.048710294,0.375775,0.020857513,0.0039110053,0.0019317538,0.00016346965,0.00022623573,0.0050704223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8773763,0.090830304,0.0037100133,0.0037006352,0.022582505,0.0018002667],"domain_scores_gemma":[0.5392582,0.41824672,0.005650083,0.019717023,0.013355733,0.0037722455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12283623,0.0020254615,0.0040202267,0.009497181,0.0044061723,0.02257561,0.00606127,0.011661175,0.0072286255],"category_scores_gemma":[0.20675133,0.0011937397,0.0018915676,0.00470441,0.06685928,0.020586064,0.011107543,0.016468879,0.0018829743],"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":[0.000021698124,0.00014134806,0.00048833515,0.00093922205,0.000071545765,0.000036636633,0.0020756403,0.0019249792,0.00007692118,0.93968946,0.0045873425,0.049946867],"study_design_scores_gemma":[0.00003060114,0.000028862569,0.00016186504,0.0010104051,0.000013845018,0.00002373543,0.0006465298,0.0018967133,0.00008870649,0.97912085,0.016962472,0.000015417038],"about_ca_topic_score_codex":0.0048083924,"about_ca_topic_score_gemma":0.0037069516,"teacher_disagreement_score":0.12283623,"about_ca_system_score_codex":0.013421562,"about_ca_system_score_gemma":0.028544163,"threshold_uncertainty_score":0.64962786},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031818084,0.041147977,0.14926356,0.06338181,0.02366943,0.00946243,0.008934873,0.0058028405,0.69515526],"genre_scores_gemma":[0.054755714,0.036359455,0.25820053,0.0117903035,0.005395758,0.0074911113,0.0085978415,0.0018347491,0.6155745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9848433,0.005281303,0.0014101503,0.0009407818,0.0067409696,0.0007834063],"domain_scores_gemma":[0.9740598,0.0045488565,0.0005906148,0.0013397095,0.017481092,0.0019800416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013220147,0.00064983475,0.0007936807,0.0053217886,0.002866744,0.008063361,0.0022769503,0.0019072609,0.06759709],"category_scores_gemma":[0.024974344,0.0011018709,0.0004798501,0.006500776,0.002342935,0.0036506043,0.0033229222,0.0033879536,0.029432638],"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":[0.000018520172,0.000059927297,0.0005795831,0.0002504765,0.0000035191542,0.000060664126,0.00039726973,0.00023610474,0.00009075076,0.020152008,0.7433009,0.23485032],"study_design_scores_gemma":[0.0000101277365,0.000015930627,0.0026002303,0.0004948166,0.0000021543174,0.00006598245,0.0004416121,0.00020404042,0.000054380558,0.0038725222,0.99221414,0.000024002604],"about_ca_topic_score_codex":0.12954894,"about_ca_topic_score_gemma":0.23942152,"teacher_disagreement_score":0.12954894,"about_ca_system_score_codex":0.012656092,"about_ca_system_score_gemma":0.019946054,"threshold_uncertainty_score":0.25758976},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3270645,0.2685396,0.058848232,0.12470975,0.0028288313,0.00037467436,0.000565003,0.00041827533,0.2166511],"genre_scores_gemma":[0.90528435,0.04180304,0.024051428,0.0041897157,0.0006694626,0.00017948798,0.00024186331,0.00015352361,0.023427261],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95900977,0.022627594,0.003405584,0.002671404,0.010012565,0.0022732078],"domain_scores_gemma":[0.9599178,0.017948816,0.0028634993,0.0022322063,0.014455899,0.002581859],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.048170812,0.0006856799,0.0012159692,0.0062637795,0.0053778426,0.015873948,0.0012188659,0.0038682166,0.0040779267],"category_scores_gemma":[0.04966149,0.00047228683,0.0010146628,0.008994031,0.0065727904,0.011566095,0.0054327683,0.0036035157,0.00073577266],"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":[0.00035657955,0.00032218915,0.02499921,0.0021710584,0.0001438707,0.00032901816,0.024605272,0.0049943556,0.001631327,0.31748942,0.017582688,0.60537505],"study_design_scores_gemma":[0.00008991915,0.0010874913,0.14393348,0.009490277,0.00019876684,0.00085997616,0.039778847,0.0053541907,0.006584674,0.080180466,0.7121086,0.00033334421],"about_ca_topic_score_codex":0.02749657,"about_ca_topic_score_gemma":0.02370891,"teacher_disagreement_score":0.9518292,"about_ca_system_score_codex":0.021594288,"about_ca_system_score_gemma":0.016688999,"threshold_uncertainty_score":0.25475466},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8109775,0.006638093,0.051963717,0.0036520686,0.00037241008,0.0014855815,0.0014612309,0.0005957706,0.12285362],"genre_scores_gemma":[0.94352,0.0026349218,0.033843424,0.00031641457,0.00005374004,0.0007399429,0.00066115416,0.000119096476,0.018111328],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9808214,0.004553445,0.001147585,0.00094695494,0.012001262,0.00052945886],"domain_scores_gemma":[0.9372249,0.030386472,0.0050284625,0.0025583524,0.022645233,0.002156534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018374665,0.0007489684,0.0008598177,0.0051805363,0.0015622393,0.0054441323,0.0014593509,0.0013604739,0.010107944],"category_scores_gemma":[0.0411616,0.00038882633,0.0015201913,0.003954635,0.0023262957,0.0039805756,0.0024344898,0.0015599048,0.0015816002],"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":[0.0012883191,0.0011075116,0.1572434,0.005754219,0.0006454217,0.0004437638,0.034122355,0.0046016145,0.014979931,0.016676992,0.006462174,0.7566744],"study_design_scores_gemma":[0.00012697431,0.0070965798,0.7353351,0.005159808,0.000970788,0.0009529151,0.06297258,0.009537119,0.04429369,0.014822074,0.11823315,0.0004992558],"about_ca_topic_score_codex":0.009382795,"about_ca_topic_score_gemma":0.010936699,"teacher_disagreement_score":0.018374665,"about_ca_system_score_codex":0.005024529,"about_ca_system_score_gemma":0.004752091,"threshold_uncertainty_score":0.09717566},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93178296,0.0020547565,0.0010695736,0.010043772,0.000042937507,0.00012373652,0.00042467698,0.00005557136,0.054402087],"genre_scores_gemma":[0.9974552,0.00019793128,0.00019916146,0.0001723017,0.000003582869,0.000010341288,0.000045094082,0.000005689403,0.0019108363],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98965573,0.0017582646,0.00026146433,0.00075116503,0.0027767187,0.004796673],"domain_scores_gemma":[0.98171276,0.002519969,0.002535486,0.00068727566,0.0066880938,0.005856497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058753593,0.00020117367,0.00047095568,0.001999495,0.0137040755,0.0073840925,0.0015484832,0.000648128,0.0035637382],"category_scores_gemma":[0.016284188,0.00037841924,0.00032861152,0.0040044636,0.008540998,0.0014114697,0.004941876,0.0015223172,0.00015613562],"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":[0.0006212623,0.00019877992,0.62871844,0.00042781822,0.00027521994,0.0010967505,0.07838702,0.008214353,0.0029867068,0.15090859,0.01788173,0.11028335],"study_design_scores_gemma":[0.00005049388,0.00007762863,0.8951156,0.00022469938,0.000098487304,0.0000882284,0.0495312,0.0025734804,0.0006664483,0.007114439,0.044381052,0.000078269564],"about_ca_topic_score_codex":0.9909905,"about_ca_topic_score_gemma":0.99667054,"teacher_disagreement_score":0.8010294,"about_ca_system_score_codex":0.19897063,"about_ca_system_score_gemma":0.18523778,"threshold_uncertainty_score":0.92908055},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6939342,0.0013253383,0.036598034,0.025498718,0.00014413726,0.001896449,0.000059078153,0.00011851252,0.24042548],"genre_scores_gemma":[0.9861065,0.00054688915,0.009318242,0.00028572406,0.000004728239,0.00021324062,0.000023733044,0.000007861456,0.0034930895],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99483335,0.0041098557,0.00006276913,0.00013719835,0.00028893634,0.00056790345],"domain_scores_gemma":[0.99753714,0.0010787284,0.00021615149,0.000094130904,0.00041316662,0.0006607319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004839819,0.00041492007,0.00023831824,0.00091444544,0.0044576004,0.004448952,0.00063277007,0.00079822505,0.0032830173],"category_scores_gemma":[0.0039350167,0.00018571384,0.00024039819,0.0019078219,0.0055707833,0.002365602,0.00423959,0.0013014327,0.00018850713],"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":[0.00015199321,0.0012845403,0.025319276,0.0022146152,0.00008609692,0.0043857414,0.19460572,0.030260429,0.003399265,0.35675597,0.012332946,0.36920345],"study_design_scores_gemma":[0.00015880013,0.0011422145,0.02525891,0.0014327304,0.00006070124,0.00066102174,0.6385622,0.01832494,0.0037356634,0.12477834,0.18580414,0.00008036095],"about_ca_topic_score_codex":0.026357355,"about_ca_topic_score_gemma":0.0549222,"teacher_disagreement_score":0.026357355,"about_ca_system_score_codex":0.01068321,"about_ca_system_score_gemma":0.029658498,"threshold_uncertainty_score":0.07751244},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41713628,0.0021861242,0.2319594,0.06332153,0.0006521919,0.004629376,0.00053503405,0.0020991066,0.277481],"genre_scores_gemma":[0.7874777,0.001078818,0.1812191,0.004048491,0.00011696155,0.0018635202,0.00039748367,0.0001190358,0.023678953],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9866915,0.008635495,0.0004469853,0.0004961949,0.0027446058,0.0009853212],"domain_scores_gemma":[0.98520875,0.00784455,0.00054452464,0.0008814234,0.0037237327,0.0017970459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031137958,0.00022395146,0.00022950298,0.0017981234,0.0033197193,0.0069229994,0.0010595315,0.0008154989,0.0041900957],"category_scores_gemma":[0.029440865,0.000358882,0.000271639,0.0014735634,0.0018130961,0.004899811,0.0059984215,0.003086574,0.00035781134],"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":[0.00018576483,0.0011798504,0.021287702,0.00025871742,0.000024972405,0.0001232495,0.011715477,0.0032389543,0.002310762,0.12240869,0.04477871,0.7924871],"study_design_scores_gemma":[0.0005224952,0.0033969139,0.16626881,0.0022263317,0.00016465322,0.0004969281,0.07111351,0.043543685,0.02020607,0.08959783,0.6021252,0.00033757303],"about_ca_topic_score_codex":0.010490428,"about_ca_topic_score_gemma":0.035728253,"teacher_disagreement_score":0.031137958,"about_ca_system_score_codex":0.007069761,"about_ca_system_score_gemma":0.021011151,"threshold_uncertainty_score":0.16467524},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9404743,0.00082841277,0.010602045,0.0010571025,0.00006777011,0.00064274063,0.0005218223,0.00015684713,0.04564904],"genre_scores_gemma":[0.9743465,0.0004389569,0.008249176,0.00006452491,0.000027279544,0.00044274025,0.0004782555,0.000025284133,0.015927276],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97889596,0.007548452,0.0009813948,0.0010655674,0.009954658,0.0015539824],"domain_scores_gemma":[0.93844795,0.02257765,0.007268026,0.0030088006,0.023927394,0.004770155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02289078,0.0005524676,0.00083150284,0.0049893544,0.0018507033,0.0044856626,0.0012440747,0.000655398,0.0071076527],"category_scores_gemma":[0.062225606,0.00025730385,0.00048077633,0.004535376,0.0017918301,0.0022711752,0.0030771273,0.0010750665,0.0012563195],"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":[0.0009199745,0.0011743661,0.25742885,0.0011716562,0.00021185058,0.00021531833,0.039037064,0.006850197,0.004174218,0.012495562,0.0044448837,0.671876],"study_design_scores_gemma":[0.00006650701,0.001245292,0.92392755,0.00065355166,0.000089503315,0.00008062896,0.019963365,0.0048019583,0.0050735674,0.0038360478,0.040149722,0.000112276444],"about_ca_topic_score_codex":0.053535495,"about_ca_topic_score_gemma":0.06801833,"teacher_disagreement_score":0.053535495,"about_ca_system_score_codex":0.01301883,"about_ca_system_score_gemma":0.017788894,"threshold_uncertainty_score":0.12105942},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016092021,0.001717543,0.018448254,0.9419833,0.0017832118,0.00004268065,0.00002328465,0.000034923214,0.019874837],"genre_scores_gemma":[0.85471874,0.0023844033,0.02357734,0.11181965,0.0016239203,0.0004049326,0.000044669458,0.000286578,0.0051398617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9324174,0.04927609,0.002592555,0.0037439025,0.0077701765,0.0041999174],"domain_scores_gemma":[0.77898526,0.1865987,0.005213008,0.008553952,0.014661656,0.0059874086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09982438,0.0008251085,0.0013065073,0.0033171992,0.013290799,0.019367613,0.006230787,0.017542243,0.004111216],"category_scores_gemma":[0.12945412,0.0012279552,0.0017008295,0.0020726752,0.114789195,0.04391478,0.013628942,0.047436535,0.0006775277],"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":[0.000017699127,0.000033336317,0.0002683016,0.00004824294,0.000010523825,0.000149965,0.03160405,0.00026168558,0.00004262389,0.9552861,0.008138598,0.0041389097],"study_design_scores_gemma":[0.00003862464,0.000027482274,0.00017176685,0.0003881442,0.000012532662,0.00015469301,0.045056317,0.0010654698,0.00021958737,0.90539736,0.047429256,0.00003878476],"about_ca_topic_score_codex":0.010408569,"about_ca_topic_score_gemma":0.0073549696,"teacher_disagreement_score":0.90017563,"about_ca_system_score_codex":0.019356858,"about_ca_system_score_gemma":0.019625654,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100755356,0.0062978165,0.0396227,0.78659755,0.009595572,0.00024290793,0.00005657916,0.0001925021,0.05663907],"genre_scores_gemma":[0.78640366,0.0033872507,0.04438452,0.14687322,0.0039059438,0.00052039773,0.000037580037,0.00020412778,0.014283213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.89269704,0.08643231,0.0022017988,0.0039647124,0.00982672,0.004877456],"domain_scores_gemma":[0.86815107,0.096069895,0.006140673,0.007546698,0.0075764307,0.014515163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07684409,0.000932808,0.0014085163,0.0032286227,0.0285015,0.039181326,0.0027872848,0.015718427,0.0069278833],"category_scores_gemma":[0.121625684,0.0015898341,0.0014979986,0.002686577,0.041498866,0.026751082,0.019654343,0.013650537,0.0019354692],"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":[0.0005221417,0.000586466,0.018652473,0.0009990213,0.00026666635,0.0031772852,0.25507057,0.0007324892,0.0024695992,0.46530315,0.10133266,0.15088753],"study_design_scores_gemma":[0.00021282099,0.00044990357,0.0036402817,0.0013182833,0.00011721162,0.0018459534,0.35266948,0.0016980924,0.00084075384,0.4783617,0.15853119,0.00031431267],"about_ca_topic_score_codex":0.00209667,"about_ca_topic_score_gemma":0.00458621,"teacher_disagreement_score":0.9231559,"about_ca_system_score_codex":0.0054623745,"about_ca_system_score_gemma":0.012661444,"threshold_uncertainty_score":0.40639526},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032346357,0.0077312374,0.18795015,0.47462642,0.0076393434,0.0017534099,0.00038609523,0.00053265004,0.28703433],"genre_scores_gemma":[0.64393777,0.011793045,0.115129404,0.097012214,0.0018640978,0.0029340785,0.0003910366,0.0006108473,0.12632754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92816865,0.04332745,0.005874735,0.0031526564,0.015485868,0.003990602],"domain_scores_gemma":[0.92339724,0.035089746,0.0016102679,0.0030983542,0.03404859,0.002755749],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07141851,0.00082517695,0.0007197226,0.0029155891,0.009127923,0.013483775,0.004551374,0.0064552487,0.004332559],"category_scores_gemma":[0.08329367,0.0005507693,0.0013810568,0.0032707243,0.02069949,0.0068854825,0.0066753686,0.008604029,0.001001035],"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":[0.00007846945,0.00014722088,0.0033396746,0.00071907457,0.000027010403,0.0006884746,0.040824898,0.0023562014,0.00076206395,0.77771837,0.087891914,0.08544666],"study_design_scores_gemma":[0.000033496883,0.0001210884,0.002630156,0.0011385742,0.000033338012,0.0004087073,0.040530827,0.0022757698,0.002783496,0.03261437,0.91730857,0.00012170942],"about_ca_topic_score_codex":0.107236065,"about_ca_topic_score_gemma":0.12658024,"teacher_disagreement_score":0.9285815,"about_ca_system_score_codex":0.036489356,"about_ca_system_score_gemma":0.0551493,"threshold_uncertainty_score":0.3777017},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6563143,0.0039531523,0.27133673,0.008134892,0.000135219,0.0014878057,0.00011804229,0.0002794402,0.05824037],"genre_scores_gemma":[0.97088665,0.00051341136,0.027373089,0.00024353743,0.000016205948,0.0005777811,0.00003887075,0.000053258766,0.00029732453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8412625,0.1203737,0.011150094,0.0031430493,0.021697989,0.002372661],"domain_scores_gemma":[0.34694257,0.5728718,0.031685498,0.019008322,0.027670953,0.0018208142],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11627305,0.0007493747,0.00089177437,0.011799896,0.0040814783,0.01359049,0.002098031,0.0026498858,0.0018915056],"category_scores_gemma":[0.37962437,0.0006970566,0.0014878666,0.011766743,0.028971242,0.020557113,0.0071137496,0.0043823035,0.0001493087],"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":[0.0002561738,0.0004901417,0.08066736,0.001598976,0.00020292273,0.0002054672,0.28812572,0.002244,0.001877612,0.4763933,0.0007293436,0.14720897],"study_design_scores_gemma":[0.00012628849,0.0012252283,0.15668416,0.007287987,0.0004199436,0.0007805972,0.29789168,0.030079061,0.0070733554,0.46595663,0.032112584,0.0003624251],"about_ca_topic_score_codex":0.0060048024,"about_ca_topic_score_gemma":0.0036908851,"teacher_disagreement_score":0.88372695,"about_ca_system_score_codex":0.00840466,"about_ca_system_score_gemma":0.00929725,"threshold_uncertainty_score":0.614918},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020795817,0.01139256,0.6458919,0.030542381,0.0026117153,0.0014439652,0.0002829244,0.00036534687,0.2866733],"genre_scores_gemma":[0.6218798,0.007308126,0.35200328,0.005404422,0.0018078481,0.0029293324,0.00018484259,0.00021891209,0.008263374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9073715,0.07821893,0.0026321106,0.0034185462,0.0073933965,0.00096539676],"domain_scores_gemma":[0.67688507,0.27891162,0.00533118,0.025638578,0.011592434,0.0016410842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08524376,0.0013364136,0.0017620643,0.006988388,0.0023867835,0.011655115,0.0035945964,0.0033303006,0.0153315645],"category_scores_gemma":[0.21895865,0.00096199394,0.001317375,0.0048539774,0.028487947,0.026939623,0.00790206,0.0075792996,0.0015543876],"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":[0.000056257737,0.00007432199,0.00042550924,0.00029684888,0.000021436439,0.000063092986,0.0023353014,0.0009471654,0.00008638779,0.97121465,0.0010699832,0.02340902],"study_design_scores_gemma":[0.000044920922,0.000061717816,0.00021876524,0.00034060696,0.000010654819,0.00005518501,0.00093736977,0.0018764908,0.00017840973,0.9781317,0.01811679,0.000027503665],"about_ca_topic_score_codex":0.0022391777,"about_ca_topic_score_gemma":0.0017745602,"teacher_disagreement_score":0.08524376,"about_ca_system_score_codex":0.0055491063,"about_ca_system_score_gemma":0.004701214,"threshold_uncertainty_score":0.45081747},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55786127,0.0074139256,0.17125471,0.009129298,0.0036013762,0.01667258,0.0070674233,0.0012827974,0.2257167],"genre_scores_gemma":[0.6528535,0.0032061622,0.2811495,0.0019185763,0.00032913534,0.022575904,0.0030326298,0.00030737385,0.03462718],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9327186,0.034359735,0.0108819315,0.0030778828,0.016780287,0.0021816136],"domain_scores_gemma":[0.8152322,0.103728145,0.012962902,0.011491507,0.052839458,0.0037457463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05324062,0.0011806182,0.0011827376,0.006119941,0.0026726222,0.005148274,0.001525206,0.0028118948,0.009777512],"category_scores_gemma":[0.12046887,0.0007426335,0.0021977518,0.0043276027,0.0029984785,0.0043653385,0.0048118434,0.002696788,0.0030407754],"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":[0.002109009,0.0015550028,0.29498217,0.0058004055,0.0006648416,0.00034859416,0.025213426,0.0018657933,0.010601068,0.030313551,0.019145366,0.6074008],"study_design_scores_gemma":[0.00039178698,0.0043689264,0.6701082,0.0066510444,0.00074923644,0.0013366548,0.023884531,0.0066797193,0.02027548,0.021320144,0.24368201,0.00055230065],"about_ca_topic_score_codex":0.005815442,"about_ca_topic_score_gemma":0.012768554,"teacher_disagreement_score":0.05324062,"about_ca_system_score_codex":0.005282767,"about_ca_system_score_gemma":0.010880085,"threshold_uncertainty_score":0.28156662},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55532897,0.03412453,0.3094875,0.010308692,0.0029464029,0.0037899893,0.006497736,0.0010304593,0.07648581],"genre_scores_gemma":[0.79622,0.0080683185,0.17944798,0.00091602927,0.00071705796,0.0042815423,0.0019497178,0.00041806317,0.007981151],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8420622,0.101274475,0.01657509,0.005874769,0.031886347,0.0023271984],"domain_scores_gemma":[0.39287296,0.4799982,0.018682908,0.024504578,0.08274911,0.0011921498],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15134035,0.0018941603,0.0019894065,0.016740253,0.0020069107,0.009382861,0.0017163492,0.0012420511,0.0070659295],"category_scores_gemma":[0.37713432,0.0008610934,0.004640033,0.018191574,0.0029593334,0.006036391,0.0032046728,0.0021134093,0.0018942957],"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":[0.0013774466,0.0004918412,0.20051166,0.0091838315,0.0040928354,0.0002861321,0.030306716,0.0033543292,0.0040087723,0.018362535,0.010093014,0.71793085],"study_design_scores_gemma":[0.0005411336,0.003803877,0.65365064,0.0151615245,0.00848235,0.0013122156,0.056032248,0.013330402,0.022581149,0.04432163,0.17994447,0.00083840353],"about_ca_topic_score_codex":0.007569758,"about_ca_topic_score_gemma":0.011359562,"teacher_disagreement_score":0.84865963,"about_ca_system_score_codex":0.0038073903,"about_ca_system_score_gemma":0.005816236,"threshold_uncertainty_score":0.80037385},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.258324,0.020973004,0.10532738,0.10975864,0.001468993,0.0059629693,0.011612848,0.004393119,0.4821791],"genre_scores_gemma":[0.8062851,0.0054396475,0.121643364,0.003288325,0.00020064745,0.0014279848,0.003784743,0.00020301071,0.05772708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9772307,0.0067681517,0.0007193658,0.0006519128,0.012997814,0.0016320659],"domain_scores_gemma":[0.96782625,0.008172655,0.0021585226,0.0015252056,0.016145263,0.0041720388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027217736,0.00047415815,0.00025342684,0.005108429,0.002904363,0.005855848,0.0019703787,0.00076548994,0.002793314],"category_scores_gemma":[0.03817638,0.00031144996,0.00025227427,0.008611948,0.0020990036,0.001988692,0.003993807,0.0010814365,0.00039661472],"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":[0.00019558857,0.00021924339,0.08297482,0.0005816293,0.000058361315,0.000105786276,0.0035845106,0.0034247914,0.0011480906,0.06501631,0.07461308,0.7680778],"study_design_scores_gemma":[0.00020215065,0.000672861,0.44986734,0.001433272,0.0002574282,0.00024040966,0.008911724,0.010223008,0.0053314967,0.022458415,0.50014144,0.00026044532],"about_ca_topic_score_codex":0.7980783,"about_ca_topic_score_gemma":0.8868503,"teacher_disagreement_score":0.95808613,"about_ca_system_score_codex":0.041913882,"about_ca_system_score_gemma":0.14767462,"threshold_uncertainty_score":0},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76100385,0.0030899362,0.080052055,0.015966758,0.00011796956,0.0006335849,0.0002615833,0.00067820406,0.1381961],"genre_scores_gemma":[0.9747328,0.0006365451,0.020223768,0.0002657762,0.000016443171,0.0001357891,0.00009004905,0.000045473458,0.0038533432],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9756133,0.008960664,0.0015486295,0.0016347524,0.007872956,0.0043696454],"domain_scores_gemma":[0.93798476,0.02118564,0.00929849,0.009329423,0.0144154485,0.0077862693],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01945586,0.0005296905,0.0006713402,0.009076743,0.0070992513,0.012819517,0.0015550154,0.0030094706,0.0047970493],"category_scores_gemma":[0.077461496,0.0010845409,0.0011576175,0.004881154,0.007661258,0.0150174275,0.012466361,0.0043415036,0.001446604],"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":[0.0005722147,0.0005563264,0.15397817,0.00077874167,0.00018259542,0.0012345808,0.06819252,0.0032359269,0.0057393657,0.33772212,0.0064913468,0.4213162],"study_design_scores_gemma":[0.0001444866,0.0020786654,0.2664995,0.002107293,0.00010727834,0.002109009,0.111037664,0.010666248,0.005551123,0.5019685,0.09720799,0.00052229944],"about_ca_topic_score_codex":0.006758286,"about_ca_topic_score_gemma":0.0070677362,"teacher_disagreement_score":0.98054415,"about_ca_system_score_codex":0.0040248437,"about_ca_system_score_gemma":0.01018638,"threshold_uncertainty_score":0.10289365},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008106108,0.019472161,0.0293152,0.108837456,0.0036891976,0.00009768676,0.000041548,0.00018862794,0.8375474],"genre_scores_gemma":[0.17660381,0.028104536,0.071057364,0.06795259,0.00577696,0.001019186,0.00016858285,0.0010050331,0.6483119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98731565,0.0074363197,0.00036640387,0.0012824219,0.0029811573,0.00061801384],"domain_scores_gemma":[0.9922708,0.0049432414,0.00022272074,0.0010707757,0.0010066146,0.0004857457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01220754,0.0012443892,0.0012056115,0.0023505623,0.0056203296,0.019921515,0.002029731,0.00818295,0.031941704],"category_scores_gemma":[0.01642454,0.0008872101,0.00049615017,0.002028441,0.03339754,0.024746723,0.0088671595,0.013653015,0.011944114],"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":[0.0000027254375,0.000012450284,0.00002060959,0.000054727992,0.0000021135236,0.000021264073,0.000997147,0.00009865498,0.00003488916,0.9464433,0.03149281,0.020819362],"study_design_scores_gemma":[0.000005728123,0.00000774876,0.000037969978,0.000524679,0.0000028397399,0.000040115538,0.0015499148,0.00026611256,0.000091726215,0.6832682,0.31419542,0.000009474045],"about_ca_topic_score_codex":0.006650078,"about_ca_topic_score_gemma":0.009732846,"teacher_disagreement_score":0.031941704,"about_ca_system_score_codex":0.009659382,"about_ca_system_score_gemma":0.01766848,"threshold_uncertainty_score":0.10685569},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003246471,0.017647702,0.028374841,0.34104428,0.004873837,0.0002834682,0.00020197446,0.00046733065,0.60386],"genre_scores_gemma":[0.12513584,0.029703643,0.109656125,0.10720061,0.0010748032,0.00057085714,0.0003438911,0.00057374605,0.6257404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99488235,0.001915515,0.00015031258,0.00025667832,0.0023421966,0.0004529425],"domain_scores_gemma":[0.99706453,0.0010075589,0.00009358436,0.00016337441,0.001122012,0.0005489249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056987586,0.0008485407,0.00034324027,0.0010734444,0.0049792305,0.010344889,0.0013170745,0.0040434776,0.007204135],"category_scores_gemma":[0.005565624,0.0003227305,0.00039168523,0.0013656573,0.011270466,0.008069828,0.003366699,0.006062942,0.0033441368],"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":[0.00001315457,0.000050788985,0.00070044125,0.000159415,0.000008183219,0.00007540492,0.005191619,0.00046037417,0.00016238749,0.2601676,0.60684526,0.12616548],"study_design_scores_gemma":[0.000008377865,0.000019284926,0.0005673852,0.00023561498,0.00000509564,0.000055459048,0.003259831,0.00021007414,0.000115382165,0.039952867,0.9555536,0.000017153692],"about_ca_topic_score_codex":0.17471775,"about_ca_topic_score_gemma":0.4869217,"teacher_disagreement_score":0.17471775,"about_ca_system_score_codex":0.019217355,"about_ca_system_score_gemma":0.036323585,"threshold_uncertainty_score":0.34740156},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7499078,0.0032931915,0.015997129,0.01631648,0.00031226478,0.00047618843,0.0003342735,0.0001826332,0.21318005],"genre_scores_gemma":[0.94889957,0.0019595283,0.0067603374,0.00088034675,0.00007679747,0.00024011241,0.00014636097,0.000030775183,0.0410062],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99035054,0.0045592533,0.0003604476,0.0005403477,0.002215044,0.0019744327],"domain_scores_gemma":[0.9730234,0.007944554,0.0033118397,0.001322726,0.006946109,0.007451277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011199492,0.00038448704,0.00042183299,0.002541903,0.004884381,0.00811119,0.00092466123,0.0014982176,0.015047045],"category_scores_gemma":[0.01854847,0.0003701113,0.00042939693,0.0024717695,0.0024428999,0.003956918,0.004573076,0.002606829,0.0026811133],"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":[0.0002555444,0.0011803183,0.1750477,0.0015106604,0.00009029288,0.00089376746,0.17692962,0.0019619232,0.0058971276,0.14870958,0.011770573,0.47575298],"study_design_scores_gemma":[0.000041990243,0.0006795955,0.41194782,0.0016966872,0.00007991475,0.0005474469,0.18565302,0.0017230543,0.0043817917,0.016170029,0.37692425,0.00015441023],"about_ca_topic_score_codex":0.043475054,"about_ca_topic_score_gemma":0.05848551,"teacher_disagreement_score":0.043475054,"about_ca_system_score_codex":0.014071536,"about_ca_system_score_gemma":0.03826848,"threshold_uncertainty_score":0.10209662},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009638879,0.0010062058,0.91813636,0.018058216,0.00049868523,0.023000691,0.0001930576,0.0010107395,0.028457185],"genre_scores_gemma":[0.09020982,0.0006051649,0.891515,0.00080071914,0.00015641961,0.008356868,0.0002233216,0.00018827277,0.007944398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.77120686,0.17000352,0.011486345,0.011337146,0.031937964,0.0040282216],"domain_scores_gemma":[0.8095368,0.10352942,0.014831413,0.020826774,0.042682722,0.0085928785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23299752,0.0023933426,0.0019275097,0.011133446,0.014993466,0.02143386,0.005147004,0.0053469394,0.0065891948],"category_scores_gemma":[0.13878389,0.0018153465,0.0017373493,0.009021017,0.020316763,0.012887462,0.013825278,0.008558618,0.0033538088],"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":[0.00017613193,0.0013156192,0.0046286285,0.0026980867,0.00023546275,0.0003571987,0.034567278,0.011284346,0.0050183525,0.26447484,0.034491513,0.6407526],"study_design_scores_gemma":[0.00064753887,0.0015869206,0.009204103,0.005844949,0.00013801486,0.0005469237,0.04260727,0.025857767,0.008042111,0.59348375,0.31110618,0.00093450263],"about_ca_topic_score_codex":0.015539119,"about_ca_topic_score_gemma":0.023015281,"teacher_disagreement_score":0.23299752,"about_ca_system_score_codex":0.027879262,"about_ca_system_score_gemma":0.14845298,"threshold_uncertainty_score":0.9458506},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016636592,0.005236961,0.00009623981,0.048208974,0.9457201,0.000020452626,0.00004738551,0.000030441151,0.00062284584],"genre_scores_gemma":[0.00029329825,0.0035153306,0.00015605887,0.03291196,0.9583212,0.000035437664,0.00003197904,0.000037998474,0.0046967226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97763693,0.005086396,0.003855335,0.0022657616,0.009937988,0.0012175342],"domain_scores_gemma":[0.86850953,0.048858948,0.0077549866,0.0038031556,0.058297414,0.012775883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026531104,0.005890069,0.011384446,0.011134265,0.006811766,0.015834775,0.008173007,0.042873275,0.014625837],"category_scores_gemma":[0.099145286,0.0028052854,0.005497147,0.006059676,0.0064462973,0.006675989,0.0027846156,0.03746589,0.014058683],"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":[0.000029619261,0.000012567541,0.000019307543,0.00017767996,0.00003133843,0.000048677393,0.000007301947,0.000018816663,0.000023448845,0.00011496502,0.9970425,0.00247397],"study_design_scores_gemma":[0.00016160698,0.00004241875,0.0005065514,0.0012086179,0.0002774671,0.00023843431,0.00006865762,0.0002522517,0.0001366506,0.0017212237,0.9953376,0.00004853122],"about_ca_topic_score_codex":0.00591404,"about_ca_topic_score_gemma":0.01451202,"teacher_disagreement_score":0.042873275,"about_ca_system_score_codex":0.009206968,"about_ca_system_score_gemma":0.009713571,"threshold_uncertainty_score":0.14031154},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037791717,0.025797324,0.0032415823,0.6554069,0.027540045,0.000062767715,0.0002662457,0.00025937989,0.28364655],"genre_scores_gemma":[0.12774833,0.034667354,0.006214856,0.22682399,0.008930001,0.000134943,0.00023962451,0.0009146614,0.5943263],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9966568,0.0013405094,0.00005170823,0.00046555142,0.00088258844,0.0006028606],"domain_scores_gemma":[0.99438936,0.001344387,0.0002610892,0.00035095154,0.0014949496,0.0021592143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004233619,0.0005743461,0.00055381306,0.0011204311,0.011997093,0.01142241,0.0010624405,0.0041052285,0.06768566],"category_scores_gemma":[0.014496369,0.00043568498,0.0004949815,0.0009772982,0.008549171,0.011489948,0.005039345,0.012571836,0.018618517],"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":[0.00001847625,0.000020417203,0.00046382495,0.000072969,0.0000059977197,0.00023460256,0.013893009,0.00002559143,0.00014347848,0.07800131,0.8763182,0.030801978],"study_design_scores_gemma":[0.0000024160431,0.000004952286,0.00014427061,0.00012691104,0.0000017337023,0.00009547424,0.0061108447,0.000008833086,0.000034221943,0.0050811665,0.9883825,0.0000066514576],"about_ca_topic_score_codex":0.035429865,"about_ca_topic_score_gemma":0.096932665,"teacher_disagreement_score":0.06768566,"about_ca_system_score_codex":0.0052918955,"about_ca_system_score_gemma":0.008880344,"threshold_uncertainty_score":0.22643113},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9204391,0.0019749135,0.02769735,0.009364312,0.00048443326,0.0014140025,0.00021468692,0.000236021,0.03817515],"genre_scores_gemma":[0.9050885,0.0028643324,0.055412747,0.0009520502,0.00014014433,0.0018754769,0.00019060934,0.000056926685,0.03341928],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99299765,0.0046008467,0.00021564237,0.0004075413,0.00130662,0.00047159774],"domain_scores_gemma":[0.9744285,0.017012658,0.0020650702,0.0012888245,0.0035001892,0.001704798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009073016,0.0005459551,0.00073103997,0.0011504205,0.0017104896,0.0026335907,0.0011844282,0.0012156924,0.016159497],"category_scores_gemma":[0.03687796,0.0003275715,0.0005571043,0.0007131338,0.0015318234,0.0017363663,0.0015944343,0.0016485756,0.0019648345],"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":[0.00073399855,0.003546912,0.05046088,0.0014739796,0.000106070824,0.000803404,0.098707266,0.000954723,0.008650353,0.006039781,0.008729073,0.81979346],"study_design_scores_gemma":[0.0005053273,0.013655371,0.37195107,0.0038773213,0.00043598362,0.0017652118,0.36530975,0.00642743,0.02880783,0.021175489,0.18565845,0.0004307656],"about_ca_topic_score_codex":0.0061347503,"about_ca_topic_score_gemma":0.011453735,"teacher_disagreement_score":0.016159497,"about_ca_system_score_codex":0.0015644721,"about_ca_system_score_gemma":0.0051494045,"threshold_uncertainty_score":0.05405891},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019018287,0.00050132035,0.00052871334,0.9900406,0.007644638,0.000034491946,0.000015621898,0.000017827875,0.0010265522],"genre_scores_gemma":[0.0019511757,0.00018546052,0.0010816619,0.9893343,0.0055520837,0.00019089546,0.000009382842,0.000022301143,0.0016727175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.73450667,0.1294275,0.034973793,0.023065202,0.061654605,0.016372245],"domain_scores_gemma":[0.29140133,0.60201883,0.020098865,0.014824896,0.04399587,0.027660199],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23195036,0.0015138577,0.0054049133,0.0032265657,0.023689378,0.02534451,0.009938867,0.19859369,0.012406497],"category_scores_gemma":[0.5283234,0.0037560076,0.00480784,0.0033430182,0.05187436,0.028844275,0.02218115,0.21234204,0.009425069],"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":[0.00017356602,0.000077910845,0.0008756657,0.00087691046,0.00009308306,0.0018242733,0.00677203,0.00018457198,0.00061353436,0.061335795,0.9125135,0.014659271],"study_design_scores_gemma":[0.00050277554,0.00013173553,0.0013639037,0.0039649736,0.00013846457,0.0025244278,0.010541477,0.0011855441,0.0006679793,0.114373654,0.86421734,0.0003876582],"about_ca_topic_score_codex":0.019943867,"about_ca_topic_score_gemma":0.037854988,"teacher_disagreement_score":0.76804966,"about_ca_system_score_codex":0.023870612,"about_ca_system_score_gemma":0.06706658,"threshold_uncertainty_score":0.94714195},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9767239,0.00048366986,0.005380864,0.0013688606,0.000024354207,0.00022580492,0.00015537308,0.000021194139,0.015616027],"genre_scores_gemma":[0.98466563,0.00029425402,0.0049316594,0.0001434609,0.0000066055536,0.00013445412,0.000084039326,0.000008266121,0.009731627],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99674135,0.0013444423,0.00008957048,0.00041837434,0.0008181469,0.0005880322],"domain_scores_gemma":[0.9896556,0.004731472,0.0011144343,0.00039664874,0.0030257776,0.0010761819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004400777,0.00030188926,0.00048898265,0.0017909228,0.004742478,0.0037502456,0.00091836153,0.00076848443,0.006319854],"category_scores_gemma":[0.008380057,0.00017215329,0.00031037015,0.0022615218,0.0034597144,0.0012255757,0.0024297927,0.0010504114,0.0004105974],"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":[0.00038446012,0.0004830196,0.40245247,0.0007725085,0.000099821504,0.00085862196,0.2914326,0.0025669702,0.009676357,0.024176762,0.0020247754,0.26507163],"study_design_scores_gemma":[0.000021173477,0.00044046383,0.76908684,0.00034536907,0.00004515475,0.00015768207,0.18528682,0.0021527628,0.002027384,0.004302798,0.0360512,0.00008230803],"about_ca_topic_score_codex":0.46652424,"about_ca_topic_score_gemma":0.68111044,"teacher_disagreement_score":0.46652424,"about_ca_system_score_codex":0.013996702,"about_ca_system_score_gemma":0.014829377,"threshold_uncertainty_score":0.92761755},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81913507,0.01072745,0.012438075,0.04747136,0.00044116843,0.0001297183,0.001822319,0.0002617939,0.10757315],"genre_scores_gemma":[0.9880127,0.0016856974,0.0018120639,0.0007368987,0.00011844486,0.000077452714,0.00030272533,0.000074513264,0.0071794796],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99116826,0.003956368,0.0005093935,0.0011297424,0.001867673,0.0013685811],"domain_scores_gemma":[0.94997036,0.022656556,0.009971305,0.0021260798,0.008197742,0.007077956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009912228,0.0003935895,0.0004901544,0.00222162,0.00351804,0.01195565,0.0016589139,0.0023526072,0.021504594],"category_scores_gemma":[0.047589038,0.00044490214,0.00070142734,0.0057146274,0.0039129793,0.008687538,0.0051540653,0.0028671927,0.0039180364],"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":[0.0005726037,0.00027919133,0.59468454,0.00074172893,0.0002385148,0.00040840832,0.05585662,0.00335502,0.00112831,0.10082519,0.014744579,0.22716531],"study_design_scores_gemma":[0.000022268778,0.0002564056,0.8629177,0.00049807824,0.000110458124,0.000296678,0.04497947,0.00262304,0.0011156461,0.020159364,0.066913314,0.00010752423],"about_ca_topic_score_codex":0.05756571,"about_ca_topic_score_gemma":0.056735594,"teacher_disagreement_score":0.99008775,"about_ca_system_score_codex":0.013012184,"about_ca_system_score_gemma":0.01206775,"threshold_uncertainty_score":0.1144613},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039394006,0.02084627,0.60567015,0.069545,0.0005850194,0.0021802313,0.00011314273,0.00017504161,0.26149118],"genre_scores_gemma":[0.8407024,0.008396662,0.14255393,0.002192306,0.00028542944,0.002949103,0.000088310764,0.00006198672,0.0027697242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92017317,0.060504965,0.0023900876,0.0023479038,0.013051433,0.0015324331],"domain_scores_gemma":[0.75570333,0.21803387,0.0061099515,0.0091407625,0.00985541,0.0011566576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.111405835,0.0010797334,0.0012347085,0.0057495134,0.0045651514,0.011594832,0.00305133,0.004607562,0.0061843502],"category_scores_gemma":[0.15683654,0.0010033743,0.0011251587,0.004205174,0.031364474,0.015670583,0.0080948975,0.0050195013,0.000549591],"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":[0.000024147635,0.00004398696,0.00069004716,0.0004410531,0.000010630439,0.000052293923,0.0024330858,0.0017399411,0.00006450642,0.96543324,0.00036061683,0.028706547],"study_design_scores_gemma":[0.000036943442,0.00010595861,0.0011639692,0.0020782205,0.000018393417,0.00018231604,0.004145402,0.009500822,0.00033604284,0.9570967,0.02529908,0.00003609853],"about_ca_topic_score_codex":0.0021969236,"about_ca_topic_score_gemma":0.0018410427,"teacher_disagreement_score":0.88859415,"about_ca_system_score_codex":0.009636865,"about_ca_system_score_gemma":0.010250106,"threshold_uncertainty_score":0.58917737},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92917526,0.010392547,0.0011821251,0.0013464122,0.00013509726,0.00039913066,0.040087517,0.00015225708,0.017129712],"genre_scores_gemma":[0.9540538,0.010292834,0.005193574,0.00019898753,0.00023235266,0.00055836025,0.025081933,0.00010284101,0.0042853034],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9890261,0.0022459775,0.0030118746,0.0008359288,0.0043149963,0.0005651055],"domain_scores_gemma":[0.9018232,0.03720455,0.027545663,0.0038630408,0.026580349,0.002983157],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.009393486,0.00034378422,0.00088998966,0.11453601,0.0016012265,0.0052174893,0.00083691295,0.0005917549,0.0026510665],"category_scores_gemma":[0.06501124,0.0002688535,0.00082737044,0.12243123,0.0010640301,0.0032156878,0.0031031908,0.0005843374,0.00081756077],"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":[0.00034013196,0.00013413951,0.7716669,0.0056089647,0.00041021485,0.0007781318,0.027848985,0.0003948717,0.0019493233,0.002953316,0.011882114,0.17603292],"study_design_scores_gemma":[0.000011854378,0.00009962695,0.9241322,0.0009756364,0.0001399927,0.00096756953,0.022324065,0.00035420936,0.001200305,0.00037060693,0.049375102,0.000048694343],"about_ca_topic_score_codex":0.009485229,"about_ca_topic_score_gemma":0.01619399,"teacher_disagreement_score":0.885464,"about_ca_system_score_codex":0.0037244766,"about_ca_system_score_gemma":0.004597033,"threshold_uncertainty_score":0.049678087},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99652123,0.000661774,0.0004429187,0.00023104099,0.000081883365,0.00005475419,0.0001826841,0.00003985759,0.0017839295],"genre_scores_gemma":[0.9913669,0.00056224474,0.00062671874,0.00008441178,0.000073234936,0.00009711263,0.00022399204,0.00001599495,0.0069493046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986437,0.00049315585,0.00012691818,0.00020145276,0.00029466418,0.00024017724],"domain_scores_gemma":[0.99491465,0.0018939319,0.0008457035,0.00021017392,0.001414764,0.00072060915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021757206,0.001113552,0.00040035354,0.0017658636,0.0013838356,0.0013018127,0.00036287552,0.001249985,0.00260026],"category_scores_gemma":[0.007803902,0.00031125406,0.00108382,0.00076305226,0.00079399656,0.000696837,0.00057904795,0.0013965366,0.00073798816],"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":[0.0028593645,0.002586952,0.808907,0.00031807733,0.00033398863,0.007677853,0.02613195,0.0017685707,0.011726877,0.00036650023,0.0027124872,0.13461046],"study_design_scores_gemma":[0.000055596127,0.0025025227,0.9750533,0.000075481184,0.0001317347,0.0017204221,0.005873513,0.00079971313,0.0038918194,0.00006390324,0.009744137,0.0000878869],"about_ca_topic_score_codex":0.10204021,"about_ca_topic_score_gemma":0.090803385,"teacher_disagreement_score":0.10204021,"about_ca_system_score_codex":0.0012983537,"about_ca_system_score_gemma":0.0011410372,"threshold_uncertainty_score":0.20289254},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032073993,0.011442889,0.39789593,0.48982066,0.0037996497,0.002405654,0.00009515625,0.0015391839,0.060926992],"genre_scores_gemma":[0.3642545,0.0022412855,0.60401887,0.018762602,0.00043041626,0.0041653276,0.000040345563,0.0005106954,0.005575996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5017094,0.4539477,0.011402382,0.008283056,0.020138131,0.0045194183],"domain_scores_gemma":[0.62679946,0.24358648,0.008638199,0.0584804,0.045157216,0.017338172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.42979315,0.0022442567,0.0022390992,0.011687401,0.02569194,0.033311848,0.006971737,0.011799879,0.0036452473],"category_scores_gemma":[0.31278744,0.002380642,0.0014670576,0.0045808144,0.10885364,0.033894114,0.03753179,0.032042563,0.0012734107],"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":[0.00017930203,0.00036884448,0.0059449114,0.0010880954,0.00008546364,0.0006239585,0.36831692,0.0006598383,0.0013372295,0.37654412,0.0361382,0.20871316],"study_design_scores_gemma":[0.00016888036,0.00033373592,0.001876555,0.0067341207,0.000072972776,0.0009883658,0.18565507,0.00279819,0.0016054171,0.42750728,0.37192452,0.0003348077],"about_ca_topic_score_codex":0.008023971,"about_ca_topic_score_gemma":0.016063184,"teacher_disagreement_score":0.42979315,"about_ca_system_score_codex":0.023287944,"about_ca_system_score_gemma":0.04327685,"threshold_uncertainty_score":0.7031666},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074971374,0.9570884,0.0028905505,0.011438576,0.0012870748,0.006017474,0.009142569,0.00004492855,0.004593268],"genre_scores_gemma":[0.088683665,0.8585431,0.023335394,0.008385728,0.00030825697,0.013822105,0.005435095,0.000049574293,0.0014371712],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8638012,0.047571525,0.04086439,0.0045664683,0.03913644,0.004059991],"domain_scores_gemma":[0.64946276,0.17573336,0.0377729,0.009363881,0.12397016,0.0036968973],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12193592,0.0018635615,0.006702048,0.044247527,0.0044265958,0.006930596,0.003744529,0.0033638156,0.0024842715],"category_scores_gemma":[0.31172124,0.001715017,0.005337957,0.05910136,0.0032845703,0.00475715,0.0038704737,0.0024868005,0.00030123634],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035892098,0.000029952284,0.0034606482,0.8174694,0.0032236862,0.00036262439,0.0057570534,0.0006156606,0.00067491597,0.0035536415,0.019790566,0.1447028],"study_design_scores_gemma":[0.00018662083,0.000074250696,0.00763268,0.8830744,0.009706603,0.00014204704,0.0025729935,0.00013867186,0.00044325675,0.0008549981,0.09507132,0.000102145736],"about_ca_topic_score_codex":0.506774,"about_ca_topic_score_gemma":0.74546385,"teacher_disagreement_score":0.930319,"about_ca_system_score_codex":0.06968097,"about_ca_system_score_gemma":0.3716157,"threshold_uncertainty_score":0.9922614},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029647386,0.10855486,0.35395193,0.3140223,0.008673091,0.006499371,0.00089277764,0.000667184,0.17709105],"genre_scores_gemma":[0.5601018,0.037338536,0.33713558,0.032424975,0.0013529297,0.009431067,0.000430455,0.00040565548,0.021378988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8564693,0.10907226,0.0059097414,0.004481861,0.021192806,0.0028740289],"domain_scores_gemma":[0.78020734,0.16406403,0.009724394,0.008778047,0.03249889,0.004727453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13009363,0.002198968,0.0026711,0.0074821496,0.007362587,0.021339806,0.004685408,0.0071686744,0.013495242],"category_scores_gemma":[0.16643022,0.0008326965,0.002478144,0.004620474,0.021426074,0.013257011,0.007473284,0.011190286,0.0012961631],"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":[0.00032537026,0.00027731972,0.004244378,0.005434811,0.0003765851,0.0002520564,0.01994275,0.004783772,0.00056285976,0.6275857,0.023883449,0.31233102],"study_design_scores_gemma":[0.0003120753,0.0009515086,0.010389408,0.022783412,0.00050306466,0.00047092178,0.029991353,0.009347258,0.0021184431,0.48237482,0.44037408,0.0003836535],"about_ca_topic_score_codex":0.06856677,"about_ca_topic_score_gemma":0.09916342,"teacher_disagreement_score":0.13009363,"about_ca_system_score_codex":0.04645804,"about_ca_system_score_gemma":0.10385557,"threshold_uncertainty_score":0.68800914},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6367585,0.007121562,0.017822327,0.0633362,0.0005855074,0.0022404888,0.00023925258,0.0002792815,0.27161697],"genre_scores_gemma":[0.98357093,0.0015913255,0.006281279,0.0019244491,0.000057971654,0.00048104738,0.000057975467,0.000055205637,0.005979802],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9036426,0.07365422,0.0018330129,0.0018121528,0.0105375135,0.008520473],"domain_scores_gemma":[0.84863657,0.07990754,0.010907312,0.005926828,0.03973775,0.014883995],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.115345046,0.00065611984,0.0006751753,0.0037685884,0.012032079,0.017179277,0.0024694165,0.0015188515,0.004654732],"category_scores_gemma":[0.09311416,0.00036059605,0.00048490267,0.0049707163,0.013115104,0.0064915717,0.011985761,0.0046199146,0.0003322408],"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":[0.0004085171,0.0014856372,0.103420325,0.0015485242,0.000094932766,0.00055274996,0.43877953,0.0010286625,0.0011093257,0.10808091,0.019061739,0.3244292],"study_design_scores_gemma":[0.00006986594,0.00076560955,0.06808283,0.003448897,0.00010812208,0.000118149735,0.78029764,0.0013843323,0.0016583969,0.016995518,0.12690453,0.0001660596],"about_ca_topic_score_codex":0.14664233,"about_ca_topic_score_gemma":0.2645175,"teacher_disagreement_score":0.88465494,"about_ca_system_score_codex":0.04923644,"about_ca_system_score_gemma":0.10536444,"threshold_uncertainty_score":0.6100102},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001752168,0.0009206151,0.942844,0.02954221,0.00028773834,0.003976263,0.00041756264,0.0003552474,0.01990428],"genre_scores_gemma":[0.0274804,0.0010183404,0.9607315,0.0019094312,0.000103361905,0.0064190226,0.00017796275,0.000053945976,0.0021060486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87032956,0.109433234,0.0042658974,0.0028225968,0.012110634,0.0010380382],"domain_scores_gemma":[0.88475937,0.092049114,0.0047631096,0.0056910166,0.010550302,0.002187065],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14372939,0.0020503767,0.0017139709,0.005455612,0.00399326,0.017302876,0.0068491893,0.0065673874,0.007312913],"category_scores_gemma":[0.091965936,0.0015656346,0.0020428903,0.0063212942,0.016077759,0.017668523,0.005565516,0.007847754,0.003283618],"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":[0.000119962926,0.000215099,0.0013010271,0.0013486437,0.000090631904,0.00015512235,0.011873851,0.013747391,0.0005590951,0.8726766,0.010669118,0.087243475],"study_design_scores_gemma":[0.00019059426,0.00034695948,0.00055932504,0.0020566199,0.00008917882,0.00016614022,0.0062825317,0.040839024,0.0005214022,0.8371028,0.111705825,0.00013962046],"about_ca_topic_score_codex":0.005527653,"about_ca_topic_score_gemma":0.0056786304,"teacher_disagreement_score":0.8562706,"about_ca_system_score_codex":0.01082245,"about_ca_system_score_gemma":0.022298643,"threshold_uncertainty_score":0.7601228},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038495395,0.021773648,0.0018695225,0.9687037,0.0043790746,0.00006650396,0.000030896143,0.000057002344,0.0027347445],"genre_scores_gemma":[0.04385554,0.069242224,0.054145552,0.81449085,0.005163321,0.00073090836,0.0002593635,0.00044228707,0.0116699785],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.89869183,0.057698347,0.006404897,0.0044726483,0.02138486,0.011347447],"domain_scores_gemma":[0.7045157,0.13366635,0.0058261002,0.01769862,0.064492725,0.07380043],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18256849,0.0021689744,0.0038404053,0.0056214966,0.017805656,0.031547822,0.0107879,0.039075267,0.019898342],"category_scores_gemma":[0.1632302,0.0022624386,0.003105515,0.0052511217,0.056350004,0.03702644,0.030502653,0.060286675,0.004540201],"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":[0.00018418398,0.0003390686,0.0009898703,0.0036533056,0.00018560095,0.00088982825,0.024764016,0.000712868,0.0007057282,0.13855778,0.64904135,0.1799763],"study_design_scores_gemma":[0.00014420315,0.00012929318,0.0015150782,0.016999824,0.000035986894,0.00019409503,0.02241902,0.00028027705,0.0002361653,0.1106981,0.847186,0.00016191979],"about_ca_topic_score_codex":0.29049397,"about_ca_topic_score_gemma":0.42231572,"teacher_disagreement_score":0.8174315,"about_ca_system_score_codex":0.078893654,"about_ca_system_score_gemma":0.25088158,"threshold_uncertainty_score":0.965526},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33427733,0.030508615,0.013090114,0.44900376,0.000770923,0.00026771057,0.0001216196,0.00009870637,0.17186116],"genre_scores_gemma":[0.9509375,0.01826546,0.004501173,0.017728737,0.00031986853,0.00017801939,0.000050633334,0.00007267195,0.007945846],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8692341,0.095671654,0.004588625,0.0043691094,0.018746572,0.007389982],"domain_scores_gemma":[0.84537244,0.09846489,0.019824969,0.0072305524,0.012527033,0.01658013],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.101379916,0.0004604448,0.0010542078,0.008297788,0.015602121,0.039072707,0.0035441972,0.009013458,0.0053942883],"category_scores_gemma":[0.19251615,0.0012002924,0.0006962877,0.00801108,0.053217813,0.03401783,0.0147526935,0.010351242,0.0015628693],"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":[0.00011019326,0.00011572133,0.038085982,0.00064813846,0.00006308512,0.00041192333,0.80167395,0.00015679644,0.0004072544,0.06774062,0.00890922,0.081677124],"study_design_scores_gemma":[0.00006879692,0.00017230977,0.033028685,0.0025408035,0.00008023976,0.0005156912,0.71398735,0.00051232945,0.000278499,0.055569828,0.1930902,0.0001552668],"about_ca_topic_score_codex":0.095088005,"about_ca_topic_score_gemma":0.10730707,"teacher_disagreement_score":0.89862007,"about_ca_system_score_codex":0.031760838,"about_ca_system_score_gemma":0.04227041,"threshold_uncertainty_score":0.5361546},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6061338,0.014483663,0.04663624,0.28682327,0.0014574411,0.0023150886,0.00024349807,0.0002781562,0.041628897],"genre_scores_gemma":[0.9795211,0.0010152855,0.01139349,0.0067583523,0.00031004497,0.0005805332,0.000028791601,0.000019153804,0.00037335043],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.21362135,0.7176023,0.029218644,0.008466208,0.026361478,0.0047300514],"domain_scores_gemma":[0.047418416,0.8686725,0.048408613,0.013751335,0.01699951,0.0047495617],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6124612,0.0007372979,0.0018406389,0.008592847,0.0055868668,0.01444699,0.0034978844,0.0074791824,0.0035062279],"category_scores_gemma":[0.8236942,0.0015154883,0.0012169054,0.003906593,0.009563898,0.0076310867,0.007802931,0.008589473,0.00034712668],"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":[0.00407647,0.0012911124,0.15053119,0.007937045,0.0020634248,0.0027066993,0.39683065,0.0034495906,0.006452054,0.053720906,0.025586158,0.34535474],"study_design_scores_gemma":[0.0029050363,0.003218945,0.26380515,0.022927929,0.0020873977,0.00405628,0.23169348,0.045419652,0.010089569,0.23727214,0.1748209,0.0017034624],"about_ca_topic_score_codex":0.0062775873,"about_ca_topic_score_gemma":0.0064168926,"teacher_disagreement_score":0.3875388,"about_ca_system_score_codex":0.0130322,"about_ca_system_score_gemma":0.035922896,"threshold_uncertainty_score":0.47790438},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66209376,0.00647303,0.0020299954,0.18303506,0.00044485257,0.00042257423,0.0030305516,0.00022202804,0.14224818],"genre_scores_gemma":[0.96150964,0.0014906857,0.001598843,0.0041088494,0.00008258132,0.0000611761,0.00032739414,0.00004573627,0.030775199],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9930599,0.0015271998,0.00018394046,0.00039110836,0.002113424,0.0027244524],"domain_scores_gemma":[0.97064024,0.0032853668,0.0026629155,0.00076858787,0.0070448215,0.015598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044260663,0.00024120935,0.00050187844,0.001979825,0.012558583,0.009325608,0.0014531881,0.0025301774,0.013401989],"category_scores_gemma":[0.014517341,0.0004455377,0.00046289645,0.0042445506,0.0056345006,0.0032390053,0.0022218947,0.0019803913,0.0010178365],"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":[0.00063180097,0.00052778557,0.30412042,0.0007237606,0.0001269543,0.0005700217,0.020869525,0.0010979695,0.0008445261,0.10458097,0.3353946,0.23051165],"study_design_scores_gemma":[0.00022115542,0.00020491058,0.5384369,0.0009859417,0.00015788544,0.00018554459,0.08201765,0.001375927,0.00068545557,0.017353658,0.35823494,0.00013998697],"about_ca_topic_score_codex":0.93297535,"about_ca_topic_score_gemma":0.9884615,"teacher_disagreement_score":0.07404744,"about_ca_system_score_codex":0.07404744,"about_ca_system_score_gemma":0.15359794,"threshold_uncertainty_score":0.5372543},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919343,0.00007591538,0.00021566632,0.00075861136,0.000011736656,0.000016293488,0.000067800065,0.000006547633,0.0069131074],"genre_scores_gemma":[0.9995066,0.000009653991,0.000035876932,0.000035954992,0.0000018506005,0.000005224174,0.00003070795,0.0000031617997,0.00037094488],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98305434,0.0085830195,0.0009412494,0.00065142225,0.0021089222,0.0046609845],"domain_scores_gemma":[0.85371995,0.08854584,0.016784588,0.011022019,0.013443777,0.016483849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015471148,0.000106268235,0.0002301659,0.001477867,0.0013554734,0.0030280494,0.0010155694,0.0009816501,0.0077460064],"category_scores_gemma":[0.0830693,0.00031852597,0.00037236264,0.0014338031,0.0026420837,0.0016005285,0.003446615,0.0012439236,0.0005754382],"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":[0.0015522501,0.001037303,0.92750114,0.00005721288,0.00008325332,0.00014756054,0.018585896,0.0006065978,0.0021138191,0.015883826,0.0017847734,0.03064631],"study_design_scores_gemma":[0.000025239911,0.00016980548,0.97722626,0.000033210225,0.000012518159,0.00010485595,0.016923022,0.0004762472,0.00029123822,0.002927482,0.0017956112,0.000014496536],"about_ca_topic_score_codex":0.016167846,"about_ca_topic_score_gemma":0.031733178,"teacher_disagreement_score":0.98452884,"about_ca_system_score_codex":0.0031563472,"about_ca_system_score_gemma":0.0049352027,"threshold_uncertainty_score":0.08182019},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027594019,0.026616888,0.048957177,0.46076447,0.020757444,0.00049637374,0.0016668249,0.00077996997,0.4123668],"genre_scores_gemma":[0.6693222,0.03929623,0.08001427,0.09431594,0.0054858034,0.0013212416,0.002035558,0.001281994,0.10692672],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9749287,0.010318783,0.001563319,0.002707989,0.009180043,0.0013011938],"domain_scores_gemma":[0.9755397,0.008681223,0.0028886274,0.002381665,0.008224673,0.0022842707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012828072,0.0012470774,0.0021178992,0.0033387996,0.006935574,0.014809238,0.0022377581,0.003294974,0.0139810145],"category_scores_gemma":[0.048383974,0.0004800576,0.0007347087,0.0055898535,0.023648513,0.023503395,0.0050527295,0.006341313,0.005440849],"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":[0.00012140962,0.00017336338,0.00976546,0.0026764073,0.00018595939,0.00019942949,0.014361924,0.0006834501,0.0013831268,0.40574318,0.17779209,0.38691416],"study_design_scores_gemma":[0.000022492548,0.00021378814,0.006975629,0.004411328,0.000107061634,0.00029376394,0.022392843,0.00051700603,0.0009399406,0.34211692,0.6218417,0.00016755812],"about_ca_topic_score_codex":0.014002357,"about_ca_topic_score_gemma":0.016054459,"teacher_disagreement_score":0.014809238,"about_ca_system_score_codex":0.006348735,"about_ca_system_score_gemma":0.014527685,"threshold_uncertainty_score":0.067842126},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16077736,0.087135695,0.03341818,0.31563637,0.004158953,0.00094886724,0.00088231603,0.0006125792,0.39642972],"genre_scores_gemma":[0.8844543,0.020433495,0.0155475065,0.0116174575,0.00044769817,0.00032090058,0.000273663,0.0003014953,0.06660347],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9654493,0.010414179,0.0009012841,0.0016946939,0.017262524,0.004278104],"domain_scores_gemma":[0.94032496,0.01194465,0.003301118,0.0025893727,0.03192625,0.009913668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039538782,0.000570469,0.00064152613,0.0039428384,0.00984642,0.015698057,0.0021018942,0.0020227057,0.0045017973],"category_scores_gemma":[0.052234154,0.00042643913,0.00050341786,0.0052302084,0.019089662,0.005205897,0.005490287,0.0055509093,0.00039545057],"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":[0.00020859967,0.00017524365,0.013733187,0.0007887469,0.000076770935,0.00015658507,0.044712078,0.0019992793,0.00093676377,0.39593923,0.068653464,0.47261995],"study_design_scores_gemma":[0.00003609989,0.00017144355,0.064244345,0.0022676794,0.000051089934,0.000111824826,0.020133425,0.0013089674,0.0015764424,0.027015463,0.8829403,0.00014300896],"about_ca_topic_score_codex":0.9321726,"about_ca_topic_score_gemma":0.9337114,"teacher_disagreement_score":0.9604612,"about_ca_system_score_codex":0.181075,"about_ca_system_score_gemma":0.29983777,"threshold_uncertainty_score":0.9498369},"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":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014020158,0.048075292,0.007973265,0.21697004,0.718491,0.000039716273,0.00007240349,0.00011407409,0.008123989],"genre_scores_gemma":[0.010629593,0.042757295,0.0074203615,0.08045308,0.8490714,0.00024065816,0.00006337926,0.0001962575,0.009168089],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9494143,0.027453851,0.0040838234,0.0032257938,0.015130703,0.00069155876],"domain_scores_gemma":[0.8057573,0.16263145,0.0036890674,0.006085371,0.018938897,0.0028979026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031051405,0.002005554,0.0031450714,0.004395169,0.005453714,0.018303504,0.005689888,0.0126754595,0.004852022],"category_scores_gemma":[0.12229424,0.00069881754,0.0020644325,0.002684373,0.04357748,0.01139199,0.0040167244,0.034534365,0.0027645878],"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":[0.000042672928,0.000016938446,0.00005837539,0.0014715563,0.000044815664,0.0001318768,0.001434942,0.00024841726,0.00009764968,0.16719216,0.7957876,0.033472963],"study_design_scores_gemma":[0.000021161006,0.000024454923,0.00009195262,0.0017285767,0.000022588007,0.00015614691,0.00067913276,0.00036498645,0.00009163537,0.08518167,0.91160524,0.000032430617],"about_ca_topic_score_codex":0.0026481585,"about_ca_topic_score_gemma":0.0037945728,"teacher_disagreement_score":0.031051405,"about_ca_system_score_codex":0.0060627637,"about_ca_system_score_gemma":0.008240582,"threshold_uncertainty_score":0.16421753},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030153085,0.017274953,0.55738986,0.30979577,0.005948647,0.00070472725,0.00007851187,0.00034905135,0.078305386],"genre_scores_gemma":[0.7345555,0.004458328,0.22559547,0.025551744,0.0038739827,0.0018518808,0.000051360585,0.00034646306,0.003715291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5609218,0.36692128,0.013899422,0.017601455,0.036410592,0.004245526],"domain_scores_gemma":[0.578674,0.32956257,0.01709457,0.04600388,0.022397658,0.0062673246],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34787917,0.0016054407,0.0033158578,0.009602366,0.016488507,0.025884109,0.005216289,0.007228448,0.0019310878],"category_scores_gemma":[0.2617431,0.0016571918,0.0020093953,0.00402983,0.16078022,0.03413927,0.030097416,0.020623228,0.00043658362],"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":[0.000045567973,0.00003158756,0.00071531814,0.0004835257,0.000108942004,0.00009974729,0.02760515,0.0004719792,0.0001682649,0.9564105,0.0019649658,0.01189439],"study_design_scores_gemma":[0.00003425139,0.000027145821,0.00016655844,0.00035570443,0.000020053121,0.00007089104,0.0034804577,0.0006956153,0.00017852455,0.9833288,0.011618488,0.000023315886],"about_ca_topic_score_codex":0.0025397553,"about_ca_topic_score_gemma":0.0026127559,"teacher_disagreement_score":0.6521208,"about_ca_system_score_codex":0.012368374,"about_ca_system_score_gemma":0.017721212,"threshold_uncertainty_score":0.8041811},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56431,0.00617791,0.005402743,0.027843514,0.00022540409,0.00032108196,0.000153814,0.00009459537,0.39547083],"genre_scores_gemma":[0.982983,0.0010030555,0.0011056141,0.0009408163,0.000027084592,0.000042767595,0.00005550792,0.000014195608,0.013827871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9873886,0.0035157683,0.00029149107,0.000913462,0.0040234304,0.0038673158],"domain_scores_gemma":[0.99233025,0.0030150323,0.00052593125,0.0004892639,0.0021335753,0.0015059542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010190977,0.00040098358,0.00047497064,0.0024230788,0.008249172,0.011717209,0.0022835548,0.0017762892,0.003925938],"category_scores_gemma":[0.014476418,0.00029437616,0.00040441228,0.004565689,0.022700634,0.00201488,0.010217509,0.0023740567,0.000100802965],"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":[0.00022718466,0.00021239284,0.024149688,0.00016562197,0.00006920479,0.00049893477,0.026705757,0.0078074518,0.00080698344,0.8034416,0.008945718,0.12696949],"study_design_scores_gemma":[0.00035860488,0.00047119474,0.133942,0.0010285511,0.00017905544,0.00021880871,0.09201417,0.011517378,0.0040992885,0.3329978,0.42291462,0.00025858227],"about_ca_topic_score_codex":0.88773817,"about_ca_topic_score_gemma":0.90144795,"teacher_disagreement_score":0.8451643,"about_ca_system_score_codex":0.15483567,"about_ca_system_score_gemma":0.12643729,"threshold_uncertainty_score":0.9802708},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039647655,0.5612034,0.027936514,0.1278905,0.024232425,0.0003944868,0.00048140786,0.00026701938,0.25362942],"genre_scores_gemma":[0.10897455,0.58512956,0.026330005,0.020788137,0.012410875,0.0008966194,0.00086076034,0.00057332654,0.2440362],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959324,0.0022568575,0.00019302175,0.00041908084,0.0010126462,0.00018608982],"domain_scores_gemma":[0.9944847,0.0041947556,0.0002436105,0.00021036479,0.0006972337,0.00016928598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005172761,0.0010818415,0.0009873483,0.0022893418,0.00172053,0.009956624,0.0009291671,0.0026726488,0.0059581622],"category_scores_gemma":[0.010073344,0.0008245988,0.0005838305,0.0039025836,0.0071812626,0.0070559504,0.003049313,0.0046651093,0.0025209216],"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":[0.000026855121,0.00006256753,0.0004371716,0.0014716833,0.000032760116,0.00011202298,0.0065808236,0.0023266254,0.00031182612,0.3303174,0.4676793,0.19064109],"study_design_scores_gemma":[0.0000092235105,0.000021268963,0.00069176237,0.0023619665,0.000008077608,0.00008492224,0.0013714305,0.0004941893,0.0001671589,0.10235804,0.8924109,0.000020991061],"about_ca_topic_score_codex":0.0057266806,"about_ca_topic_score_gemma":0.00452073,"teacher_disagreement_score":0.009956624,"about_ca_system_score_codex":0.0059298156,"about_ca_system_score_gemma":0.010820813,"threshold_uncertainty_score":0.043024004},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41165656,0.006306849,0.16952486,0.23575334,0.0020362749,0.000883845,0.00006600906,0.000342691,0.17342962],"genre_scores_gemma":[0.97113377,0.00069869024,0.014834713,0.009725428,0.00021401432,0.00041705027,0.000013600055,0.00012504208,0.0028376093],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5120551,0.43410945,0.010586588,0.0077235093,0.024543902,0.010981429],"domain_scores_gemma":[0.5772742,0.3266524,0.03125395,0.017335879,0.03298106,0.014502513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21150197,0.00091222516,0.001324825,0.00341084,0.019745559,0.029953262,0.0037191138,0.008961262,0.0035170373],"category_scores_gemma":[0.43639562,0.0013428611,0.0011616118,0.002049129,0.06641145,0.023305988,0.022705322,0.015345817,0.0009654629],"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":[0.00027137413,0.0001270105,0.011402652,0.00053728087,0.00010989955,0.0012308101,0.6273545,0.0010759162,0.001323991,0.2971383,0.009341587,0.050086632],"study_design_scores_gemma":[0.000091692295,0.00018759813,0.00707584,0.002242244,0.000060149912,0.0012657103,0.46699038,0.0023521315,0.0029095975,0.42880455,0.087702155,0.0003179334],"about_ca_topic_score_codex":0.0022311627,"about_ca_topic_score_gemma":0.0027990097,"teacher_disagreement_score":0.21150197,"about_ca_system_score_codex":0.011057451,"about_ca_system_score_gemma":0.011710198,"threshold_uncertainty_score":0.97235847},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017786942,0.08067156,0.02283814,0.8052026,0.0017645931,0.00018185466,0.000034860226,0.000077391705,0.07144204],"genre_scores_gemma":[0.86710733,0.037716094,0.029999427,0.055899955,0.0035371054,0.00064878794,0.000033688233,0.0001884666,0.0048691453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.53826064,0.3771663,0.011099495,0.0063180155,0.06118645,0.005969012],"domain_scores_gemma":[0.3363493,0.597455,0.010676372,0.011089872,0.03664458,0.007784816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.45002288,0.00069830584,0.002218258,0.007978109,0.01340846,0.04227686,0.003095166,0.011899442,0.0016933744],"category_scores_gemma":[0.3774643,0.00073239586,0.0010323584,0.007014369,0.10130494,0.030979222,0.016399825,0.013466807,0.0005342013],"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":[0.0001230203,0.00010767899,0.005493326,0.0016972116,0.0000507318,0.0001590652,0.039452225,0.0006025484,0.00016693577,0.61236626,0.017196318,0.32258472],"study_design_scores_gemma":[0.00007153099,0.00019575216,0.0076897894,0.011591237,0.000068804526,0.00060052506,0.1323897,0.002404023,0.0005465635,0.6639637,0.18024644,0.00023195476],"about_ca_topic_score_codex":0.012949975,"about_ca_topic_score_gemma":0.017188547,"teacher_disagreement_score":0.45002288,"about_ca_system_score_codex":0.022223061,"about_ca_system_score_gemma":0.03881035,"threshold_uncertainty_score":0.67821974},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23323898,0.008991037,0.5561439,0.004452121,0.00043226132,0.0014235047,0.0023050122,0.00035469822,0.19265854],"genre_scores_gemma":[0.7409242,0.004103749,0.21480963,0.00032587728,0.00015124913,0.0010911145,0.0007933615,0.00015303565,0.037647948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974438,0.0006499799,0.00017764185,0.00045632687,0.0009329247,0.00033938914],"domain_scores_gemma":[0.99241287,0.0019337449,0.0009516396,0.00048616677,0.00349973,0.0007159177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024758796,0.0006616915,0.0004611645,0.0034092728,0.0022515398,0.006323745,0.0010529697,0.0010513564,0.005813276],"category_scores_gemma":[0.0056493073,0.0002801696,0.0007237286,0.004480353,0.004958477,0.0041512595,0.0012683572,0.0013998676,0.00061219366],"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":[0.00012825837,0.00009048111,0.02708857,0.0006578035,0.00006938837,0.00025394504,0.0094110705,0.01131466,0.0045303144,0.7750858,0.004390676,0.16697909],"study_design_scores_gemma":[0.000037120128,0.0003915604,0.07219254,0.0011578329,0.000091305104,0.0008043927,0.01080379,0.028584465,0.0041597458,0.32217407,0.55941755,0.0001856063],"about_ca_topic_score_codex":0.14899507,"about_ca_topic_score_gemma":0.13860722,"teacher_disagreement_score":0.14899507,"about_ca_system_score_codex":0.009243116,"about_ca_system_score_gemma":0.009465005,"threshold_uncertainty_score":0.29625565},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063610254,0.014107693,0.077205926,0.6964036,0.14391574,0.00033741983,0.00057090377,0.0015607001,0.059536964],"genre_scores_gemma":[0.17534098,0.0118568875,0.14765167,0.3748783,0.101408444,0.0014475832,0.0012544161,0.0037648939,0.18239681],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9174917,0.044327695,0.0021959776,0.008875917,0.024014598,0.0030940913],"domain_scores_gemma":[0.83733976,0.05884472,0.009519971,0.02768589,0.049567554,0.017042097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060337614,0.0015849649,0.001343337,0.0016198609,0.00446457,0.011686141,0.003665127,0.006320995,0.029394915],"category_scores_gemma":[0.22365497,0.0006931818,0.0016644883,0.0014139526,0.009782088,0.015191075,0.0139350295,0.017631426,0.019349033],"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":[0.00046353112,0.00012308417,0.0035337533,0.0013925554,0.00022631955,0.0015103726,0.008717137,0.00029075582,0.004646562,0.12363489,0.59013885,0.26532215],"study_design_scores_gemma":[0.000044566812,0.000114932365,0.0012258212,0.0011306934,0.00005296404,0.001720977,0.0063556274,0.00053226104,0.0020803574,0.08636391,0.90024626,0.0001316219],"about_ca_topic_score_codex":0.0006745684,"about_ca_topic_score_gemma":0.0015851302,"teacher_disagreement_score":0.060337614,"about_ca_system_score_codex":0.0034732427,"about_ca_system_score_gemma":0.0053342567,"threshold_uncertainty_score":0.31909966},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010549128,0.6568964,0.23652442,0.03412484,0.00859059,0.0028350845,0.010243739,0.0027802896,0.037455533],"genre_scores_gemma":[0.12033486,0.35378012,0.48202762,0.005900644,0.0032463619,0.0063949903,0.009385131,0.001388003,0.017542304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9631186,0.02112925,0.006024602,0.001490408,0.007885371,0.0003517958],"domain_scores_gemma":[0.7297756,0.21949986,0.008604717,0.008591656,0.032063197,0.001465005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.070714496,0.0039981017,0.003921797,0.0151898395,0.0024927668,0.006569703,0.0044995244,0.0041098786,0.019314365],"category_scores_gemma":[0.19613801,0.004799816,0.0028867426,0.013330798,0.00638662,0.0109747425,0.0031202843,0.012342458,0.016504282],"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":[0.0003706726,0.000284565,0.008633945,0.0061725774,0.0007182368,0.00019490202,0.0034074166,0.0024087818,0.0009902421,0.015479036,0.2267547,0.7345849],"study_design_scores_gemma":[0.00071059045,0.0012578178,0.09711694,0.033821557,0.0031877342,0.0036231093,0.006696636,0.006471994,0.0061732256,0.15739217,0.6823293,0.0012189532],"about_ca_topic_score_codex":0.009426818,"about_ca_topic_score_gemma":0.01747698,"teacher_disagreement_score":0.070714496,"about_ca_system_score_codex":0.0039395927,"about_ca_system_score_gemma":0.00484435,"threshold_uncertainty_score":0.3739785},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000693135,0.008666056,0.006019515,0.67246634,0.3039096,0.0004005533,0.0002265952,0.0006695558,0.006948724],"genre_scores_gemma":[0.015965892,0.014705214,0.026163774,0.5140182,0.3813316,0.0012483405,0.00047886744,0.0023708788,0.043717284],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.81666785,0.07696282,0.034234237,0.0055072,0.06071504,0.00591276],"domain_scores_gemma":[0.2701736,0.28089,0.055165235,0.043186,0.30025253,0.050332632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18018086,0.0016735921,0.0028359569,0.005310628,0.0060170502,0.029696893,0.005228492,0.021554567,0.03759408],"category_scores_gemma":[0.59801304,0.0011979304,0.0034335076,0.005462092,0.0075838272,0.018078264,0.0072208783,0.022200758,0.024986412],"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":[0.00015232108,0.00013960198,0.00038715912,0.0016455486,0.000042284726,0.00020101551,0.00070797757,0.00012427424,0.00041262072,0.006077604,0.9224788,0.06763077],"study_design_scores_gemma":[0.00007653223,0.00014678844,0.0005269711,0.0033598659,0.000057163215,0.0005658991,0.00063683995,0.0003342853,0.0008716004,0.008247062,0.98509,0.0000869541],"about_ca_topic_score_codex":0.00067427056,"about_ca_topic_score_gemma":0.001240695,"teacher_disagreement_score":0.18018086,"about_ca_system_score_codex":0.008799252,"about_ca_system_score_gemma":0.033147983,"threshold_uncertainty_score":0.95289886},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34195882,0.01282884,0.2983791,0.04494164,0.0016763285,0.19380076,0.0019375149,0.0010957106,0.10338135],"genre_scores_gemma":[0.6613549,0.0008824474,0.27535075,0.003215952,0.00012453376,0.056296676,0.00032824892,0.00009432829,0.0023521911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.4926823,0.47506386,0.007595421,0.0050916076,0.013191519,0.006375362],"domain_scores_gemma":[0.6317319,0.2928706,0.013601931,0.01610723,0.03710142,0.008586793],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.36361077,0.0012691608,0.0014137796,0.0026852782,0.004631243,0.008220206,0.0047045304,0.002957333,0.005191008],"category_scores_gemma":[0.2824604,0.0009062811,0.0016598129,0.0028292115,0.0062180236,0.0057829954,0.008245174,0.0044498537,0.00042846016],"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":[0.010495703,0.007343344,0.04756113,0.017546082,0.001665655,0.0011905171,0.03619706,0.060898263,0.0020413892,0.1738381,0.024818847,0.61640394],"study_design_scores_gemma":[0.032204736,0.08420837,0.14651929,0.032063268,0.0035757897,0.0016823515,0.09449425,0.12610406,0.012620604,0.23471871,0.23031183,0.0014967411],"about_ca_topic_score_codex":0.014938066,"about_ca_topic_score_gemma":0.017115565,"teacher_disagreement_score":0.36361077,"about_ca_system_score_codex":0.03080253,"about_ca_system_score_gemma":0.05794125,"threshold_uncertainty_score":0.7847812},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20711558,0.23218013,0.0120979315,0.050557215,0.0016274432,0.0008035606,0.0029285334,0.00032036984,0.4923693],"genre_scores_gemma":[0.8739834,0.034097668,0.008700227,0.0019401144,0.0003991841,0.000490123,0.0010744453,0.00015392956,0.079160966],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96382016,0.01865617,0.0009783927,0.001285613,0.012776671,0.0024829546],"domain_scores_gemma":[0.96456015,0.014479201,0.0037174954,0.0007895332,0.014301802,0.0021519216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026819,0.0007227995,0.000801823,0.0075550918,0.0049250666,0.00937959,0.00097160536,0.0012713373,0.010821287],"category_scores_gemma":[0.038276754,0.0003349996,0.0007784706,0.011358152,0.004919426,0.0033422557,0.0026409482,0.0015355356,0.0012584608],"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":[0.0005122143,0.00028078194,0.05422401,0.0031840396,0.00042562096,0.00017458256,0.031156005,0.002989618,0.0009886838,0.11852909,0.07436569,0.7131697],"study_design_scores_gemma":[0.00011798589,0.00045395587,0.31651288,0.0044149323,0.00032456318,0.00021651933,0.04279584,0.001153587,0.0019762942,0.014335301,0.6175653,0.00013294158],"about_ca_topic_score_codex":0.2608046,"about_ca_topic_score_gemma":0.3167929,"teacher_disagreement_score":0.2608046,"about_ca_system_score_codex":0.03170053,"about_ca_system_score_gemma":0.040590975,"threshold_uncertainty_score":0.51857305},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942972,0.00033388752,0.00014785878,0.00034715713,0.000005852742,0.000103445665,0.0008640868,0.000011738961,0.0038887651],"genre_scores_gemma":[0.9976941,0.00041548896,0.00026125088,0.000094621595,0.000002430256,0.000046903133,0.0004300957,0.000007193946,0.0010479412],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955382,0.00078346283,0.00036230424,0.00030164424,0.0020963354,0.00091808336],"domain_scores_gemma":[0.9695155,0.0041063456,0.003643461,0.0008197826,0.0184449,0.0034699799],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008102149,0.00026691778,0.0003081682,0.0027566063,0.0033724832,0.0018433628,0.0009595311,0.00036574827,0.0017807226],"category_scores_gemma":[0.01954207,0.00033025726,0.0003625996,0.0042704884,0.0014254086,0.00069970614,0.0017096879,0.0007356384,0.0002770408],"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":[0.000101462145,0.00009902543,0.94335693,0.00015865562,0.000028064616,0.00007688154,0.030811548,0.000100455916,0.00032411274,0.00020693264,0.0022428944,0.02249311],"study_design_scores_gemma":[0.0000040991804,0.000046591525,0.9728845,0.00006241631,0.000008596255,0.000025181147,0.023857193,0.0001454379,0.00011838019,0.000020887157,0.002806386,0.000020358058],"about_ca_topic_score_codex":0.9583757,"about_ca_topic_score_gemma":0.9743662,"teacher_disagreement_score":0.9918978,"about_ca_system_score_codex":0.015433948,"about_ca_system_score_gemma":0.027887633,"threshold_uncertainty_score":0.11198163},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53723675,0.010703452,0.19202633,0.060898725,0.001264729,0.0060793,0.0007763287,0.0008917969,0.19012263],"genre_scores_gemma":[0.954291,0.0014024858,0.037924223,0.0019603414,0.00024272018,0.0016052475,0.00012287658,0.00020532262,0.002245763],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.5384009,0.3303151,0.033323627,0.008872657,0.083179824,0.0059079113],"domain_scores_gemma":[0.1610719,0.5975445,0.052765,0.05146332,0.1334064,0.003748896],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.378672,0.0007734969,0.0009723425,0.011553247,0.007429758,0.01521679,0.0032353695,0.0021532583,0.0024713227],"category_scores_gemma":[0.6073475,0.001104555,0.0011679971,0.008925288,0.022948004,0.012321677,0.007823947,0.0053680274,0.00038450278],"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":[0.00034411217,0.00041068366,0.11650802,0.004031832,0.0001655636,0.0008532116,0.45814162,0.0006244838,0.0025392377,0.08253301,0.012291191,0.32155702],"study_design_scores_gemma":[0.00011144887,0.0014427954,0.30162016,0.015841663,0.00027839997,0.0023587628,0.32216573,0.0039183917,0.009237339,0.046322152,0.29626682,0.0004363291],"about_ca_topic_score_codex":0.040948313,"about_ca_topic_score_gemma":0.036682397,"teacher_disagreement_score":0.378672,"about_ca_system_score_codex":0.023536187,"about_ca_system_score_gemma":0.03640089,"threshold_uncertainty_score":0.76620805},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16128927,0.009002596,0.011903947,0.7580073,0.0020361796,0.000659175,0.00011716129,0.00022022093,0.056764133],"genre_scores_gemma":[0.9074556,0.0035910795,0.007226212,0.073394135,0.001849865,0.0009681296,0.00007535837,0.00014686014,0.0052927523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.38702214,0.39885727,0.036716457,0.030037051,0.10840432,0.038962774],"domain_scores_gemma":[0.1283137,0.6441304,0.07728094,0.024651263,0.08980627,0.035817426],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49089113,0.0007888776,0.001897264,0.008126211,0.025640301,0.03299076,0.006030109,0.02117122,0.0035387487],"category_scores_gemma":[0.5858356,0.0019522049,0.0016835436,0.01002372,0.033537805,0.018020153,0.02899993,0.026644064,0.0005401871],"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":[0.00072059943,0.00097045244,0.07257799,0.0022926661,0.00031195948,0.0015846523,0.124663234,0.004500308,0.0024455118,0.42096388,0.09778333,0.2711855],"study_design_scores_gemma":[0.00046881574,0.0010306734,0.09127519,0.004934258,0.00016755625,0.0007129621,0.1660181,0.005516108,0.0028099332,0.11494432,0.6110847,0.001037372],"about_ca_topic_score_codex":0.029504746,"about_ca_topic_score_gemma":0.026242997,"teacher_disagreement_score":0.5091089,"about_ca_system_score_codex":0.06365176,"about_ca_system_score_gemma":0.12919855,"threshold_uncertainty_score":0.62782186},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85102,0.0010001687,0.02680342,0.0038527702,0.00049388123,0.063968025,0.012165757,0.0006545166,0.040041484],"genre_scores_gemma":[0.5784982,0.002917268,0.27314946,0.002721315,0.00025381753,0.10665026,0.011708385,0.000117762655,0.02398342],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9961676,0.0014561658,0.0007613703,0.00014593042,0.0011587356,0.0003102012],"domain_scores_gemma":[0.98637855,0.0067572044,0.0016145024,0.00056323275,0.003698651,0.00098792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072494196,0.0005096141,0.0006807811,0.002747315,0.0010398558,0.00058301614,0.0008319197,0.00082561426,0.0070006894],"category_scores_gemma":[0.018725118,0.00040915812,0.00068377436,0.0013348801,0.0004179247,0.0013177432,0.0014179886,0.0013386002,0.0015697732],"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":[0.0007022838,0.006244263,0.14338252,0.0026937902,0.00019557962,0.0010334256,0.025929749,0.0027490577,0.009326299,0.0041925483,0.0857294,0.717821],"study_design_scores_gemma":[0.000836117,0.008193784,0.6692731,0.0015721032,0.000111055364,0.0021414927,0.02657741,0.009178944,0.0035405466,0.0070934854,0.27102888,0.00045302272],"about_ca_topic_score_codex":0.0026122376,"about_ca_topic_score_gemma":0.0074328706,"teacher_disagreement_score":0.0072494196,"about_ca_system_score_codex":0.0016769712,"about_ca_system_score_gemma":0.0038032907,"threshold_uncertainty_score":0.03833902},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57028633,0.004841339,0.0017044796,0.21285623,0.0019035548,0.0009431523,0.0007481316,0.00016448641,0.20655225],"genre_scores_gemma":[0.9574597,0.0013733383,0.002092773,0.004298886,0.00015498446,0.00007673326,0.00015363104,0.000030858148,0.03435914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9806116,0.0031074453,0.00077294756,0.000709283,0.008836894,0.00596183],"domain_scores_gemma":[0.9263947,0.0041553713,0.0046611107,0.0010494448,0.02704527,0.036694095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009818153,0.000317533,0.00036083127,0.0029902533,0.020092443,0.012685984,0.0023054925,0.002620572,0.008783542],"category_scores_gemma":[0.032309927,0.0004853892,0.00040587256,0.0037887227,0.005627713,0.0021829575,0.006053389,0.0026029649,0.0006148267],"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":[0.0005613346,0.00030011684,0.36028194,0.000934734,0.00013319521,0.0010140812,0.025663475,0.0023678595,0.0014600743,0.06289151,0.30878097,0.23561068],"study_design_scores_gemma":[0.00011631165,0.00027414467,0.57087785,0.0007646809,0.00009209735,0.00026646355,0.06934159,0.0015165256,0.0011159073,0.008076867,0.34734416,0.0002133134],"about_ca_topic_score_codex":0.96613675,"about_ca_topic_score_gemma":0.99443686,"teacher_disagreement_score":0.8268766,"about_ca_system_score_codex":0.17312343,"about_ca_system_score_gemma":0.4251153,"threshold_uncertainty_score":0.9590596},"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":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019034049,0.02065824,0.20996836,0.54328066,0.055254757,0.03180173,0.0006518618,0.0009407484,0.118409574],"genre_scores_gemma":[0.19516453,0.022697262,0.36321408,0.21067652,0.025486236,0.06542986,0.0013475772,0.0010458892,0.11493799],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.30572492,0.52283764,0.075868845,0.008788277,0.07769795,0.009082445],"domain_scores_gemma":[0.23992185,0.42172256,0.034470797,0.08520039,0.20051211,0.018172415],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.553005,0.0010885493,0.00228633,0.0065236115,0.007575621,0.014003001,0.00522744,0.018734215,0.004534627],"category_scores_gemma":[0.68810284,0.0017368152,0.00232499,0.0052049984,0.015355201,0.007345965,0.009499885,0.01688552,0.0032170098],"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":[0.00053221965,0.00024558674,0.0023770612,0.004229293,0.00022166326,0.0012508666,0.033352997,0.00082627265,0.0022471955,0.32964587,0.3840805,0.24099034],"study_design_scores_gemma":[0.00020504028,0.00012588222,0.0011606779,0.0063191224,0.00009851797,0.00035915853,0.005012629,0.0011450229,0.0017584222,0.04723594,0.9364629,0.00011664696],"about_ca_topic_score_codex":0.0027740072,"about_ca_topic_score_gemma":0.0042292895,"teacher_disagreement_score":0.44699502,"about_ca_system_score_codex":0.009652692,"about_ca_system_score_gemma":0.10670305,"threshold_uncertainty_score":0.55122447},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043764333,0.13554263,0.0016250988,0.8226174,0.010625873,0.00029351286,0.0002712912,0.00013926651,0.02450843],"genre_scores_gemma":[0.3077827,0.27953887,0.018734742,0.34510744,0.018485812,0.00080422696,0.0006994506,0.00040052304,0.028446248],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8162163,0.083674505,0.01801742,0.0042837225,0.07068206,0.007126038],"domain_scores_gemma":[0.29447246,0.3206843,0.03160045,0.016345331,0.32172844,0.015168939],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.21837881,0.00057705183,0.0013818475,0.005194558,0.00414893,0.015414895,0.0042926976,0.008552757,0.0026670003],"category_scores_gemma":[0.43482926,0.000802911,0.0011413809,0.006596939,0.007363842,0.008376341,0.0037876896,0.0073986286,0.0005737596],"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":[0.00018416072,0.000053988828,0.0052217576,0.010953402,0.00022345908,0.0007237361,0.0148667935,0.00060656865,0.00042763763,0.023407912,0.646359,0.2969715],"study_design_scores_gemma":[0.000058583064,0.00006325949,0.006968213,0.011884684,0.00014681894,0.00017780976,0.0044276104,0.00024087183,0.00023404213,0.002283335,0.97341365,0.00010120295],"about_ca_topic_score_codex":0.5299846,"about_ca_topic_score_gemma":0.7699648,"teacher_disagreement_score":0.9958511,"about_ca_system_score_codex":0.061118707,"about_ca_system_score_gemma":0.18354076,"threshold_uncertainty_score":0.9638781},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99476564,0.00012893531,0.00012150172,0.0026388403,0.00001961982,0.000019180594,0.0000107689675,0.0000050177537,0.002290574],"genre_scores_gemma":[0.994961,0.0002745572,0.0002263036,0.0010925694,0.000012638027,0.00003583803,0.000020448695,0.000008511231,0.0033681665],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99775547,0.0010744542,0.000029608967,0.00015284643,0.00018207812,0.0008055674],"domain_scores_gemma":[0.99786025,0.0005723058,0.00020533853,0.000081612845,0.00019156035,0.0010889884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021773237,0.00036712975,0.0004584927,0.00068842625,0.019043835,0.0038699976,0.0015160036,0.0014940539,0.003984584],"category_scores_gemma":[0.0026104704,0.00032089918,0.00028537124,0.00074785796,0.004203232,0.0021624516,0.0075620203,0.002568888,0.00036107367],"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":[0.000077728095,0.00034219155,0.027681341,0.00007720497,0.0000128888405,0.0036931832,0.9431267,0.000067978675,0.0021542395,0.0012776282,0.001975404,0.019513516],"study_design_scores_gemma":[0.0000034888935,0.000099574565,0.009407579,0.000052425494,0.000006767081,0.0005200556,0.98059446,0.00008441562,0.00020704632,0.00024092807,0.008772367,0.000010904139],"about_ca_topic_score_codex":0.084565595,"about_ca_topic_score_gemma":0.19996318,"teacher_disagreement_score":0.084565595,"about_ca_system_score_codex":0.0035827172,"about_ca_system_score_gemma":0.006381638,"threshold_uncertainty_score":0.16814673},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78910786,0.003792318,0.031687435,0.052678723,0.000725525,0.010966756,0.0005383372,0.0012148584,0.10928815],"genre_scores_gemma":[0.9285489,0.0009322172,0.04923735,0.0015102761,0.00007966976,0.0024464596,0.00024186801,0.00009735636,0.01690592],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8918985,0.059940614,0.0074647297,0.0065555377,0.028103495,0.006037146],"domain_scores_gemma":[0.7898125,0.031210978,0.01258698,0.012332983,0.12854476,0.02551186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10203096,0.00031921393,0.00037267586,0.0050109643,0.006815893,0.00821282,0.0033823652,0.0013017879,0.0025939015],"category_scores_gemma":[0.13503781,0.0009826861,0.00026987097,0.0033261944,0.004367049,0.0022684722,0.0049312655,0.002398428,0.00069398066],"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":[0.00037739033,0.0017475133,0.12300701,0.0010958607,0.000103886225,0.00038100922,0.07251464,0.0033314698,0.004474242,0.010017335,0.041464735,0.7414849],"study_design_scores_gemma":[0.000491106,0.0015838756,0.57334566,0.0022876535,0.00008311413,0.00031212476,0.07402243,0.004907727,0.0072926604,0.004145559,0.3311758,0.00035240612],"about_ca_topic_score_codex":0.25116083,"about_ca_topic_score_gemma":0.4171345,"teacher_disagreement_score":0.25116083,"about_ca_system_score_codex":0.045113053,"about_ca_system_score_gemma":0.110489585,"threshold_uncertainty_score":0.53959775},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05201906,0.098814115,0.18167941,0.36708707,0.0039413497,0.0015243145,0.0014789904,0.000365168,0.29309058],"genre_scores_gemma":[0.8250352,0.048392113,0.10028387,0.014511411,0.0014433602,0.0015163311,0.00043670373,0.00009731297,0.008283791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88960916,0.08624451,0.0031800496,0.0031881055,0.016346233,0.001431896],"domain_scores_gemma":[0.7291405,0.22934438,0.009266387,0.012014009,0.018242832,0.0019918168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10638445,0.0015577704,0.0023802605,0.007869563,0.0028466173,0.019764334,0.0024924325,0.0042868867,0.0070463717],"category_scores_gemma":[0.17803787,0.0006660891,0.002316672,0.004529326,0.013873685,0.01110195,0.005960831,0.006517258,0.00094619807],"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":[0.00026662258,0.00020107462,0.0057946397,0.0058998633,0.0007821526,0.00013262873,0.003676915,0.006653482,0.00047082483,0.79664385,0.014535403,0.16494256],"study_design_scores_gemma":[0.00024630124,0.00039357514,0.007855436,0.016496994,0.0012556171,0.00018455856,0.0053999224,0.008041228,0.0018345558,0.83165663,0.12647234,0.00016282359],"about_ca_topic_score_codex":0.0068252897,"about_ca_topic_score_gemma":0.006973599,"teacher_disagreement_score":0.10638445,"about_ca_system_score_codex":0.011439388,"about_ca_system_score_gemma":0.028578795,"threshold_uncertainty_score":0.5626215},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14952032,0.16431247,0.40671352,0.06733693,0.0057647526,0.022312876,0.0013126335,0.00060699583,0.1821195],"genre_scores_gemma":[0.59616894,0.042880848,0.32171747,0.0076852795,0.0009863685,0.019936731,0.00026861596,0.000161685,0.010194019],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6872639,0.27726513,0.01146163,0.0033925087,0.019172916,0.0014439075],"domain_scores_gemma":[0.658439,0.29581383,0.012037961,0.009874314,0.02166902,0.0021660044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16467269,0.0017743956,0.0027701303,0.005097414,0.0031764188,0.007949354,0.0018575734,0.002937452,0.0071769026],"category_scores_gemma":[0.2119419,0.00080613274,0.0022290759,0.0040752264,0.006763329,0.0060219574,0.004587978,0.0033396313,0.00074658054],"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":[0.0018306053,0.0018413884,0.011432635,0.04051996,0.0018937172,0.00030273435,0.018365914,0.0045731342,0.0030674418,0.12052098,0.004686113,0.7909653],"study_design_scores_gemma":[0.004093804,0.028382128,0.08037113,0.13518253,0.008436837,0.0019982837,0.038777653,0.0179723,0.03844517,0.28164393,0.36372373,0.00097245316],"about_ca_topic_score_codex":0.008820913,"about_ca_topic_score_gemma":0.0108872615,"teacher_disagreement_score":0.16467269,"about_ca_system_score_codex":0.0086388225,"about_ca_system_score_gemma":0.021597687,"threshold_uncertainty_score":0.8708828},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011933271,0.027830807,0.63591367,0.055200666,0.0014540763,0.00227558,0.0005699868,0.0006620222,0.26415995],"genre_scores_gemma":[0.5661375,0.014625835,0.3948479,0.0059176707,0.00137693,0.006570905,0.00047345695,0.000369529,0.009680359],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6575161,0.28604418,0.016530424,0.008882196,0.028218009,0.0028089702],"domain_scores_gemma":[0.5127546,0.42227402,0.015722305,0.020130116,0.02688184,0.0022371116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21811213,0.0021421656,0.0022565222,0.0120012425,0.0033490832,0.020914659,0.0039469586,0.0061313994,0.007887036],"category_scores_gemma":[0.31215215,0.0011601847,0.0019412054,0.008572827,0.023895914,0.022778196,0.0073315394,0.0048001898,0.0013175242],"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":[0.000040660158,0.000044341392,0.0011191156,0.00082955376,0.000099794495,0.000055512384,0.0016259224,0.0025244432,0.00005498298,0.9558261,0.0029778902,0.034801777],"study_design_scores_gemma":[0.00007330798,0.00008249567,0.0006350555,0.002016814,0.00007427326,0.00012171947,0.0010605067,0.0054169493,0.00031108523,0.940789,0.049357314,0.000061510196],"about_ca_topic_score_codex":0.0034015342,"about_ca_topic_score_gemma":0.0019283318,"teacher_disagreement_score":0.21811213,"about_ca_system_score_codex":0.014985848,"about_ca_system_score_gemma":0.012509117,"threshold_uncertainty_score":0.96420693},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001569578,0.002837413,0.00020351532,0.023045242,0.9726565,0.00002278119,0.000054320895,0.000051241066,0.0011131498],"genre_scores_gemma":[0.00063534884,0.0038710488,0.00038748528,0.019999787,0.96277386,0.00010770611,0.00006440829,0.0001138389,0.012046596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97823834,0.0068583745,0.0029710643,0.002002487,0.009014119,0.00091555505],"domain_scores_gemma":[0.9079383,0.05654526,0.0029969746,0.0025803267,0.02546146,0.0044776755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029641202,0.0057088374,0.007884428,0.0075301626,0.007850955,0.016550763,0.0068017533,0.032962516,0.022357682],"category_scores_gemma":[0.08864706,0.0018531537,0.0035680267,0.004260322,0.006987095,0.008788782,0.0029808755,0.030320928,0.015813462],"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":[0.000020223595,0.000008450684,0.000006252371,0.00016450016,0.000007698127,0.000030159716,0.00002304454,0.000013931854,0.0000135866885,0.0004297866,0.9970108,0.0022714916],"study_design_scores_gemma":[0.00009898218,0.000022388294,0.00018407691,0.0013681978,0.000068489564,0.00015416885,0.00010924934,0.0002196663,0.000079614634,0.003004416,0.9946603,0.000030476811],"about_ca_topic_score_codex":0.004877702,"about_ca_topic_score_gemma":0.010189318,"teacher_disagreement_score":0.032962516,"about_ca_system_score_codex":0.0071349717,"about_ca_system_score_gemma":0.008488988,"threshold_uncertainty_score":0.1567595},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99377173,0.00050350244,0.00024957125,0.003314041,0.000020857757,0.000067728106,0.000013081549,0.00000401103,0.0020554834],"genre_scores_gemma":[0.9963595,0.0009833657,0.0005214802,0.0010832611,0.000017169694,0.00008200738,0.000012104028,0.000006093187,0.0009349933],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9757296,0.016071172,0.0016871806,0.000782752,0.0022510819,0.0034782144],"domain_scores_gemma":[0.93909395,0.041708935,0.008305656,0.0014803644,0.0044540614,0.004956919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026109062,0.00052367634,0.0009317766,0.0032978675,0.013527637,0.009864027,0.0012247995,0.0030743626,0.0022733395],"category_scores_gemma":[0.054184385,0.0012823085,0.00056627084,0.0032097187,0.010435667,0.005131043,0.0073673422,0.0041844966,0.00039304054],"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":[0.000049081544,0.00008483564,0.021623561,0.00023231127,0.000013839716,0.000513595,0.96760154,0.00003346391,0.0010281926,0.00083945814,0.00021410009,0.007766144],"study_design_scores_gemma":[0.000007760728,0.00015438917,0.010465472,0.00023613762,0.000010982126,0.00019363652,0.9827943,0.0000660197,0.00023890793,0.0003042866,0.005505693,0.00002252956],"about_ca_topic_score_codex":0.012334531,"about_ca_topic_score_gemma":0.014581708,"teacher_disagreement_score":0.026109062,"about_ca_system_score_codex":0.0075542554,"about_ca_system_score_gemma":0.010169538,"threshold_uncertainty_score":0.13807952},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094650243,0.0143099185,0.865456,0.0047911527,0.0030947828,0.034496043,0.011719761,0.008049429,0.05713634],"genre_scores_gemma":[0.0020061145,0.009036577,0.91164905,0.0024377487,0.00046010147,0.04697941,0.0022538523,0.0016364562,0.023540791],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9699893,0.02278107,0.0019295495,0.0009833202,0.004027391,0.00028944362],"domain_scores_gemma":[0.94526565,0.041000172,0.0014761332,0.0038088153,0.0074941786,0.00095503306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047982145,0.002934917,0.0028263396,0.0042223153,0.0014606995,0.003276173,0.004907077,0.0028175053,0.10063071],"category_scores_gemma":[0.045770254,0.0029531857,0.001981684,0.003778634,0.0018645365,0.0023271025,0.0031975522,0.006116259,0.052279662],"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":[0.00035311416,0.0005245726,0.0003406141,0.008751496,0.00017196129,0.00026339688,0.0022707044,0.00194536,0.0026512286,0.02764417,0.39819193,0.5568915],"study_design_scores_gemma":[0.0001256639,0.00026246312,0.00044828406,0.0028992211,0.000032882206,0.0002775925,0.00035160035,0.0011994175,0.000838553,0.015390643,0.9780903,0.00008327243],"about_ca_topic_score_codex":0.0016200722,"about_ca_topic_score_gemma":0.0045704115,"teacher_disagreement_score":0.10063071,"about_ca_system_score_codex":0.0018255442,"about_ca_system_score_gemma":0.0065731737,"threshold_uncertainty_score":0.33664322},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4970524,0.08551641,0.014437443,0.13028792,0.0018633223,0.000083903215,0.00015569078,0.000120404125,0.2704825],"genre_scores_gemma":[0.97815335,0.012212785,0.0016454736,0.0012913481,0.00018467953,0.00001565533,0.000025490941,0.000030379604,0.0064407606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9888532,0.00730155,0.0006380966,0.000662278,0.0015806725,0.0009641659],"domain_scores_gemma":[0.9898887,0.0054482,0.0009674707,0.0006141761,0.0016917925,0.0013895652],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01593084,0.0001891113,0.00043778925,0.0016397124,0.0040908605,0.0062693674,0.0005167555,0.0013548383,0.002498366],"category_scores_gemma":[0.0069286996,0.00018779295,0.0003791152,0.0018075496,0.009449309,0.0037556097,0.004760897,0.0031953736,0.0005580468],"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":[0.00022300691,0.00042977778,0.031141143,0.0011441405,0.00003820952,0.0019149997,0.11119834,0.0013475864,0.0023399303,0.5700189,0.016323535,0.26388043],"study_design_scores_gemma":[0.000040744773,0.00044312555,0.058974683,0.003277535,0.000041428506,0.0030734017,0.11076149,0.002070068,0.0025580265,0.061607707,0.7570572,0.0000944919],"about_ca_topic_score_codex":0.007119925,"about_ca_topic_score_gemma":0.0052182763,"teacher_disagreement_score":0.98406917,"about_ca_system_score_codex":0.009166071,"about_ca_system_score_gemma":0.014157137,"threshold_uncertainty_score":0.084251404},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00841749,0.0031277586,0.934138,0.011142353,0.00044597193,0.0021192185,0.00035460253,0.00048462063,0.039770007],"genre_scores_gemma":[0.16453417,0.0018141911,0.82460177,0.000995328,0.00013828192,0.0061233775,0.00036309176,0.0001563527,0.001273459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7401654,0.21195881,0.021872288,0.006225798,0.017094946,0.0026827215],"domain_scores_gemma":[0.620535,0.28456232,0.025584437,0.021931201,0.042860117,0.0045269644],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23014463,0.0027353142,0.0020893468,0.022680994,0.0034590731,0.028631616,0.004126417,0.0049312464,0.00425409],"category_scores_gemma":[0.2586781,0.0013486345,0.0022960093,0.018363066,0.031166688,0.026975239,0.010992639,0.008142759,0.0010248193],"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":[0.000054235006,0.00005830187,0.0022988857,0.0012990521,0.000047004214,0.00006164556,0.008581688,0.0031619498,0.0003928445,0.93008834,0.0014787684,0.052477304],"study_design_scores_gemma":[0.000069486654,0.00028784008,0.0019231063,0.00520897,0.00010887495,0.000260221,0.015684903,0.015940415,0.0020949151,0.867116,0.09113363,0.00017169859],"about_ca_topic_score_codex":0.0023757762,"about_ca_topic_score_gemma":0.0015185319,"teacher_disagreement_score":0.7698554,"about_ca_system_score_codex":0.013232794,"about_ca_system_score_gemma":0.013598834,"threshold_uncertainty_score":0.9493687},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.077484146,0.08317073,0.6002732,0.1128947,0.0024359263,0.0033834246,0.0002914057,0.0009872561,0.119079255],"genre_scores_gemma":[0.7125596,0.013016416,0.2639785,0.005279391,0.000720644,0.0022521866,0.00014049251,0.0002533814,0.0017993995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73382443,0.21279427,0.010146356,0.007088457,0.03405853,0.0020879335],"domain_scores_gemma":[0.6152456,0.31731814,0.016104896,0.023803344,0.024325442,0.0032026467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13731025,0.002239636,0.0030308894,0.0050529432,0.0031421771,0.016183242,0.0052039516,0.0056934897,0.012346108],"category_scores_gemma":[0.24187751,0.0012351397,0.003421712,0.004728082,0.017306216,0.017786803,0.007594235,0.007248884,0.0011922057],"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":[0.0015969536,0.00079188496,0.005398371,0.012395022,0.0015221324,0.00021232267,0.00737848,0.023645055,0.0014568181,0.41094515,0.006722624,0.5279352],"study_design_scores_gemma":[0.0015753806,0.0025654242,0.008041162,0.03574196,0.0013483954,0.0010639052,0.007763007,0.046506945,0.0071669216,0.77866644,0.108987726,0.00057285],"about_ca_topic_score_codex":0.0053010224,"about_ca_topic_score_gemma":0.0049981684,"teacher_disagreement_score":0.13731025,"about_ca_system_score_codex":0.013535624,"about_ca_system_score_gemma":0.015926251,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07620635,0.0069607473,0.85238117,0.026966816,0.0010821038,0.0021689662,0.0008448727,0.0006340571,0.032754835],"genre_scores_gemma":[0.6821942,0.0029635858,0.30688176,0.0018861516,0.0008081393,0.002851926,0.00038018244,0.00027627332,0.001757882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.62184274,0.3450418,0.0060194395,0.0052676117,0.020286448,0.0015418608],"domain_scores_gemma":[0.35186538,0.5888912,0.017448701,0.023152616,0.015948726,0.002693381],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24916588,0.002556654,0.0036038633,0.010494947,0.001823782,0.008527176,0.002607144,0.002089679,0.004304762],"category_scores_gemma":[0.43781227,0.00069766334,0.0033119551,0.00826245,0.00643957,0.015509189,0.010358742,0.004612654,0.00044648687],"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":[0.002026092,0.0010777059,0.070238054,0.0036641508,0.003813097,0.00013948293,0.007637242,0.01934117,0.00034146264,0.297558,0.0039794664,0.59018403],"study_design_scores_gemma":[0.0005062584,0.00222728,0.02097457,0.0027378525,0.0018334467,0.00017827119,0.0045729945,0.08434153,0.0016574865,0.8640453,0.016622353,0.00030253688],"about_ca_topic_score_codex":0.0041305753,"about_ca_topic_score_gemma":0.0028690214,"teacher_disagreement_score":0.24916588,"about_ca_system_score_codex":0.0042708516,"about_ca_system_score_gemma":0.010448112,"threshold_uncertainty_score":0.92591214},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40805522,0.01392702,0.052732065,0.21806453,0.00080778706,0.0016066908,0.00080051646,0.0004241037,0.30358207],"genre_scores_gemma":[0.97208744,0.002974977,0.014876603,0.0059145046,0.0002784138,0.000726451,0.00014083512,0.00006598632,0.0029347287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5976369,0.33439785,0.009393171,0.008729685,0.04143274,0.008409772],"domain_scores_gemma":[0.15810072,0.75170344,0.035631947,0.030053249,0.020081015,0.004429696],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.27419803,0.0006966455,0.0015671162,0.014568784,0.006798176,0.028923908,0.0027842724,0.005624406,0.008305745],"category_scores_gemma":[0.5680684,0.0013904506,0.0011618288,0.011849257,0.018816246,0.013652308,0.016808398,0.007494759,0.0011087958],"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":[0.0007577147,0.000568431,0.13264225,0.0025824124,0.0011574171,0.000894706,0.07357515,0.0036830518,0.0025286211,0.39722776,0.017992806,0.36638972],"study_design_scores_gemma":[0.0005718562,0.0005050894,0.08539321,0.008480428,0.0009698345,0.0006203514,0.05573308,0.010146888,0.0076704095,0.6201404,0.20944767,0.00032075477],"about_ca_topic_score_codex":0.007972872,"about_ca_topic_score_gemma":0.0086930515,"teacher_disagreement_score":0.99320185,"about_ca_system_score_codex":0.012902556,"about_ca_system_score_gemma":0.046320673,"threshold_uncertainty_score":0.8950431},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99814343,0.000093584895,0.00023621418,0.0004615733,0.0000029362166,0.000017481269,0.000008903712,0.0000032037808,0.0010325848],"genre_scores_gemma":[0.9992055,0.00007479656,0.00029906133,0.00008114964,0.0000028817908,0.000013400761,0.000012300373,0.0000013807191,0.00030954188],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967649,0.0019134351,0.00021481735,0.00013606653,0.00057367125,0.00039704167],"domain_scores_gemma":[0.9657151,0.018103236,0.008271043,0.00072997273,0.0035479842,0.003632607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007848575,0.00010814254,0.00013863838,0.0007598211,0.00094140077,0.0012235432,0.00022571698,0.00058738707,0.0014708934],"category_scores_gemma":[0.0349742,0.00018072093,0.00017677632,0.00035296837,0.0007139375,0.0006042692,0.00090431276,0.0008121529,0.0001633318],"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":[0.00007973504,0.0004903075,0.9492379,0.00008952386,0.000027987253,0.0001709971,0.019089146,0.00019053978,0.0014621326,0.00028689657,0.0003672731,0.028507492],"study_design_scores_gemma":[0.0000139437425,0.00036022728,0.9555858,0.00015570175,0.00001782274,0.00036695288,0.038583774,0.0007937037,0.00037293084,0.00038571778,0.0033356394,0.00002773068],"about_ca_topic_score_codex":0.005030912,"about_ca_topic_score_gemma":0.01072212,"teacher_disagreement_score":0.007848575,"about_ca_system_score_codex":0.0010119395,"about_ca_system_score_gemma":0.0022047227,"threshold_uncertainty_score":0.04150772},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006383251,0.009293725,0.004618915,0.9488504,0.004780214,0.000069051064,0.00013054693,0.000202969,0.025670942],"genre_scores_gemma":[0.62476116,0.03275753,0.03926841,0.20148975,0.0034688334,0.00054142525,0.00082958746,0.0012545573,0.09562873],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9584162,0.017985588,0.0012251304,0.001800383,0.01173649,0.008836241],"domain_scores_gemma":[0.90415597,0.01358562,0.0028018458,0.003018065,0.03289482,0.04354363],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051344033,0.00078363396,0.0016920577,0.0020120065,0.021266678,0.029414348,0.0054388857,0.012553766,0.02456126],"category_scores_gemma":[0.09177009,0.00054321124,0.00142799,0.0018959806,0.0146309575,0.023550466,0.017370991,0.02417138,0.008298164],"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":[0.00033201586,0.0003488236,0.0058145006,0.00088922156,0.000062629886,0.0011791196,0.01672985,0.0007347158,0.00036054986,0.17300858,0.49021134,0.3103287],"study_design_scores_gemma":[0.00004437368,0.00032780267,0.0057639983,0.0063425363,0.00006675618,0.000998015,0.099373296,0.0011361677,0.0005996949,0.21204394,0.6730679,0.0002355119],"about_ca_topic_score_codex":0.0876167,"about_ca_topic_score_gemma":0.19683765,"teacher_disagreement_score":0.96641195,"about_ca_system_score_codex":0.033588056,"about_ca_system_score_gemma":0.15851727,"threshold_uncertainty_score":0.27153647},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008669186,0.06909935,0.004727026,0.8911448,0.0018712607,0.000039275503,0.00002979426,0.000028206165,0.024391077],"genre_scores_gemma":[0.82668793,0.08808627,0.010875368,0.065061994,0.002934637,0.00026077253,0.00004581292,0.00008291765,0.005964329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9320333,0.046700727,0.0022264146,0.00175408,0.010652104,0.0066335103],"domain_scores_gemma":[0.8042049,0.1275642,0.0063791284,0.0037516325,0.044196058,0.013904135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09453895,0.0007441158,0.0019197024,0.0032657338,0.013223643,0.039629493,0.006655422,0.009024436,0.0032894786],"category_scores_gemma":[0.086857095,0.0005761143,0.00091426645,0.005204655,0.062448885,0.04166558,0.007487863,0.011085576,0.00044919577],"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":[0.00007167263,0.000064741434,0.004194131,0.0013366351,0.000037618378,0.0002039702,0.02282851,0.00051120634,0.00013964812,0.8760219,0.022566613,0.07202337],"study_design_scores_gemma":[0.000028283348,0.00010657302,0.007320994,0.007909664,0.000054287437,0.00044058703,0.27171567,0.0029530728,0.0005085714,0.5504567,0.15830006,0.00020552776],"about_ca_topic_score_codex":0.1265264,"about_ca_topic_score_gemma":0.116819,"teacher_disagreement_score":0.1265264,"about_ca_system_score_codex":0.040787585,"about_ca_system_score_gemma":0.07495842,"threshold_uncertainty_score":0.49997574},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000662856,0.9637902,0.029592857,0.001809872,0.0005243037,0.00017706671,0.00023275778,0.000088596316,0.0031215288],"genre_scores_gemma":[0.03331121,0.90852326,0.05261211,0.0014124305,0.0015585339,0.0011387519,0.0003976202,0.0002008246,0.0008452564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94203955,0.04046372,0.0042523895,0.0027713107,0.010125386,0.00034768213],"domain_scores_gemma":[0.6091166,0.36921716,0.007821132,0.0030381272,0.010255454,0.00055151375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0842432,0.0024773122,0.006307065,0.012054585,0.0006060084,0.003363133,0.0037637632,0.0026165545,0.009332888],"category_scores_gemma":[0.14684696,0.0013726634,0.004451546,0.022121554,0.003473228,0.0044083507,0.0027937922,0.003038088,0.0017909076],"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":[0.0002606903,0.00008904155,0.0024204429,0.03696968,0.0013870475,0.000056883695,0.00017409961,0.0030896526,0.00012840226,0.017927907,0.0067545874,0.93074167],"study_design_scores_gemma":[0.0006889768,0.002486497,0.024997706,0.12805106,0.007863371,0.001697896,0.0009928534,0.026850773,0.0024559852,0.19479266,0.6084571,0.000665165],"about_ca_topic_score_codex":0.003956561,"about_ca_topic_score_gemma":0.0036790315,"teacher_disagreement_score":0.0842432,"about_ca_system_score_codex":0.003279292,"about_ca_system_score_gemma":0.0049353456,"threshold_uncertainty_score":0.44552594},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033212784,0.0019644331,0.94446117,0.0036889282,0.0009020524,0.0032323769,0.000092556824,0.00046328356,0.04187393],"genre_scores_gemma":[0.04687547,0.0008789368,0.9393961,0.00069979514,0.0001926218,0.007191857,0.000037250094,0.00023652315,0.004491401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.79125816,0.18940178,0.0045119966,0.0035466915,0.010320472,0.00096088357],"domain_scores_gemma":[0.8214675,0.14798994,0.004874726,0.012426579,0.011609963,0.0016312434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12593493,0.0017708981,0.001626872,0.0086322175,0.005328714,0.0111433985,0.0033387917,0.0031330273,0.011330701],"category_scores_gemma":[0.1181617,0.0009934239,0.0014404304,0.0047920183,0.023246348,0.008917383,0.010345924,0.005698867,0.001659116],"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":[0.00022595983,0.00014863604,0.0004992246,0.001622105,0.00006736968,0.00021143057,0.022780517,0.0011470554,0.0013817662,0.8246864,0.006404317,0.14082517],"study_design_scores_gemma":[0.00021304021,0.00041875138,0.000960485,0.003420281,0.00008031175,0.0006339041,0.013910049,0.008607619,0.003279214,0.77177346,0.19650179,0.00020101608],"about_ca_topic_score_codex":0.0016834802,"about_ca_topic_score_gemma":0.0029953183,"teacher_disagreement_score":0.12593493,"about_ca_system_score_codex":0.007559355,"about_ca_system_score_gemma":0.01354809,"threshold_uncertainty_score":0.6660155},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11519906,0.18711497,0.19948801,0.16219532,0.00245129,0.00067313755,0.0001360732,0.00051007647,0.33223206],"genre_scores_gemma":[0.9123126,0.037518304,0.029204378,0.007760148,0.0019657859,0.0005818707,0.00007442563,0.00028412853,0.010298352],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81535566,0.15466206,0.0061423127,0.0034924224,0.017651776,0.0026958333],"domain_scores_gemma":[0.79297113,0.17336369,0.009770291,0.0074183987,0.01311134,0.0033651628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09284067,0.000976844,0.0014916117,0.0093328,0.007083756,0.026317853,0.002008205,0.003849813,0.007858272],"category_scores_gemma":[0.11347172,0.0006861214,0.0012903842,0.0062853405,0.023736823,0.02825382,0.01651269,0.004106529,0.0012207387],"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":[0.000257854,0.00020696064,0.014677493,0.004743645,0.0003711373,0.00081371574,0.114114046,0.0011978442,0.0010545993,0.3801392,0.011210725,0.47121283],"study_design_scores_gemma":[0.00007658566,0.00049768056,0.019192778,0.016121123,0.00035690237,0.0022014366,0.12235869,0.0021800387,0.0027360034,0.3957915,0.43815595,0.00033122936],"about_ca_topic_score_codex":0.0022458152,"about_ca_topic_score_gemma":0.002871097,"teacher_disagreement_score":0.09284067,"about_ca_system_score_codex":0.0065481244,"about_ca_system_score_gemma":0.008386086,"threshold_uncertainty_score":0.49099427},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34114975,0.024702597,0.120411396,0.30129832,0.0072110174,0.02000583,0.0053055296,0.0005281547,0.1793874],"genre_scores_gemma":[0.8807205,0.00967552,0.07254196,0.007834974,0.0010452626,0.00814582,0.0013156973,0.00020004644,0.01852023],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.89916176,0.07307247,0.00570514,0.0025044943,0.015784157,0.0037720527],"domain_scores_gemma":[0.5906268,0.27123088,0.016597774,0.011260655,0.09565208,0.014631932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17425744,0.0011676803,0.0016467535,0.0042162505,0.0034245409,0.011255375,0.0037678308,0.003088429,0.004155125],"category_scores_gemma":[0.227594,0.00052094215,0.0019002263,0.0055770073,0.003184127,0.004739899,0.006435937,0.0036383215,0.000849412],"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":[0.0011867774,0.0016211164,0.065610945,0.004861476,0.0007241215,0.0006047579,0.024317674,0.0037480455,0.0037176937,0.029283442,0.09147807,0.77284586],"study_design_scores_gemma":[0.00068610243,0.00662473,0.2508699,0.024316488,0.0020285568,0.0006009747,0.10179039,0.011191235,0.033585723,0.071228504,0.4957948,0.0012826578],"about_ca_topic_score_codex":0.020267596,"about_ca_topic_score_gemma":0.027297018,"teacher_disagreement_score":0.17425744,"about_ca_system_score_codex":0.015155775,"about_ca_system_score_gemma":0.025251213,"threshold_uncertainty_score":0.92157245},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036957134,0.0017610537,0.10809966,0.65527636,0.0047473577,0.0019142273,0.00026228427,0.00067321735,0.19030873],"genre_scores_gemma":[0.6980892,0.001874836,0.16726826,0.04650839,0.0014056826,0.002746663,0.00043071623,0.00035351075,0.08132283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92927146,0.03461302,0.0030855578,0.003827611,0.020814283,0.00838802],"domain_scores_gemma":[0.77839786,0.051886316,0.005932121,0.01492758,0.11183548,0.037020605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13150595,0.00072765816,0.00055069424,0.004400374,0.011664016,0.012058738,0.0036559016,0.0063401354,0.011891703],"category_scores_gemma":[0.12538296,0.00076177396,0.000848301,0.002154319,0.01732673,0.0070357737,0.017871657,0.0109340325,0.0018260995],"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":[0.00009090327,0.00060105027,0.0050750007,0.00031889393,0.000020618814,0.00025679465,0.009462375,0.002709863,0.0006514044,0.7475447,0.101407334,0.13186106],"study_design_scores_gemma":[0.000110185705,0.00026847806,0.006828647,0.0015067002,0.000019037503,0.00012336024,0.01642804,0.0043560886,0.0020945019,0.12169948,0.8464427,0.00012277928],"about_ca_topic_score_codex":0.1473158,"about_ca_topic_score_gemma":0.16437735,"teacher_disagreement_score":0.1473158,"about_ca_system_score_codex":0.05875874,"about_ca_system_score_gemma":0.2808949,"threshold_uncertainty_score":0.69547826},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016136382,0.034804534,0.051390193,0.44197908,0.005098042,0.0001088389,0.000057678513,0.00020149106,0.4502237],"genre_scores_gemma":[0.86358607,0.01425931,0.018558614,0.04648434,0.0045477366,0.00035321762,0.0000509908,0.0005031586,0.051656604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8913752,0.092369564,0.0012492584,0.003496347,0.0081802355,0.003329415],"domain_scores_gemma":[0.9475804,0.037814025,0.001884446,0.002379418,0.0058730417,0.004468746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058461428,0.0008056386,0.0010516278,0.0038614096,0.018343117,0.04147071,0.0018737743,0.0064550503,0.004218417],"category_scores_gemma":[0.05238507,0.00067932345,0.00042400783,0.0035864455,0.091330424,0.02313066,0.0076118317,0.012217469,0.0010638468],"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":[0.00001827646,0.000018508055,0.00031429913,0.00006591958,0.000008860087,0.00007220335,0.018766118,0.00016424846,0.00008799622,0.95262295,0.016833909,0.011026742],"study_design_scores_gemma":[0.000032185664,0.000043848373,0.0005625318,0.00067968154,0.000012738148,0.00014525982,0.020770198,0.0007656987,0.00036833945,0.6220622,0.35450792,0.000049480503],"about_ca_topic_score_codex":0.006378277,"about_ca_topic_score_gemma":0.005940548,"teacher_disagreement_score":0.058461428,"about_ca_system_score_codex":0.013731429,"about_ca_system_score_gemma":0.0151489,"threshold_uncertainty_score":0.30917728},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016239177,0.020579264,0.024280515,0.27373263,0.37163132,0.013291156,0.013814419,0.0027588492,0.26367265],"genre_scores_gemma":[0.041269735,0.021254973,0.051675588,0.025297284,0.061906695,0.0049118763,0.010796349,0.0016154825,0.78127205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98852086,0.003155184,0.00083110505,0.00048107508,0.006435912,0.0005758826],"domain_scores_gemma":[0.8828057,0.043421194,0.0045216973,0.00958397,0.04119405,0.018473357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03935267,0.0015943409,0.00093410554,0.0059395265,0.0021276777,0.0033248605,0.002087108,0.0026610151,0.08299433],"category_scores_gemma":[0.05414337,0.00065463514,0.0008061485,0.004433258,0.0019730446,0.0036998175,0.004830322,0.0028500697,0.015257654],"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":[0.00015101192,0.00034392613,0.00051328284,0.00038000432,0.000011709166,0.00011379438,0.0004821692,0.00016874672,0.0019197172,0.0011280281,0.8746588,0.12012874],"study_design_scores_gemma":[0.00012672598,0.0004359843,0.005346302,0.00051861885,0.000016882268,0.00009915478,0.00087848323,0.00027742263,0.0014791472,0.0018618307,0.98893213,0.000027291788],"about_ca_topic_score_codex":0.007952938,"about_ca_topic_score_gemma":0.03945897,"teacher_disagreement_score":0.9920471,"about_ca_system_score_codex":0.003672542,"about_ca_system_score_gemma":0.020441888,"threshold_uncertainty_score":0.27764368},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15195686,0.0017505758,0.5173674,0.14046383,0.001242352,0.0021437951,0.0022427894,0.003244074,0.17958823],"genre_scores_gemma":[0.79986703,0.0013026486,0.19018944,0.0021510979,0.00030091894,0.0013959422,0.00080929813,0.00026453758,0.0037191166],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8623679,0.10562748,0.009063789,0.0020352723,0.018603718,0.0023019195],"domain_scores_gemma":[0.5885613,0.2771844,0.048098873,0.024239596,0.053322285,0.008593654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13499267,0.0012009374,0.00052310363,0.0050444617,0.004015363,0.0168375,0.002463764,0.0027867202,0.00431065],"category_scores_gemma":[0.29031834,0.0006777737,0.000599569,0.0030353768,0.008964244,0.02110801,0.0076236776,0.0043365476,0.0010833229],"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":[0.00074540375,0.0005456429,0.042355616,0.0014216867,0.000102325364,0.00071806565,0.06965319,0.011282896,0.0015891334,0.3031508,0.065797664,0.50263757],"study_design_scores_gemma":[0.00023932804,0.0020273414,0.04055053,0.006001134,0.00024792607,0.00084908825,0.11194831,0.056916773,0.028248556,0.42621472,0.32573077,0.0010256037],"about_ca_topic_score_codex":0.0081196,"about_ca_topic_score_gemma":0.0051956316,"teacher_disagreement_score":0.13499267,"about_ca_system_score_codex":0.010593505,"about_ca_system_score_gemma":0.013618991,"threshold_uncertainty_score":0.71391803},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038190137,0.010307518,0.0041821375,0.94109917,0.022295339,0.000080461,0.00026572385,0.00037084988,0.02101675],"genre_scores_gemma":[0.04210814,0.032080907,0.03500331,0.7614429,0.024988197,0.00034845984,0.0009500818,0.0015353349,0.10154272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9723858,0.008907099,0.0018935058,0.0018408941,0.012279979,0.0026927239],"domain_scores_gemma":[0.8633866,0.03488118,0.004135776,0.010365559,0.071371675,0.015859146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045211907,0.0018181873,0.0022144313,0.003883231,0.008952899,0.017066702,0.0034904694,0.009884306,0.06824603],"category_scores_gemma":[0.14707194,0.00068074634,0.0019463819,0.0025296852,0.014048482,0.027976207,0.009232402,0.027000776,0.03194931],"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":[0.00005256478,0.00006573563,0.0009429418,0.0005491868,0.00004632354,0.00008161488,0.0011229505,0.00011952553,0.0001846663,0.030938327,0.8949285,0.07096759],"study_design_scores_gemma":[0.000028957269,0.00004794793,0.0009140583,0.002453103,0.000039353235,0.0001684201,0.0038510442,0.00018858325,0.00028178093,0.034889504,0.95703435,0.00010291064],"about_ca_topic_score_codex":0.11731861,"about_ca_topic_score_gemma":0.1522988,"teacher_disagreement_score":0.11731861,"about_ca_system_score_codex":0.014226317,"about_ca_system_score_gemma":0.041144487,"threshold_uncertainty_score":0.2391063},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61453176,0.09237478,0.008656415,0.111188434,0.012008906,0.002413821,0.010853751,0.00033089585,0.14764127],"genre_scores_gemma":[0.8978544,0.042664662,0.016472926,0.008653469,0.0028699841,0.0019319396,0.004025506,0.00033060825,0.025196476],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97346956,0.003813983,0.0023108027,0.0010769329,0.01799537,0.0013333911],"domain_scores_gemma":[0.8028624,0.042025816,0.013643512,0.003764428,0.12926771,0.0084360875],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.032058302,0.00041317233,0.00088374113,0.027719649,0.008792662,0.014143109,0.0012790089,0.0009173305,0.004798028],"category_scores_gemma":[0.08794782,0.00053224474,0.0005249112,0.04212042,0.00437531,0.004185707,0.0029440385,0.0018067146,0.00045400098],"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":[0.0005482987,0.00039314374,0.14060943,0.0060674995,0.00028428782,0.0007959411,0.116852626,0.00025714238,0.0033138671,0.039634403,0.18665831,0.504585],"study_design_scores_gemma":[0.000040908697,0.00026615598,0.38518623,0.0075542945,0.00029289923,0.00044937345,0.10765623,0.0005783622,0.0024772317,0.003139964,0.49220163,0.0001568095],"about_ca_topic_score_codex":0.16940992,"about_ca_topic_score_gemma":0.30669677,"teacher_disagreement_score":0.9722803,"about_ca_system_score_codex":0.029470855,"about_ca_system_score_gemma":0.10486789,"threshold_uncertainty_score":0.33684772},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013094762,0.00028893398,0.943543,0.0033824097,0.000167174,0.0060599125,0.0022934093,0.0003749646,0.030795353],"genre_scores_gemma":[0.085767865,0.0002618803,0.89207345,0.00035541612,0.00001931346,0.016092157,0.0007171398,0.00017984389,0.0045329514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9652097,0.029924385,0.000704965,0.0010519456,0.0024149092,0.00069403683],"domain_scores_gemma":[0.9577108,0.03386558,0.00095122866,0.0025604782,0.0043064933,0.00060533267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038343146,0.0012186221,0.0011121432,0.0067993603,0.005839689,0.0063183424,0.0029383667,0.0013142345,0.014406513],"category_scores_gemma":[0.049540907,0.0007016055,0.0011603058,0.007611493,0.0068617957,0.004583627,0.0045612785,0.0025444212,0.0013383235],"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":[0.00011088095,0.00018190139,0.0010843137,0.001691485,0.00005042772,0.00015804876,0.09595521,0.0037183196,0.0024905985,0.7056505,0.016970024,0.17193836],"study_design_scores_gemma":[0.00023683095,0.0001720816,0.001222638,0.0017779212,0.000083484825,0.00021566996,0.12235257,0.019450499,0.0040436904,0.66962564,0.18066429,0.00015466184],"about_ca_topic_score_codex":0.012396288,"about_ca_topic_score_gemma":0.02264684,"teacher_disagreement_score":0.038343146,"about_ca_system_score_codex":0.010682287,"about_ca_system_score_gemma":0.019741159,"threshold_uncertainty_score":0.20278037},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6965817,0.009312118,0.013682273,0.047080096,0.00013450325,0.0003137638,0.0008452146,0.000108196225,0.23194212],"genre_scores_gemma":[0.9852638,0.0013548326,0.002140632,0.0006877534,0.000011906391,0.00004215224,0.00009362656,0.000010664029,0.01039467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99902916,0.0003899959,0.000019086558,0.000103005565,0.00017870747,0.00027999762],"domain_scores_gemma":[0.99800164,0.000909108,0.0002341769,0.00006826684,0.0005043972,0.00028236108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012647712,0.00033429483,0.00020417024,0.0014316658,0.008324524,0.007316092,0.0013592306,0.00146314,0.004409012],"category_scores_gemma":[0.0022032838,0.00017964715,0.00026743615,0.0033731626,0.008039243,0.0027321358,0.0016773615,0.0015519859,0.00012039243],"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":[0.000089659865,0.00017916247,0.08490921,0.00062723143,0.00007864698,0.004559537,0.24282792,0.012998007,0.0029786038,0.526114,0.022778777,0.10185922],"study_design_scores_gemma":[0.000023206776,0.00006937665,0.15195698,0.0008621525,0.00005168336,0.000403336,0.37073842,0.014046954,0.00085721567,0.045081135,0.41580352,0.00010610139],"about_ca_topic_score_codex":0.9874965,"about_ca_topic_score_gemma":0.993541,"teacher_disagreement_score":0.117606945,"about_ca_system_score_codex":0.117606945,"about_ca_system_score_gemma":0.058596496,"threshold_uncertainty_score":0.8533021},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19825996,0.010047627,0.0056495075,0.6143846,0.00093731325,0.0001845777,0.00026012107,0.000113986025,0.17016238],"genre_scores_gemma":[0.9804434,0.0017790303,0.0018921099,0.007484774,0.00014765884,0.00007564048,0.000039897535,0.000031878022,0.008105743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9210155,0.039852735,0.0022023818,0.0031711622,0.014606404,0.019151894],"domain_scores_gemma":[0.7552395,0.10910053,0.008980038,0.0065128687,0.04881607,0.07135105],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.080907166,0.00039850606,0.001054993,0.0038490763,0.03206582,0.042158,0.004717879,0.007623237,0.006805965],"category_scores_gemma":[0.1388264,0.0007751837,0.0005948214,0.0066782883,0.045085877,0.0124275,0.014726039,0.006828403,0.00047577856],"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":[0.00019313022,0.00020413037,0.02744902,0.0005887497,0.00017097796,0.00031301944,0.053285416,0.006065472,0.000528742,0.763975,0.039909866,0.107316405],"study_design_scores_gemma":[0.00017462924,0.00018757528,0.052748524,0.0028051252,0.00014629486,0.00016353383,0.14862551,0.0073278835,0.0009643837,0.42669046,0.3596895,0.0004765428],"about_ca_topic_score_codex":0.92894936,"about_ca_topic_score_gemma":0.93596375,"teacher_disagreement_score":0.91909283,"about_ca_system_score_codex":0.1708425,"about_ca_system_score_gemma":0.53895485,"threshold_uncertainty_score":0.96170515},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002088198,0.5906293,0.0059540747,0.3603713,0.0035784836,0.00008367725,0.00009167765,0.00006405523,0.03713928],"genre_scores_gemma":[0.14865166,0.68907505,0.01634259,0.12891543,0.009321282,0.00057656533,0.00026028018,0.00029324237,0.0065639527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8183343,0.12500305,0.011149975,0.010245843,0.028858237,0.0064085242],"domain_scores_gemma":[0.66948146,0.25081775,0.01095751,0.009770887,0.050610214,0.008362183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1837502,0.000653704,0.002067415,0.010882415,0.0045184237,0.03230108,0.0054457276,0.010001632,0.0046047657],"category_scores_gemma":[0.16869281,0.0009229867,0.0012353914,0.01515732,0.028355598,0.029265951,0.00899121,0.014166225,0.0011987186],"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":[0.00007951053,0.00012220303,0.0011481746,0.008652712,0.000049363283,0.00015443431,0.0045657866,0.0008736643,0.00022563622,0.45031026,0.0657152,0.46810317],"study_design_scores_gemma":[0.00003876515,0.00013633742,0.0031478342,0.027057406,0.00002897829,0.00034729092,0.0057971897,0.000523733,0.00047362776,0.0774398,0.8849086,0.000100524885],"about_ca_topic_score_codex":0.014512176,"about_ca_topic_score_gemma":0.012658934,"teacher_disagreement_score":0.1837502,"about_ca_system_score_codex":0.038097356,"about_ca_system_score_gemma":0.053178307,"threshold_uncertainty_score":0.97177553},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034960885,0.01231939,0.11850689,0.50165886,0.03326332,0.0015197679,0.00089094386,0.0010228486,0.2958571],"genre_scores_gemma":[0.7406821,0.010892721,0.116340496,0.058447763,0.007515802,0.002365191,0.0008185278,0.002218305,0.06071917],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90711004,0.048931506,0.006922855,0.0041520363,0.029672945,0.0032106563],"domain_scores_gemma":[0.74525285,0.104936786,0.01595283,0.01968692,0.10659746,0.007573119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07751524,0.00083312317,0.0019173922,0.005111321,0.006465048,0.018421184,0.0028564485,0.00560486,0.011498692],"category_scores_gemma":[0.2983591,0.00052022014,0.0008776543,0.0030811776,0.011540664,0.015826374,0.005710733,0.0068359813,0.0067383708],"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":[0.00053728087,0.00023675202,0.009681882,0.0020503402,0.00016325962,0.0006579049,0.084603034,0.00043706587,0.0030461003,0.26119813,0.28663555,0.35075268],"study_design_scores_gemma":[0.00011940642,0.00031488787,0.013780004,0.012062824,0.00028660477,0.00088214205,0.0699472,0.001927871,0.004067445,0.14890084,0.74725777,0.00045309658],"about_ca_topic_score_codex":0.010748865,"about_ca_topic_score_gemma":0.011926895,"teacher_disagreement_score":0.07751524,"about_ca_system_score_codex":0.00897011,"about_ca_system_score_gemma":0.010953878,"threshold_uncertainty_score":0.40994465},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.555611,0.0033177454,0.010959597,0.116974846,0.00034375183,0.00033403834,0.00031769462,0.0000495888,0.3120918],"genre_scores_gemma":[0.9793961,0.0006142048,0.0012325649,0.0016541578,0.000028582945,0.00005497404,0.000027389244,0.000028313569,0.016963689],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9864696,0.006514972,0.00031439544,0.0009240649,0.0033083328,0.0024685208],"domain_scores_gemma":[0.9849967,0.0095436005,0.001017175,0.00046455514,0.0026754776,0.0013024615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013715314,0.00041058994,0.0004576048,0.0017886857,0.029997382,0.010881337,0.0024241428,0.0041001043,0.00231482],"category_scores_gemma":[0.016591636,0.0005239455,0.00031262595,0.0028241582,0.04297562,0.0053985217,0.0047745584,0.004290293,0.00015422347],"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":[0.000024175291,0.000012622852,0.0028220457,0.0000839785,0.0000038414164,0.00051702885,0.85649955,0.00019247543,0.00041235343,0.13017492,0.003941071,0.005315986],"study_design_scores_gemma":[0.000010801564,0.000015770654,0.005852514,0.00024683267,0.00001111801,0.0001648438,0.74543107,0.0005404268,0.00045896953,0.013705409,0.23352301,0.000039191567],"about_ca_topic_score_codex":0.9627629,"about_ca_topic_score_gemma":0.974879,"teacher_disagreement_score":0.20712952,"about_ca_system_score_codex":0.20712952,"about_ca_system_score_gemma":0.13830544,"threshold_uncertainty_score":0.91961735},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027425664,0.0018098265,0.00007541077,0.046283618,0.9492654,0.000036137582,0.00004802286,0.00006729058,0.0023868657],"genre_scores_gemma":[0.0007940521,0.0020142475,0.00019895395,0.063425794,0.894902,0.000088046145,0.00006652629,0.00007999921,0.038430437],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98751754,0.0028186832,0.0013668225,0.0012468285,0.0061513963,0.0008986214],"domain_scores_gemma":[0.9471562,0.013866884,0.0036687509,0.001998847,0.024710152,0.008599159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0115706595,0.0047076037,0.007291628,0.0058506154,0.005418657,0.015174952,0.006101785,0.03480138,0.034654904],"category_scores_gemma":[0.06868452,0.0017895662,0.0033883227,0.0031312825,0.0045057354,0.0044261357,0.0023057582,0.026305355,0.03517152],"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":[0.000025467867,0.000008353918,0.000011683359,0.00006185013,0.000013295842,0.000050891624,0.0000033305191,0.000008375727,0.0000135259215,0.0001074267,0.99803704,0.0016588626],"study_design_scores_gemma":[0.00019554248,0.000037892743,0.0003490379,0.0005062927,0.00010696681,0.00019383822,0.000055238248,0.00022375502,0.000105855186,0.0012266793,0.99696535,0.000033565255],"about_ca_topic_score_codex":0.0033230279,"about_ca_topic_score_gemma":0.011373557,"teacher_disagreement_score":0.03480138,"about_ca_system_score_codex":0.0076021273,"about_ca_system_score_gemma":0.005588282,"threshold_uncertainty_score":0.115932226},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97249943,0.002031688,0.0017100365,0.007589558,0.00006358978,0.00021012254,0.00012496882,0.000026144624,0.015744433],"genre_scores_gemma":[0.9920793,0.0009194805,0.001221319,0.0006190958,0.000008031401,0.00008493426,0.00006235276,0.000010769804,0.004994721],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9917883,0.004210399,0.0002751858,0.00040384935,0.002030417,0.0012918017],"domain_scores_gemma":[0.9848941,0.0063264105,0.001145359,0.00040951394,0.0050490038,0.0021756538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007905515,0.0004366995,0.00042842078,0.00084751734,0.0075882575,0.0041487743,0.0012103382,0.0012144009,0.0031236515],"category_scores_gemma":[0.026648171,0.00036233006,0.0002659426,0.0014855186,0.0050630025,0.0018530558,0.0030913078,0.0021944644,0.00019774534],"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":[0.0001993155,0.00022938185,0.05939678,0.00058969576,0.000052066305,0.00080140313,0.79339576,0.0010987085,0.0013126389,0.009062569,0.005478838,0.12838288],"study_design_scores_gemma":[0.00006104633,0.00043677576,0.14319275,0.00088078546,0.000091202244,0.00020613536,0.7581403,0.0014297091,0.0010290294,0.0013703639,0.09303989,0.0001220258],"about_ca_topic_score_codex":0.93108916,"about_ca_topic_score_gemma":0.9668259,"teacher_disagreement_score":0.06891084,"about_ca_system_score_codex":0.05578387,"about_ca_system_score_gemma":0.046967812,"threshold_uncertainty_score":0.40474218},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4980766,0.009236477,0.16811337,0.040437512,0.0015692385,0.008944071,0.0015668526,0.001124641,0.27093124],"genre_scores_gemma":[0.84572333,0.0036224553,0.08458479,0.0016878303,0.00010133474,0.003994666,0.00052901753,0.00017784395,0.059578758],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9400685,0.03930206,0.0028183686,0.0019954764,0.013340986,0.0024746405],"domain_scores_gemma":[0.8900896,0.038431387,0.008188498,0.0047953436,0.050231915,0.008263341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049783666,0.00072991883,0.0007561464,0.0034152402,0.0055535394,0.008048234,0.0016923501,0.0014248481,0.0071277805],"category_scores_gemma":[0.08597398,0.0006139723,0.00089658605,0.0024044297,0.0059424243,0.004613212,0.005211249,0.0033073984,0.0017225442],"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":[0.00062984193,0.00044576783,0.05139028,0.002172876,0.00011088188,0.00020779019,0.25034994,0.0015669494,0.003603559,0.059241537,0.028832337,0.6014482],"study_design_scores_gemma":[0.00023885386,0.0018223411,0.2390804,0.0067017428,0.00019842153,0.00039709426,0.23102935,0.004619286,0.011729026,0.030162007,0.4733777,0.00064381404],"about_ca_topic_score_codex":0.13139898,"about_ca_topic_score_gemma":0.20967402,"teacher_disagreement_score":0.13139898,"about_ca_system_score_codex":0.02675315,"about_ca_system_score_gemma":0.05688394,"threshold_uncertainty_score":0.26328433},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989718,0.00013353306,0.00004991018,0.00020305939,0.0000039717343,0.000015891908,0.000025665306,0.000002015787,0.0005940927],"genre_scores_gemma":[0.9984725,0.00026427643,0.00011923545,0.00008401295,0.0000021763283,0.000013047028,0.000041279785,0.0000017081317,0.0010017009],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99814045,0.00037387075,0.00008068599,0.00013407692,0.0007280268,0.000542866],"domain_scores_gemma":[0.99140376,0.0011815056,0.0013922893,0.00011570041,0.003106121,0.0028006204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021458687,0.00019009804,0.0002605034,0.00064813136,0.006107696,0.001585679,0.00074933574,0.00037302615,0.0009885756],"category_scores_gemma":[0.0055849124,0.00038368738,0.00016964063,0.0010773938,0.0018502135,0.0004459354,0.00078389427,0.0010819441,0.00008658275],"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":[0.00008619897,0.00017288308,0.6587102,0.00009133681,0.00001691117,0.0005057014,0.31991047,0.00008679927,0.0014699644,0.00019993316,0.0012480019,0.017501643],"study_design_scores_gemma":[0.00000707118,0.00012721468,0.70747125,0.0000697585,0.000007959065,0.00008746256,0.2871676,0.00012897584,0.00028651158,0.00002127658,0.0046082214,0.000016752198],"about_ca_topic_score_codex":0.9519648,"about_ca_topic_score_gemma":0.9791033,"teacher_disagreement_score":0.048035204,"about_ca_system_score_codex":0.015964545,"about_ca_system_score_gemma":0.030941376,"threshold_uncertainty_score":0.115831435},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4843683,0.0064269416,0.006484169,0.32080796,0.00039605115,0.00019970161,0.00030627145,0.00011681007,0.18089375],"genre_scores_gemma":[0.9851982,0.000769562,0.0013615721,0.008096837,0.000062075655,0.000089423396,0.000050245144,0.000021553855,0.0043505034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9859364,0.005491124,0.00055130944,0.0018022121,0.0016145506,0.0046043796],"domain_scores_gemma":[0.9434261,0.043159973,0.0020593614,0.0015792293,0.00544752,0.004327893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03702705,0.00045186855,0.0007693421,0.0029742464,0.027310885,0.019372877,0.0027934653,0.007597966,0.0076277293],"category_scores_gemma":[0.050141595,0.0006890653,0.0006769303,0.0026258745,0.033618446,0.015726492,0.00900571,0.011411306,0.00019115717],"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":[0.0002019418,0.00018395376,0.006215659,0.0002123353,0.000042552925,0.0002139864,0.03945924,0.0015668253,0.0003726114,0.90107936,0.015509159,0.034942333],"study_design_scores_gemma":[0.00027722112,0.00020889958,0.046062265,0.0021980763,0.00025195093,0.00013034955,0.18109974,0.0032553782,0.0025264982,0.513409,0.2501625,0.00041814035],"about_ca_topic_score_codex":0.5023043,"about_ca_topic_score_gemma":0.5932179,"teacher_disagreement_score":0.5023043,"about_ca_system_score_codex":0.07218626,"about_ca_system_score_gemma":0.07806171,"threshold_uncertainty_score":0.9987612},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97800684,0.00021405412,0.0034562831,0.003919574,0.00007172897,0.0007011446,0.00008839599,0.000029320367,0.013512553],"genre_scores_gemma":[0.9879288,0.00029666914,0.004385525,0.00074040896,0.000032224805,0.00029318937,0.000040556417,0.000024397135,0.0062581757],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98648167,0.009264503,0.00038937462,0.00036415848,0.0012801326,0.002220099],"domain_scores_gemma":[0.96885586,0.017232709,0.0019737973,0.0011131597,0.004280844,0.0065435255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011570495,0.00060382363,0.0005800339,0.001951016,0.013278998,0.0028119776,0.002080128,0.004275039,0.0036334395],"category_scores_gemma":[0.028489528,0.0005800334,0.0006265996,0.0018734105,0.0026996173,0.002299305,0.0040209386,0.004015279,0.00037356446],"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":[0.0018228316,0.036928233,0.17731853,0.0012695941,0.0001776296,0.10881853,0.4042824,0.0067751408,0.0053705242,0.026989708,0.01972506,0.21052186],"study_design_scores_gemma":[0.00042992274,0.009396638,0.07553933,0.0011360948,0.00018305743,0.03348365,0.7846856,0.010863528,0.008623526,0.005415494,0.06998059,0.00026248992],"about_ca_topic_score_codex":0.02469294,"about_ca_topic_score_gemma":0.076924175,"teacher_disagreement_score":0.02469294,"about_ca_system_score_codex":0.011104186,"about_ca_system_score_gemma":0.011059929,"threshold_uncertainty_score":0.08056682},"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":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020092246,0.5878399,0.0295222,0.18689989,0.16119905,0.0006145964,0.0008166902,0.001199073,0.031707693],"genre_scores_gemma":[0.008113623,0.5600451,0.06551442,0.18151641,0.14853364,0.0033624244,0.0011700979,0.0016991927,0.030045047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8541032,0.09388171,0.02313557,0.009438519,0.017620318,0.0018206403],"domain_scores_gemma":[0.57753915,0.29764056,0.04964582,0.024922451,0.03981179,0.010440264],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07610103,0.0032777865,0.0063997167,0.015172089,0.003344639,0.024561318,0.0054715704,0.017452253,0.041096307],"category_scores_gemma":[0.23935829,0.001643307,0.0029235054,0.039960228,0.024587017,0.027676204,0.00887765,0.024347456,0.041545473],"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":[0.00012901082,0.000050957246,0.00024424048,0.025419146,0.00031490572,0.00018222214,0.0034403526,0.00021544313,0.00026591943,0.12671795,0.63476205,0.2082577],"study_design_scores_gemma":[0.000056562025,0.00004131037,0.000155786,0.013665206,0.00008208328,0.00057210104,0.00066708645,0.00014866068,0.000069192145,0.054292724,0.93016815,0.00008118316],"about_ca_topic_score_codex":0.002970856,"about_ca_topic_score_gemma":0.0032692591,"teacher_disagreement_score":0.923899,"about_ca_system_score_codex":0.007473871,"about_ca_system_score_gemma":0.020492172,"threshold_uncertainty_score":0.40246552},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6364221,0.00183339,0.12948975,0.020680198,0.00053712784,0.0049597006,0.0009189502,0.0033974503,0.20176136],"genre_scores_gemma":[0.83115244,0.00052194716,0.16047193,0.00088263827,0.000029135232,0.0014435163,0.00030591505,0.00009559135,0.0050968104],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.918222,0.06350303,0.0032154664,0.00233713,0.010965018,0.0017573759],"domain_scores_gemma":[0.9042893,0.056844518,0.009908103,0.010585665,0.013882795,0.0044896496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06247624,0.00062835513,0.0005168267,0.0040572425,0.0026159536,0.00518308,0.001969117,0.00090450875,0.002263159],"category_scores_gemma":[0.1003126,0.00045008922,0.00045190254,0.003642384,0.00508192,0.002772327,0.004849635,0.0015175237,0.0005185978],"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":[0.0002576867,0.001769268,0.0854074,0.0010459807,0.00008008016,0.00023037421,0.040308487,0.001567945,0.0028023976,0.011170575,0.014926094,0.84043366],"study_design_scores_gemma":[0.000730752,0.004722258,0.59745663,0.0029484602,0.00036368836,0.00095564005,0.10208524,0.017678382,0.027108133,0.04601626,0.19929007,0.000644453],"about_ca_topic_score_codex":0.06057667,"about_ca_topic_score_gemma":0.15373132,"teacher_disagreement_score":0.06247624,"about_ca_system_score_codex":0.008823953,"about_ca_system_score_gemma":0.02331971,"threshold_uncertainty_score":0.33040982},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0261263,0.1161213,0.009706175,0.34830415,0.008956888,0.0063462867,0.0034537495,0.00093521446,0.48004997],"genre_scores_gemma":[0.44845635,0.16906233,0.040369768,0.13025764,0.00217016,0.010100217,0.0048254807,0.00062732183,0.19413085],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9804308,0.009120961,0.0006247298,0.00059806823,0.007100662,0.002124722],"domain_scores_gemma":[0.9773169,0.004861305,0.0010351875,0.0010693198,0.008935375,0.006781979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02169381,0.0006378551,0.00066451915,0.0024905528,0.008532991,0.0058766543,0.0019468322,0.0021511489,0.014653792],"category_scores_gemma":[0.02809497,0.0003968577,0.00053938554,0.0029576006,0.004154103,0.0027713543,0.006362087,0.0028549538,0.0016201299],"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":[0.00017058347,0.00023463818,0.0015544797,0.0070507997,0.00008932127,0.0001727829,0.0124555845,0.000086362284,0.0005825039,0.021651618,0.45878878,0.49716255],"study_design_scores_gemma":[0.00012327527,0.00009608684,0.006544935,0.006335476,0.00007156862,0.000056887133,0.0063115195,0.000029013736,0.00038775307,0.0024815248,0.97753716,0.0000248751],"about_ca_topic_score_codex":0.63439184,"about_ca_topic_score_gemma":0.88280356,"teacher_disagreement_score":0.63439184,"about_ca_system_score_codex":0.042909626,"about_ca_system_score_gemma":0.1858075,"threshold_uncertainty_score":0.73552257},"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":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111279935,0.034498844,0.020334639,0.018577542,0.0007198411,0.00069250545,0.0022948491,0.00061964407,0.8109822],"genre_scores_gemma":[0.507762,0.02235601,0.03123323,0.0011169554,0.000080986436,0.00013794437,0.0013101373,0.00017905275,0.43582368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961845,0.00045002333,0.00012428197,0.00018462694,0.0024067818,0.00064971764],"domain_scores_gemma":[0.99585813,0.00054592744,0.00012135579,0.00007189024,0.0029512264,0.0004514706],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030382655,0.00052483764,0.00059980847,0.004376972,0.005590418,0.0075008553,0.001728398,0.0010787047,0.005101546],"category_scores_gemma":[0.006991354,0.0004009794,0.00030554697,0.008425008,0.0017669778,0.00119624,0.0010014261,0.0011552008,0.000581103],"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":[0.000058748352,0.00013559335,0.014391949,0.00038865267,0.000031973414,0.00021832554,0.0033933239,0.01988457,0.0006027707,0.1424825,0.14727032,0.67114115],"study_design_scores_gemma":[0.0000328994,0.000114636736,0.070895374,0.0013000845,0.00008056177,0.00016699091,0.011102389,0.026695404,0.0032127802,0.03839418,0.84782153,0.00018320575],"about_ca_topic_score_codex":0.99292153,"about_ca_topic_score_gemma":0.99760145,"teacher_disagreement_score":0.9969617,"about_ca_system_score_codex":0.15703999,"about_ca_system_score_gemma":0.2329996,"threshold_uncertainty_score":0.9777141},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81898963,0.0026166306,0.011846734,0.01288353,0.0006400025,0.0073317126,0.0028941925,0.0006531721,0.14214432],"genre_scores_gemma":[0.9053839,0.00081453146,0.009482072,0.0009096692,0.0000683037,0.0022443493,0.0010545234,0.000055468223,0.07998716],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9826554,0.007123951,0.00042062846,0.0011593397,0.005307497,0.0033332],"domain_scores_gemma":[0.9499821,0.0077488776,0.0016369773,0.0015780453,0.024264123,0.014789907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025727812,0.0008272609,0.00059473724,0.0026499385,0.00402484,0.004199282,0.0017802193,0.0014239894,0.009121619],"category_scores_gemma":[0.035320185,0.00045780136,0.00052652427,0.0022300824,0.002143755,0.0015220591,0.0039013992,0.0016079657,0.0012570375],"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":[0.0052108597,0.0076286304,0.0786837,0.00092302996,0.00025981967,0.00025010167,0.01644446,0.010439858,0.0069583454,0.03419373,0.06184859,0.7771589],"study_design_scores_gemma":[0.002402823,0.018788893,0.66221446,0.000998027,0.000440884,0.00012568226,0.02014497,0.011066439,0.016837467,0.0038429676,0.26288933,0.00024806964],"about_ca_topic_score_codex":0.6925114,"about_ca_topic_score_gemma":0.74334556,"teacher_disagreement_score":0.95001626,"about_ca_system_score_codex":0.049983744,"about_ca_system_score_gemma":0.17016643,"threshold_uncertainty_score":0.61859894},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026660983,0.000039431518,0.9561428,0.0015611666,0.000028097702,0.00083410996,0.00087990833,0.0021910476,0.011662379],"genre_scores_gemma":[0.22796372,0.000061341205,0.7668128,0.00027819816,0.000009551336,0.0006590111,0.0010773132,0.00022051089,0.002917543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9937405,0.0036155262,0.00045547387,0.00061543036,0.0010973451,0.00047573692],"domain_scores_gemma":[0.9772145,0.017027732,0.0010006416,0.0009533731,0.0033758327,0.00042780506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0102439355,0.00081550586,0.000616422,0.0036290647,0.0021664256,0.008209674,0.0027867334,0.0015692381,0.011815331],"category_scores_gemma":[0.030522278,0.000918481,0.0016520536,0.0015866229,0.0015729181,0.0054697804,0.0017394339,0.00228386,0.0014581264],"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":[0.00044858898,0.00064515637,0.013253736,0.00053954154,0.00011031621,0.0005537185,0.0028345329,0.40511653,0.0030226184,0.3549471,0.007941154,0.210587],"study_design_scores_gemma":[0.00011525826,0.00015534341,0.000724031,0.00023741048,0.00008658292,0.0000842022,0.0009388924,0.87705874,0.003976846,0.10439417,0.012156118,0.00007243172],"about_ca_topic_score_codex":0.047979478,"about_ca_topic_score_gemma":0.05573281,"teacher_disagreement_score":0.047979478,"about_ca_system_score_codex":0.008629181,"about_ca_system_score_gemma":0.01149419,"threshold_uncertainty_score":0.09540039},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017389528,0.06754097,0.18231851,0.30977213,0.003105531,0.00054877315,0.0003641407,0.0001979622,0.41876248],"genre_scores_gemma":[0.84495455,0.04998621,0.06484673,0.019935368,0.0012713484,0.0007911086,0.00020455047,0.00011788631,0.01789237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9772474,0.014430002,0.00092627073,0.0010906832,0.004586464,0.0017190975],"domain_scores_gemma":[0.9727667,0.01815535,0.0017064974,0.002144659,0.0038979237,0.0013287574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030663988,0.0007642177,0.0011114442,0.0045101605,0.0047137854,0.011259808,0.0016137187,0.0051945774,0.0063880426],"category_scores_gemma":[0.043007825,0.00046904577,0.0009955917,0.0037495757,0.02024506,0.0168082,0.004859518,0.0061521027,0.0009375348],"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":[0.000015617064,0.000028421387,0.00053458306,0.0004238738,0.000030612908,0.000039854363,0.00074448733,0.0008517233,0.0000415497,0.9481327,0.008626393,0.040530257],"study_design_scores_gemma":[0.000032031716,0.00008864803,0.0011065888,0.0026551404,0.000051172436,0.00012855133,0.00182391,0.0013423279,0.00027924567,0.7968739,0.19556884,0.000049718645],"about_ca_topic_score_codex":0.009623817,"about_ca_topic_score_gemma":0.006620967,"teacher_disagreement_score":0.030663988,"about_ca_system_score_codex":0.012337518,"about_ca_system_score_gemma":0.026758246,"threshold_uncertainty_score":0.16216856},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0116724,0.013934052,0.5403521,0.34631535,0.0036759337,0.0024232594,0.00011565808,0.0002478735,0.081263274],"genre_scores_gemma":[0.5677692,0.0049212766,0.38834578,0.024885148,0.0013559465,0.008564959,0.000060410297,0.00021116165,0.0038860468],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.20183599,0.75352037,0.009764491,0.0046850406,0.027305052,0.0028890988],"domain_scores_gemma":[0.22680412,0.7208032,0.009662305,0.01562617,0.024975859,0.0021284213],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6110678,0.0019273206,0.0033527378,0.010552181,0.009479492,0.027337512,0.007351535,0.011473642,0.0030737927],"category_scores_gemma":[0.5568083,0.001215601,0.0031010646,0.0066500427,0.078576244,0.028692676,0.014353582,0.014605468,0.00038070226],"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":[0.00006059413,0.000055183897,0.0007161958,0.0012536395,0.000079391786,0.00011955094,0.0131626045,0.0011589185,0.000042015537,0.9511057,0.0037736513,0.028472558],"study_design_scores_gemma":[0.00014589343,0.0002598174,0.0007540023,0.0064894296,0.00014406163,0.00021974507,0.014185077,0.009291566,0.0005865722,0.9227872,0.045025837,0.000110795176],"about_ca_topic_score_codex":0.0086250715,"about_ca_topic_score_gemma":0.008803242,"teacher_disagreement_score":0.38893223,"about_ca_system_score_codex":0.027926037,"about_ca_system_score_gemma":0.03796918,"threshold_uncertainty_score":0.47962272},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07390438,0.037235156,0.24314478,0.56952155,0.0057161916,0.008224281,0.00012149917,0.0009719642,0.06116024],"genre_scores_gemma":[0.60077316,0.01031477,0.33830225,0.036888447,0.0013632464,0.006919856,0.00009313114,0.00045613202,0.0048890645],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.3440154,0.56161994,0.034342203,0.006122866,0.04696998,0.006929655],"domain_scores_gemma":[0.21898256,0.5851072,0.02464549,0.01603955,0.13751282,0.017712444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5843487,0.001249053,0.0023166663,0.0057309256,0.018313188,0.024543399,0.007070913,0.009229776,0.003182311],"category_scores_gemma":[0.64920163,0.001627154,0.0016185496,0.004000848,0.021490712,0.01917372,0.017914258,0.015674194,0.0011405259],"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":[0.00057904504,0.0014172887,0.019882783,0.007907379,0.00034953118,0.004056654,0.25405258,0.004468784,0.0017250944,0.07140253,0.05783278,0.57632554],"study_design_scores_gemma":[0.0006213227,0.0014253046,0.02059788,0.04320857,0.000326148,0.0055833464,0.3990986,0.010594317,0.0050006164,0.19125466,0.3212739,0.0010153585],"about_ca_topic_score_codex":0.014984707,"about_ca_topic_score_gemma":0.026538692,"teacher_disagreement_score":0.41565132,"about_ca_system_score_codex":0.03249208,"about_ca_system_score_gemma":0.09903822,"threshold_uncertainty_score":0.5125721},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079574175,0.022088323,0.03219138,0.5595326,0.0028002877,0.0004629329,0.00019467827,0.00030723732,0.30284837],"genre_scores_gemma":[0.9654458,0.004285406,0.010711109,0.008535135,0.00031556364,0.00016844095,0.00006885576,0.000057601195,0.010412112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9708191,0.015875518,0.0011807836,0.0015277591,0.006977625,0.003619209],"domain_scores_gemma":[0.9710923,0.013303727,0.0025679704,0.0015023387,0.005648958,0.0058846716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02467747,0.00069578394,0.00070982054,0.0021516872,0.004534082,0.0207315,0.0017694228,0.00450027,0.007956137],"category_scores_gemma":[0.041614983,0.0006996849,0.00063279906,0.0021755488,0.016630825,0.014016748,0.006080971,0.0061920863,0.001178264],"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":[0.00013731088,0.0002965448,0.012236552,0.0008182705,0.00010558728,0.0002943234,0.014518477,0.0011596222,0.0003323356,0.75060993,0.030896556,0.1885945],"study_design_scores_gemma":[0.00011159376,0.00047306536,0.016183807,0.002268547,0.000115858915,0.0003742694,0.044966437,0.0036057488,0.0015752019,0.7386148,0.19158797,0.00012259111],"about_ca_topic_score_codex":0.039702684,"about_ca_topic_score_gemma":0.026305074,"teacher_disagreement_score":0.039702684,"about_ca_system_score_codex":0.024401432,"about_ca_system_score_gemma":0.06616518,"threshold_uncertainty_score":0.17704564},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.882881,0.013230659,0.0067009986,0.02339044,0.00061651913,0.00091024564,0.0001962279,0.00013095554,0.071943],"genre_scores_gemma":[0.97338516,0.005621038,0.0029683197,0.002316132,0.00009053792,0.000539792,0.00008849359,0.000061110826,0.014929422],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9750667,0.018136729,0.0005639225,0.0012141375,0.0028040728,0.0022144315],"domain_scores_gemma":[0.98419476,0.008068314,0.0015185175,0.0006354901,0.0024329657,0.003149864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015421302,0.00062368426,0.0008521894,0.0015936049,0.0102433935,0.007111231,0.0018840088,0.0024329454,0.004825481],"category_scores_gemma":[0.024320446,0.00076725107,0.00035698497,0.0023121906,0.013109983,0.0032539924,0.008072737,0.0046395683,0.0008001861],"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":[0.00009026739,0.00024558595,0.011236878,0.0006016564,0.00002434888,0.0015992337,0.9429598,0.00009427897,0.0004066461,0.007268835,0.0035183865,0.031954113],"study_design_scores_gemma":[0.00003530281,0.00028136396,0.014425399,0.0017660853,0.000028969707,0.0011676273,0.85977554,0.00019198137,0.0005188567,0.0017100902,0.12004935,0.00004957062],"about_ca_topic_score_codex":0.052219402,"about_ca_topic_score_gemma":0.075513974,"teacher_disagreement_score":0.052219402,"about_ca_system_score_codex":0.012947313,"about_ca_system_score_gemma":0.024395917,"threshold_uncertainty_score":0.103830874},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.706167,0.016632065,0.009366836,0.07337433,0.0015581,0.00058257405,0.00005139624,0.0001751731,0.19209246],"genre_scores_gemma":[0.94233334,0.0030089263,0.003283561,0.0030720169,0.0001435588,0.000088864974,0.00002019639,0.000052898624,0.047996618],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97041804,0.014172097,0.0018860229,0.0024291654,0.008829535,0.0022652107],"domain_scores_gemma":[0.94153434,0.015193426,0.0035243279,0.0030761873,0.023764454,0.0129071465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034270275,0.00019728694,0.0005077716,0.0025365923,0.0063509466,0.0072444594,0.001365086,0.0022507259,0.00517299],"category_scores_gemma":[0.048506696,0.00060103135,0.0004282046,0.002499174,0.0072380174,0.0034748556,0.009920084,0.0030366527,0.00050428667],"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":[0.00021807825,0.00063841423,0.031399414,0.0015250813,0.000029896086,0.002437351,0.32230818,0.0009168077,0.003338182,0.09806353,0.016094394,0.52303064],"study_design_scores_gemma":[0.00006171367,0.0009036706,0.16456512,0.0019812009,0.000027035037,0.0028328206,0.116168894,0.005697189,0.0023320655,0.024642205,0.6805676,0.00022043995],"about_ca_topic_score_codex":0.08095817,"about_ca_topic_score_gemma":0.091051094,"teacher_disagreement_score":0.08095817,"about_ca_system_score_codex":0.033713978,"about_ca_system_score_gemma":0.069117785,"threshold_uncertainty_score":0.24461323},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019372335,0.072828986,0.016692907,0.07642924,0.0023918485,0.00018946917,0.00019843421,0.00016757855,0.81172925],"genre_scores_gemma":[0.25737074,0.080907434,0.03249333,0.017225258,0.0015947007,0.00031104824,0.0002807245,0.0002683724,0.60954833],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99908614,0.00037843766,0.000027904682,0.00011073204,0.00028943687,0.0001074615],"domain_scores_gemma":[0.9986993,0.0006128358,0.00005687904,0.000054153636,0.00036672913,0.00021004291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020529442,0.0003543215,0.00018983522,0.0013008292,0.0008909361,0.0032740904,0.0009698213,0.0018423086,0.007845697],"category_scores_gemma":[0.0033069958,0.0002599241,0.00017035335,0.0012879089,0.003963823,0.0024164945,0.001471748,0.0030036888,0.00107746],"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":[0.00003350669,0.00018360293,0.0010640522,0.00022596116,0.000004291344,0.0000693578,0.002046741,0.0013297095,0.00036440036,0.40003735,0.054615818,0.54002523],"study_design_scores_gemma":[0.000010413727,0.00007932283,0.0054900907,0.0012134993,0.0000055142773,0.00016330127,0.0014725251,0.0013724101,0.000835282,0.06304953,0.92628384,0.000024330368],"about_ca_topic_score_codex":0.018892772,"about_ca_topic_score_gemma":0.039308593,"teacher_disagreement_score":0.018892772,"about_ca_system_score_codex":0.006381738,"about_ca_system_score_gemma":0.009807311,"threshold_uncertainty_score":0.046302974},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3141737,0.0026894372,0.073578596,0.15786646,0.0013049436,0.006906826,0.00071108923,0.001126909,0.44164208],"genre_scores_gemma":[0.78848076,0.0024372053,0.16155592,0.00531922,0.00014246174,0.0035210631,0.0007751737,0.00014068834,0.037627477],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9694847,0.024135629,0.00055404275,0.00071774295,0.0036345131,0.0014733943],"domain_scores_gemma":[0.97796863,0.011595895,0.0016011508,0.0010321897,0.004094519,0.0037076317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0499566,0.0005604228,0.0003723027,0.0034748078,0.0073907184,0.008844249,0.001278053,0.0024755546,0.008106235],"category_scores_gemma":[0.033713564,0.00035800977,0.00043784414,0.001448892,0.0028615245,0.005577645,0.005184263,0.0023016823,0.0012039057],"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":[0.00021637886,0.0018170319,0.016981201,0.0007759348,0.00005772654,0.00034762963,0.11004403,0.0015303467,0.0028875521,0.094140016,0.14908017,0.622122],"study_design_scores_gemma":[0.00015261708,0.0011242471,0.013707808,0.0014627316,0.00007484976,0.00016791209,0.25494704,0.0017833448,0.0030609646,0.047484502,0.6758665,0.00016746271],"about_ca_topic_score_codex":0.014064144,"about_ca_topic_score_gemma":0.031449806,"teacher_disagreement_score":0.0499566,"about_ca_system_score_codex":0.008602858,"about_ca_system_score_gemma":0.03215309,"threshold_uncertainty_score":0.26419896},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34938166,0.008175638,0.101082295,0.091604725,0.0005664222,0.0011875306,0.00030869967,0.00035647687,0.44733655],"genre_scores_gemma":[0.94616896,0.0018522922,0.04330655,0.001084627,0.000044770808,0.0003480128,0.00013611556,0.00004761916,0.007011047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97626436,0.018974323,0.00037062564,0.0006034112,0.001901033,0.001886133],"domain_scores_gemma":[0.97013503,0.017012374,0.0024785846,0.001952344,0.0024847665,0.0059370208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026139736,0.00057245354,0.0004326812,0.0024381902,0.008891974,0.008839477,0.00194266,0.0026627204,0.007997617],"category_scores_gemma":[0.048431616,0.0003031716,0.00037151983,0.0024758372,0.0070884903,0.008351939,0.011545638,0.0024206615,0.00097528956],"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":[0.00029225077,0.00081646425,0.020899916,0.00072482124,0.00019035238,0.00043765453,0.034653563,0.009674456,0.001084859,0.5008947,0.044024073,0.38630682],"study_design_scores_gemma":[0.00019406778,0.00045721483,0.015708877,0.0011594463,0.00015873027,0.00020688493,0.117285185,0.016309518,0.002098039,0.62314886,0.22317067,0.00010250301],"about_ca_topic_score_codex":0.028520698,"about_ca_topic_score_gemma":0.06347414,"teacher_disagreement_score":0.028520698,"about_ca_system_score_codex":0.0068547246,"about_ca_system_score_gemma":0.02449692,"threshold_uncertainty_score":0.13824177},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029469267,0.011048539,0.002619076,0.85430825,0.0015461204,0.00020491226,0.0004784866,0.00015641963,0.10016894],"genre_scores_gemma":[0.6939329,0.011038237,0.01619946,0.16783719,0.00083722395,0.0002817343,0.0005159869,0.00007129442,0.109285906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98411083,0.0029629814,0.0004287054,0.00084121956,0.0054014577,0.006254899],"domain_scores_gemma":[0.9756269,0.0050781053,0.0008423633,0.0004948219,0.007022188,0.010935603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020777993,0.00041418185,0.0005097205,0.001546164,0.02107693,0.019450791,0.0034830335,0.010669671,0.009305576],"category_scores_gemma":[0.018014602,0.000523926,0.00074592483,0.00213784,0.008302765,0.0053266673,0.006683452,0.0076983455,0.00029559896],"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":[0.00016014154,0.00018135135,0.019042086,0.0006424015,0.000043651355,0.0009045095,0.011820977,0.0028486082,0.0010563176,0.5954372,0.2746011,0.09326156],"study_design_scores_gemma":[0.0000839063,0.00012075619,0.042712923,0.00088084885,0.00006168958,0.00025671802,0.020738244,0.002146013,0.0006425315,0.04154351,0.89061874,0.00019403093],"about_ca_topic_score_codex":0.98893017,"about_ca_topic_score_gemma":0.9933802,"teacher_disagreement_score":0.82066,"about_ca_system_score_codex":0.17933998,"about_ca_system_score_gemma":0.5627497,"threshold_uncertainty_score":0.9518493},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030161364,0.013868798,0.84041744,0.11023677,0.0022779286,0.009031439,0.00017465392,0.00041253286,0.020564375],"genre_scores_gemma":[0.029388253,0.0031635824,0.9569552,0.0042676954,0.0002445022,0.0053242915,0.000083876126,0.00005862253,0.00051402854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.33379608,0.51675075,0.07010379,0.011648082,0.06392045,0.0037808737],"domain_scores_gemma":[0.27690932,0.5771062,0.024898369,0.030002296,0.085480236,0.005603571],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5746235,0.003932948,0.005515346,0.028634386,0.011596618,0.03210038,0.016280133,0.017812906,0.0023479213],"category_scores_gemma":[0.56535465,0.003991971,0.005193956,0.011077273,0.045044065,0.025871368,0.025334602,0.035222605,0.0017713526],"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":[0.00014438503,0.0005861977,0.004545994,0.014985781,0.00082370604,0.0011130382,0.042072274,0.009353304,0.00086448627,0.60322195,0.026986962,0.295302],"study_design_scores_gemma":[0.00027420907,0.00033448587,0.0017479402,0.038930602,0.00030675417,0.0006584228,0.014600765,0.0077646533,0.0016617312,0.77099955,0.16235791,0.00036295044],"about_ca_topic_score_codex":0.008942683,"about_ca_topic_score_gemma":0.014068931,"teacher_disagreement_score":0.42537647,"about_ca_system_score_codex":0.02609422,"about_ca_system_score_gemma":0.07054382,"threshold_uncertainty_score":0.524565},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47943577,0.006528887,0.32313383,0.016067874,0.0004759704,0.00064748013,0.0001483581,0.0005455219,0.17301632],"genre_scores_gemma":[0.94238985,0.00069927576,0.054203715,0.00034714848,0.000029683315,0.00013188842,0.000030677536,0.000036268935,0.0021315715],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9749348,0.019067476,0.0009339244,0.00053694996,0.0037561154,0.0007707004],"domain_scores_gemma":[0.947444,0.030324465,0.0033248863,0.0027020297,0.013915185,0.002289478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02203511,0.0005097961,0.00049493427,0.0034580757,0.0013859128,0.008618077,0.00095449697,0.0007266388,0.0013593826],"category_scores_gemma":[0.05507427,0.000215815,0.00033422792,0.002083295,0.0025585906,0.0045698234,0.0037017302,0.0013398367,0.00020881798],"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":[0.00014677482,0.0006416152,0.07959671,0.0004736985,0.0001402302,0.00022158407,0.009139216,0.008498634,0.0013196251,0.15509623,0.002991638,0.7417341],"study_design_scores_gemma":[0.00015593186,0.0019187913,0.13444878,0.003279006,0.0005155991,0.00055310805,0.087106615,0.14649123,0.03444803,0.5240612,0.06662758,0.00039415093],"about_ca_topic_score_codex":0.007895435,"about_ca_topic_score_gemma":0.012850923,"teacher_disagreement_score":0.02203511,"about_ca_system_score_codex":0.0052689784,"about_ca_system_score_gemma":0.011814117,"threshold_uncertainty_score":0.11653417},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13441747,0.03719863,0.034621563,0.531663,0.0012599933,0.0006737897,0.0013514952,0.00033380976,0.25848022],"genre_scores_gemma":[0.95767164,0.010539833,0.013857297,0.006604909,0.00033576306,0.00017634542,0.000236908,0.00015073271,0.010426646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.971849,0.018148547,0.00075801037,0.0010163945,0.0041688746,0.004059127],"domain_scores_gemma":[0.9245122,0.041563943,0.0032203295,0.0019952033,0.01933669,0.009371619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026758688,0.0010816519,0.0012149967,0.004319767,0.010946359,0.018252816,0.00344374,0.0034589549,0.007352951],"category_scores_gemma":[0.05501112,0.00059039687,0.0006509707,0.008496057,0.012770851,0.0069840583,0.006514979,0.005813711,0.00045358375],"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":[0.0006883818,0.00046996254,0.057443984,0.0028395534,0.00039631544,0.0022727575,0.05660112,0.035916302,0.0012132742,0.34930804,0.18015595,0.31269437],"study_design_scores_gemma":[0.00031168264,0.000502534,0.15642679,0.005744428,0.0003724445,0.000441922,0.16270603,0.024183558,0.002117981,0.29854414,0.34819847,0.00045005442],"about_ca_topic_score_codex":0.9233403,"about_ca_topic_score_gemma":0.971621,"teacher_disagreement_score":0.13658594,"about_ca_system_score_codex":0.13658594,"about_ca_system_score_gemma":0.16166662,"threshold_uncertainty_score":0.99100494},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015887346,0.0029537329,0.00082670123,0.0088610845,0.012237741,0.00077989924,0.14626399,0.0031035508,0.8233845],"genre_scores_gemma":[0.0007934116,0.0009208635,0.0007192596,0.0011305101,0.00021218916,0.00018126823,0.021462131,0.0003248952,0.9742555],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913055,0.00005793988,0.00006123565,0.000073139774,0.00046763386,0.00020952948],"domain_scores_gemma":[0.9953746,0.00025041637,0.000081424536,0.00038148594,0.0033508237,0.000561343],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012818072,0.0022593527,0.0016592172,0.0071131964,0.0030691496,0.0053313104,0.0029620908,0.002533026,0.67242706],"category_scores_gemma":[0.005716831,0.0014788525,0.0011571192,0.011408661,0.0005834389,0.0026057367,0.0024596294,0.002801119,0.48956653],"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":[0.000014377705,0.000023926887,0.0002844521,0.000046447447,0.0000017710693,0.000020113479,0.000009101686,0.000047224665,0.00003100837,0.00018286455,0.9784266,0.020912174],"study_design_scores_gemma":[0.000022704104,0.0000076013757,0.0046778414,0.00012772575,0.0000045576276,0.00001948266,0.000073313924,0.00006123313,0.00006485858,0.0001883699,0.994736,0.00001630287],"about_ca_topic_score_codex":0.55933577,"about_ca_topic_score_gemma":0.8168832,"teacher_disagreement_score":0.67242706,"about_ca_system_score_codex":0.010959712,"about_ca_system_score_gemma":0.02659161,"threshold_uncertainty_score":0.8865188},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05669184,0.116865836,0.048944242,0.44488606,0.0023414595,0.00018076331,0.00023994582,0.0001920113,0.32965788],"genre_scores_gemma":[0.88659734,0.041652344,0.01136915,0.01290846,0.0008665929,0.00025761285,0.000072985014,0.00011412722,0.046161443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.94511455,0.03835242,0.0010703673,0.0016882631,0.009821067,0.003953391],"domain_scores_gemma":[0.9199649,0.059868973,0.002783455,0.0017095212,0.012815987,0.0028571812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03450841,0.00095305714,0.0009756409,0.00905232,0.010138873,0.031383682,0.002139913,0.0075587644,0.0049268147],"category_scores_gemma":[0.034617253,0.00081099453,0.000668187,0.013452529,0.040493757,0.012186099,0.0050420137,0.010441671,0.00063048437],"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":[0.000035940342,0.000074767864,0.0021698854,0.00046589482,0.000024914101,0.00036741278,0.062331196,0.0009639434,0.00018817392,0.8862764,0.009304915,0.03779648],"study_design_scores_gemma":[0.000035910412,0.00011241836,0.010468416,0.003873872,0.000059044374,0.0004986199,0.12373137,0.0023088264,0.00071714283,0.19476411,0.663216,0.00021436677],"about_ca_topic_score_codex":0.5962246,"about_ca_topic_score_gemma":0.55152094,"teacher_disagreement_score":0.90938514,"about_ca_system_score_codex":0.090614855,"about_ca_system_score_gemma":0.09294581,"threshold_uncertainty_score":0.81230664},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025630607,0.095673144,0.0023289986,0.58389825,0.005230127,0.000025615103,0.00029610237,0.00007706794,0.30990764],"genre_scores_gemma":[0.40204978,0.2997176,0.006074123,0.09644571,0.012724415,0.00032169928,0.00077008904,0.0005193627,0.1813771],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99392927,0.0036956177,0.00016199077,0.0004126581,0.0013116943,0.00048885867],"domain_scores_gemma":[0.9944455,0.0033065584,0.00025139403,0.0004551233,0.00058729236,0.00095417735],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00983362,0.0005583573,0.00085103716,0.0026669023,0.0066070943,0.02194027,0.0009693214,0.0066643907,0.03823724],"category_scores_gemma":[0.010310689,0.000532294,0.0004660208,0.0051331273,0.024951074,0.01881832,0.008116735,0.010123419,0.006335118],"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":[0.00002054592,0.00002738684,0.0004173739,0.00033140875,0.000014799362,0.000099190605,0.005170239,0.0001395856,0.0000890934,0.7648005,0.18955338,0.03933651],"study_design_scores_gemma":[0.000005788094,0.0000062313707,0.0004045765,0.0012022188,0.0000049048485,0.00004125972,0.0043650223,0.000051173633,0.00008449586,0.28373054,0.71009433,0.000009361857],"about_ca_topic_score_codex":0.004865429,"about_ca_topic_score_gemma":0.009069005,"teacher_disagreement_score":0.9933929,"about_ca_system_score_codex":0.014291127,"about_ca_system_score_gemma":0.016570155,"threshold_uncertainty_score":0.12791634},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35771912,0.012060142,0.1950939,0.12404424,0.0013733439,0.001811408,0.00025783113,0.00042609175,0.3072139],"genre_scores_gemma":[0.91286284,0.0046200017,0.043467477,0.0029747,0.00023197262,0.0010695396,0.000099878234,0.00013027163,0.034543294],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.951748,0.035462774,0.0011488567,0.0033875764,0.0063287355,0.0019239694],"domain_scores_gemma":[0.94768757,0.032050822,0.004675247,0.003346724,0.006979058,0.0052605886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031142524,0.00087623886,0.0009329208,0.00248484,0.009874157,0.017176861,0.002543181,0.0040166634,0.010069257],"category_scores_gemma":[0.03708566,0.0007830611,0.001161172,0.002298978,0.031011816,0.0115070855,0.011783583,0.008401386,0.0019822188],"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":[0.000089195826,0.00027680676,0.010998992,0.0015732179,0.00008348296,0.0005101905,0.45817244,0.00080883875,0.0036291527,0.42606953,0.0036174508,0.094170734],"study_design_scores_gemma":[0.00005512712,0.00046427822,0.019830052,0.0025227582,0.00010569856,0.00053924957,0.41462564,0.0018607154,0.0034407973,0.20090552,0.3554873,0.00016294217],"about_ca_topic_score_codex":0.013521027,"about_ca_topic_score_gemma":0.015986374,"teacher_disagreement_score":0.9843461,"about_ca_system_score_codex":0.015653888,"about_ca_system_score_gemma":0.041997638,"threshold_uncertainty_score":0.16469932},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63940036,0.006786391,0.0005795545,0.030265022,0.00018777861,0.00008840442,0.0020024083,0.00013002766,0.32056004],"genre_scores_gemma":[0.8960285,0.0020498629,0.00052107277,0.0011608131,0.000021584112,0.000023011735,0.00044430094,0.000035444336,0.099715404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976004,0.00022905439,0.00007137882,0.00015374759,0.0008532304,0.001092227],"domain_scores_gemma":[0.9966882,0.00034452302,0.00028694884,0.00010096126,0.0011886464,0.0013908463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010255782,0.00014114853,0.00024315795,0.0009378743,0.007020722,0.0025475759,0.000835489,0.0008831927,0.011983451],"category_scores_gemma":[0.0033487137,0.0002584572,0.0002860345,0.0033046757,0.0028432463,0.0010186465,0.002366537,0.001051455,0.0007838749],"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":[0.00080461113,0.00020953547,0.16615331,0.0010919038,0.000065254135,0.0021620963,0.08395078,0.004030781,0.0027362218,0.31007028,0.14366843,0.2850567],"study_design_scores_gemma":[0.000121833225,0.00012392791,0.45621055,0.0005475695,0.000041898227,0.00020914478,0.036747113,0.0014327376,0.0008613289,0.009291392,0.4943188,0.00009371901],"about_ca_topic_score_codex":0.991525,"about_ca_topic_score_gemma":0.99780756,"teacher_disagreement_score":0.833805,"about_ca_system_score_codex":0.16619496,"about_ca_system_score_gemma":0.13844253,"threshold_uncertainty_score":0.9670957},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004053166,0.004461537,0.0014405615,0.96954715,0.010370391,0.00002621758,0.00007609524,0.000083053135,0.009941809],"genre_scores_gemma":[0.13452782,0.013077551,0.00617812,0.7906252,0.0074324785,0.00017900139,0.00016291083,0.00034407078,0.047472853],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882796,0.0064354367,0.0003316812,0.0009849161,0.0021898132,0.0017786968],"domain_scores_gemma":[0.9591215,0.007999026,0.0030401398,0.0013035183,0.010586417,0.017949516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009421921,0.00066319184,0.0012013271,0.0008570424,0.008095387,0.0066985437,0.0015520406,0.0077090184,0.017793493],"category_scores_gemma":[0.067284405,0.0004847756,0.000746414,0.0007522588,0.010066533,0.009399047,0.0043914355,0.018398535,0.009443152],"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":[0.00006736967,0.00009239289,0.0066178907,0.00030834053,0.000054193588,0.0010644848,0.026053566,0.000063384105,0.00044942228,0.013483826,0.90383893,0.04790631],"study_design_scores_gemma":[0.00002480192,0.00009202403,0.0022815384,0.0013138948,0.00005354773,0.002876832,0.12666073,0.00019111915,0.00034177754,0.031100677,0.83491564,0.00014741132],"about_ca_topic_score_codex":0.019312259,"about_ca_topic_score_gemma":0.027268527,"teacher_disagreement_score":0.019312259,"about_ca_system_score_codex":0.0050399187,"about_ca_system_score_gemma":0.009886047,"threshold_uncertainty_score":0.05952519},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058053574,0.2098056,0.024970815,0.72808635,0.004109131,0.00069047016,0.00028292366,0.00029935603,0.02595007],"genre_scores_gemma":[0.26269612,0.49769208,0.16647437,0.05235716,0.007321685,0.0044850735,0.0010390787,0.0003036922,0.0076307203],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9177865,0.06385884,0.0036005455,0.0026070592,0.007940116,0.0042069885],"domain_scores_gemma":[0.6078269,0.2930885,0.0076835887,0.012649769,0.059883565,0.018867677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1942762,0.0016245261,0.0040399074,0.0058858604,0.0055380976,0.022868829,0.0089072995,0.008207167,0.020507492],"category_scores_gemma":[0.19028741,0.000942501,0.0022269238,0.009491239,0.014262942,0.03615897,0.010304107,0.011094445,0.0026844735],"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":[0.00036031235,0.0008226399,0.006991296,0.009629723,0.00018819724,0.00022528213,0.0046330905,0.0032644868,0.00014992178,0.23523599,0.09327324,0.64522576],"study_design_scores_gemma":[0.00023418806,0.0005699656,0.006539204,0.04435234,0.0001876225,0.00051390694,0.099507086,0.011119537,0.00038029245,0.60470265,0.23162627,0.0002669293],"about_ca_topic_score_codex":0.018945199,"about_ca_topic_score_gemma":0.029843388,"teacher_disagreement_score":0.1942762,"about_ca_system_score_codex":0.014278511,"about_ca_system_score_gemma":0.0709635,"threshold_uncertainty_score":0.9936009},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75211495,0.009027677,0.13916726,0.040020753,0.0005075219,0.0032095036,0.00039050455,0.0005863834,0.054975323],"genre_scores_gemma":[0.924734,0.0023174526,0.064732715,0.0018264578,0.000047700643,0.0010562862,0.00014985897,0.000039348328,0.0050961617],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884089,0.008167233,0.00039935435,0.00060505554,0.0017303121,0.0006891994],"domain_scores_gemma":[0.98288006,0.00883795,0.0017380391,0.0022505394,0.0019474122,0.0023458933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016666751,0.0005899258,0.0007869619,0.0007480868,0.0022537445,0.0027814514,0.001565165,0.001344811,0.0063228253],"category_scores_gemma":[0.035677917,0.00034549538,0.00071610644,0.00078355824,0.00282339,0.0031058341,0.003952194,0.002446294,0.00058556587],"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":[0.0008284509,0.0018615302,0.05552445,0.004138452,0.0003308074,0.00035174174,0.08346505,0.0072449087,0.0063539227,0.045650445,0.007518153,0.786732],"study_design_scores_gemma":[0.001578871,0.008355683,0.43929473,0.017210456,0.0014668327,0.0011926785,0.11629735,0.023348654,0.013238128,0.111009754,0.26642957,0.00057725084],"about_ca_topic_score_codex":0.044995584,"about_ca_topic_score_gemma":0.12726772,"teacher_disagreement_score":0.044995584,"about_ca_system_score_codex":0.008741677,"about_ca_system_score_gemma":0.023624716,"threshold_uncertainty_score":0.08946735},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013001786,0.0018884751,0.95976424,0.0010176945,0.00024902364,0.000413443,0.002246946,0.0038833746,0.01753506],"genre_scores_gemma":[0.29060018,0.0018820922,0.69774306,0.00025531393,0.0011018639,0.0005683264,0.002592772,0.00039207598,0.0048643043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97184396,0.0074793044,0.0022277476,0.0024529914,0.0154843,0.0005117692],"domain_scores_gemma":[0.9621223,0.020764925,0.0038329945,0.0048360876,0.0078052212,0.00063844875],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.010916188,0.0021721595,0.0037932985,0.046097446,0.0014569265,0.012164502,0.002425497,0.0016725615,0.005459386],"category_scores_gemma":[0.05257709,0.0008214183,0.0022684562,0.035490002,0.0012597704,0.0074101267,0.0049391123,0.0018695579,0.0036245205],"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":[0.000115004295,0.00049788697,0.013316219,0.0010175135,0.0010746771,0.0001308104,0.00040140864,0.021043511,0.004399554,0.036681373,0.011521354,0.9098007],"study_design_scores_gemma":[0.00012802688,0.00031523622,0.028373562,0.00038055182,0.0010879856,0.0007011541,0.0004973125,0.6486671,0.008269526,0.26387158,0.04742148,0.00028637127],"about_ca_topic_score_codex":0.0031072693,"about_ca_topic_score_gemma":0.00455972,"teacher_disagreement_score":0.9890838,"about_ca_system_score_codex":0.001928015,"about_ca_system_score_gemma":0.003908063,"threshold_uncertainty_score":0.057731032},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013093353,0.28814927,0.009387641,0.59422576,0.063953824,0.0010584664,0.0003595515,0.00012057762,0.029651545],"genre_scores_gemma":[0.3852138,0.22947538,0.06346894,0.25765666,0.031051544,0.003306733,0.00050905516,0.00036369328,0.028954184],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8204589,0.12559488,0.014802622,0.0032865484,0.032194134,0.0036630046],"domain_scores_gemma":[0.48780578,0.37340432,0.017991263,0.013512049,0.09556555,0.0117210215],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17857638,0.001172402,0.0024394998,0.00570495,0.004707827,0.018056907,0.0026186223,0.009739033,0.010022991],"category_scores_gemma":[0.38258734,0.00062772597,0.003678776,0.004399837,0.007486999,0.013473859,0.007996808,0.013318109,0.0014391554],"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":[0.0016475186,0.00047411828,0.008028033,0.023613779,0.0012532735,0.00024345404,0.013070565,0.0005703267,0.00084459403,0.089275084,0.2694755,0.59150374],"study_design_scores_gemma":[0.000604488,0.0014625014,0.01707561,0.07670161,0.0017389501,0.00050410675,0.014301412,0.0012645704,0.0025198583,0.04242455,0.8410479,0.00035457348],"about_ca_topic_score_codex":0.018004686,"about_ca_topic_score_gemma":0.037849467,"teacher_disagreement_score":0.9851192,"about_ca_system_score_codex":0.014880786,"about_ca_system_score_gemma":0.04408631,"threshold_uncertainty_score":0.9444134},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015335981,0.00039154978,0.90458447,0.0014688307,0.00071118097,0.0018108914,0.0032353825,0.0034573977,0.06900435],"genre_scores_gemma":[0.08204544,0.0003877556,0.89310324,0.0003928091,0.00011280292,0.0016777455,0.0024903866,0.00051227276,0.019277494],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98656636,0.004620989,0.0014379383,0.0034120008,0.003539219,0.00042344915],"domain_scores_gemma":[0.93949986,0.022029819,0.006898409,0.015571049,0.014739317,0.0012615967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013873548,0.0015997696,0.0012320522,0.007059128,0.0012653333,0.0069271186,0.0028536967,0.0015748783,0.016885472],"category_scores_gemma":[0.06283363,0.00056351663,0.0014185827,0.006025915,0.0017574121,0.007353974,0.005929017,0.0026083207,0.006836253],"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":[0.00035009652,0.0005333116,0.0127127,0.0016628094,0.00023908993,0.00041976542,0.005181659,0.0062934053,0.014341318,0.26077628,0.011291095,0.68619853],"study_design_scores_gemma":[0.00021556845,0.0018437781,0.014692802,0.0015831246,0.0007181987,0.0016841204,0.0058779535,0.04985878,0.057910047,0.2484351,0.6167482,0.0004324183],"about_ca_topic_score_codex":0.0023215695,"about_ca_topic_score_gemma":0.0027764142,"teacher_disagreement_score":0.016885472,"about_ca_system_score_codex":0.0016579989,"about_ca_system_score_gemma":0.003962667,"threshold_uncertainty_score":0.07337123},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02386088,0.018487837,0.71618414,0.16764982,0.006116772,0.024402598,0.0005387304,0.0009248645,0.041834395],"genre_scores_gemma":[0.5920556,0.0031021966,0.2961497,0.023631832,0.001961563,0.080189906,0.00018221869,0.0003977328,0.0023292282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.048709698,0.8487831,0.036157597,0.018740345,0.044441912,0.0031672902],"domain_scores_gemma":[0.022422848,0.8409105,0.03806238,0.07117465,0.025932975,0.0014965043],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.88119924,0.0036262276,0.007326443,0.014356058,0.013365257,0.027934652,0.012344753,0.015945483,0.0063953404],"category_scores_gemma":[0.92139727,0.0061807204,0.004692952,0.012384251,0.09624412,0.045108225,0.029899498,0.020576982,0.0011424355],"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":[0.00096168846,0.00026599324,0.01273254,0.011210867,0.001839387,0.0002861927,0.13110383,0.0011579376,0.00057811907,0.73204476,0.0082405545,0.0995781],"study_design_scores_gemma":[0.0021929073,0.001052036,0.0073560206,0.026513457,0.0011590477,0.00053727307,0.022438768,0.0093206875,0.0026999793,0.8793231,0.04663457,0.0007720937],"about_ca_topic_score_codex":0.0072228545,"about_ca_topic_score_gemma":0.0036100668,"teacher_disagreement_score":0.11880076,"about_ca_system_score_codex":0.02786605,"about_ca_system_score_gemma":0.039733518,"threshold_uncertainty_score":0.2021833},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9539906,0.00022699239,0.012350688,0.005015511,0.0001147242,0.003934534,0.000043338456,0.000089765796,0.024233803],"genre_scores_gemma":[0.9742011,0.00031698772,0.018732721,0.00063701294,0.00003110955,0.0022496032,0.00005043668,0.00003889246,0.0037421642],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95724154,0.03602541,0.00077236776,0.0007109419,0.0029851794,0.0022645027],"domain_scores_gemma":[0.9522458,0.028273687,0.0027381957,0.0017944045,0.00888409,0.0060638078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05262571,0.00075810886,0.00039069713,0.000937542,0.007409408,0.004409312,0.0020441213,0.0021482396,0.0028685823],"category_scores_gemma":[0.060078952,0.00041409166,0.00051257265,0.00040632475,0.006988666,0.001984585,0.008750511,0.0042409445,0.00032928513],"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":[0.0007937041,0.01014209,0.01008125,0.0012093267,0.000070647955,0.0011197202,0.6870671,0.002379032,0.006968067,0.010247876,0.007653749,0.26226747],"study_design_scores_gemma":[0.00077368435,0.012286165,0.017566977,0.0024551235,0.00017262044,0.00095853105,0.788912,0.006058317,0.046223395,0.013711272,0.11066458,0.00021737108],"about_ca_topic_score_codex":0.0050964733,"about_ca_topic_score_gemma":0.008369077,"teacher_disagreement_score":0.9949035,"about_ca_system_score_codex":0.0064427406,"about_ca_system_score_gemma":0.019724207,"threshold_uncertainty_score":0.27831465},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33329794,0.0121042095,0.06656579,0.049669985,0.00085407466,0.00048442653,0.0029616621,0.000345813,0.5337161],"genre_scores_gemma":[0.8333911,0.007296949,0.020801207,0.0027715513,0.00010591644,0.00025401468,0.0011559563,0.0001872242,0.13403608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99645895,0.0012802613,0.00009918282,0.00042143476,0.0011130223,0.0006271621],"domain_scores_gemma":[0.99262273,0.0020878753,0.0004765279,0.00034917693,0.0039483234,0.0005153399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036280178,0.0007188894,0.0006199689,0.0033313076,0.0071908534,0.010992084,0.001507343,0.0017833344,0.02709109],"category_scores_gemma":[0.008503054,0.00044247252,0.0008594635,0.005015131,0.0042809965,0.004330192,0.002616623,0.0025353779,0.0016250242],"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":[0.0001489397,0.00017234025,0.07227646,0.0014099597,0.00019916035,0.0012572535,0.15848401,0.0057635577,0.003286967,0.53835493,0.04898905,0.16965745],"study_design_scores_gemma":[0.000022603634,0.00008781256,0.14679524,0.0031190757,0.00023049704,0.0003445057,0.23730381,0.014489775,0.0025268341,0.0489779,0.54586136,0.00024066641],"about_ca_topic_score_codex":0.9050945,"about_ca_topic_score_gemma":0.9266991,"teacher_disagreement_score":0.9523711,"about_ca_system_score_codex":0.047628906,"about_ca_system_score_gemma":0.04698102,"threshold_uncertainty_score":0.34557354},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003338497,0.00926092,0.02103386,0.9033659,0.0022290037,0.0001563747,0.00013396743,0.00007836236,0.060403116],"genre_scores_gemma":[0.51385856,0.05144092,0.10306876,0.28977722,0.00532468,0.0049888277,0.00077131676,0.0009400084,0.029829765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8573906,0.114869975,0.0044009555,0.004391608,0.013151632,0.005795372],"domain_scores_gemma":[0.6344238,0.33455965,0.0044945395,0.007972971,0.012038955,0.0065100095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21092378,0.0016068814,0.0022947306,0.010278823,0.01669342,0.04954616,0.008350786,0.023511609,0.010770033],"category_scores_gemma":[0.17880118,0.0016908926,0.0015623724,0.013682365,0.12790869,0.07409396,0.021770542,0.041223034,0.0015579069],"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":[0.0000071449786,0.000029790002,0.00010304073,0.000117310585,0.000002755562,0.000026820502,0.00647527,0.00017167356,0.000008870234,0.9708331,0.0152817685,0.0069424864],"study_design_scores_gemma":[0.000027469556,0.00002047199,0.00021333648,0.0019720495,0.0000049377836,0.000039084094,0.024603048,0.0006554121,0.00013049568,0.82035244,0.15194057,0.0000407841],"about_ca_topic_score_codex":0.03401693,"about_ca_topic_score_gemma":0.021985458,"teacher_disagreement_score":0.21092378,"about_ca_system_score_codex":0.041572005,"about_ca_system_score_gemma":0.07119708,"threshold_uncertainty_score":0.97307146},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11905708,0.12778299,0.1389456,0.3180472,0.0054542995,0.005183393,0.00093083776,0.0003815254,0.284217],"genre_scores_gemma":[0.8945893,0.023960501,0.062569864,0.013037999,0.0012376664,0.0024496014,0.0002093139,0.00011484768,0.0018309036],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.20695063,0.63660675,0.028469441,0.0100454455,0.113349795,0.0045780637],"domain_scores_gemma":[0.047679532,0.84913665,0.032972895,0.023458142,0.04469252,0.0020602087],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5486119,0.0019866063,0.0032790068,0.015160202,0.004930666,0.023244556,0.004394612,0.0068866275,0.008151031],"category_scores_gemma":[0.8136303,0.0012866546,0.0024427162,0.014517742,0.022180505,0.025614142,0.018286804,0.009095642,0.0009189603],"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":[0.00044803304,0.00041060025,0.043142743,0.014543055,0.0017551577,0.00022560013,0.01012744,0.005406774,0.0006142105,0.44987887,0.010908556,0.462539],"study_design_scores_gemma":[0.00040476857,0.0030918142,0.081441596,0.0845484,0.0029354284,0.0005632733,0.0378311,0.015356779,0.0048855245,0.643161,0.12544242,0.00033785572],"about_ca_topic_score_codex":0.00488868,"about_ca_topic_score_gemma":0.0051830187,"teacher_disagreement_score":0.45138812,"about_ca_system_score_codex":0.031195842,"about_ca_system_score_gemma":0.036840495,"threshold_uncertainty_score":0.55664194},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00996335,0.009513581,0.01175787,0.00844804,0.0005010692,0.00015434643,0.00006171017,0.00010971283,0.9594903],"genre_scores_gemma":[0.21274525,0.02253359,0.016213056,0.00319068,0.0003493249,0.00039910764,0.00017110727,0.00019997696,0.7441978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99781114,0.0010320677,0.000077239754,0.00010664272,0.0007012758,0.0002716149],"domain_scores_gemma":[0.995378,0.0031924574,0.00018463394,0.0001828993,0.00081718445,0.000244842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031192328,0.00044633046,0.00033463986,0.002216432,0.004717608,0.0073092687,0.0013649558,0.0020069527,0.010649515],"category_scores_gemma":[0.008792372,0.00024041653,0.00016612984,0.0030429503,0.004380219,0.0046549155,0.0025535647,0.0022682738,0.001261482],"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":[0.000009959002,0.00015525849,0.0008687797,0.00021952369,0.000002580267,0.00023318277,0.0100469105,0.0015398351,0.0001911465,0.63969916,0.08953317,0.25750053],"study_design_scores_gemma":[0.000005678594,0.000057103014,0.002014119,0.0013792367,0.000007492521,0.00017692817,0.019223744,0.0014131871,0.000995065,0.23027372,0.74442863,0.000025174359],"about_ca_topic_score_codex":0.025813831,"about_ca_topic_score_gemma":0.07583784,"teacher_disagreement_score":0.025813831,"about_ca_system_score_codex":0.0069730906,"about_ca_system_score_gemma":0.012960061,"threshold_uncertainty_score":0.05132711},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03091358,0.06475729,0.12400159,0.21587814,0.0012103841,0.00050700334,0.00014325432,0.00031215465,0.56227654],"genre_scores_gemma":[0.8209678,0.040471625,0.08984256,0.014954691,0.0014324725,0.0007803102,0.0001812355,0.00017884736,0.03119041],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.96924454,0.023225723,0.0010361843,0.0012819687,0.0039292397,0.0012823343],"domain_scores_gemma":[0.9519083,0.034806956,0.0033673246,0.002812011,0.004505866,0.002599532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01764681,0.0011302303,0.0013070556,0.0051465402,0.0035987457,0.019346686,0.001715298,0.003951057,0.008110185],"category_scores_gemma":[0.030702483,0.000613987,0.0009630839,0.0054364717,0.032837667,0.021564784,0.009571109,0.0073403693,0.0012675239],"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":[0.000028215067,0.00012785122,0.00178393,0.00049974734,0.000029115372,0.00005840307,0.0097957365,0.0014871338,0.00006406277,0.9278545,0.005838684,0.05243271],"study_design_scores_gemma":[0.000022062426,0.00008232683,0.001576,0.000846352,0.000009892583,0.00011811707,0.012213772,0.00374073,0.00009638843,0.8866925,0.09456801,0.000033855664],"about_ca_topic_score_codex":0.011786693,"about_ca_topic_score_gemma":0.0075937854,"teacher_disagreement_score":0.019346686,"about_ca_system_score_codex":0.008657624,"about_ca_system_score_gemma":0.015873434,"threshold_uncertainty_score":0.09332633},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14221586,0.069395564,0.01953491,0.24943326,0.0030784933,0.00031712092,0.0014847348,0.00049221335,0.5140479],"genre_scores_gemma":[0.68156666,0.018971073,0.015753096,0.008063067,0.00058854953,0.00017452445,0.00041373866,0.00033450345,0.2741347],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97700787,0.00539255,0.00066468393,0.001496442,0.011855162,0.0035832655],"domain_scores_gemma":[0.96128285,0.008675537,0.0012237538,0.0013532053,0.02238577,0.005078824],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016810006,0.0005607233,0.00082485937,0.0034165485,0.010664468,0.013486566,0.0016718227,0.0030394546,0.011008103],"category_scores_gemma":[0.033571795,0.0005429209,0.0005428147,0.0061033703,0.006410581,0.0031869432,0.0036303077,0.0044136886,0.0011056155],"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":[0.0003355231,0.00012857775,0.016828429,0.0004967554,0.000065482345,0.0006543219,0.00909583,0.00246902,0.0011500552,0.3964904,0.14232214,0.42996344],"study_design_scores_gemma":[0.000101027574,0.00010446283,0.07100943,0.0011802133,0.000044668755,0.00025777737,0.0077412315,0.0027649028,0.00088936154,0.022904094,0.8928469,0.000155913],"about_ca_topic_score_codex":0.9811063,"about_ca_topic_score_gemma":0.9890983,"teacher_disagreement_score":0.98319,"about_ca_system_score_codex":0.10591793,"about_ca_system_score_gemma":0.20288347,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010368889,0.11617434,0.0015511775,0.05651298,0.002463103,0.00020929176,0.011801272,0.00047583078,0.80044305],"genre_scores_gemma":[0.024041856,0.028928876,0.0009642917,0.00072531373,0.00013995629,0.00004871154,0.0012555157,0.00016557935,0.94372994],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992567,0.000042372885,0.000032000047,0.00007839155,0.0003799978,0.00021049293],"domain_scores_gemma":[0.99920195,0.000057731937,0.000045164612,0.000031248826,0.00033848916,0.00032545478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059824757,0.0009199095,0.00047407727,0.0017436094,0.00792268,0.006948104,0.000994854,0.0019331364,0.10945807],"category_scores_gemma":[0.0010137251,0.0008972214,0.00032684745,0.010324814,0.0019336694,0.0024481963,0.0013871944,0.0015442166,0.012122168],"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":[0.000024788113,0.000013128959,0.0012175234,0.00032578653,0.000005287099,0.00019591974,0.0021979029,0.00038324922,0.00017223172,0.03841571,0.87480307,0.08224539],"study_design_scores_gemma":[0.0000044048847,0.000005261018,0.0049749576,0.00016406928,0.0000040824402,0.00004012539,0.0016045666,0.000085258485,0.000052931387,0.0013071379,0.99174654,0.000010652082],"about_ca_topic_score_codex":0.9801021,"about_ca_topic_score_gemma":0.99760914,"teacher_disagreement_score":0.10945807,"about_ca_system_score_codex":0.085385196,"about_ca_system_score_gemma":0.1223405,"threshold_uncertainty_score":0.6195159},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008613336,0.03408322,0.05375697,0.82292455,0.04288379,0.006879828,0.0008974733,0.00038570887,0.029575111],"genre_scores_gemma":[0.16578771,0.03720759,0.2261146,0.35316554,0.012621672,0.03635491,0.00076605496,0.0015448114,0.16643716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.914032,0.06751527,0.0025763705,0.0021709816,0.011371155,0.0023341966],"domain_scores_gemma":[0.79180473,0.11288907,0.0048946473,0.01040617,0.047218055,0.03278739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10808114,0.00082208,0.0013145837,0.0021326758,0.013174653,0.009294742,0.0025076629,0.005351339,0.009315842],"category_scores_gemma":[0.15734804,0.0014751429,0.0009349986,0.0015243095,0.012241846,0.00489883,0.0187602,0.014194248,0.0041097323],"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":[0.00019540804,0.00033803305,0.0018020909,0.003991774,0.000032934662,0.001059634,0.1251163,0.00026378944,0.0028993462,0.035281215,0.5897654,0.239254],"study_design_scores_gemma":[0.000069619615,0.0001798246,0.0026279595,0.00671353,0.000017156994,0.00091209746,0.077254765,0.00021392305,0.00096983905,0.0296291,0.88130754,0.00010461672],"about_ca_topic_score_codex":0.011970457,"about_ca_topic_score_gemma":0.043448955,"teacher_disagreement_score":0.10808114,"about_ca_system_score_codex":0.014519645,"about_ca_system_score_gemma":0.06452924,"threshold_uncertainty_score":0.57159454},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031612557,0.09781751,0.034274347,0.39593956,0.022024138,0.0010917857,0.0011569123,0.00122318,0.44331142],"genre_scores_gemma":[0.1916764,0.21201213,0.09611835,0.16002972,0.008250928,0.0019661414,0.0020183376,0.001803102,0.3261248],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95644814,0.008623948,0.0026312922,0.0024858604,0.02510009,0.004710658],"domain_scores_gemma":[0.8978099,0.016554235,0.0015619698,0.002231088,0.06984154,0.01200126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037137415,0.00074630807,0.0009629128,0.0069311378,0.014650089,0.01480928,0.0034526098,0.0055371756,0.018710526],"category_scores_gemma":[0.06258437,0.000971051,0.00088829064,0.011971973,0.014562892,0.0049253376,0.0072551183,0.009618955,0.004330404],"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":[0.00003543634,0.00007723329,0.001150183,0.0009826485,0.000010429259,0.00024358828,0.0055347374,0.00045331012,0.00021345845,0.1316387,0.6329164,0.22674388],"study_design_scores_gemma":[0.0000081031385,0.000012605193,0.0027135503,0.00148293,0.0000040551276,0.000117449454,0.0016566307,0.00021194338,0.00009507638,0.010334178,0.983316,0.00004740461],"about_ca_topic_score_codex":0.9271729,"about_ca_topic_score_gemma":0.9509911,"teacher_disagreement_score":0.8155248,"about_ca_system_score_codex":0.1844752,"about_ca_system_score_gemma":0.38110316,"threshold_uncertainty_score":0.94589317},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93938315,0.0024451762,0.016954744,0.0052789976,0.00015394474,0.0018548334,0.00018208033,0.000105604166,0.033641424],"genre_scores_gemma":[0.98578554,0.0008226595,0.010021237,0.00082046806,0.00004110078,0.0015474475,0.00004415437,0.000046794557,0.0008704994],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.49653,0.45388538,0.012328223,0.0021911939,0.027784174,0.0072809565],"domain_scores_gemma":[0.71103644,0.23762831,0.012717487,0.005414373,0.026470207,0.0067332275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24872448,0.00082408823,0.00092461193,0.0052136425,0.005812267,0.014171267,0.0018455434,0.0029262952,0.003100926],"category_scores_gemma":[0.23451796,0.00089532684,0.0008747753,0.003260448,0.00772458,0.00580579,0.013520956,0.0024769786,0.00044510426],"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":[0.0014709809,0.0014734183,0.07469971,0.0033915131,0.0002485272,0.0011911968,0.6824385,0.0012926424,0.004692133,0.0112942355,0.003934787,0.21387222],"study_design_scores_gemma":[0.00028669686,0.0048532733,0.047097337,0.0045322767,0.00024029789,0.0012266657,0.8750736,0.0019061981,0.0077660927,0.007963924,0.04882892,0.0002246407],"about_ca_topic_score_codex":0.0029131547,"about_ca_topic_score_gemma":0.0038088756,"teacher_disagreement_score":0.24872448,"about_ca_system_score_codex":0.009827999,"about_ca_system_score_gemma":0.013121401,"threshold_uncertainty_score":0.92645645},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72386694,0.0016274714,0.08682124,0.005131932,0.00028684636,0.005978178,0.06750672,0.0026346426,0.10614597],"genre_scores_gemma":[0.8739078,0.00053102453,0.09281639,0.0002494265,0.000035365945,0.0031527188,0.021488963,0.00018032666,0.0076380065],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99043626,0.0033500702,0.00032391294,0.0004489154,0.004093763,0.0013470155],"domain_scores_gemma":[0.9814355,0.0058609685,0.0010021954,0.0013365382,0.009379871,0.0009850326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01758802,0.0006740331,0.00093783584,0.005352504,0.0016637477,0.004152661,0.0022107647,0.00085592427,0.009387112],"category_scores_gemma":[0.034027454,0.00037393265,0.0012278372,0.0071566976,0.0007152079,0.0020164119,0.0054772245,0.0011186076,0.0005136183],"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":[0.0019263339,0.0010903603,0.25195497,0.003785515,0.0005956686,0.00046404795,0.013596563,0.09340795,0.0012395282,0.08077712,0.09071706,0.4604449],"study_design_scores_gemma":[0.0004621218,0.0017776915,0.46487418,0.0024306667,0.00074323267,0.00022791022,0.093247436,0.24913411,0.005358877,0.05926577,0.12221049,0.00026748187],"about_ca_topic_score_codex":0.46516788,"about_ca_topic_score_gemma":0.4287274,"teacher_disagreement_score":0.46516788,"about_ca_system_score_codex":0.02346693,"about_ca_system_score_gemma":0.034367915,"threshold_uncertainty_score":0.9249206},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7136894,0.0026003134,0.11806984,0.024369515,0.0010325799,0.0013380762,0.0018651659,0.00061761565,0.1364174],"genre_scores_gemma":[0.9863906,0.0001650194,0.010055445,0.00047239126,0.000034378452,0.0001235468,0.00018647523,0.0000519818,0.0025201673],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8152125,0.075421154,0.016423326,0.008219205,0.07790162,0.0068223346],"domain_scores_gemma":[0.6927815,0.097908534,0.026416222,0.025101047,0.15299754,0.0047951424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12328953,0.00044841543,0.00094330194,0.003748409,0.004782761,0.0075764195,0.00259915,0.0008480359,0.0023352248],"category_scores_gemma":[0.3083293,0.00038817062,0.0006289971,0.0063656517,0.0043256674,0.0026902363,0.0041634873,0.0019385307,0.000420663],"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":[0.0011113946,0.00021107566,0.36582235,0.0009786687,0.0006297818,0.0006215069,0.0655159,0.007815163,0.0038166156,0.11510784,0.021349391,0.41702035],"study_design_scores_gemma":[0.00014705675,0.0006796202,0.704958,0.002358752,0.0004371322,0.0006870932,0.07074696,0.024711443,0.015773136,0.09233153,0.08655247,0.0006168257],"about_ca_topic_score_codex":0.32290068,"about_ca_topic_score_gemma":0.38125315,"teacher_disagreement_score":0.67709935,"about_ca_system_score_codex":0.020396866,"about_ca_system_score_gemma":0.03485588,"threshold_uncertainty_score":0.65202516},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591,0.0007761514,0.0050811023,0.0016954388,0.00004049304,0.0011877896,0.00046054178,0.000060832084,0.031597715],"genre_scores_gemma":[0.97914153,0.00035747304,0.004954772,0.00016433444,0.000008848045,0.0008344633,0.00017463074,0.000014582979,0.014349288],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96920824,0.017754795,0.0011435838,0.0014190088,0.008408504,0.0020657587],"domain_scores_gemma":[0.87072915,0.07102254,0.006207974,0.0025666952,0.0456287,0.0038449685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.036157254,0.00045281198,0.0006195029,0.0027009195,0.0047694203,0.005552231,0.0011893592,0.0008834494,0.006427332],"category_scores_gemma":[0.09061635,0.00030878934,0.00049458817,0.003052826,0.0041927006,0.0022604375,0.0029930298,0.001045724,0.00037707225],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017297594,0.0012472024,0.19951442,0.0021007198,0.00016776478,0.00049801485,0.475622,0.0022298202,0.009426874,0.020268396,0.008239167,0.27895585],"study_design_scores_gemma":[0.0001758105,0.0021018477,0.58563143,0.0014229125,0.00021529786,0.00017121177,0.33292595,0.003792212,0.008640052,0.0038482095,0.0609113,0.00016378232],"about_ca_topic_score_codex":0.4134919,"about_ca_topic_score_gemma":0.47069618,"teacher_disagreement_score":0.9692913,"about_ca_system_score_codex":0.030708699,"about_ca_system_score_gemma":0.040615737,"threshold_uncertainty_score":0.82217026},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012077361,0.006278372,0.0024532387,0.91061836,0.011821573,0.00019421092,0.0007424233,0.00021182404,0.055602767],"genre_scores_gemma":[0.3687463,0.015829183,0.019576808,0.42410696,0.0070761405,0.00036784777,0.0021344316,0.00040114936,0.16176116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99124193,0.002060136,0.00026738166,0.00031584018,0.0030763897,0.0030382732],"domain_scores_gemma":[0.9740458,0.0021453972,0.0008107025,0.0003975264,0.008254195,0.01434637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010904924,0.00045703922,0.00059615803,0.00079686777,0.0043320884,0.015767688,0.0012762819,0.0065144147,0.029529696],"category_scores_gemma":[0.02118711,0.0003036472,0.0008732974,0.0013315185,0.001916095,0.005773621,0.0042310753,0.009817528,0.0064251493],"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":[0.0002905711,0.0003610981,0.0103618475,0.0006373766,0.00006754675,0.00056316,0.0018238373,0.0007094678,0.00081963645,0.05076779,0.75168544,0.18191224],"study_design_scores_gemma":[0.000059447026,0.00024739144,0.016746191,0.0013005412,0.000035850855,0.00024524087,0.01125097,0.0007177991,0.0010087674,0.022584565,0.9456909,0.000112336755],"about_ca_topic_score_codex":0.086558916,"about_ca_topic_score_gemma":0.27724344,"teacher_disagreement_score":0.9829802,"about_ca_system_score_codex":0.017019786,"about_ca_system_score_gemma":0.0708625,"threshold_uncertainty_score":0.17211014},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11043031,0.013945504,0.5090948,0.062905274,0.0008131323,0.0012866609,0.0004690691,0.0009173051,0.30013803],"genre_scores_gemma":[0.72772115,0.0039534657,0.23401421,0.0028710044,0.0004544571,0.0011282887,0.00045790308,0.00033716357,0.029062213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9492041,0.023681661,0.0030597418,0.005760294,0.016057016,0.002237159],"domain_scores_gemma":[0.93322515,0.037300576,0.0047634114,0.00795231,0.0142211905,0.0025373143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030064046,0.0010345258,0.0011834528,0.005585604,0.0038241493,0.01776692,0.0022350661,0.0035649287,0.009996765],"category_scores_gemma":[0.05901311,0.00072276883,0.0013923204,0.006346889,0.013327913,0.025190733,0.009049489,0.0055410503,0.0017008042],"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":[0.000106877735,0.0001808368,0.009720968,0.00070881133,0.000091800204,0.0003018179,0.019573126,0.0016342057,0.0011167099,0.7391735,0.006404285,0.22098711],"study_design_scores_gemma":[0.00010348822,0.00033062804,0.023122707,0.0018695885,0.00015245302,0.0009034955,0.0263951,0.0106665725,0.002846871,0.7092796,0.2241606,0.0001689203],"about_ca_topic_score_codex":0.015180477,"about_ca_topic_score_gemma":0.012004131,"teacher_disagreement_score":0.030064046,"about_ca_system_score_codex":0.009464062,"about_ca_system_score_gemma":0.008797879,"threshold_uncertainty_score":0.15899575},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026782472,0.025353102,0.32994083,0.32264638,0.0016925266,0.00508458,0.001983879,0.0011088465,0.28540745],"genre_scores_gemma":[0.38579515,0.013175715,0.57181597,0.012164786,0.00046233545,0.0031686006,0.001672403,0.00023881588,0.011506223],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81814307,0.08223532,0.01352657,0.0073669357,0.06298525,0.015742859],"domain_scores_gemma":[0.76301956,0.05063183,0.011257205,0.009783087,0.14511795,0.020190392],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20331666,0.002226947,0.0022480076,0.02783872,0.022614345,0.03784795,0.013991675,0.006216934,0.0025656256],"category_scores_gemma":[0.14966126,0.0015602955,0.0022423621,0.038281485,0.035826843,0.012305868,0.020026634,0.011723897,0.0005715322],"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":true,"study_design_scores_codex":[0.00001849383,0.00008201882,0.0059438413,0.00074931065,0.000053333926,0.00013693531,0.013121128,0.0070219417,0.00026463755,0.85244626,0.029365461,0.09079661],"study_design_scores_gemma":[0.00005720963,0.00009026048,0.034031235,0.006673797,0.0001381401,0.0001420266,0.04094446,0.017068034,0.0007412219,0.4828537,0.4168234,0.00043648924],"about_ca_topic_score_codex":0.95824873,"about_ca_topic_score_gemma":0.9719866,"teacher_disagreement_score":0.7966833,"about_ca_system_score_codex":0.33708423,"about_ca_system_score_gemma":0.5652824,"threshold_uncertainty_score":0.9824524},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.697027,0.008069423,0.0018070271,0.022295088,0.00015676885,0.00083369715,0.00085247523,0.00003284421,0.26892555],"genre_scores_gemma":[0.98427975,0.0065386784,0.0018431612,0.0007022381,0.000024621519,0.0002242297,0.00023166368,0.000024636221,0.006130956],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9758221,0.007800392,0.00065997854,0.0007973147,0.010425983,0.0044943644],"domain_scores_gemma":[0.972203,0.012036359,0.0015935141,0.0006438581,0.011030468,0.00249271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017379401,0.0007658311,0.0007006029,0.012217882,0.028583229,0.012599652,0.003939705,0.0014522446,0.0018789191],"category_scores_gemma":[0.028699772,0.00047320637,0.0007023886,0.029469954,0.016897248,0.003526073,0.006468311,0.0032128722,0.00013244829],"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":true,"study_design_scores_codex":[0.0000348541,0.00010299016,0.05016263,0.0005111496,0.000061589795,0.00094201026,0.7738616,0.0011759928,0.00037672376,0.09143415,0.011048584,0.070287734],"study_design_scores_gemma":[0.0000047840854,0.000029757874,0.10783009,0.00071134866,0.000044116146,0.000102306796,0.78038585,0.00095480675,0.00019971778,0.002299426,0.10733662,0.00010122797],"about_ca_topic_score_codex":0.9871852,"about_ca_topic_score_gemma":0.9912224,"teacher_disagreement_score":0.759631,"about_ca_system_score_codex":0.240369,"about_ca_system_score_gemma":0.2786176,"threshold_uncertainty_score":0.8810643},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48570842,0.0030093098,0.012161646,0.4293215,0.002026107,0.002518917,0.00018282255,0.00023568433,0.06483557],"genre_scores_gemma":[0.9597897,0.00077516667,0.0063891425,0.021386022,0.00026687604,0.0013229914,0.000060320686,0.00013490857,0.009874773],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7863214,0.17167863,0.002807359,0.004615096,0.01223777,0.022339728],"domain_scores_gemma":[0.7746875,0.15753108,0.0047336523,0.008273578,0.027251696,0.027522437],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19265522,0.0009200751,0.0011607584,0.0023395568,0.052675083,0.021407701,0.0076201605,0.01637576,0.0042593107],"category_scores_gemma":[0.1647966,0.0012177634,0.0011365213,0.003021481,0.03201214,0.009827884,0.029296238,0.022694586,0.00044809323],"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":[0.00033592203,0.004210659,0.0047796946,0.00057180144,0.0000560242,0.004121655,0.73516834,0.0012961247,0.0015588845,0.09649716,0.05200438,0.099399365],"study_design_scores_gemma":[0.00019779672,0.00072087534,0.00474966,0.0008144151,0.000039275757,0.0005976089,0.72823125,0.0014259889,0.0028592765,0.01685295,0.24334331,0.00016764615],"about_ca_topic_score_codex":0.07198215,"about_ca_topic_score_gemma":0.12115761,"teacher_disagreement_score":0.92801785,"about_ca_system_score_codex":0.054893512,"about_ca_system_score_gemma":0.08605649,"threshold_uncertainty_score":0.99559987},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44291738,0.010095514,0.021142123,0.059988793,0.00095646275,0.0032378514,0.12586622,0.0025547214,0.33324084],"genre_scores_gemma":[0.81724524,0.0033162108,0.01841897,0.0019062675,0.00012615969,0.0009644237,0.03427946,0.00014229688,0.12360098],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99256414,0.00038753345,0.00041872635,0.0004035723,0.005007469,0.0012185882],"domain_scores_gemma":[0.9715099,0.0009536131,0.0026527564,0.00056063116,0.020934738,0.0033883692],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004788877,0.0003003717,0.00025122607,0.0028278574,0.0034396106,0.003064161,0.0015652127,0.000582549,0.0045665363],"category_scores_gemma":[0.01272599,0.00033301927,0.00044949236,0.0052564745,0.0012650356,0.00080425106,0.0017320119,0.000728538,0.0009158262],"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":[0.000605837,0.00018653413,0.1816176,0.0018781439,0.00013931858,0.0002936992,0.0076292655,0.007899007,0.003654243,0.052711155,0.37331554,0.37006956],"study_design_scores_gemma":[0.000075134514,0.0000928802,0.584128,0.00024845081,0.000041536616,0.000049604463,0.0017753702,0.0030443445,0.0010682461,0.0012051553,0.4081802,0.00009101158],"about_ca_topic_score_codex":0.98758984,"about_ca_topic_score_gemma":0.9920724,"teacher_disagreement_score":0.9952111,"about_ca_system_score_codex":0.18392631,"about_ca_system_score_gemma":0.2873385,"threshold_uncertainty_score":0.9465298},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021787821,0.12839459,0.18000843,0.6361864,0.030844873,0.006406806,0.0024529507,0.00075141253,0.0127757685],"genre_scores_gemma":[0.06295165,0.12188242,0.65266204,0.12174403,0.007889637,0.027946528,0.0019200032,0.00072161044,0.0022819855],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3257355,0.5489312,0.065482445,0.013193822,0.04198378,0.004673313],"domain_scores_gemma":[0.162827,0.6816831,0.03109991,0.036741458,0.08281288,0.0048356364],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.62638867,0.0053079966,0.016190244,0.037320014,0.0077421037,0.05294964,0.013841684,0.025282864,0.015997088],"category_scores_gemma":[0.818008,0.005359637,0.011547042,0.021668885,0.022681622,0.072141595,0.022764655,0.027489146,0.007548927],"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":[0.00064992136,0.0003291027,0.0022155722,0.14572506,0.005318697,0.0005051232,0.033596307,0.004581968,0.00089701207,0.34666583,0.09388918,0.36562616],"study_design_scores_gemma":[0.0005178578,0.00026698483,0.0008355418,0.24643417,0.0019783915,0.00017910644,0.023271782,0.0022877138,0.001219287,0.5308438,0.19166608,0.0004992596],"about_ca_topic_score_codex":0.00921943,"about_ca_topic_score_gemma":0.007655337,"teacher_disagreement_score":0.37361133,"about_ca_system_score_codex":0.033078495,"about_ca_system_score_gemma":0.08183084,"threshold_uncertainty_score":0.46072936},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11795196,0.001333387,0.7143464,0.012162019,0.0012489058,0.0043812445,0.00086441805,0.0032751884,0.14443642],"genre_scores_gemma":[0.4421252,0.00078372064,0.53455746,0.00088543765,0.00017875784,0.0020894813,0.0005390956,0.0005269669,0.0183139],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9470792,0.034717854,0.0021369294,0.0011849122,0.013796013,0.0010850608],"domain_scores_gemma":[0.9183102,0.05822788,0.0016755941,0.004563067,0.016496817,0.0007264358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042342328,0.0011382592,0.00066137215,0.0031166123,0.0031323584,0.0070931935,0.0018009765,0.0032030435,0.0074545587],"category_scores_gemma":[0.06550897,0.0005285867,0.0015615618,0.003074117,0.004117515,0.002573141,0.002838601,0.0029075297,0.0019923854],"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":[0.0018772989,0.0019013888,0.015164779,0.004092549,0.00033221729,0.0071164756,0.07304845,0.017464258,0.029823063,0.28223673,0.039336357,0.52760637],"study_design_scores_gemma":[0.0007605541,0.002592526,0.02890115,0.0049843853,0.00040804208,0.005737545,0.020708298,0.11624743,0.12999615,0.084279805,0.60478455,0.0005995114],"about_ca_topic_score_codex":0.014149839,"about_ca_topic_score_gemma":0.008246593,"teacher_disagreement_score":0.042342328,"about_ca_system_score_codex":0.0049622282,"about_ca_system_score_gemma":0.004386368,"threshold_uncertainty_score":0.22393024},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017462492,0.47014505,0.0056030215,0.42694086,0.059332337,0.0007163158,0.0028290746,0.00012969115,0.032557443],"genre_scores_gemma":[0.07609593,0.6343642,0.019329067,0.18442273,0.056946386,0.0018144883,0.0041875998,0.00033879935,0.022500882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9403839,0.027516171,0.010677845,0.0026159126,0.017765708,0.0010404747],"domain_scores_gemma":[0.590124,0.29187578,0.020764409,0.014509752,0.07582689,0.006899109],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06594802,0.00089027465,0.0021351553,0.005380652,0.0012767573,0.0076646744,0.0034399163,0.006004597,0.04272334],"category_scores_gemma":[0.36640164,0.0007189079,0.002607098,0.0045636394,0.002653726,0.008535028,0.0040348954,0.008195864,0.009967055],"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":[0.001901192,0.00014524008,0.0018807019,0.0814865,0.0016044301,0.0002048649,0.00021453628,0.0007086443,0.000871679,0.02303603,0.20133206,0.68661416],"study_design_scores_gemma":[0.0005863534,0.000634333,0.011094583,0.3098743,0.0044099395,0.0005173744,0.00096966035,0.000982449,0.002348218,0.06586914,0.60254437,0.00016919267],"about_ca_topic_score_codex":0.0044684396,"about_ca_topic_score_gemma":0.009498885,"teacher_disagreement_score":0.934052,"about_ca_system_score_codex":0.0097253015,"about_ca_system_score_gemma":0.015578724,"threshold_uncertainty_score":0.34877062},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06160971,0.003040971,0.54112107,0.038520265,0.0003828779,0.004208102,0.0001380809,0.000261606,0.3507173],"genre_scores_gemma":[0.8048489,0.0012188772,0.18100488,0.0019932066,0.00010297127,0.0039077415,0.0000736434,0.00008009017,0.006769668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9105441,0.07647929,0.0019476957,0.0023767403,0.006712957,0.0019391166],"domain_scores_gemma":[0.9268636,0.05960801,0.0030345314,0.0035680716,0.0048672087,0.0020585028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0533634,0.00091277505,0.0007736926,0.006291434,0.0057310755,0.012103116,0.0033206441,0.0030529655,0.003704246],"category_scores_gemma":[0.048755493,0.00058902544,0.0009788657,0.004693398,0.031904407,0.011117504,0.0048924163,0.0032878611,0.00049764186],"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":[0.000023222092,0.00023073932,0.002131037,0.0004128356,0.000022866558,0.00014748258,0.043179784,0.0020854895,0.00012046849,0.9137584,0.001999212,0.03588855],"study_design_scores_gemma":[0.00015968022,0.00025990885,0.0021035962,0.0021936223,0.000035932964,0.0003303989,0.041295793,0.013251762,0.0005674641,0.8428806,0.09686214,0.000059141268],"about_ca_topic_score_codex":0.004578984,"about_ca_topic_score_gemma":0.004049237,"teacher_disagreement_score":0.0533634,"about_ca_system_score_codex":0.022500368,"about_ca_system_score_gemma":0.020012842,"threshold_uncertainty_score":0.282216},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0272315,0.03406514,0.7620467,0.077840246,0.0037032655,0.02844498,0.0009195732,0.0004154632,0.06533309],"genre_scores_gemma":[0.31792986,0.0049280683,0.5692228,0.014154855,0.0008822,0.09073061,0.00028530144,0.00020733719,0.0016590147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.18490471,0.71555376,0.03952654,0.010132737,0.047357958,0.0025242146],"domain_scores_gemma":[0.17944977,0.72143334,0.024261577,0.030367037,0.04311664,0.0013716802],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.645545,0.0028261906,0.003369095,0.011756118,0.00555551,0.020634498,0.009372035,0.00874722,0.005668481],"category_scores_gemma":[0.7772201,0.002506965,0.00428061,0.011697194,0.034295566,0.020432614,0.010273624,0.012812954,0.000777072],"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":[0.00050330395,0.00055581925,0.0036762592,0.012542201,0.00078415155,0.00007580528,0.013342523,0.003994418,0.00041338356,0.8489612,0.00516361,0.10998739],"study_design_scores_gemma":[0.0011682892,0.0010379927,0.003923003,0.020710748,0.0006361548,0.00013035537,0.01007073,0.012108954,0.0025541617,0.9098287,0.037592027,0.00023892369],"about_ca_topic_score_codex":0.0053426353,"about_ca_topic_score_gemma":0.004413544,"teacher_disagreement_score":0.354455,"about_ca_system_score_codex":0.023887606,"about_ca_system_score_gemma":0.025782386,"threshold_uncertainty_score":0.43710613},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877337,0.00022812192,0.0022598193,0.0007064317,0.000031675172,0.00019739708,0.00006252734,0.000015096189,0.008765205],"genre_scores_gemma":[0.99828523,0.00005681822,0.0010634013,0.00009975199,0.000011070127,0.00013690247,0.00002627923,0.000010673527,0.00030973819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9271256,0.059526138,0.0027241586,0.0020237355,0.0050173993,0.0035830147],"domain_scores_gemma":[0.6954092,0.23293298,0.030901972,0.009510519,0.015671892,0.01557355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06355909,0.00024284102,0.0004775615,0.0010775314,0.0015100793,0.00537579,0.0006518945,0.00077082665,0.005932205],"category_scores_gemma":[0.1778159,0.00023371117,0.0003843049,0.0012128911,0.0022580826,0.002224898,0.0032890036,0.0008172519,0.00064454135],"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":[0.0068700593,0.0021980624,0.76518005,0.00075804844,0.0002946296,0.00045320383,0.027190316,0.0011831999,0.0036262448,0.008308164,0.0029119293,0.18102609],"study_design_scores_gemma":[0.00075683,0.0031605759,0.8913553,0.0012876249,0.00029946724,0.00032053288,0.072200164,0.0038899132,0.0055521727,0.008218035,0.012810316,0.00014902299],"about_ca_topic_score_codex":0.0015950971,"about_ca_topic_score_gemma":0.002829279,"teacher_disagreement_score":0.06355909,"about_ca_system_score_codex":0.0022796784,"about_ca_system_score_gemma":0.004623576,"threshold_uncertainty_score":0.33613664},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807966,0.0025598758,0.0042316634,0.003216593,0.00009307466,0.00014268844,0.00004131558,0.000027801845,0.008890506],"genre_scores_gemma":[0.9968502,0.00058644585,0.001597352,0.00039924457,0.00003063066,0.00013093652,0.00003221087,0.0000140850725,0.0003588552],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8942397,0.08140605,0.0066054724,0.0029222625,0.011678676,0.0031478177],"domain_scores_gemma":[0.6568459,0.23765358,0.053669665,0.01033164,0.03338679,0.008112387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.088899545,0.000310519,0.000659669,0.0041816323,0.0016823787,0.006900586,0.0009411572,0.0015130565,0.0012370009],"category_scores_gemma":[0.30771148,0.00037906753,0.0005462221,0.0026334783,0.0039435225,0.00729974,0.0046064444,0.0011910695,0.00028415062],"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":[0.0007093258,0.00039172953,0.33458292,0.0018286312,0.00032176328,0.00041024093,0.4114484,0.0002523866,0.0014583709,0.00478912,0.0025109642,0.2412962],"study_design_scores_gemma":[0.00012171861,0.0008798745,0.365412,0.0037457321,0.00021974312,0.00078731054,0.5947846,0.0011010038,0.0023624601,0.008107229,0.022256918,0.00022135024],"about_ca_topic_score_codex":0.0016844101,"about_ca_topic_score_gemma":0.0036164997,"teacher_disagreement_score":0.088899545,"about_ca_system_score_codex":0.0022626885,"about_ca_system_score_gemma":0.0030749005,"threshold_uncertainty_score":0.47015136},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036069362,0.4161439,0.056452304,0.47081655,0.0029136965,0.00034487067,0.00016361613,0.00012191778,0.049436275],"genre_scores_gemma":[0.45657954,0.31424418,0.124546655,0.08711064,0.011474954,0.0028910148,0.00019890888,0.00016738549,0.002786796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7686601,0.17758335,0.012264154,0.008257756,0.02900746,0.0042271037],"domain_scores_gemma":[0.6753007,0.28738505,0.008678274,0.011832453,0.010384608,0.006418868],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.19138493,0.004402942,0.012202883,0.026171638,0.010293363,0.051781584,0.007143807,0.022623986,0.0046091345],"category_scores_gemma":[0.14471541,0.0034178428,0.0029376866,0.014301085,0.12422503,0.063923396,0.034941677,0.025458908,0.0006085194],"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":[0.00004674111,0.000051650382,0.00033096477,0.002353002,0.0002844458,0.0001087768,0.0015794379,0.0009871534,0.00005647342,0.967986,0.0027346134,0.02348079],"study_design_scores_gemma":[0.000026804457,0.000018023451,0.00012603335,0.002573266,0.00006652692,0.00002317866,0.00081300177,0.00031458662,0.00005410148,0.98715985,0.008795114,0.000029509913],"about_ca_topic_score_codex":0.007122892,"about_ca_topic_score_gemma":0.006520361,"teacher_disagreement_score":0.98970664,"about_ca_system_score_codex":0.036966663,"about_ca_system_score_gemma":0.035158042,"threshold_uncertainty_score":0.99716634},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8206194,0.0014909084,0.0072883754,0.02540062,0.00043481152,0.001048704,0.000271262,0.0006604396,0.14278546],"genre_scores_gemma":[0.9259697,0.0021643073,0.03134885,0.0031049657,0.00009529734,0.0007355764,0.00032734964,0.000042597174,0.03621139],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983822,0.0005275505,0.000080033424,0.00012903757,0.00048996665,0.0003912885],"domain_scores_gemma":[0.9953284,0.00077373587,0.0005109085,0.00031589775,0.0007425031,0.0023284953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026883255,0.0003446913,0.00028268446,0.0009813831,0.0016414062,0.0029608982,0.00097475306,0.0007189185,0.01410958],"category_scores_gemma":[0.007017801,0.00023338472,0.00035920306,0.0003658229,0.00058970373,0.0015709072,0.004285975,0.0013978493,0.0019416006],"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":[0.00009497406,0.016724838,0.036218457,0.00034806557,0.000035405374,0.00022425251,0.0042209607,0.00059680175,0.0013192124,0.004085434,0.036931682,0.8991999],"study_design_scores_gemma":[0.00062057166,0.007381573,0.48618716,0.0063024242,0.00019856673,0.0014530522,0.041000772,0.0060756346,0.010459622,0.022068137,0.41808197,0.00017051876],"about_ca_topic_score_codex":0.0037411847,"about_ca_topic_score_gemma":0.011721815,"teacher_disagreement_score":0.01410958,"about_ca_system_score_codex":0.0014257494,"about_ca_system_score_gemma":0.009180849,"threshold_uncertainty_score":0.047201276},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9359608,0.0004963128,0.01058922,0.0059156767,0.00008137461,0.0021303848,0.00035477304,0.00017721143,0.044294246],"genre_scores_gemma":[0.96646434,0.0008708524,0.021032063,0.00081666047,0.00003328417,0.0010844432,0.0002647772,0.00004473795,0.009388815],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9953489,0.0028690752,0.00012011969,0.00026873645,0.0007840231,0.00060922076],"domain_scores_gemma":[0.9921262,0.0046663983,0.00067310745,0.00054648647,0.0007533943,0.0012344483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045117885,0.0004404001,0.0003079397,0.0015266589,0.007375416,0.0023608082,0.0022428734,0.00285909,0.0038044073],"category_scores_gemma":[0.013341414,0.00038423017,0.00033026165,0.0027835523,0.00209969,0.0013908751,0.0022671043,0.002393773,0.00035269928],"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":[0.0008910575,0.01652565,0.11157693,0.0012295797,0.00010733982,0.1058938,0.19323453,0.022290116,0.0029934433,0.06293,0.0606529,0.42167467],"study_design_scores_gemma":[0.0006453053,0.0045299097,0.076749705,0.0011063903,0.00011643933,0.027939254,0.4755548,0.054823782,0.006450715,0.017088247,0.33470905,0.00028643457],"about_ca_topic_score_codex":0.053441398,"about_ca_topic_score_gemma":0.116290815,"teacher_disagreement_score":0.053441398,"about_ca_system_score_codex":0.006170573,"about_ca_system_score_gemma":0.0068114405,"threshold_uncertainty_score":0.10626066},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46643305,0.026330147,0.24534607,0.11239994,0.0010391286,0.003775685,0.00086729886,0.00031137478,0.14349738],"genre_scores_gemma":[0.9261191,0.0032566744,0.060048632,0.0038790945,0.00011431702,0.0032832515,0.000186533,0.00011626352,0.002996166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.478582,0.4256545,0.028902743,0.008973766,0.053138305,0.004748635],"domain_scores_gemma":[0.42863095,0.48770145,0.016460355,0.015353408,0.04931586,0.0025380012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.369276,0.0016830356,0.0017626717,0.00788973,0.008072217,0.028133305,0.0042523555,0.0049231295,0.0018331654],"category_scores_gemma":[0.36741847,0.0014216825,0.0019146148,0.008616855,0.02660407,0.014269527,0.011664918,0.0067182304,0.0005784613],"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":[0.0007927441,0.0006043258,0.055513833,0.0067732064,0.00040500643,0.0008609605,0.25165328,0.0039350586,0.0022591902,0.39431432,0.0077360687,0.275152],"study_design_scores_gemma":[0.00077409996,0.0022870407,0.09100209,0.023669258,0.000740165,0.0034110998,0.41889322,0.01704881,0.01663131,0.177658,0.24727935,0.0006055777],"about_ca_topic_score_codex":0.02492975,"about_ca_topic_score_gemma":0.017151073,"teacher_disagreement_score":0.369276,"about_ca_system_score_codex":0.02425151,"about_ca_system_score_gemma":0.037948024,"threshold_uncertainty_score":0.777795},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022268761,0.8233325,0.006315656,0.09776816,0.04058226,0.0002968136,0.00026950703,0.00015510115,0.031057315],"genre_scores_gemma":[0.005867054,0.8552266,0.011457233,0.03851068,0.027384112,0.000780277,0.00044150025,0.00032432342,0.060008287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9806818,0.008078596,0.0014354772,0.0007483981,0.00871301,0.00034268197],"domain_scores_gemma":[0.93487906,0.043425694,0.0020428172,0.00096881896,0.017565392,0.0011182341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013145307,0.0017204637,0.002839207,0.0066110515,0.0014330156,0.00909835,0.0021367904,0.0050706756,0.011011847],"category_scores_gemma":[0.05243472,0.0007331287,0.0014282961,0.008681946,0.0053128987,0.0058013876,0.0020001603,0.008114302,0.0080942735],"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":[0.000017813905,0.00002255719,0.00008447914,0.002216351,0.00004550572,0.000018560311,0.00020992603,0.00022445378,0.00006164855,0.009891449,0.848704,0.13850331],"study_design_scores_gemma":[0.000023641409,0.000056868448,0.0004822836,0.0096581355,0.00007927687,0.00016774418,0.00027021606,0.00024729164,0.00014908382,0.0146904,0.9741251,0.000049997678],"about_ca_topic_score_codex":0.010872109,"about_ca_topic_score_gemma":0.02362646,"teacher_disagreement_score":0.013145307,"about_ca_system_score_codex":0.008241903,"about_ca_system_score_gemma":0.01432727,"threshold_uncertainty_score":0.06951988},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83529294,0.003137999,0.001023243,0.06513005,0.00055911945,0.00037884698,0.00034140237,0.000064886364,0.094071455],"genre_scores_gemma":[0.98683816,0.0016180986,0.0007056188,0.0020208482,0.00002928242,0.0000838252,0.000103374965,0.000032778244,0.0085679935],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97649264,0.008547588,0.00046932424,0.00085149216,0.0070324894,0.006606425],"domain_scores_gemma":[0.95819587,0.0038727238,0.0016242625,0.0005390398,0.01226976,0.023498252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020869792,0.00036891285,0.00049357326,0.001565958,0.026500234,0.008645825,0.0027201988,0.0018247996,0.00458555],"category_scores_gemma":[0.033086833,0.0003617288,0.00035015238,0.0027059384,0.008342774,0.00419241,0.007670798,0.0038721948,0.00031716813],"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":[0.0002850059,0.0008709241,0.11934085,0.00030837435,0.00005327369,0.0018623157,0.6237332,0.0010022153,0.00055910624,0.031418543,0.083580345,0.13698578],"study_design_scores_gemma":[0.000041878462,0.00029428853,0.056110088,0.00056118646,0.000031467654,0.0003604581,0.76175827,0.0009942502,0.00047265927,0.0018404782,0.17740642,0.00012849785],"about_ca_topic_score_codex":0.94189125,"about_ca_topic_score_gemma":0.9703372,"teacher_disagreement_score":0.10585578,"about_ca_system_score_codex":0.10585578,"about_ca_system_score_gemma":0.11862825,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001626451,0.9208531,0.0016802667,0.05158802,0.007623212,0.000019883717,0.0003970754,0.00018386864,0.017491939],"genre_scores_gemma":[0.0036050677,0.9553924,0.002985776,0.0081331255,0.0037550477,0.00005345253,0.00033966405,0.00009232943,0.025643175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99785477,0.00064755237,0.00024807046,0.0001383798,0.0009998999,0.00011133337],"domain_scores_gemma":[0.99277335,0.0037033863,0.000498724,0.00017019069,0.0022164972,0.0006378442],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041298615,0.0019070684,0.0010727814,0.0060992385,0.001422733,0.0047247536,0.002366491,0.0037497752,0.025044061],"category_scores_gemma":[0.009535159,0.0012798273,0.0010261266,0.0063438853,0.0019008414,0.0072783236,0.001825267,0.0049243583,0.024561075],"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":[0.000022090753,0.000008565406,0.00026181474,0.00043536464,0.000009850807,0.000044521727,0.00024239688,0.00009370963,0.00004465171,0.002158938,0.8672827,0.12939534],"study_design_scores_gemma":[0.000011051526,0.000012127937,0.0010017848,0.0025903273,0.000027954133,0.0002586722,0.00043119726,0.00006985552,0.000161851,0.0047425386,0.9906729,0.000019655701],"about_ca_topic_score_codex":0.03845313,"about_ca_topic_score_gemma":0.100693665,"teacher_disagreement_score":0.9958701,"about_ca_system_score_codex":0.0030159226,"about_ca_system_score_gemma":0.0062532094,"threshold_uncertainty_score":0.083780706},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011469653,0.99589854,0.0002694609,0.0016577322,0.00005981847,0.000042345826,0.00012312303,0.0000048387824,0.0007971226],"genre_scores_gemma":[0.0098037,0.9887211,0.00078620977,0.00044297092,0.0000509539,0.000051795854,0.00008303653,0.0000034311304,0.00005698968],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96054536,0.01927731,0.0075374646,0.0022469196,0.009768381,0.00062448723],"domain_scores_gemma":[0.67460144,0.28873426,0.017815134,0.0030398502,0.01462055,0.0011887985],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047708794,0.00086401816,0.003651841,0.014423376,0.0006977993,0.006310467,0.0018115944,0.0028027697,0.004037602],"category_scores_gemma":[0.16327941,0.0011780749,0.0020118428,0.024282975,0.002809735,0.007361228,0.0026817904,0.0024828364,0.0007065288],"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":[0.00014102318,0.00011895393,0.005433095,0.2463799,0.0009850156,0.00011391233,0.0020391543,0.00025454996,0.00024377965,0.003921396,0.006189509,0.73417974],"study_design_scores_gemma":[0.00010921087,0.00023467325,0.029661762,0.77803075,0.004555779,0.00075482164,0.005287261,0.00029968974,0.00066164933,0.006988839,0.17330341,0.00011226529],"about_ca_topic_score_codex":0.0064696656,"about_ca_topic_score_gemma":0.011891159,"teacher_disagreement_score":0.9522912,"about_ca_system_score_codex":0.004532582,"about_ca_system_score_gemma":0.015835557,"threshold_uncertainty_score":0.25231123},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903605,0.00049797277,0.0021289808,0.00149653,0.00005888679,0.00032532393,0.000017124192,0.000019630434,0.0050950362],"genre_scores_gemma":[0.99699366,0.00020368617,0.0015984239,0.00028380906,0.00003654658,0.00023182097,0.00001329341,0.000008188825,0.00063058635],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.92881054,0.057496764,0.0030067195,0.002634321,0.0046272525,0.003424497],"domain_scores_gemma":[0.83437586,0.13008112,0.013330457,0.0055890842,0.005753581,0.010869886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043499246,0.0003297183,0.0006687412,0.0017874483,0.011380997,0.009645679,0.0013828921,0.0025888102,0.0029421928],"category_scores_gemma":[0.1247637,0.00076176925,0.00053403375,0.0011900772,0.005458407,0.006140219,0.010242214,0.0027252561,0.00050441356],"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":[0.0005594969,0.0022157612,0.052950796,0.00053355406,0.000058834765,0.0043290453,0.8750445,0.00013895339,0.0023987684,0.0031596117,0.0013136754,0.05729709],"study_design_scores_gemma":[0.00022997834,0.0020357792,0.035447072,0.00044791348,0.000070874295,0.002592395,0.9362576,0.00040466053,0.0015911679,0.0029991297,0.01783404,0.00008937205],"about_ca_topic_score_codex":0.0017937347,"about_ca_topic_score_gemma":0.002368091,"teacher_disagreement_score":0.95650077,"about_ca_system_score_codex":0.0029813757,"about_ca_system_score_gemma":0.008151247,"threshold_uncertainty_score":0.23004878},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04167095,0.0006480507,0.9177156,0.012434506,0.0001587528,0.0041971984,0.0007427185,0.0011732649,0.021258948],"genre_scores_gemma":[0.23332779,0.00021935652,0.7628095,0.0003500894,0.000044573906,0.0016119062,0.000544212,0.000060182272,0.0010323144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92095256,0.052266072,0.00648421,0.002599983,0.013511097,0.004186113],"domain_scores_gemma":[0.9185206,0.03473868,0.008769048,0.0035104018,0.03023247,0.004228877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11828042,0.0014596803,0.0016456578,0.0084314225,0.0031708584,0.012412283,0.003550093,0.0021964796,0.0020688963],"category_scores_gemma":[0.104766995,0.0006874101,0.0017632205,0.0063401563,0.0024542839,0.006525444,0.00627991,0.004155141,0.0004990389],"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":[0.0004061104,0.001956741,0.061624005,0.0009902503,0.0005883343,0.0002492324,0.0043010837,0.12672432,0.0016991886,0.42220372,0.017451616,0.36180535],"study_design_scores_gemma":[0.00036768577,0.0021768422,0.036838517,0.0022841324,0.0004781888,0.00022380923,0.008484425,0.62398434,0.006143079,0.27099246,0.04765591,0.00037069136],"about_ca_topic_score_codex":0.056922045,"about_ca_topic_score_gemma":0.040154155,"teacher_disagreement_score":0.11828042,"about_ca_system_score_codex":0.017802414,"about_ca_system_score_gemma":0.051164195,"threshold_uncertainty_score":0.6255341},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3478865,0.004462243,0.24945718,0.2596808,0.0013976117,0.0021512066,0.00010697665,0.00034252432,0.13451491],"genre_scores_gemma":[0.9698982,0.0005309428,0.02384968,0.0036416403,0.00014641436,0.00044809154,0.000024784023,0.000035469933,0.0014248333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7042856,0.25323367,0.005372545,0.004352473,0.02502022,0.007735472],"domain_scores_gemma":[0.8439048,0.10382651,0.011775523,0.007871256,0.023625676,0.008996277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19905643,0.0008765328,0.0012362007,0.0023059347,0.010789976,0.02079101,0.0031725485,0.008443471,0.003908744],"category_scores_gemma":[0.2097749,0.0008929856,0.00089850934,0.0027563246,0.017869674,0.026660142,0.014954248,0.006582718,0.0007703504],"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":[0.000548769,0.0010222378,0.04010129,0.0022435368,0.00037337848,0.0015902898,0.21175088,0.0038600639,0.006926747,0.3736603,0.009465517,0.3484569],"study_design_scores_gemma":[0.00021717376,0.0010547622,0.015936226,0.0050910395,0.00035171836,0.0009298368,0.2700365,0.011639328,0.013304,0.5640898,0.11699284,0.0003568842],"about_ca_topic_score_codex":0.0040871087,"about_ca_topic_score_gemma":0.004581197,"teacher_disagreement_score":0.19905643,"about_ca_system_score_codex":0.01086177,"about_ca_system_score_gemma":0.021009775,"threshold_uncertainty_score":0.987706},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083839126,0.01604566,0.021587323,0.72634494,0.001415798,0.00023487877,0.000572433,0.00020673806,0.14975303],"genre_scores_gemma":[0.93047243,0.006100822,0.010934004,0.04340984,0.0012812242,0.00036479594,0.00021698533,0.00015992981,0.0070600593],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.706062,0.19652432,0.01259723,0.0059640855,0.070996515,0.007855764],"domain_scores_gemma":[0.22338107,0.6217951,0.025080143,0.01862092,0.103619486,0.0075032874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25959286,0.0006389892,0.002001962,0.007821637,0.0065045864,0.028086443,0.0027486912,0.007150341,0.00573559],"category_scores_gemma":[0.43091205,0.00089001434,0.0010228398,0.010382536,0.014806559,0.017189095,0.012319083,0.0094021205,0.0011422536],"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":[0.00075245847,0.00026043292,0.031422734,0.0022737742,0.00020338748,0.0002942944,0.02004851,0.0022044524,0.00074024603,0.3687584,0.060373377,0.51266795],"study_design_scores_gemma":[0.0003590254,0.0010853535,0.06912809,0.015298081,0.0005387436,0.0011952093,0.052179936,0.009683685,0.007989997,0.49428543,0.34755167,0.00070471904],"about_ca_topic_score_codex":0.038251996,"about_ca_topic_score_gemma":0.02810482,"teacher_disagreement_score":0.25959286,"about_ca_system_score_codex":0.021087721,"about_ca_system_score_gemma":0.03540715,"threshold_uncertainty_score":0.9130538},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069713866,0.001432538,0.0050785146,0.6167255,0.3610411,0.0006447383,0.00028498116,0.0003942695,0.013701189],"genre_scores_gemma":[0.016870676,0.0013925239,0.007482317,0.74797136,0.1307918,0.004624975,0.0003666496,0.0009697895,0.089529976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9523409,0.019466914,0.0041170046,0.004593928,0.014933901,0.004547427],"domain_scores_gemma":[0.8402686,0.07535925,0.0058079655,0.00880966,0.053217232,0.016537365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04747,0.002500714,0.0024181907,0.0022676112,0.0116679305,0.016633859,0.0076935864,0.051202785,0.05876767],"category_scores_gemma":[0.24972987,0.0010339066,0.0043105436,0.0016832766,0.0074742464,0.017999193,0.01720339,0.054893903,0.03272835],"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":[0.000120934674,0.00006752064,0.00011558544,0.00042351533,0.000019960928,0.0004963873,0.0027705503,0.00008559325,0.0007411418,0.040177748,0.9460407,0.008940346],"study_design_scores_gemma":[0.000034923563,0.000034602053,0.00011977227,0.00040406143,0.000009013727,0.00011087566,0.002177009,0.00020551181,0.00020426071,0.01051801,0.9861356,0.000046325804],"about_ca_topic_score_codex":0.0023383573,"about_ca_topic_score_gemma":0.0020822543,"teacher_disagreement_score":0.05876767,"about_ca_system_score_codex":0.0100689335,"about_ca_system_score_gemma":0.0144254705,"threshold_uncertainty_score":0.2510484},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09648212,0.17367366,0.0052618654,0.5185377,0.025060283,0.0002625317,0.0020163406,0.00056178024,0.17814375],"genre_scores_gemma":[0.68610364,0.07405893,0.0060444167,0.09746838,0.009016056,0.00023254384,0.0021702782,0.00030867374,0.12459702],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98765,0.002706078,0.0006450846,0.0010346636,0.0056871353,0.0022769778],"domain_scores_gemma":[0.96202755,0.007433397,0.002552269,0.0032514767,0.013736792,0.010998482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015757345,0.00065466756,0.001002479,0.0030395081,0.006234972,0.010437169,0.0013610305,0.0039491453,0.017240522],"category_scores_gemma":[0.030622138,0.00038407012,0.0008989285,0.0073782858,0.004874201,0.005234775,0.0066346233,0.0056226915,0.0035409636],"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":[0.00042567126,0.0005532128,0.020560341,0.0013730593,0.00016137688,0.00053656875,0.008432472,0.00085178396,0.0006846738,0.059915017,0.23441134,0.67209446],"study_design_scores_gemma":[0.000033618595,0.00012786755,0.035985418,0.0011522026,0.000030388092,0.00021839174,0.0058632516,0.00018973857,0.00025035226,0.010025166,0.94606894,0.000054682972],"about_ca_topic_score_codex":0.05072806,"about_ca_topic_score_gemma":0.10057256,"teacher_disagreement_score":0.05072806,"about_ca_system_score_codex":0.015448889,"about_ca_system_score_gemma":0.028551267,"threshold_uncertainty_score":0.11209005},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5441941,0.016323976,0.23320377,0.10217907,0.0043366244,0.003280084,0.0008956615,0.0017365178,0.09385017],"genre_scores_gemma":[0.9615669,0.0006806292,0.03077158,0.0035413185,0.00039186058,0.0013103111,0.00022236849,0.00021949691,0.0012953987],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.46349546,0.3339906,0.052743066,0.028760323,0.11346759,0.0075429464],"domain_scores_gemma":[0.2614932,0.47273606,0.06305351,0.06523217,0.131915,0.0055699684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30926162,0.00087906996,0.002317202,0.004599632,0.0038782856,0.010506561,0.004698615,0.0036111546,0.0024303857],"category_scores_gemma":[0.69959414,0.0016412251,0.0012486035,0.0033178898,0.0096146,0.0123038925,0.008008682,0.0053899814,0.0007042405],"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":[0.002226568,0.00074946065,0.20727979,0.006355224,0.0020584543,0.0009717003,0.11868762,0.0054328046,0.0044551496,0.117522776,0.047265626,0.4869949],"study_design_scores_gemma":[0.0011297013,0.0026927928,0.2812625,0.011805165,0.0007574112,0.0023992239,0.05638814,0.022129018,0.012055814,0.5159787,0.0922029,0.0011986786],"about_ca_topic_score_codex":0.006150278,"about_ca_topic_score_gemma":0.0042685387,"teacher_disagreement_score":0.30926162,"about_ca_system_score_codex":0.008008338,"about_ca_system_score_gemma":0.00708043,"threshold_uncertainty_score":0.8518034},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042764284,0.047844715,0.27516702,0.554916,0.005339212,0.0021949986,0.00006547049,0.0005686366,0.07113967],"genre_scores_gemma":[0.7766484,0.012713482,0.14212693,0.05121756,0.0046005277,0.0065467954,0.00005497956,0.00049606065,0.005595319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.14882767,0.74421144,0.029847687,0.014879947,0.056167223,0.0060659833],"domain_scores_gemma":[0.1042697,0.79156697,0.019076835,0.032034148,0.04314361,0.009908788],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7301786,0.0018743942,0.006284974,0.015876928,0.015486139,0.04943062,0.0074745617,0.013236254,0.003959014],"category_scores_gemma":[0.6980662,0.0031302257,0.0016730808,0.009548042,0.1006884,0.051139906,0.041770637,0.021559667,0.0011325603],"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":[0.0005061971,0.0003378964,0.0061459974,0.004396831,0.0003454243,0.0009904495,0.15854713,0.0012142754,0.00080636895,0.51911837,0.012312264,0.29527882],"study_design_scores_gemma":[0.00046729553,0.0008581026,0.0039156107,0.012890758,0.00018439245,0.0014293692,0.10325854,0.0044121724,0.0012162455,0.76274234,0.10820525,0.00042003102],"about_ca_topic_score_codex":0.0031638488,"about_ca_topic_score_gemma":0.0030883367,"teacher_disagreement_score":0.2698214,"about_ca_system_score_codex":0.03255483,"about_ca_system_score_gemma":0.052853774,"threshold_uncertainty_score":0.33273786},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022235108,0.8677721,0.01880082,0.056586515,0.003825346,0.00043250405,0.0020639992,0.00038739183,0.04790785],"genre_scores_gemma":[0.040831063,0.82974243,0.04518641,0.0044764355,0.0012748189,0.0003987198,0.0026256396,0.0003219777,0.0751425],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9839139,0.0034384057,0.0013359287,0.0008535499,0.009716453,0.00074172945],"domain_scores_gemma":[0.95744133,0.015851762,0.0029376443,0.0013595471,0.020501278,0.0019084085],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01981525,0.0018044035,0.002106956,0.009024146,0.003011238,0.009766332,0.0032279259,0.0038643766,0.023733933],"category_scores_gemma":[0.03402543,0.001428545,0.0014596491,0.010668086,0.0059727635,0.005916193,0.0019071356,0.0047116694,0.01616297],"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":[0.00007127062,0.000046116238,0.0042353226,0.0035929962,0.00009109419,0.00010150804,0.001963949,0.0004948256,0.0005755996,0.005814468,0.35955963,0.6234532],"study_design_scores_gemma":[0.000034210574,0.00010215398,0.029905416,0.009223608,0.0001818948,0.0006484008,0.0027143438,0.00066913734,0.0013615238,0.008201624,0.94678503,0.00017265738],"about_ca_topic_score_codex":0.64482754,"about_ca_topic_score_gemma":0.7756401,"teacher_disagreement_score":0.98018473,"about_ca_system_score_codex":0.032301683,"about_ca_system_score_gemma":0.057008907,"threshold_uncertainty_score":0.71452826},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073958814,0.01056835,0.43589702,0.06277229,0.00042433254,0.0016820172,0.000099477365,0.00056869816,0.41402906],"genre_scores_gemma":[0.8674265,0.0029546365,0.122635596,0.0020840063,0.000091601796,0.0010165924,0.000039332004,0.0001445667,0.003607173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74239546,0.22711095,0.006280934,0.003314413,0.016646646,0.0042515127],"domain_scores_gemma":[0.57370156,0.37786654,0.008866041,0.016090045,0.020328177,0.0031476086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16166079,0.0012312129,0.0010764115,0.008369868,0.005066621,0.017172499,0.0032344395,0.00354057,0.0043488354],"category_scores_gemma":[0.22253811,0.000773814,0.0010819673,0.0038426332,0.03223392,0.028180672,0.012934297,0.0040431265,0.0004947126],"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":[0.0001005008,0.00017868068,0.0052687284,0.0007192925,0.000028831853,0.00032535996,0.037442632,0.0015819524,0.0003999371,0.80945045,0.0021268704,0.1423767],"study_design_scores_gemma":[0.00013143585,0.0005166459,0.0052496106,0.003994573,0.00007348069,0.0011189299,0.04566437,0.008933743,0.0042129704,0.77001244,0.15988739,0.0002044635],"about_ca_topic_score_codex":0.0048516677,"about_ca_topic_score_gemma":0.004775603,"teacher_disagreement_score":0.16166079,"about_ca_system_score_codex":0.014105084,"about_ca_system_score_gemma":0.016004415,"threshold_uncertainty_score":0.8549542},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035382723,0.0020662271,0.050889634,0.0681817,0.025017874,0.064978145,0.32060722,0.05100172,0.41371927],"genre_scores_gemma":[0.013863711,0.004496764,0.1318012,0.051765993,0.008091146,0.090921074,0.16335444,0.021742865,0.51396286],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9809663,0.0050295633,0.003779171,0.00089244207,0.007957528,0.0013749105],"domain_scores_gemma":[0.76511574,0.101271465,0.010554387,0.028023545,0.08391351,0.011121342],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02457903,0.0011978687,0.0018346222,0.011059861,0.0027068264,0.006353273,0.0024239155,0.005893985,0.683755],"category_scores_gemma":[0.22234195,0.0019429178,0.0015853528,0.008819188,0.0017187822,0.0064344066,0.00334126,0.0058174026,0.4804361],"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":[0.00009188849,0.00013707664,0.00020112484,0.00041858014,0.000004336853,0.000050596325,0.000048178394,0.000094223076,0.000092899245,0.0017605774,0.9504001,0.04670041],"study_design_scores_gemma":[0.0002633302,0.00012466569,0.0017400626,0.0012852413,0.0000097460115,0.00013746787,0.00021921011,0.00033450677,0.00046714587,0.006456297,0.98889846,0.00006376367],"about_ca_topic_score_codex":0.00433706,"about_ca_topic_score_gemma":0.0052380515,"teacher_disagreement_score":0.683755,"about_ca_system_score_codex":0.0036465882,"about_ca_system_score_gemma":0.014247257,"threshold_uncertainty_score":0.4510851},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017363592,0.02502836,0.022300992,0.94287753,0.004913406,0.00030038226,0.000024906825,0.000119664895,0.0026983456],"genre_scores_gemma":[0.35052052,0.03673281,0.20481502,0.38244018,0.015073636,0.0052330405,0.00012734078,0.0006111635,0.004446303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.20099114,0.6322136,0.05689109,0.021730445,0.07785188,0.010321926],"domain_scores_gemma":[0.059644703,0.7810767,0.026790343,0.0348081,0.089741655,0.007938532],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.80836934,0.003917541,0.008438697,0.018720418,0.020485086,0.052935354,0.0140061695,0.04262701,0.0075753196],"category_scores_gemma":[0.80046123,0.003830778,0.0037325572,0.01727401,0.10902404,0.07864936,0.04181642,0.06501592,0.001716667],"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":[0.00048192294,0.00031469064,0.0037786816,0.007053988,0.00025398945,0.00052577123,0.032556813,0.0014013012,0.0004659483,0.7173346,0.05310851,0.18272384],"study_design_scores_gemma":[0.00039557088,0.0003877303,0.003226204,0.03204655,0.00022686293,0.00075186713,0.056795977,0.0055659395,0.001363355,0.7062678,0.19218409,0.00078808365],"about_ca_topic_score_codex":0.022646403,"about_ca_topic_score_gemma":0.01749084,"teacher_disagreement_score":0.92286557,"about_ca_system_score_codex":0.077134445,"about_ca_system_score_gemma":0.1538007,"threshold_uncertainty_score":0.5596522},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8975459,0.0008097989,0.046192486,0.0046075126,0.00010444371,0.0053494154,0.000512213,0.0041715163,0.040706784],"genre_scores_gemma":[0.88016677,0.00041160994,0.11293873,0.000427341,0.00008530379,0.003150689,0.00032023917,0.0001236423,0.0023756397],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9707912,0.024188235,0.0014073697,0.0007629996,0.0019414137,0.00090869603],"domain_scores_gemma":[0.80861557,0.16425808,0.006811108,0.007421334,0.006833086,0.006060785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032910064,0.00047916156,0.00044344898,0.003232071,0.0015002248,0.0037548055,0.0015641504,0.0007879902,0.007788299],"category_scores_gemma":[0.088279806,0.00059986225,0.00049045635,0.0018356529,0.001061221,0.004308489,0.00445124,0.0011359579,0.0011082692],"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":[0.0013845746,0.008623603,0.043814555,0.0008303784,0.000092166025,0.00026492792,0.00965341,0.0024526704,0.0029907422,0.001671266,0.0090629505,0.9191588],"study_design_scores_gemma":[0.0065684607,0.021035628,0.5146611,0.008386381,0.0009877618,0.0023221893,0.05705778,0.1285015,0.052750297,0.029764244,0.1766816,0.001283012],"about_ca_topic_score_codex":0.0036736727,"about_ca_topic_score_gemma":0.0062885317,"teacher_disagreement_score":0.032910064,"about_ca_system_score_codex":0.0025610975,"about_ca_system_score_gemma":0.005021707,"threshold_uncertainty_score":0.17404711},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23330109,0.015751293,0.09677105,0.22499487,0.0013198166,0.0063843373,0.00049790734,0.0004521637,0.42052752],"genre_scores_gemma":[0.9390412,0.002410637,0.046813503,0.005375356,0.00032128053,0.0018946143,0.0001340385,0.00006491844,0.003944524],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6151212,0.29072607,0.020043956,0.002993474,0.062453575,0.008661706],"domain_scores_gemma":[0.44595358,0.40718418,0.03423904,0.010760771,0.09461954,0.007242876],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.31279516,0.00094400544,0.0009812261,0.008018583,0.007884192,0.023036465,0.002618478,0.004932272,0.004553647],"category_scores_gemma":[0.42696324,0.00068323145,0.0009813869,0.005798663,0.012158859,0.012755026,0.013850388,0.006014886,0.0003844876],"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":[0.00030949357,0.0009005373,0.04017117,0.0032713376,0.0001770934,0.00049001863,0.05321988,0.007523844,0.00109742,0.3751696,0.043551974,0.47411764],"study_design_scores_gemma":[0.0005468617,0.0019088613,0.07656398,0.033929124,0.0006469482,0.00063269766,0.086643845,0.018928852,0.01013253,0.26403826,0.5054038,0.00062419893],"about_ca_topic_score_codex":0.026337123,"about_ca_topic_score_gemma":0.043981392,"teacher_disagreement_score":0.31279516,"about_ca_system_score_codex":0.032069255,"about_ca_system_score_gemma":0.08126467,"threshold_uncertainty_score":0.8474459},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014510752,0.052280772,0.02303229,0.8416501,0.0021477502,0.00022722901,0.000049740338,0.00018829343,0.06591304],"genre_scores_gemma":[0.6255465,0.12472101,0.13649157,0.085865125,0.0034420989,0.0019418483,0.00014682765,0.00042663584,0.021418437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8313368,0.14903317,0.0023412015,0.0034310962,0.0093290685,0.0045286235],"domain_scores_gemma":[0.7257341,0.23271208,0.0028512885,0.010750691,0.012738935,0.015212962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21086642,0.0010107977,0.0016086103,0.0025849065,0.011519655,0.0376148,0.004470803,0.0073328717,0.0051379777],"category_scores_gemma":[0.08486462,0.0012453705,0.0010350489,0.0027405873,0.044601683,0.02380257,0.015356132,0.022623474,0.0012747117],"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":[0.00024415256,0.0006929292,0.007215749,0.0017455369,0.000082276114,0.001126631,0.06057307,0.0017019702,0.00022104957,0.51948446,0.07063164,0.33628055],"study_design_scores_gemma":[0.00017839426,0.0004877616,0.0030043428,0.0077851554,0.00005322631,0.0007265187,0.094033934,0.0017821087,0.0008059019,0.35619977,0.5347752,0.00016766277],"about_ca_topic_score_codex":0.015498473,"about_ca_topic_score_gemma":0.0310766,"teacher_disagreement_score":0.21086642,"about_ca_system_score_codex":0.018334297,"about_ca_system_score_gemma":0.04981406,"threshold_uncertainty_score":0.9731422},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038840476,0.033644836,0.061302703,0.45837584,0.005865942,0.0004884606,0.00006412588,0.00028188142,0.4011358],"genre_scores_gemma":[0.82838297,0.016517933,0.040482856,0.07641774,0.002054451,0.0008228888,0.000063180465,0.0005359396,0.034722053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9233077,0.061938822,0.0013831734,0.0025904472,0.007082956,0.0036968298],"domain_scores_gemma":[0.93505067,0.0406809,0.0020235698,0.004365362,0.012917844,0.004961632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.082768306,0.0010580583,0.0012152871,0.0061006662,0.010886301,0.030636324,0.0029183517,0.00525841,0.0054302798],"category_scores_gemma":[0.06554596,0.0005126978,0.0006813688,0.005687824,0.074207865,0.02274885,0.015537951,0.011381726,0.0006565677],"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":[0.000035540892,0.00006954614,0.0027312562,0.00072053063,0.0000334093,0.00028258582,0.15993963,0.0005523238,0.0002398341,0.7449596,0.02837085,0.06206492],"study_design_scores_gemma":[0.000024985742,0.00009610669,0.0017697145,0.0021756208,0.000034943205,0.00026704007,0.27756983,0.001092297,0.00049824227,0.3686788,0.34774628,0.00004612424],"about_ca_topic_score_codex":0.015725954,"about_ca_topic_score_gemma":0.023573328,"teacher_disagreement_score":0.082768306,"about_ca_system_score_codex":0.02055611,"about_ca_system_score_gemma":0.03468882,"threshold_uncertainty_score":0.4377259},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047094873,0.102193095,0.026688723,0.6433228,0.0059938114,0.00026927175,0.0011255462,0.00041395912,0.21528323],"genre_scores_gemma":[0.32984352,0.25373134,0.067087494,0.15318592,0.00406432,0.00091067527,0.001468405,0.0009103254,0.18879803],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957065,0.00165077,0.00029721254,0.00016343532,0.0020581158,0.00012398184],"domain_scores_gemma":[0.95087844,0.028194694,0.0023795422,0.0011311624,0.015689367,0.0017267916],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012022469,0.00035529194,0.00033990154,0.002964032,0.004255221,0.008109794,0.0018457016,0.00270747,0.013899151],"category_scores_gemma":[0.05382413,0.00043850916,0.00033457446,0.003436477,0.004265888,0.008479493,0.002264778,0.004954531,0.005954977],"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":[0.000048679194,0.0000364838,0.0023091205,0.0006873334,0.00002451,0.00004932079,0.0041502994,0.0000831467,0.00022997486,0.01860814,0.7427324,0.23104048],"study_design_scores_gemma":[0.000031574302,0.00007286492,0.013381667,0.0038658504,0.00006419088,0.0002048433,0.008120933,0.00024346352,0.0009819957,0.038864236,0.93411267,0.000055736822],"about_ca_topic_score_codex":0.059194863,"about_ca_topic_score_gemma":0.18894006,"teacher_disagreement_score":0.9879775,"about_ca_system_score_codex":0.005846118,"about_ca_system_score_gemma":0.012603853,"threshold_uncertainty_score":0.11770064},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76902306,0.0018857296,0.053602256,0.013248666,0.00013900871,0.0018401172,0.00021253826,0.0010452485,0.15900342],"genre_scores_gemma":[0.86988664,0.0007755528,0.089384675,0.00065811496,0.000017911876,0.0006232366,0.00021898786,0.00012487208,0.03830999],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98805004,0.009128766,0.00031641123,0.0003762371,0.0012111019,0.00091748213],"domain_scores_gemma":[0.9870868,0.008343759,0.00038177808,0.00070588314,0.0024326888,0.0010491406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013164651,0.00037197364,0.00034296094,0.0009123143,0.006762422,0.008570976,0.0024836254,0.0017852709,0.003316668],"category_scores_gemma":[0.0151587995,0.00058200874,0.0002749528,0.0012734582,0.0026806989,0.003962387,0.0036357087,0.0024861027,0.0008801419],"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":[0.00034801566,0.0036707933,0.10445954,0.0008683296,0.00004241943,0.0017713939,0.14971364,0.019818543,0.004790291,0.04619825,0.052629307,0.6156895],"study_design_scores_gemma":[0.00036289627,0.0026365137,0.13606575,0.001678839,0.00018317514,0.0018284352,0.45564827,0.035238143,0.02305409,0.033367544,0.30940622,0.0005301713],"about_ca_topic_score_codex":0.08356879,"about_ca_topic_score_gemma":0.2924673,"teacher_disagreement_score":0.98683536,"about_ca_system_score_codex":0.009253694,"about_ca_system_score_gemma":0.014023517,"threshold_uncertainty_score":0.1661647},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02103524,0.20753466,0.029539097,0.52184224,0.06931586,0.00018590988,0.0047516217,0.0008259081,0.1449695],"genre_scores_gemma":[0.35571602,0.33597368,0.09988916,0.099599764,0.043334063,0.0007230941,0.010465785,0.002110677,0.052187815],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9763464,0.009292659,0.0041863057,0.0013490246,0.0071641174,0.0016614617],"domain_scores_gemma":[0.8875396,0.040835634,0.00913961,0.01132145,0.04796488,0.0031988036],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03410174,0.0006289698,0.00075902324,0.013752834,0.0022705616,0.016767738,0.0016349349,0.002262572,0.0043923636],"category_scores_gemma":[0.07674022,0.00033845936,0.0011046792,0.025225153,0.0070216926,0.024264283,0.0050988677,0.0055394736,0.0017534897],"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":[0.00007330417,0.00006888345,0.008193092,0.0012287305,0.00003634624,0.00008828385,0.006286728,0.00070177944,0.00050478295,0.14528847,0.44589725,0.39163232],"study_design_scores_gemma":[0.0000032473324,0.000019458797,0.00859359,0.0016901075,0.000016718426,0.000119407676,0.005427285,0.00021382877,0.0003560998,0.010856579,0.9726571,0.000046644473],"about_ca_topic_score_codex":0.023527319,"about_ca_topic_score_gemma":0.029300652,"teacher_disagreement_score":0.9658983,"about_ca_system_score_codex":0.01288418,"about_ca_system_score_gemma":0.015002983,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030333963,0.7015738,0.06000872,0.11053339,0.003765368,0.00040340677,0.0028133758,0.0013237786,0.11654486],"genre_scores_gemma":[0.041439176,0.82448775,0.06721609,0.0055718445,0.0011958798,0.00041875365,0.0017087626,0.00061002135,0.057351723],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967624,0.0011242374,0.00033836206,0.00021689595,0.0014367728,0.00012124447],"domain_scores_gemma":[0.9713496,0.02047839,0.001624409,0.0008700741,0.00462455,0.0010530755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009728352,0.0010360571,0.0007284199,0.0071539977,0.0027607097,0.0068452945,0.0019138996,0.0024140773,0.021677954],"category_scores_gemma":[0.021834433,0.0012625812,0.0008339988,0.008936114,0.0032094105,0.010691251,0.0023616767,0.003803327,0.014676695],"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":[0.000036587924,0.000034042638,0.0012207327,0.0025659802,0.000024908524,0.000066396075,0.0050940807,0.00025740734,0.0003381867,0.007830364,0.39900196,0.58352935],"study_design_scores_gemma":[0.00002065136,0.00008004492,0.0048011634,0.008926621,0.00009575492,0.0004986358,0.006546317,0.00031529873,0.0010115703,0.023772018,0.9538463,0.00008561073],"about_ca_topic_score_codex":0.06275889,"about_ca_topic_score_gemma":0.13631506,"teacher_disagreement_score":0.9902716,"about_ca_system_score_codex":0.005046324,"about_ca_system_score_gemma":0.012355147,"threshold_uncertainty_score":0.12478721},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9407682,0.0005835334,0.005698431,0.016359054,0.0006114625,0.0022826854,0.0005167774,0.00019227719,0.03298749],"genre_scores_gemma":[0.9746202,0.000521448,0.019878255,0.0009897873,0.00015227974,0.0009770392,0.0004411162,0.000016788603,0.002403059],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9901861,0.001655515,0.0012360793,0.00035879738,0.00455688,0.0020065669],"domain_scores_gemma":[0.92747325,0.01152854,0.006918335,0.0016559361,0.014976574,0.037447434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011770363,0.0004228351,0.00061098294,0.0029239487,0.0032143507,0.0035024963,0.001077558,0.001459387,0.007712787],"category_scores_gemma":[0.04521519,0.00053950737,0.00066125265,0.001416999,0.0012235502,0.0018143791,0.0035493558,0.0023521662,0.0013638657],"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":[0.0006451673,0.006057412,0.31707817,0.0031244094,0.00012853261,0.0012333436,0.012576038,0.0025126028,0.022221139,0.01308345,0.03218274,0.5891571],"study_design_scores_gemma":[0.00007797861,0.0018628594,0.92488325,0.0011072052,0.000048201066,0.00045900495,0.020317635,0.0022680252,0.0062670517,0.006527273,0.036076345,0.000105143954],"about_ca_topic_score_codex":0.002875723,"about_ca_topic_score_gemma":0.0061498145,"teacher_disagreement_score":0.011770363,"about_ca_system_score_codex":0.0046303025,"about_ca_system_score_gemma":0.021892149,"threshold_uncertainty_score":0.06224841},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024413723,0.020471847,0.40611273,0.47920582,0.005767566,0.0012417121,0.00026526424,0.00014623377,0.062375125],"genre_scores_gemma":[0.7407493,0.0068548983,0.16695923,0.06921841,0.004079023,0.006247926,0.00012054844,0.00024355542,0.0055271583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5377978,0.41500637,0.0102387,0.005844287,0.02797679,0.00313604],"domain_scores_gemma":[0.25040874,0.71547496,0.007716072,0.009556624,0.014746899,0.0020966167],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4083926,0.0011288207,0.002248431,0.006372112,0.00658789,0.025266264,0.004428235,0.006113381,0.0046897614],"category_scores_gemma":[0.43243387,0.0010597864,0.0008979214,0.0041305833,0.048570823,0.02861031,0.013932469,0.009064091,0.0005125165],"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":[0.00014849396,0.000067960464,0.0013293589,0.0016316447,0.00008796784,0.00018678,0.053855024,0.00042377395,0.00057154737,0.8791821,0.0039035736,0.058611836],"study_design_scores_gemma":[0.00010110384,0.00007153525,0.0010366248,0.0023291735,0.000054799668,0.00014638115,0.03859426,0.0020571526,0.0005718415,0.9253485,0.02962987,0.000058803573],"about_ca_topic_score_codex":0.004944918,"about_ca_topic_score_gemma":0.0066406536,"teacher_disagreement_score":0.5916074,"about_ca_system_score_codex":0.018483965,"about_ca_system_score_gemma":0.021860713,"threshold_uncertainty_score":0.7295573},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008256958,0.0019523632,0.009803188,0.92608494,0.010880906,0.00015143552,0.00013910215,0.0009250013,0.04180603],"genre_scores_gemma":[0.21730608,0.0036915806,0.017809998,0.7100068,0.006293215,0.00038110933,0.00032059217,0.0008141714,0.04337646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9371335,0.029301131,0.0036701784,0.0051658493,0.019129256,0.005600048],"domain_scores_gemma":[0.8332693,0.045153268,0.013515107,0.011618506,0.06732642,0.029117428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050615676,0.0012016767,0.0008787765,0.0025532697,0.005379802,0.016168354,0.0047086226,0.0215513,0.01081653],"category_scores_gemma":[0.11852397,0.00081345224,0.00069171,0.002513323,0.01200308,0.01039106,0.021374486,0.022397988,0.0057742186],"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":[0.00013802397,0.00015159546,0.013848702,0.00032397965,0.000039729828,0.0016556963,0.0073050205,0.0008422834,0.0015209904,0.03486082,0.83390206,0.105411015],"study_design_scores_gemma":[0.00003062727,0.00011388901,0.0049320245,0.0006507997,0.000018701536,0.0016695535,0.010490241,0.001356982,0.0013105638,0.015572937,0.96369284,0.00016082214],"about_ca_topic_score_codex":0.006672521,"about_ca_topic_score_gemma":0.0056856778,"teacher_disagreement_score":0.050615676,"about_ca_system_score_codex":0.010391197,"about_ca_system_score_gemma":0.022475159,"threshold_uncertainty_score":0.26768452},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063144416,0.007206681,0.005158105,0.40823126,0.16596083,0.00015567278,0.0003819117,0.00069620676,0.40589485],"genre_scores_gemma":[0.20487718,0.015349946,0.01643897,0.10076233,0.14941421,0.00026245206,0.0005750215,0.0015849031,0.51073486],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9806167,0.004243234,0.00083968893,0.00070469914,0.012169151,0.0014265388],"domain_scores_gemma":[0.91936105,0.019874679,0.0037268167,0.004439746,0.036128502,0.016469233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014583141,0.0011458227,0.0012659361,0.004600259,0.0057049547,0.02661381,0.002125143,0.0072673755,0.095398426],"category_scores_gemma":[0.11627878,0.00046615946,0.00084257685,0.002550118,0.003730593,0.012165173,0.0062527265,0.0063355677,0.04755625],"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":[0.00010050381,0.00020164861,0.0010782825,0.00028874283,0.000049448743,0.00018415571,0.00021218906,0.0001866402,0.0005342476,0.034203473,0.8381328,0.12482785],"study_design_scores_gemma":[0.00007970721,0.0002042138,0.0023328688,0.00076260924,0.00012842807,0.0005187575,0.0016473554,0.00080117915,0.0034371526,0.08305096,0.90693176,0.00010495778],"about_ca_topic_score_codex":0.00066537946,"about_ca_topic_score_gemma":0.0016188757,"teacher_disagreement_score":0.9854169,"about_ca_system_score_codex":0.0028259337,"about_ca_system_score_gemma":0.00979886,"threshold_uncertainty_score":0.31913954},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3116767,0.6228138,0.008050878,0.0064136717,0.001709285,0.022735469,0.0180766,0.00034951596,0.008174106],"genre_scores_gemma":[0.88991684,0.08431486,0.00871772,0.0014911786,0.00022743658,0.010221937,0.0037806022,0.000059682963,0.0012697994],"study_design_codex":"meta_analysis","study_design_gemma":"systematic_review","domain_scores_codex":[0.934086,0.043896284,0.0057422477,0.002319257,0.012267266,0.0016888313],"domain_scores_gemma":[0.89746624,0.05419417,0.0132257575,0.0033868963,0.028053442,0.003673575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.059121016,0.0022568111,0.0077091428,0.0060642064,0.0030198595,0.0026265113,0.0030676136,0.0018441657,0.0035732293],"category_scores_gemma":[0.13470954,0.0010837994,0.013379367,0.011514155,0.0018507369,0.0010837152,0.0019073308,0.0018906947,0.00014161416],"study_design_candidate":"systematic_review","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":[0.04153133,0.0014608236,0.07693619,0.1886291,0.551327,0.00037737217,0.0018841375,0.007328368,0.0004384176,0.0012158782,0.011884665,0.11698665],"study_design_scores_gemma":[0.023381345,0.004042233,0.10628773,0.054764505,0.7941281,0.0001302297,0.0013103024,0.002843445,0.00090030214,0.0007556625,0.011236363,0.00021974198],"about_ca_topic_score_codex":0.8252498,"about_ca_topic_score_gemma":0.8805843,"teacher_disagreement_score":0.940879,"about_ca_system_score_codex":0.059720833,"about_ca_system_score_gemma":0.091916814,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09689896,0.32883576,0.14010103,0.20098619,0.0053859637,0.0014564358,0.00026013269,0.00019945331,0.22587597],"genre_scores_gemma":[0.90840894,0.04938227,0.026336297,0.011305368,0.00072045944,0.0012753124,0.00006724575,0.00019973818,0.0023042983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.52860296,0.42184725,0.01577566,0.0049167587,0.025625667,0.0032316144],"domain_scores_gemma":[0.3908407,0.525955,0.015382981,0.016603855,0.048988022,0.002229391],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30277503,0.0010874562,0.0021817104,0.014543129,0.010010002,0.038963802,0.0038425731,0.004154768,0.0031616883],"category_scores_gemma":[0.29179966,0.0010369404,0.0010949287,0.017357161,0.05848233,0.03415407,0.01948835,0.008546423,0.0003056897],"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":[0.00007157081,0.00006373919,0.003018834,0.0073497086,0.0001428703,0.00037028553,0.30386183,0.00057473755,0.00037002677,0.5253039,0.0062312963,0.15264119],"study_design_scores_gemma":[0.000036359706,0.00015665118,0.003618502,0.05463069,0.00022723853,0.0005555096,0.43831676,0.0010558214,0.0019471324,0.18432914,0.3149887,0.00013759712],"about_ca_topic_score_codex":0.007183796,"about_ca_topic_score_gemma":0.0072252005,"teacher_disagreement_score":0.30277503,"about_ca_system_score_codex":0.034880564,"about_ca_system_score_gemma":0.046339437,"threshold_uncertainty_score":0.85980254},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553799,0.0017615671,0.0036136948,0.023684684,0.0001224532,0.00007011365,0.000018735662,0.000009980104,0.015338931],"genre_scores_gemma":[0.9976419,0.0006464068,0.00057259836,0.0007665805,0.000019974463,0.00003265769,0.0000066466487,0.000006346923,0.00030678723],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8663738,0.11689098,0.0037454206,0.0020648635,0.006771905,0.0041529834],"domain_scores_gemma":[0.7996152,0.17019832,0.010816187,0.0036591594,0.010437235,0.0052738595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08793241,0.00048189794,0.00068273675,0.0066203643,0.014186283,0.011658301,0.0018064876,0.0028988735,0.0013371883],"category_scores_gemma":[0.10270011,0.000830257,0.00048654378,0.0051296316,0.029406285,0.006851447,0.012761513,0.0055453973,0.00010129362],"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":[0.00001998086,0.000024099794,0.0074054906,0.00010148211,0.000012670036,0.00039481954,0.9775743,0.00003881319,0.00022602544,0.008731236,0.00021497003,0.005255994],"study_design_scores_gemma":[0.000005371422,0.000041523544,0.004693161,0.00022410734,0.000008124944,0.00018789947,0.9857721,0.00012964303,0.00013143393,0.0019695526,0.0068220003,0.00001521435],"about_ca_topic_score_codex":0.00954307,"about_ca_topic_score_gemma":0.012623825,"teacher_disagreement_score":0.08793241,"about_ca_system_score_codex":0.015636967,"about_ca_system_score_gemma":0.011992319,"threshold_uncertainty_score":0.46503657},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00287946,0.11588673,0.047462843,0.5784533,0.01161708,0.0005793498,0.0019463995,0.0010127864,0.24016203],"genre_scores_gemma":[0.21345817,0.33742645,0.13046846,0.15304205,0.013271632,0.0017773341,0.003250809,0.0014321242,0.14587289],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99055594,0.004246309,0.00082224543,0.00029922492,0.0038616834,0.00021460211],"domain_scores_gemma":[0.91112447,0.0492553,0.006890342,0.0024357329,0.028376633,0.0019174562],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023872172,0.0004787055,0.00054109254,0.005863498,0.0020810785,0.0066194804,0.0026704445,0.002509652,0.018749466],"category_scores_gemma":[0.11689339,0.00036956146,0.000694015,0.0050656283,0.002990815,0.0044505172,0.0021780531,0.003984334,0.0077754357],"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":[0.00004272823,0.000025165338,0.0013500766,0.0007730697,0.00002637129,0.000040523664,0.00081434136,0.00012871824,0.00023041308,0.006956711,0.74145436,0.24815756],"study_design_scores_gemma":[0.000036549543,0.00009172689,0.0134540545,0.007995787,0.00014329213,0.00034084608,0.0020730882,0.0006848803,0.001692793,0.028754422,0.94462806,0.00010447655],"about_ca_topic_score_codex":0.036257427,"about_ca_topic_score_gemma":0.10442495,"teacher_disagreement_score":0.9761278,"about_ca_system_score_codex":0.005884761,"about_ca_system_score_gemma":0.008834197,"threshold_uncertainty_score":0.12624961},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059782877,0.023710448,0.118903615,0.32757664,0.01065141,0.0017333917,0.00014370697,0.0002858118,0.51101667],"genre_scores_gemma":[0.36149502,0.034417078,0.20966816,0.14610238,0.0024831812,0.0061491304,0.00030140026,0.0003855549,0.23899807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9088609,0.07219876,0.0021555808,0.004304075,0.010675388,0.0018052123],"domain_scores_gemma":[0.8790336,0.09656194,0.0029177181,0.0065284893,0.0097318515,0.005226346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06685122,0.0011665334,0.0011778667,0.0028932283,0.0054234215,0.012432669,0.0029082336,0.006777431,0.020305548],"category_scores_gemma":[0.096168794,0.000761039,0.0011653184,0.0021026114,0.016783183,0.008606417,0.00776534,0.009852443,0.0046798787],"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":[0.00007042478,0.00029229315,0.0011269061,0.0010538688,0.000051017705,0.00016052631,0.014592571,0.00048939226,0.00031112443,0.735293,0.09507395,0.15148501],"study_design_scores_gemma":[0.00007382924,0.00020643655,0.0006447788,0.0026298945,0.000028628516,0.0002456587,0.017576477,0.00071880413,0.0006514013,0.3171775,0.65998846,0.000058088335],"about_ca_topic_score_codex":0.0025749404,"about_ca_topic_score_gemma":0.003723553,"teacher_disagreement_score":0.9331488,"about_ca_system_score_codex":0.0055147605,"about_ca_system_score_gemma":0.013939611,"threshold_uncertainty_score":0.35354728},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010252086,0.038249716,0.21421328,0.6635755,0.017439513,0.0006605107,0.00012637358,0.00037353675,0.05510946],"genre_scores_gemma":[0.4910052,0.020810269,0.2443148,0.2005197,0.017811807,0.0041997274,0.00007019225,0.00079404283,0.020474236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.49071953,0.45979035,0.012340705,0.009000415,0.024350883,0.0037982096],"domain_scores_gemma":[0.5486373,0.376872,0.02388359,0.019292204,0.023057243,0.008257632],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26702595,0.0022785466,0.0032130417,0.016158033,0.021994548,0.025374506,0.0054710256,0.020958707,0.0044957157],"category_scores_gemma":[0.36740777,0.0018672238,0.0021292889,0.012750619,0.14758787,0.050066784,0.022117816,0.017189497,0.0020967496],"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":[0.00017459756,0.00004633201,0.00081192504,0.0012118699,0.000056686884,0.00057521067,0.13060509,0.00020816276,0.0006053392,0.8203541,0.027372759,0.017977837],"study_design_scores_gemma":[0.00024536342,0.0002054335,0.00037154884,0.0034992758,0.000077146746,0.0014062778,0.04612417,0.0008762208,0.0006110827,0.5571727,0.3892195,0.00019130274],"about_ca_topic_score_codex":0.003952457,"about_ca_topic_score_gemma":0.004362614,"teacher_disagreement_score":0.73297405,"about_ca_system_score_codex":0.008874341,"about_ca_system_score_gemma":0.024575545,"threshold_uncertainty_score":0.9038875},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19110748,0.00050101936,0.55653244,0.002775743,0.00077069196,0.23036909,0.00036743746,0.0009154734,0.016660692],"genre_scores_gemma":[0.10170646,0.00027566907,0.6244973,0.0012781159,0.00010647184,0.2665953,0.00011128408,0.00019043699,0.0052390113],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94899136,0.04069931,0.0018971501,0.0039764433,0.0027261234,0.0017095278],"domain_scores_gemma":[0.94466925,0.039273925,0.0016984529,0.0059833946,0.0055828574,0.0027922315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.074287735,0.0012381367,0.0010963028,0.0021844828,0.0036294954,0.0036149381,0.0032164918,0.0019359696,0.014001743],"category_scores_gemma":[0.0516646,0.0012432495,0.001172641,0.0014764736,0.0064030085,0.0014014202,0.0079083955,0.0036767824,0.00199722],"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":[0.0042703077,0.0098330155,0.0072041284,0.0065306746,0.00022177075,0.0011447903,0.2373666,0.0058492394,0.037296094,0.040204,0.013192818,0.63688666],"study_design_scores_gemma":[0.014046562,0.032074794,0.028319245,0.007547214,0.00049731066,0.0023337672,0.15920371,0.029827721,0.045954473,0.14946228,0.5299798,0.000753058],"about_ca_topic_score_codex":0.0005679262,"about_ca_topic_score_gemma":0.0013944024,"teacher_disagreement_score":0.074287735,"about_ca_system_score_codex":0.003312769,"about_ca_system_score_gemma":0.00735927,"threshold_uncertainty_score":0.3928758},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16775867,0.0009167347,0.6970684,0.0054526,0.00011611208,0.00083296694,0.00025029792,0.0009939888,0.12661032],"genre_scores_gemma":[0.69724655,0.00054120994,0.26204875,0.00027798218,0.000051969753,0.00086778513,0.00024167963,0.00027194418,0.038452215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9779494,0.010881658,0.0011502905,0.00310815,0.0057771136,0.0011334098],"domain_scores_gemma":[0.9369294,0.037655234,0.0053625465,0.008580119,0.0090491725,0.0024236075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021367637,0.00081741664,0.0006328425,0.0030444376,0.0041155186,0.010631842,0.002658244,0.0021185877,0.015292569],"category_scores_gemma":[0.05625968,0.0014016391,0.0014901352,0.0028617354,0.011253789,0.014142151,0.008666079,0.003229559,0.0028039133],"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":[0.00032095308,0.00014915595,0.01861702,0.0007857302,0.00008976646,0.00055502146,0.123716846,0.0036918935,0.009702024,0.70907724,0.0016995532,0.13159469],"study_design_scores_gemma":[0.00015103036,0.0008811897,0.03162184,0.0011802693,0.00027935475,0.0014417956,0.065102756,0.038071435,0.029120024,0.51546395,0.3163627,0.00032371713],"about_ca_topic_score_codex":0.01059186,"about_ca_topic_score_gemma":0.011147729,"teacher_disagreement_score":0.021367637,"about_ca_system_score_codex":0.006725136,"about_ca_system_score_gemma":0.010524849,"threshold_uncertainty_score":0.11300421},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016404372,0.0017093486,0.9071468,0.030532679,0.0004452469,0.009705694,0.000060995302,0.00020804933,0.033786748],"genre_scores_gemma":[0.257771,0.0006421912,0.7306971,0.001381565,0.00008369256,0.007610059,0.000035502948,0.000059179678,0.0017196822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.39187846,0.5616597,0.011106796,0.005195627,0.02610277,0.00405663],"domain_scores_gemma":[0.618196,0.28757718,0.011649317,0.01975302,0.05612039,0.0067041786],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4249276,0.0017186488,0.0015341225,0.005782678,0.015969858,0.015052219,0.005366095,0.0050812108,0.0035581612],"category_scores_gemma":[0.26664072,0.0013649715,0.001397669,0.0051499833,0.033774454,0.013109619,0.019965166,0.00888994,0.000460148],"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":[0.00017209622,0.0004840343,0.0032339226,0.002355772,0.00015608539,0.00083171984,0.10121861,0.007509625,0.0012426988,0.65374094,0.006217145,0.22283748],"study_design_scores_gemma":[0.00039748676,0.00075290236,0.002043,0.0077928146,0.00018568334,0.0007374353,0.06311563,0.029319959,0.004019943,0.7673873,0.12393216,0.00031577426],"about_ca_topic_score_codex":0.014975123,"about_ca_topic_score_gemma":0.020905608,"teacher_disagreement_score":0.5750724,"about_ca_system_score_codex":0.025683282,"about_ca_system_score_gemma":0.09186479,"threshold_uncertainty_score":0.70916665},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013134537,0.47742856,0.0015683902,0.24674101,0.2428937,0.00026913514,0.00035506126,0.0001983048,0.030414464],"genre_scores_gemma":[0.0019339853,0.43140647,0.002072028,0.1749949,0.14908795,0.0005657579,0.000645766,0.00033774058,0.23895542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995204,0.001198054,0.0003003854,0.0004062955,0.0027244606,0.00016675588],"domain_scores_gemma":[0.96521574,0.017446388,0.0013129065,0.0007720119,0.013664436,0.0015886504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058504627,0.0014932454,0.002076463,0.004089099,0.0015389734,0.0058059855,0.0025807335,0.005133337,0.032494657],"category_scores_gemma":[0.027390104,0.00065927714,0.0010088427,0.0046479106,0.002752365,0.0048344866,0.0019859653,0.006525231,0.03068088],"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":[0.0000044990106,0.0000042069782,0.000012806226,0.00026852707,0.0000028203724,0.000006893593,0.000010587988,0.000015037273,0.000016209673,0.00035556348,0.98006755,0.0192353],"study_design_scores_gemma":[0.0000079149995,0.000012704154,0.00012601414,0.0010072334,0.0000059955605,0.00006008431,0.000032873537,0.000023583158,0.000033123342,0.0008690794,0.9978119,0.0000096196245],"about_ca_topic_score_codex":0.010461472,"about_ca_topic_score_gemma":0.032236196,"teacher_disagreement_score":0.032494657,"about_ca_system_score_codex":0.0043441267,"about_ca_system_score_gemma":0.007468242,"threshold_uncertainty_score":0.10870546},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44770432,0.021360049,0.051675387,0.101855904,0.00052360824,0.002057549,0.0009673847,0.0006673287,0.3731885],"genre_scores_gemma":[0.9772723,0.002604079,0.0062801917,0.0029747158,0.000049056463,0.00036542027,0.00014030452,0.00006286726,0.0102510415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9296283,0.02445621,0.003708207,0.006315358,0.01931901,0.01657296],"domain_scores_gemma":[0.92703354,0.030309893,0.009176481,0.00907002,0.012733674,0.011676387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03380056,0.0006190381,0.00095797866,0.007259853,0.028532298,0.01925522,0.0046108677,0.0034180474,0.006898031],"category_scores_gemma":[0.059633303,0.0009443671,0.00089457387,0.019645661,0.033512585,0.0069141244,0.019490773,0.0036562663,0.00048376466],"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":[0.00014405944,0.00009264606,0.0773031,0.00068238395,0.00011334173,0.0029674447,0.29879534,0.0008772569,0.0011597474,0.5122935,0.011249593,0.094321504],"study_design_scores_gemma":[0.00012239217,0.0000864882,0.078462906,0.0019461695,0.0001765918,0.0013409852,0.32650125,0.0032099641,0.0007939666,0.09806362,0.48905382,0.00024183135],"about_ca_topic_score_codex":0.90417045,"about_ca_topic_score_gemma":0.8991743,"teacher_disagreement_score":0.96619946,"about_ca_system_score_codex":0.13022172,"about_ca_system_score_gemma":0.26025307,"threshold_uncertainty_score":0.94482917},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053988058,0.53772765,0.16687876,0.083785124,0.0023463443,0.0008022091,0.0014352159,0.00028861137,0.15274797],"genre_scores_gemma":[0.7887647,0.14576647,0.055860143,0.0029756268,0.0013100608,0.0016567245,0.0008417051,0.00019324779,0.0026312585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"systematic_review","domain_scores_codex":[0.96967906,0.020721288,0.003073616,0.001290546,0.004380941,0.0008545508],"domain_scores_gemma":[0.7812503,0.19471014,0.0051611955,0.0051480164,0.012765197,0.0009651449],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04813911,0.0009561449,0.0014236037,0.019586958,0.00219312,0.018048061,0.0015795473,0.0016941653,0.005061273],"category_scores_gemma":[0.08660619,0.0005489521,0.00096418237,0.020368159,0.008246149,0.018782018,0.006251995,0.0034657975,0.00028660859],"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":[0.00010491399,0.00014519556,0.01035812,0.01865835,0.00033483506,0.00017801476,0.047715243,0.0038798177,0.0004874363,0.48393613,0.014346263,0.41985565],"study_design_scores_gemma":[0.000029533534,0.00019426466,0.018364098,0.05131261,0.00044682494,0.00033233876,0.09442487,0.007274862,0.002235865,0.44079986,0.38445956,0.00012537473],"about_ca_topic_score_codex":0.0041358196,"about_ca_topic_score_gemma":0.004159071,"teacher_disagreement_score":0.9518609,"about_ca_system_score_codex":0.013427143,"about_ca_system_score_gemma":0.015534406,"threshold_uncertainty_score":0.254587},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006869258,0.92166764,0.010961566,0.022963976,0.004367459,0.00020837791,0.00021983376,0.00019834243,0.03872588],"genre_scores_gemma":[0.0056492966,0.9532645,0.016689291,0.0019514689,0.00097054895,0.00025560745,0.0003119948,0.00014679196,0.020760674],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99326915,0.002467746,0.0005077209,0.0008159444,0.0026639318,0.0002755415],"domain_scores_gemma":[0.9813875,0.013415351,0.0012103207,0.00051214243,0.0024558417,0.001018921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010262148,0.0020391704,0.0023140316,0.0065724016,0.0036730918,0.0129016405,0.0026788905,0.0047922553,0.017427225],"category_scores_gemma":[0.015481805,0.002399786,0.0011826662,0.012094111,0.0064457045,0.01433517,0.0036701856,0.008107489,0.011411603],"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":[0.000055113578,0.00004813322,0.00071462226,0.005710562,0.00004862718,0.00014795846,0.006261734,0.00047636442,0.00040799068,0.025263779,0.37957397,0.5812912],"study_design_scores_gemma":[0.000012452636,0.000051111732,0.0013022912,0.005909358,0.00004308269,0.00029398748,0.0025105262,0.00015971067,0.00034316134,0.020002233,0.96930254,0.00006962022],"about_ca_topic_score_codex":0.019707514,"about_ca_topic_score_gemma":0.033343293,"teacher_disagreement_score":0.019707514,"about_ca_system_score_codex":0.005451299,"about_ca_system_score_gemma":0.016772369,"threshold_uncertainty_score":0.0582999},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09482811,0.026750667,0.42741123,0.1453155,0.0012709525,0.0025481684,0.0008232766,0.00030709483,0.30074495],"genre_scores_gemma":[0.8634875,0.0033460448,0.12174327,0.0033681856,0.00023231305,0.0026783335,0.0002177558,0.000093439165,0.0048331884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8129813,0.14845833,0.0051439675,0.0043326505,0.02667547,0.0024082633],"domain_scores_gemma":[0.77883077,0.17392251,0.009412893,0.007874613,0.0267415,0.003217696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.119195886,0.0016735954,0.0016548935,0.010771746,0.0054484867,0.031712938,0.005024107,0.0070257005,0.010042531],"category_scores_gemma":[0.15208401,0.00094676175,0.0021092512,0.008276842,0.040096506,0.024413481,0.0068817437,0.010375278,0.00048705656],"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":[0.00014438127,0.0001936597,0.0023892852,0.0007824391,0.00008975471,0.000052110372,0.008708178,0.005012575,0.00012573358,0.9425826,0.0018797584,0.038039513],"study_design_scores_gemma":[0.00025327574,0.0003448152,0.0066158976,0.004207041,0.00020402344,0.00015960226,0.017888172,0.022130266,0.0011643197,0.8893021,0.05758975,0.00014075261],"about_ca_topic_score_codex":0.018038189,"about_ca_topic_score_gemma":0.016715853,"teacher_disagreement_score":0.119195886,"about_ca_system_score_codex":0.04303408,"about_ca_system_score_gemma":0.022439405,"threshold_uncertainty_score":0.6303756},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92318267,0.00037781885,0.0004947544,0.0075684753,0.0000237358,0.00021004933,0.0001990637,0.000011701821,0.067931764],"genre_scores_gemma":[0.97720873,0.0006904469,0.0005683532,0.00037884185,0.000010014929,0.0001031453,0.000080069745,0.000009471262,0.020950945],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99533856,0.0016360265,0.000111268266,0.0002243374,0.0008861947,0.0018035948],"domain_scores_gemma":[0.994017,0.0031547926,0.0005655592,0.00023473971,0.00084344984,0.0011843727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027480533,0.00026884503,0.00036640788,0.0018119522,0.023558844,0.0044123917,0.0018054622,0.0023084418,0.004565812],"category_scores_gemma":[0.008177883,0.0004158387,0.0002498454,0.004841066,0.0077671595,0.0022015425,0.0031220496,0.001971157,0.00028833223],"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":[0.00015554529,0.00064715545,0.059287608,0.000274509,0.000017527338,0.011198374,0.7890001,0.0017506824,0.0010015075,0.0894144,0.013818602,0.033434004],"study_design_scores_gemma":[0.000041690044,0.00013065086,0.048687316,0.00025795482,0.000019958854,0.00038635038,0.79669327,0.0011354852,0.0005257452,0.0021456685,0.14994235,0.000033543038],"about_ca_topic_score_codex":0.95829284,"about_ca_topic_score_gemma":0.98350936,"teacher_disagreement_score":0.8704083,"about_ca_system_score_codex":0.12959167,"about_ca_system_score_gemma":0.099839166,"threshold_uncertainty_score":0.9402578},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9370736,0.005468234,0.00041313807,0.0073132142,0.00006112651,0.00046091282,0.0004952223,0.00002116767,0.048693392],"genre_scores_gemma":[0.9927551,0.0013124077,0.0003631284,0.0006278462,0.000006479214,0.000052848045,0.00011059308,0.000004962312,0.004766644],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9846831,0.005057123,0.00072348875,0.0007922158,0.0038755175,0.004868557],"domain_scores_gemma":[0.95778954,0.013754994,0.0037260894,0.0010351078,0.018103477,0.005590808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010453118,0.00017811924,0.0005169641,0.0033490702,0.017995546,0.0065962113,0.002400391,0.0014520888,0.0024013002],"category_scores_gemma":[0.03135951,0.00052985107,0.0003424134,0.011961318,0.004020234,0.0016990376,0.0031775045,0.0020554683,0.00012088768],"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":true,"study_design_scores_codex":[0.00039428638,0.00039313163,0.3766084,0.0023306177,0.0002135647,0.010108935,0.38677496,0.002399863,0.0018704924,0.049338,0.033506475,0.1360613],"study_design_scores_gemma":[0.000038872124,0.00015231698,0.46291763,0.00089917134,0.000111611276,0.0007740734,0.4235916,0.0010865028,0.00043611653,0.00087822526,0.10902504,0.00008879006],"about_ca_topic_score_codex":0.9918162,"about_ca_topic_score_gemma":0.99723035,"teacher_disagreement_score":0.8268748,"about_ca_system_score_codex":0.17312522,"about_ca_system_score_gemma":0.22892408,"threshold_uncertainty_score":0.95905757},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01652556,0.014569134,0.49212083,0.2630203,0.006413016,0.072589785,0.0022144506,0.004602902,0.12794407],"genre_scores_gemma":[0.0773038,0.004425315,0.8518768,0.016734995,0.0005076601,0.038096357,0.0009878951,0.0007239826,0.0093432255],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5471944,0.39518154,0.022779997,0.006733748,0.020418435,0.0076918136],"domain_scores_gemma":[0.6285377,0.24325643,0.012994417,0.04201299,0.04077398,0.03242454],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3878057,0.0013167434,0.0023710534,0.0063178865,0.0048621725,0.015821487,0.0072796196,0.007501647,0.022430105],"category_scores_gemma":[0.34652376,0.0017751718,0.004071611,0.005066448,0.0073577655,0.018767292,0.042260565,0.01064381,0.007408451],"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":[0.0003000848,0.0011333115,0.003929889,0.0118992245,0.0002144448,0.0006291862,0.03003563,0.0025576386,0.00052419864,0.07243295,0.06268521,0.81365824],"study_design_scores_gemma":[0.0008319604,0.0017359144,0.008645195,0.08837197,0.0004631973,0.0014629907,0.022094242,0.005950167,0.001843193,0.16917276,0.6990341,0.00039427698],"about_ca_topic_score_codex":0.0052098744,"about_ca_topic_score_gemma":0.0092607,"teacher_disagreement_score":0.6121943,"about_ca_system_score_codex":0.019978018,"about_ca_system_score_gemma":0.14612736,"threshold_uncertainty_score":0.75494456},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039674705,0.0050950036,0.0013507886,0.006946775,0.0015869747,0.000025975523,0.0001540737,0.000042516305,0.98440117],"genre_scores_gemma":[0.021620229,0.007270271,0.0029680328,0.005861319,0.00085861795,0.00014533075,0.00035464228,0.00012656259,0.9607949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974825,0.0008229489,0.0000968441,0.00030767778,0.0010050108,0.00028507668],"domain_scores_gemma":[0.9991941,0.00026903418,0.000041740317,0.00013115142,0.00030506332,0.000058987025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027939556,0.0010686183,0.00049715425,0.002459165,0.0035872974,0.008999945,0.0011607363,0.0045660855,0.050550535],"category_scores_gemma":[0.006621795,0.00040476208,0.00060799246,0.0022774844,0.0026553555,0.005921417,0.0029580053,0.0059167794,0.012174057],"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":[0.0000068755085,0.000012088179,0.000077310906,0.000053014035,0.0000037088466,0.000061118015,0.00036025918,0.00020584885,0.00007048502,0.802285,0.16464071,0.032223534],"study_design_scores_gemma":[0.0000012439435,0.0000030875076,0.00012960637,0.00016451262,0.0000018529454,0.000060765964,0.00018104383,0.00008216548,0.000089352485,0.060757346,0.93852323,0.00000590525],"about_ca_topic_score_codex":0.017380582,"about_ca_topic_score_gemma":0.02627587,"teacher_disagreement_score":0.050550535,"about_ca_system_score_codex":0.0053059054,"about_ca_system_score_gemma":0.005158241,"threshold_uncertainty_score":0.16910839},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97395587,0.00022647437,0.010943259,0.0005254866,0.00010086744,0.008986772,0.0005402564,0.00006029265,0.0046607177],"genre_scores_gemma":[0.96405023,0.00011964524,0.016907549,0.00019298909,0.000029106723,0.017583115,0.00038477546,0.000025780462,0.00070676877],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.88557833,0.079877056,0.014173015,0.0014914083,0.017317813,0.001562458],"domain_scores_gemma":[0.7400023,0.18005954,0.023584498,0.0071676355,0.044733368,0.004452685],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1516111,0.00048082013,0.0008418028,0.0022355171,0.001069703,0.0013417689,0.0014463726,0.0007988392,0.0018692387],"category_scores_gemma":[0.19294167,0.000486676,0.0012889814,0.0018792008,0.0015811055,0.001736898,0.0028595359,0.0010899849,0.00025544493],"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":[0.005717937,0.004540256,0.6783242,0.002896255,0.0007728072,0.00042231946,0.042857956,0.0025444967,0.004593725,0.0035544336,0.0067184293,0.24705707],"study_design_scores_gemma":[0.0018966952,0.014978098,0.9214504,0.0012914431,0.0002610926,0.00043125497,0.020288117,0.010598962,0.0059035104,0.0019163499,0.020767365,0.00021663634],"about_ca_topic_score_codex":0.0024194806,"about_ca_topic_score_gemma":0.0036177866,"teacher_disagreement_score":0.8483889,"about_ca_system_score_codex":0.0032839754,"about_ca_system_score_gemma":0.005469129,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081697494,0.00824846,0.33451667,0.2171474,0.017344417,0.017740548,0.0025719777,0.0031966423,0.31753644],"genre_scores_gemma":[0.2958522,0.004081074,0.5367998,0.039232172,0.0021935478,0.01207952,0.003632643,0.000978248,0.10515076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.88880754,0.037600435,0.021346502,0.0049898676,0.042268284,0.004987479],"domain_scores_gemma":[0.6864768,0.03925582,0.008575617,0.023880186,0.23124447,0.010567108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18069564,0.00066765,0.0010354877,0.006238651,0.005492556,0.009997521,0.003408761,0.004341743,0.0019185616],"category_scores_gemma":[0.14873894,0.0010523123,0.0014965031,0.003519826,0.0050548804,0.0053131073,0.006609752,0.01078417,0.0008839285],"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":[0.00014747678,0.00048868655,0.010483503,0.0012979776,0.00009073857,0.00043144985,0.010622304,0.0015346431,0.00555957,0.38266712,0.27981877,0.3068577],"study_design_scores_gemma":[0.00007769376,0.00024154942,0.022324525,0.0018339871,0.00010036749,0.00028735303,0.002916777,0.0025351816,0.0039157704,0.031523522,0.9340553,0.00018802706],"about_ca_topic_score_codex":0.0314597,"about_ca_topic_score_gemma":0.03636597,"teacher_disagreement_score":0.18069564,"about_ca_system_score_codex":0.016892092,"about_ca_system_score_gemma":0.1264432,"threshold_uncertainty_score":0.9556213},"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":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033441513,0.029498605,0.0006124618,0.04683821,0.9208824,0.00004040631,0.00017846133,0.000063612686,0.0018523016],"genre_scores_gemma":[0.0012688966,0.034860756,0.0008535041,0.034494918,0.91924936,0.00009040331,0.000093442,0.000051826155,0.009036931],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98493123,0.0040476574,0.0027438016,0.00080917834,0.007082886,0.00038524152],"domain_scores_gemma":[0.86560124,0.09262697,0.0032601324,0.0025853526,0.03285748,0.0030689146],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.023778446,0.004497938,0.0074595455,0.006859794,0.0032848185,0.009844022,0.008824149,0.027296524,0.009612176],"category_scores_gemma":[0.1250006,0.0020162084,0.0035983163,0.0044501857,0.006672973,0.007321659,0.0019833266,0.02923456,0.007949504],"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":[0.00003698855,0.000010245825,0.000017073418,0.00074189476,0.00004723699,0.000088442575,0.00001594903,0.00006082245,0.00001523922,0.0020591903,0.99078596,0.0061209938],"study_design_scores_gemma":[0.00015024624,0.000046941303,0.0004343168,0.0026706334,0.00025952625,0.00029495134,0.00007189944,0.00051129813,0.00016086038,0.015858736,0.97948265,0.000057807654],"about_ca_topic_score_codex":0.0054221223,"about_ca_topic_score_gemma":0.012666894,"teacher_disagreement_score":0.9931402,"about_ca_system_score_codex":0.0047889883,"about_ca_system_score_gemma":0.00797397,"threshold_uncertainty_score":0.125754},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9237253,0.0060277604,0.0023683778,0.0108404,0.00016723183,0.0009058003,0.00025233606,0.00027007758,0.055442743],"genre_scores_gemma":[0.9734307,0.0016405262,0.0025567366,0.0011549201,0.00001229182,0.00015539421,0.00010147572,0.000046123634,0.020901885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98632807,0.006119497,0.0007971619,0.0013272411,0.0028604174,0.0025675215],"domain_scores_gemma":[0.9655654,0.012343639,0.0012550829,0.0014582833,0.011678639,0.0076989434],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009884069,0.00030064903,0.0005647361,0.0031127215,0.016313966,0.0064569092,0.0032339827,0.001820092,0.005626115],"category_scores_gemma":[0.02819898,0.00088892947,0.00020731025,0.0065664104,0.005139784,0.0015606215,0.005200499,0.0023957938,0.0004289747],"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":[0.0005317036,0.0012045909,0.14277913,0.002439563,0.00010142293,0.004029906,0.28844473,0.0034557541,0.0053323642,0.017054433,0.029469617,0.50515676],"study_design_scores_gemma":[0.00010917429,0.0006186672,0.29843965,0.0017152749,0.00007224311,0.00064818887,0.43667826,0.0025763449,0.0024395252,0.0023978543,0.25396168,0.00034318143],"about_ca_topic_score_codex":0.9418538,"about_ca_topic_score_gemma":0.9766898,"teacher_disagreement_score":0.99011594,"about_ca_system_score_codex":0.10086885,"about_ca_system_score_gemma":0.1632295,"threshold_uncertainty_score":0.73185813},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105037436,0.017773287,0.0054232273,0.45601204,0.02908156,0.0035749585,0.13937055,0.0015292197,0.24219769],"genre_scores_gemma":[0.27956176,0.02077294,0.0101018725,0.118301466,0.014858091,0.0050145146,0.06314526,0.00045079296,0.4877934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926523,0.0015172622,0.0009479114,0.00032966255,0.0038429867,0.0007097745],"domain_scores_gemma":[0.9642107,0.0074361865,0.0030886752,0.0015702702,0.017431024,0.0062632076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007155336,0.0003522191,0.00033403776,0.0019067026,0.0006813139,0.0016330681,0.0008827376,0.0026385905,0.016643595],"category_scores_gemma":[0.024164231,0.00027434557,0.00027948045,0.0015483386,0.00034459552,0.00073216733,0.0017380294,0.0014192833,0.005970969],"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":[0.00069831946,0.0002493776,0.02067206,0.00039109102,0.000037585527,0.0007928208,0.00035293298,0.00015339156,0.00063068623,0.00069007085,0.93100435,0.04432736],"study_design_scores_gemma":[0.00031528852,0.0005520188,0.114481494,0.00045819444,0.000076884615,0.0006525197,0.0016489166,0.0003569401,0.0018131097,0.0005201502,0.8790622,0.00006234464],"about_ca_topic_score_codex":0.028665181,"about_ca_topic_score_gemma":0.03519903,"teacher_disagreement_score":0.028665181,"about_ca_system_score_codex":0.002098652,"about_ca_system_score_gemma":0.011037571,"threshold_uncertainty_score":0.056996644},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96771294,0.001314468,0.008595064,0.0049813013,0.00008822577,0.0014600813,0.00007241464,0.00002381363,0.015751602],"genre_scores_gemma":[0.99143547,0.00068603037,0.0038912424,0.00055535935,0.000018894536,0.00061433786,0.000028844874,0.000012828003,0.0027569328],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9543534,0.039448403,0.00084653764,0.0010832141,0.0014866857,0.0027817213],"domain_scores_gemma":[0.9613762,0.027658189,0.0028765753,0.0009843791,0.0032547396,0.0038498505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032907538,0.00075539586,0.0008920421,0.0025370617,0.024537794,0.005210638,0.0024025661,0.003325652,0.002679135],"category_scores_gemma":[0.030844258,0.00057229534,0.00041810639,0.0032428438,0.011461879,0.004930362,0.007356704,0.0027990432,0.0002810334],"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":[0.00006012349,0.00028811258,0.0035890045,0.0002604842,0.000006975095,0.005439089,0.9749649,0.00021525464,0.0007408495,0.004223035,0.0005518249,0.0096602],"study_design_scores_gemma":[0.00000613571,0.000119482575,0.0013330108,0.00027529767,0.000004546364,0.0005531263,0.98637795,0.00022528232,0.00034723344,0.00052191823,0.010223815,0.000012131444],"about_ca_topic_score_codex":0.015071226,"about_ca_topic_score_gemma":0.02724653,"teacher_disagreement_score":0.96709245,"about_ca_system_score_codex":0.01297231,"about_ca_system_score_gemma":0.010520987,"threshold_uncertainty_score":0.17403376},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029815198,0.15892255,0.0014917868,0.23621106,0.59937656,0.00010842598,0.00037717182,0.00009267224,0.0031216678],"genre_scores_gemma":[0.01121697,0.07548496,0.003226754,0.07091609,0.83411014,0.00042999303,0.0003712218,0.00012992624,0.0041139517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.89316773,0.036037855,0.030187704,0.0050394405,0.03360971,0.0019575695],"domain_scores_gemma":[0.49413362,0.36737087,0.030423755,0.008322429,0.09017975,0.009569489],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07778951,0.003531551,0.011731861,0.015576584,0.0019631865,0.014860137,0.004660449,0.01950505,0.0095214695],"category_scores_gemma":[0.43986064,0.0020712218,0.004920575,0.009977987,0.006941981,0.007116592,0.0040220483,0.032664612,0.0029185475],"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":[0.00040851563,0.00007065672,0.0010277783,0.0073036496,0.0011077238,0.00014996695,0.00012469139,0.00018436664,0.000060118353,0.0067328434,0.8921276,0.09070214],"study_design_scores_gemma":[0.0019048112,0.00032729076,0.014312281,0.033300173,0.0045176726,0.001600637,0.00047289074,0.002266537,0.00046967805,0.05943965,0.8808973,0.0004910935],"about_ca_topic_score_codex":0.0026895558,"about_ca_topic_score_gemma":0.0045716567,"teacher_disagreement_score":0.9222105,"about_ca_system_score_codex":0.009340479,"about_ca_system_score_gemma":0.009804186,"threshold_uncertainty_score":0.41139513},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14974032,0.0017346425,0.7445137,0.0374818,0.0021043443,0.020748613,0.00015142848,0.0010052194,0.042519953],"genre_scores_gemma":[0.3755807,0.00083946297,0.5891534,0.003216622,0.00046454166,0.0166959,0.00009724488,0.00028893456,0.0136631355],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.74089193,0.23254107,0.004987118,0.0076665888,0.01078797,0.0031252934],"domain_scores_gemma":[0.7499968,0.18895167,0.006161452,0.02066357,0.020879969,0.013346542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14600721,0.0013987615,0.0012591442,0.0044977646,0.01971805,0.012829769,0.0066697686,0.0050284946,0.0049377577],"category_scores_gemma":[0.18146625,0.0014245734,0.0013502056,0.0024854832,0.016536325,0.010469115,0.033219848,0.007290609,0.0014015163],"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":[0.00019354337,0.0008530092,0.0015506153,0.00054882775,0.00003871768,0.0016437434,0.76572835,0.0006218746,0.003084611,0.03524829,0.0064316955,0.18405664],"study_design_scores_gemma":[0.0004697274,0.0012348907,0.0013231649,0.0021105816,0.000092467206,0.0027876955,0.616082,0.0055151167,0.006378233,0.11492974,0.24879146,0.00028491372],"about_ca_topic_score_codex":0.0010530856,"about_ca_topic_score_gemma":0.002644558,"teacher_disagreement_score":0.14600721,"about_ca_system_score_codex":0.006277581,"about_ca_system_score_gemma":0.028056059,"threshold_uncertainty_score":0.7721692},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6214244,0.003697951,0.032168176,0.05878352,0.000508518,0.0037312438,0.003783906,0.0008280601,0.2750743],"genre_scores_gemma":[0.9183973,0.000690714,0.030956216,0.0032077578,0.000029001325,0.00074161123,0.00090870867,0.00006191925,0.045006767],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9911975,0.0038458358,0.00026091022,0.00055569405,0.002985145,0.0011548835],"domain_scores_gemma":[0.98981875,0.0017552987,0.00044980404,0.00045492416,0.0056397705,0.0018814552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009703834,0.00037479206,0.0002843555,0.0021542935,0.0033669246,0.0053818333,0.0023614136,0.0017134021,0.008186911],"category_scores_gemma":[0.01289024,0.00019563234,0.00037100998,0.002970243,0.0017612426,0.0016794429,0.0022919865,0.0017205194,0.00033448802],"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":[0.0009304138,0.002716745,0.07613833,0.0010099484,0.0004075244,0.0009733275,0.01420956,0.031714927,0.005609974,0.26175123,0.090416566,0.5141214],"study_design_scores_gemma":[0.0009356543,0.0029427984,0.38673007,0.0023236775,0.0007313408,0.00051729596,0.037071582,0.07313024,0.007856205,0.046446968,0.4408582,0.0004559091],"about_ca_topic_score_codex":0.9405736,"about_ca_topic_score_gemma":0.9758428,"teacher_disagreement_score":0.0712369,"about_ca_system_score_codex":0.0712369,"about_ca_system_score_gemma":0.16216923,"threshold_uncertainty_score":0.5168623},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012910493,0.023038775,0.46730095,0.27132773,0.008751486,0.0071683186,0.00035194805,0.0037728837,0.21699683],"genre_scores_gemma":[0.041603275,0.016698562,0.8146741,0.052917644,0.0038766027,0.016579764,0.00037023923,0.0018621327,0.051417705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7742114,0.1659277,0.019250141,0.006354777,0.03036589,0.0038900063],"domain_scores_gemma":[0.68337476,0.22002013,0.006454085,0.026472269,0.051969383,0.011709416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21263112,0.0022849415,0.0024138535,0.008715734,0.0100725265,0.03251008,0.007877892,0.019016217,0.018107325],"category_scores_gemma":[0.25014442,0.0023208272,0.002562071,0.0070404895,0.037250783,0.02168218,0.019849751,0.023697082,0.015534886],"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":[0.00006658801,0.00030794388,0.0005090018,0.0024359904,0.000033255434,0.0005266589,0.0143352095,0.0008315057,0.0002575877,0.53163487,0.27937043,0.16969095],"study_design_scores_gemma":[0.000085058935,0.0000782643,0.0002732044,0.008027175,0.000020777228,0.0005196958,0.008111308,0.00085722265,0.00038921676,0.25471017,0.726855,0.000072987925],"about_ca_topic_score_codex":0.005532323,"about_ca_topic_score_gemma":0.006472848,"teacher_disagreement_score":0.21263112,"about_ca_system_score_codex":0.014700657,"about_ca_system_score_gemma":0.036042467,"threshold_uncertainty_score":0.970966},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011646611,0.04713371,0.001163851,0.22788705,0.038336623,0.00010609002,0.0047713337,0.0002392462,0.66871554],"genre_scores_gemma":[0.048849475,0.02529897,0.00096065755,0.08648343,0.001588489,0.00015367221,0.0015486885,0.00022441249,0.8348922],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989748,0.00011693551,0.00007788558,0.00024696765,0.00026983456,0.00031362608],"domain_scores_gemma":[0.99835336,0.0002470467,0.00008514751,0.00015613854,0.00072782516,0.0004305353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081237627,0.0004731074,0.00046379835,0.0011797682,0.006004902,0.005211202,0.0014677884,0.0032297233,0.11470593],"category_scores_gemma":[0.0024651918,0.00047160775,0.00049304,0.002492724,0.0022691975,0.0028885866,0.003259796,0.007151722,0.016331669],"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":[0.00006593069,0.000025905969,0.0026262987,0.00023057965,0.000024696179,0.0014647242,0.001382937,0.000120225515,0.00057965884,0.07450862,0.84148073,0.077489726],"study_design_scores_gemma":[0.0000054679767,0.0000026054843,0.0023369093,0.00014216945,0.0000048396264,0.00015464067,0.0007550073,0.00001889631,0.00005917485,0.0017728424,0.9947336,0.000013958961],"about_ca_topic_score_codex":0.8082353,"about_ca_topic_score_gemma":0.9440134,"teacher_disagreement_score":0.19176471,"about_ca_system_score_codex":0.020789366,"about_ca_system_score_gemma":0.0498086,"threshold_uncertainty_score":0.38578808},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14800951,0.021168642,0.19562393,0.038422924,0.0029904146,0.0017112964,0.0037930561,0.007946975,0.58033323],"genre_scores_gemma":[0.73005825,0.008638141,0.22125648,0.001685225,0.0004724922,0.0013145992,0.002864699,0.0008385614,0.03287153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9680062,0.019325644,0.002654994,0.0016432406,0.0074253264,0.0009445498],"domain_scores_gemma":[0.819529,0.12295961,0.007801091,0.023075081,0.022215981,0.004419235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024938468,0.00069784484,0.00060572283,0.005826582,0.0022468807,0.00850695,0.0015450234,0.0013368763,0.021513827],"category_scores_gemma":[0.15644242,0.00038638007,0.0004783725,0.004775977,0.0030969868,0.0088158585,0.0052914913,0.0013155587,0.005792418],"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":[0.00022137901,0.00029476173,0.005310581,0.0027595756,0.00007305236,0.000116952615,0.009268234,0.0005321212,0.0015376629,0.09881879,0.047835384,0.83323157],"study_design_scores_gemma":[0.00019799404,0.0007249701,0.016856987,0.008595201,0.00034435207,0.0004406851,0.018512664,0.0027151105,0.010613262,0.22758381,0.71326625,0.0001488573],"about_ca_topic_score_codex":0.0028656865,"about_ca_topic_score_gemma":0.006708151,"teacher_disagreement_score":0.024938468,"about_ca_system_score_codex":0.0024562236,"about_ca_system_score_gemma":0.009007722,"threshold_uncertainty_score":0.1318888},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011818402,0.7060541,0.0030553616,0.21498169,0.006242681,0.000028668486,0.00006348165,0.00005615823,0.06833603],"genre_scores_gemma":[0.068547055,0.7749254,0.007031532,0.03198662,0.009224449,0.00020914404,0.00014740037,0.00021864369,0.10770969],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806684,0.0011057641,0.00006689209,0.00017742475,0.0004055538,0.00017755594],"domain_scores_gemma":[0.996049,0.0029280053,0.00015790554,0.00009777574,0.0003087636,0.0004586498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036482324,0.0012132844,0.0010577186,0.002937149,0.0043610963,0.011374463,0.0018405215,0.003435468,0.009851824],"category_scores_gemma":[0.0036823717,0.0007347966,0.0006022502,0.004453294,0.015514825,0.013521954,0.0040547824,0.0064733205,0.003150834],"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":[0.00004075915,0.00004155782,0.00033794536,0.0009393913,0.000018189738,0.00042990406,0.040165663,0.00031514847,0.00025135578,0.3234917,0.5380199,0.095948465],"study_design_scores_gemma":[0.000007392737,0.00001430405,0.0005267127,0.002083205,0.0000079032,0.00031347392,0.011005031,0.00009064854,0.00006017385,0.11993857,0.86593854,0.000014121112],"about_ca_topic_score_codex":0.015883792,"about_ca_topic_score_gemma":0.03113975,"teacher_disagreement_score":0.015883792,"about_ca_system_score_codex":0.0070935665,"about_ca_system_score_gemma":0.006171472,"threshold_uncertainty_score":0.051467657},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086621135,0.0789429,0.029376617,0.10676082,0.006165208,0.04043701,0.08047913,0.0023967014,0.5688205],"genre_scores_gemma":[0.39544138,0.1249766,0.28568435,0.017081877,0.0031246128,0.057796594,0.040723257,0.00082345866,0.074347906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9505601,0.036508776,0.0062593855,0.000879791,0.0041664816,0.0016254766],"domain_scores_gemma":[0.6390651,0.26707423,0.015608001,0.018337505,0.045597084,0.014318145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06297371,0.00036574638,0.001074553,0.004284915,0.0016096199,0.0027461133,0.0012050896,0.0012083442,0.06356543],"category_scores_gemma":[0.25375196,0.0004969685,0.00060690235,0.0051133824,0.0009333294,0.0025448534,0.002128585,0.001575437,0.014305738],"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":[0.0012177255,0.00046704075,0.026018318,0.0146352295,0.00019982048,0.00020963847,0.0019360177,0.00017607695,0.0007556358,0.0063820286,0.26513028,0.6828721],"study_design_scores_gemma":[0.00090543425,0.0014093822,0.07894191,0.036314648,0.00057648076,0.0006688614,0.008396618,0.00061727973,0.003422709,0.010562935,0.85808325,0.00010048726],"about_ca_topic_score_codex":0.008382459,"about_ca_topic_score_gemma":0.02260542,"teacher_disagreement_score":0.06356543,"about_ca_system_score_codex":0.002567288,"about_ca_system_score_gemma":0.055983793,"threshold_uncertainty_score":0.33304077},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019480003,0.010408708,0.1900172,0.026305016,0.0033914584,0.024704447,0.0042815465,0.0012157279,0.72019583],"genre_scores_gemma":[0.44193628,0.008756287,0.34856412,0.005584746,0.00089771935,0.040455192,0.0044454555,0.0010952447,0.14826494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.79790974,0.15081733,0.011587174,0.00394011,0.032713067,0.003032513],"domain_scores_gemma":[0.791372,0.07033464,0.008957419,0.02432299,0.09888131,0.0061317193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14036667,0.00087250053,0.001384978,0.0071804435,0.0036283971,0.012722222,0.0022954077,0.0015317359,0.028157232],"category_scores_gemma":[0.16701648,0.0004347784,0.00072662847,0.0072817253,0.0050957263,0.00467689,0.0066659,0.0023501876,0.0073095076],"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":[0.00022609578,0.0003390887,0.004980696,0.0020564867,0.00008359922,0.00005946299,0.0051790825,0.0011457507,0.00035894781,0.27149627,0.07280471,0.64126986],"study_design_scores_gemma":[0.00016903982,0.0007180449,0.011925017,0.0063636494,0.00010545606,0.00017484337,0.011642605,0.0030174726,0.0022102748,0.084806554,0.8787739,0.00009318677],"about_ca_topic_score_codex":0.0052600713,"about_ca_topic_score_gemma":0.0036677157,"teacher_disagreement_score":0.14036667,"about_ca_system_score_codex":0.011650002,"about_ca_system_score_gemma":0.037378915,"threshold_uncertainty_score":0.7423388},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10621526,0.00089839014,0.049609587,0.07194978,0.0021778585,0.000114371906,0.00012460857,0.00026718143,0.7686429],"genre_scores_gemma":[0.88343626,0.00032684146,0.015542508,0.00186315,0.0002749137,0.00010551024,0.000060978746,0.00013490152,0.09825492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99491477,0.0031012192,0.00013379613,0.00038530477,0.0009156955,0.00054917135],"domain_scores_gemma":[0.99509394,0.0016984058,0.00030316666,0.0009050423,0.001193208,0.0008062128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044522835,0.00051453686,0.00050172396,0.0011825417,0.010801805,0.010105287,0.0015864287,0.0049403007,0.013226593],"category_scores_gemma":[0.009972077,0.00028772207,0.000504963,0.00062042766,0.014238333,0.0056291413,0.0060385005,0.0061667673,0.0020917403],"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":[0.00002064528,0.00003157407,0.000247816,0.000018058812,0.0000041128756,0.00022645155,0.0039198264,0.0003221458,0.00013466341,0.9818094,0.009285327,0.003979855],"study_design_scores_gemma":[0.000029385086,0.00013625428,0.0010651214,0.00015040135,0.000020850344,0.0012345847,0.018965876,0.004841821,0.0011121765,0.6603252,0.31204465,0.0000735978],"about_ca_topic_score_codex":0.004455523,"about_ca_topic_score_gemma":0.0060657267,"teacher_disagreement_score":0.013226593,"about_ca_system_score_codex":0.0035102055,"about_ca_system_score_gemma":0.002149621,"threshold_uncertainty_score":0.04424739},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.284013,0.0040749013,0.019403107,0.071867675,0.00041843607,0.0009840752,0.00013300014,0.00020349902,0.6189023],"genre_scores_gemma":[0.9875858,0.0007129928,0.004036653,0.00085003814,0.00004847264,0.00014838259,0.000027523092,0.000015599742,0.006574646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9568391,0.026465647,0.0010159512,0.0019174584,0.0070638517,0.0066979895],"domain_scores_gemma":[0.89707005,0.055509172,0.0069368733,0.008527851,0.012514989,0.019441014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043998912,0.00047049645,0.00048774158,0.0033252805,0.01146128,0.019582264,0.0025530972,0.0027847916,0.008256677],"category_scores_gemma":[0.058427557,0.00047190185,0.00026175522,0.0033538854,0.03173126,0.008594692,0.012543533,0.0027251213,0.0007944514],"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":[0.00014804167,0.00087244774,0.03828329,0.0010968208,0.000058325877,0.0007713236,0.10946521,0.0032746666,0.00086244865,0.5466642,0.022152923,0.2763503],"study_design_scores_gemma":[0.00015215318,0.00030378514,0.05286275,0.0031276694,0.00004348532,0.00029191977,0.19213209,0.0041821785,0.0018230935,0.2525377,0.49243346,0.00010968791],"about_ca_topic_score_codex":0.09558906,"about_ca_topic_score_gemma":0.109731086,"teacher_disagreement_score":0.09558906,"about_ca_system_score_codex":0.06825663,"about_ca_system_score_gemma":0.13354911,"threshold_uncertainty_score":0.49523884},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03891534,0.02957157,0.59666747,0.17387009,0.001378425,0.00624513,0.0009856707,0.0012389509,0.15112732],"genre_scores_gemma":[0.52700025,0.010063516,0.43844572,0.009914854,0.0010508042,0.009428403,0.00016932058,0.0003999321,0.003527225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.51946324,0.34371033,0.02206506,0.014456267,0.096254595,0.0040504956],"domain_scores_gemma":[0.3482687,0.56877565,0.016833158,0.025176482,0.038861334,0.002084733],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35569146,0.0035199746,0.0048621055,0.014981245,0.006892954,0.032825813,0.0075561074,0.00783619,0.0027619055],"category_scores_gemma":[0.38644022,0.0024031068,0.003044701,0.009571212,0.08757192,0.03644998,0.01958795,0.010555538,0.0009014119],"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":[0.00025737085,0.0004376283,0.009559433,0.006454495,0.00046386087,0.00015988234,0.012339679,0.009673897,0.0005826686,0.7533325,0.009437944,0.19730069],"study_design_scores_gemma":[0.00015166264,0.0004841758,0.0030570533,0.005036762,0.00019545018,0.0001248076,0.007670007,0.0057451813,0.002330965,0.95042676,0.024589,0.00018817512],"about_ca_topic_score_codex":0.007070283,"about_ca_topic_score_gemma":0.0040987106,"teacher_disagreement_score":0.35569146,"about_ca_system_score_codex":0.019430675,"about_ca_system_score_gemma":0.025787782,"threshold_uncertainty_score":0.79454714},"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":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04002923,0.013039735,0.42268848,0.1970794,0.009648227,0.0016402982,0.000087740664,0.003296437,0.31249046],"genre_scores_gemma":[0.42164624,0.009678028,0.42130533,0.042439237,0.002887567,0.0016933723,0.0002566292,0.0010624797,0.09903111],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93380827,0.049114533,0.00250478,0.0033879671,0.008623244,0.0025611096],"domain_scores_gemma":[0.84053457,0.10115129,0.006713965,0.019185863,0.020185018,0.012229295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050900932,0.0014785954,0.0006536894,0.0022218833,0.004395768,0.008806351,0.0032015594,0.0062855193,0.0130755715],"category_scores_gemma":[0.12432341,0.0008273871,0.00069744827,0.0010764914,0.008964384,0.0077029476,0.012095935,0.013676313,0.0078928955],"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":[0.0001857086,0.0007896475,0.0023408958,0.001994234,0.0000632879,0.0012766093,0.10881261,0.0016163499,0.0070115454,0.15374002,0.17237872,0.54979044],"study_design_scores_gemma":[0.00008988549,0.00031032047,0.0014427815,0.006711638,0.000032212403,0.003411319,0.03921751,0.0020523572,0.0058763153,0.18462864,0.7561176,0.00010949087],"about_ca_topic_score_codex":0.00065522594,"about_ca_topic_score_gemma":0.0014014744,"teacher_disagreement_score":0.050900932,"about_ca_system_score_codex":0.002778736,"about_ca_system_score_gemma":0.013334166,"threshold_uncertainty_score":0.2691931},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034759045,0.0018408694,0.048806246,0.6358397,0.020958658,0.0012099723,0.00038307274,0.0026806623,0.2535218],"genre_scores_gemma":[0.44296655,0.0026958236,0.12461834,0.24217857,0.0012492024,0.00071614917,0.00037535233,0.0014319104,0.18376802],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9770323,0.0074000154,0.00069843157,0.0011172566,0.008302647,0.005449331],"domain_scores_gemma":[0.95618325,0.0055456758,0.0015402945,0.0023257907,0.015473595,0.01893146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017369846,0.0007623102,0.00058274006,0.001486306,0.03229441,0.014347876,0.0035459374,0.007087343,0.024450855],"category_scores_gemma":[0.058486838,0.00071819813,0.00076432334,0.0012641912,0.013969727,0.008835717,0.010520605,0.017483171,0.0096081905],"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":[0.00016432215,0.0004632069,0.007592609,0.00044392588,0.00005595628,0.0009082688,0.029481584,0.0003726616,0.0025357811,0.08573473,0.71428657,0.1579604],"study_design_scores_gemma":[0.00004764926,0.00035152008,0.012069579,0.0010177965,0.00005377954,0.0006386969,0.092574224,0.00071611744,0.0020460817,0.031475592,0.85866076,0.00034824805],"about_ca_topic_score_codex":0.33785158,"about_ca_topic_score_gemma":0.71055573,"teacher_disagreement_score":0.9838236,"about_ca_system_score_codex":0.016176388,"about_ca_system_score_gemma":0.08903958,"threshold_uncertainty_score":0.6717701},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012472753,0.047848687,0.55493087,0.07090147,0.022549665,0.13912669,0.021720843,0.0043639215,0.1260851],"genre_scores_gemma":[0.019339366,0.029245934,0.73528224,0.01917485,0.0024433567,0.14930299,0.0045332043,0.0006516907,0.04002638],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.977007,0.017789386,0.0022086524,0.00060964917,0.0019118204,0.00047345206],"domain_scores_gemma":[0.9229015,0.06345377,0.0022438804,0.001954562,0.0074485806,0.0019977253],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03982165,0.0011091183,0.0010016036,0.005903251,0.0038049477,0.0031657787,0.0022802046,0.0025918433,0.050807737],"category_scores_gemma":[0.05772627,0.0012059842,0.0010017,0.004921873,0.003031976,0.0037727456,0.0035078863,0.00418777,0.017740438],"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":[0.00060942693,0.0010011757,0.0016020774,0.026762897,0.000046326662,0.0010873579,0.034197357,0.0007694545,0.011652299,0.06443267,0.39132598,0.46651295],"study_design_scores_gemma":[0.00012348978,0.00063322554,0.0027171934,0.0085989665,0.000017947335,0.0010793415,0.0145645905,0.00035753267,0.0015905591,0.025254233,0.9449276,0.00013530815],"about_ca_topic_score_codex":0.0038285695,"about_ca_topic_score_gemma":0.012042559,"teacher_disagreement_score":0.9601784,"about_ca_system_score_codex":0.0038187872,"about_ca_system_score_gemma":0.008834152,"threshold_uncertainty_score":0.21059954},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023584957,0.009543431,0.24506718,0.15176433,0.059297174,0.061106067,0.033207953,0.059019733,0.37863567],"genre_scores_gemma":[0.013360699,0.010417833,0.54533416,0.027676726,0.027923593,0.07704626,0.024872972,0.02086645,0.25250125],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93998736,0.028152386,0.01006692,0.0017534002,0.018506879,0.0015329877],"domain_scores_gemma":[0.53522027,0.20132224,0.021002645,0.024507731,0.19688347,0.021063672],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045960262,0.002960051,0.0037780276,0.0175274,0.002307617,0.004861628,0.0057592005,0.007692647,0.6266404],"category_scores_gemma":[0.32693115,0.003183833,0.0030412725,0.009345024,0.0013692179,0.006425207,0.0078251865,0.011725865,0.48382455],"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":[0.000048029007,0.00009675202,0.000041438234,0.0008814224,0.000008103828,0.000041536987,0.00006474533,0.00007244718,0.00014867069,0.00037579553,0.9080383,0.09018275],"study_design_scores_gemma":[0.001112283,0.00017409322,0.0015301158,0.005493966,0.000055605717,0.00059164915,0.00043819865,0.0013358602,0.00085053704,0.01774807,0.9705037,0.00016589611],"about_ca_topic_score_codex":0.0017853787,"about_ca_topic_score_gemma":0.004706603,"teacher_disagreement_score":0.95403975,"about_ca_system_score_codex":0.0032588495,"about_ca_system_score_gemma":0.027109608,"threshold_uncertainty_score":0.5325521},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02411376,0.01039714,0.0027052322,0.108335026,0.0024845283,0.00008280047,0.0005613684,0.00027282324,0.8510473],"genre_scores_gemma":[0.51032716,0.009036206,0.007418279,0.016398314,0.00054924143,0.00012363427,0.0003107436,0.00036919842,0.4554673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99349904,0.0015008532,0.00012500785,0.0008795447,0.0019078543,0.0020876687],"domain_scores_gemma":[0.99408215,0.0007247908,0.00034224647,0.0004529446,0.0018917435,0.0025061027],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047740373,0.00089364697,0.0005525832,0.0036717919,0.04656151,0.018859247,0.0023680045,0.0044896505,0.035204254],"category_scores_gemma":[0.008550355,0.00060728594,0.0004266304,0.0056496426,0.034247544,0.0065121436,0.01153868,0.005190934,0.0032711052],"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":[0.000054632823,0.000020100499,0.006191395,0.00018192838,0.000015522495,0.00068458455,0.12822174,0.00016181075,0.00034713774,0.606219,0.14476377,0.11313839],"study_design_scores_gemma":[0.000003782636,0.0000063391835,0.0021973932,0.00018130084,0.000008104716,0.00008180805,0.042504795,0.000033941866,0.00009636477,0.006550664,0.9483027,0.00003270751],"about_ca_topic_score_codex":0.98041874,"about_ca_topic_score_gemma":0.9883605,"teacher_disagreement_score":0.96479577,"about_ca_system_score_codex":0.123536445,"about_ca_system_score_gemma":0.17471775,"threshold_uncertainty_score":0.89632386},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003956061,0.72312176,0.0044009923,0.1047101,0.15499173,0.00028571335,0.00037230283,0.00028031023,0.011441539],"genre_scores_gemma":[0.005137408,0.65578526,0.008346661,0.087751076,0.16032127,0.00052364514,0.00066254503,0.0005932703,0.08087895],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872672,0.004763697,0.0015483034,0.00079829106,0.005267142,0.00035525145],"domain_scores_gemma":[0.8971945,0.05312161,0.0044203317,0.0018135771,0.040574,0.0028760054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008244293,0.0017595121,0.0047335643,0.0072532534,0.0012316534,0.0054336055,0.002517363,0.007173709,0.016941004],"category_scores_gemma":[0.057237163,0.0013484951,0.001288037,0.007895976,0.00336967,0.0036942777,0.0016837392,0.007665316,0.014721661],"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":[0.000021044754,0.000023118011,0.00009947709,0.0013474373,0.000026870766,0.000055130655,0.000028774177,0.000086445165,0.00009945158,0.00041795295,0.9476714,0.05012287],"study_design_scores_gemma":[0.00004109874,0.000071187605,0.001273872,0.0047821207,0.00008112918,0.0010230091,0.00009162139,0.00029079532,0.00027753838,0.0015747992,0.99043125,0.0000615883],"about_ca_topic_score_codex":0.012577195,"about_ca_topic_score_gemma":0.039938163,"teacher_disagreement_score":0.016941004,"about_ca_system_score_codex":0.0065172515,"about_ca_system_score_gemma":0.009922791,"threshold_uncertainty_score":0.056673348},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006377152,0.07433215,0.10769139,0.5032312,0.23669298,0.010166072,0.0019960315,0.0017907342,0.05772225],"genre_scores_gemma":[0.14637849,0.11274769,0.3133429,0.14950387,0.11026676,0.043133892,0.01219011,0.0041330284,0.108303264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8346867,0.10498122,0.01079519,0.007441151,0.035309114,0.0067865555],"domain_scores_gemma":[0.8037261,0.054697096,0.013963561,0.01586784,0.052082907,0.059662513],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21971053,0.0028335722,0.0026335644,0.00419532,0.0077675222,0.01810935,0.0063296715,0.011763344,0.03508317],"category_scores_gemma":[0.19768137,0.0018465557,0.0026737293,0.0019981766,0.007309961,0.010886554,0.035124462,0.020769825,0.010281685],"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":[0.0003030531,0.00046390304,0.0010357322,0.0015374405,0.00017194822,0.00014799414,0.0028760433,0.00061519176,0.00075185735,0.022146065,0.72451174,0.24543893],"study_design_scores_gemma":[0.00010686373,0.00024083651,0.001928547,0.0038598245,0.000041569525,0.00008346194,0.0011699103,0.0007105396,0.00046895814,0.019556815,0.9717333,0.00009950731],"about_ca_topic_score_codex":0.003074747,"about_ca_topic_score_gemma":0.006566896,"teacher_disagreement_score":0.7802895,"about_ca_system_score_codex":0.009178456,"about_ca_system_score_gemma":0.05703779,"threshold_uncertainty_score":0.9622358},"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":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7879842,0.0017520403,0.05641727,0.06438055,0.00036769547,0.0011762452,0.00024021651,0.00047581695,0.08720598],"genre_scores_gemma":[0.9739734,0.0004399742,0.021112084,0.0006256002,0.000020969484,0.00019802993,0.00006694837,0.00004877486,0.003514244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9827252,0.011249744,0.00048914447,0.0008383441,0.0019353624,0.0027623344],"domain_scores_gemma":[0.98237,0.0045282217,0.00151234,0.0013031095,0.0023551604,0.00793112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022687282,0.00033975416,0.0004064119,0.0027269868,0.023945779,0.02649133,0.0024494857,0.004516063,0.0054015457],"category_scores_gemma":[0.019457184,0.0006844048,0.0005897802,0.0026398858,0.013702225,0.018762099,0.023478854,0.005923579,0.0010414227],"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":[0.00037865984,0.0011093699,0.068950504,0.0004478423,0.00006489038,0.009108865,0.35634834,0.0040599774,0.0045671286,0.36024958,0.013473264,0.18124162],"study_design_scores_gemma":[0.00006405138,0.00063069456,0.035103943,0.00065908296,0.000024619629,0.0026433256,0.6486812,0.005943596,0.0014130479,0.11603136,0.18860519,0.00019988236],"about_ca_topic_score_codex":0.009639181,"about_ca_topic_score_gemma":0.023222076,"teacher_disagreement_score":0.02649133,"about_ca_system_score_codex":0.010138769,"about_ca_system_score_gemma":0.02152965,"threshold_uncertainty_score":0.119983256},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11769474,0.016084908,0.4150046,0.043625463,0.00097071216,0.0035976649,0.0006235508,0.0007498779,0.40164837],"genre_scores_gemma":[0.7967105,0.0066011506,0.16242549,0.0034640126,0.0002447032,0.003677708,0.00032524057,0.00026775998,0.026283415],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8498915,0.12116988,0.004427305,0.0041996627,0.018288309,0.002023507],"domain_scores_gemma":[0.7963282,0.14838837,0.009813385,0.011685767,0.031460892,0.0023234806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08843244,0.0012726337,0.0013770511,0.005024908,0.0031314031,0.015045441,0.0029940999,0.003011165,0.01232376],"category_scores_gemma":[0.1319343,0.00068338803,0.0016950665,0.00460824,0.009212002,0.009713475,0.007031441,0.0039610113,0.0014224926],"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":[0.00055286306,0.0006355937,0.012081542,0.0065920916,0.0004816109,0.00023731246,0.040969018,0.0083586145,0.0023058446,0.36327407,0.009375606,0.5551358],"study_design_scores_gemma":[0.00040659853,0.0026526556,0.03348026,0.027079381,0.0011808781,0.00063854596,0.045506686,0.019742616,0.011260169,0.38789767,0.46981683,0.00033767146],"about_ca_topic_score_codex":0.005742708,"about_ca_topic_score_gemma":0.007334775,"teacher_disagreement_score":0.08843244,"about_ca_system_score_codex":0.013884212,"about_ca_system_score_gemma":0.01742605,"threshold_uncertainty_score":0.46768105},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00406215,0.008692274,0.52648914,0.00994663,0.00029369906,0.00031792955,0.0005321359,0.00033488555,0.44933113],"genre_scores_gemma":[0.3912931,0.01076302,0.4993788,0.002191778,0.0006734082,0.0016397679,0.0013410252,0.00029331003,0.09242577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967443,0.0021297897,0.00015630237,0.00029081068,0.0005419578,0.00013689973],"domain_scores_gemma":[0.99733824,0.00186166,0.00013700745,0.00017140195,0.00039970866,0.000091966576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044699097,0.001061665,0.00060702435,0.0033400771,0.0014365024,0.007936931,0.0018469907,0.0013781218,0.0126006305],"category_scores_gemma":[0.0034031656,0.0003970537,0.00087531214,0.0030709798,0.0083707785,0.0054979683,0.0018733445,0.0020437136,0.002019501],"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":[0.000003458305,0.000007981878,0.000035628793,0.00007287736,0.0000052121927,0.000034498014,0.00028372786,0.0018713687,0.00005981998,0.983648,0.002781182,0.011196285],"study_design_scores_gemma":[0.0000052882915,0.00000853586,0.00006413707,0.00017021307,0.0000054632624,0.00004208728,0.00031947324,0.0049017626,0.00012280032,0.9245487,0.06980384,0.000007722627],"about_ca_topic_score_codex":0.0057551474,"about_ca_topic_score_gemma":0.0044968487,"teacher_disagreement_score":0.0126006305,"about_ca_system_score_codex":0.007053285,"about_ca_system_score_gemma":0.0039643315,"threshold_uncertainty_score":0.051175416},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041355412,0.003437335,0.87464756,0.010063166,0.002015991,0.026774792,0.0014028726,0.0009825465,0.03932035],"genre_scores_gemma":[0.2383232,0.001234089,0.686878,0.006140893,0.00048256048,0.053587295,0.001087512,0.0004307258,0.011835707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.55003613,0.3455272,0.021621628,0.020805014,0.058615286,0.0033947192],"domain_scores_gemma":[0.41848907,0.43794587,0.0135573195,0.054175206,0.07318371,0.0026488004],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32005367,0.0016494965,0.002376035,0.00999888,0.004239395,0.011318619,0.0034859148,0.0038847553,0.011069232],"category_scores_gemma":[0.44019124,0.0021248225,0.0018012259,0.0056282845,0.0053240126,0.010640637,0.013084712,0.004068785,0.0034353046],"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":[0.0015398065,0.0017634968,0.018462062,0.013957775,0.000807019,0.0004357676,0.131957,0.0015760113,0.027816756,0.16698332,0.011351628,0.62334937],"study_design_scores_gemma":[0.0012927393,0.0028675369,0.031316545,0.017306553,0.001436627,0.0010143416,0.12203323,0.019089753,0.06289372,0.4678446,0.27214506,0.0007593377],"about_ca_topic_score_codex":0.0014040145,"about_ca_topic_score_gemma":0.0029657925,"teacher_disagreement_score":0.6799463,"about_ca_system_score_codex":0.0072546685,"about_ca_system_score_gemma":0.015404188,"threshold_uncertainty_score":0.8384949},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091266364,0.7196499,0.010742233,0.19646627,0.021301087,0.00011504194,0.0016545664,0.000837629,0.04832063],"genre_scores_gemma":[0.025155066,0.6924748,0.025937783,0.055066753,0.006430501,0.0003716962,0.0016764441,0.0012474349,0.19163957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972191,0.00078164553,0.0003113741,0.00020832702,0.0012937115,0.00018582662],"domain_scores_gemma":[0.98591423,0.0057194433,0.0009456686,0.00037158097,0.0057863547,0.0012627187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009798957,0.0009532079,0.0008106186,0.0023912338,0.001642023,0.004798618,0.001427512,0.0031816154,0.03719293],"category_scores_gemma":[0.03372928,0.0008500099,0.0004123264,0.0025179535,0.0017930355,0.0054617454,0.002138133,0.0043553608,0.022454323],"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":[0.000035156303,0.000012123235,0.00033321718,0.0003954996,0.000005484753,0.000042055646,0.0005034371,0.000051607818,0.000076288576,0.0018830355,0.820234,0.17642796],"study_design_scores_gemma":[0.000011494963,0.000015382517,0.0016573273,0.0016488254,0.000015593778,0.00014895809,0.0006831952,0.00005191298,0.00023234828,0.00316815,0.99233466,0.000032159747],"about_ca_topic_score_codex":0.08271793,"about_ca_topic_score_gemma":0.21534412,"teacher_disagreement_score":0.08271793,"about_ca_system_score_codex":0.0029199116,"about_ca_system_score_gemma":0.017735437,"threshold_uncertainty_score":0.16447288},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004200149,0.023417113,0.0056940657,0.03511221,0.003772168,0.00006857087,0.000043093336,0.00012307015,0.92756945],"genre_scores_gemma":[0.21114928,0.018627962,0.0063328645,0.015922956,0.0025156557,0.0002582115,0.00011389859,0.00026129957,0.74481785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982162,0.0009353716,0.000051208182,0.0002867651,0.00036825016,0.00014216766],"domain_scores_gemma":[0.9987425,0.0005720742,0.00005081955,0.00020487273,0.0001534414,0.00027629596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019961009,0.00039019372,0.0004134225,0.0010623818,0.006403969,0.01494945,0.0008847336,0.0037228528,0.01153185],"category_scores_gemma":[0.0034293807,0.00025609237,0.00019514089,0.0015385777,0.013002218,0.010878135,0.0051371716,0.005942103,0.0034237518],"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":[0.0000043933946,0.00003462825,0.000089470464,0.000046845093,9.685474e-7,0.00005279271,0.0051503615,0.000051278854,0.00006109234,0.91761744,0.050658885,0.02623179],"study_design_scores_gemma":[0.0000032676019,0.000014421104,0.00013370473,0.0002141587,0.0000010950566,0.00012244069,0.00379002,0.00011424247,0.00010275869,0.11785765,0.877641,0.000005151299],"about_ca_topic_score_codex":0.0017956627,"about_ca_topic_score_gemma":0.0036498464,"teacher_disagreement_score":0.01494945,"about_ca_system_score_codex":0.004794475,"about_ca_system_score_gemma":0.0060281768,"threshold_uncertainty_score":0.038577914},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034686879,0.0014033162,0.9713414,0.0040210728,0.00036775,0.00037646145,0.00042033268,0.001353795,0.017247204],"genre_scores_gemma":[0.056857444,0.0018910421,0.9326773,0.0010347511,0.00018549208,0.0010684313,0.0007840709,0.0010798746,0.004421593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9797364,0.014223994,0.0011633252,0.0014109581,0.002884683,0.0005806237],"domain_scores_gemma":[0.95835733,0.029753612,0.0012907849,0.0057302737,0.0038762286,0.0009918046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027242055,0.0022387113,0.0014401589,0.003855217,0.0016839884,0.006650308,0.004655468,0.0031949559,0.01985366],"category_scores_gemma":[0.07160936,0.0018490077,0.0038699184,0.0026858258,0.0021041878,0.007357585,0.005167373,0.0061412985,0.006863492],"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":[0.00021568101,0.00024495536,0.0034682504,0.0015449619,0.000521697,0.00030643464,0.0010201122,0.12546265,0.0013989192,0.62416077,0.029761612,0.21189393],"study_design_scores_gemma":[0.00020727192,0.00015840204,0.0005020008,0.0012629261,0.00022683987,0.00028326444,0.0005903588,0.25861645,0.0024452282,0.6097278,0.12583812,0.00014137251],"about_ca_topic_score_codex":0.0016951099,"about_ca_topic_score_gemma":0.002505113,"teacher_disagreement_score":0.027242055,"about_ca_system_score_codex":0.002797139,"about_ca_system_score_gemma":0.004241732,"threshold_uncertainty_score":0.14407146},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068443676,0.13425039,0.009499318,0.36732194,0.012756908,0.00007115872,0.00021279,0.00032129395,0.47488183],"genre_scores_gemma":[0.053860065,0.1648686,0.016012952,0.32640395,0.012530654,0.0003695422,0.00048674367,0.0010126833,0.42445475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97638535,0.0076348213,0.0009595327,0.0015902171,0.012580468,0.0008495388],"domain_scores_gemma":[0.9694835,0.01577896,0.0008199131,0.002689593,0.009717114,0.0015109843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011907563,0.00090570626,0.001263912,0.0019363242,0.0035447984,0.013758021,0.0016152451,0.005810906,0.02427312],"category_scores_gemma":[0.04072801,0.00047835446,0.00071163545,0.0026777708,0.012633314,0.021517156,0.002692705,0.01108578,0.018054353],"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":[0.000018125844,0.000052032672,0.00033518733,0.0008998971,0.000020675268,0.00007876211,0.0017372929,0.00019618057,0.00012292892,0.23961054,0.60078025,0.15614814],"study_design_scores_gemma":[0.000004082279,0.000013482773,0.00019586895,0.0016223728,0.0000064804053,0.0001582181,0.0006313337,0.000066544206,0.00008809901,0.08894244,0.9082558,0.000015280957],"about_ca_topic_score_codex":0.007425181,"about_ca_topic_score_gemma":0.0096652815,"teacher_disagreement_score":0.02427312,"about_ca_system_score_codex":0.0063637034,"about_ca_system_score_gemma":0.008024108,"threshold_uncertainty_score":0.08120167},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019007862,0.06451339,0.86022377,0.019299855,0.0026939437,0.006706994,0.0013624819,0.0007341971,0.04256464],"genre_scores_gemma":[0.010720814,0.011643139,0.9712138,0.00090288365,0.00029234536,0.0029254854,0.0005813893,0.00011607377,0.0016038931],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81433266,0.088241585,0.051478345,0.003118973,0.04121298,0.0016154113],"domain_scores_gemma":[0.6601056,0.27244398,0.012435106,0.007744839,0.04445583,0.002814615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17440489,0.0038933724,0.009431401,0.03439423,0.003069097,0.020388268,0.007657532,0.00724638,0.009523619],"category_scores_gemma":[0.33173758,0.003609645,0.0047538797,0.01693046,0.007810932,0.012610822,0.010300733,0.01122816,0.0032995387],"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":[0.000114266564,0.00011944501,0.0009833017,0.016835073,0.00087730744,0.00025227136,0.0020085473,0.0054682572,0.0005516153,0.3720624,0.047875673,0.5528518],"study_design_scores_gemma":[0.00015297429,0.00017087272,0.0007761581,0.03410609,0.00087150943,0.00042065667,0.0016811909,0.0104690455,0.0012437725,0.81941247,0.13050604,0.00018928935],"about_ca_topic_score_codex":0.0045328704,"about_ca_topic_score_gemma":0.0071054283,"teacher_disagreement_score":0.17440489,"about_ca_system_score_codex":0.010556863,"about_ca_system_score_gemma":0.025837531,"threshold_uncertainty_score":0.92235225},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009899253,0.2432119,0.044658136,0.32907766,0.058625713,0.00034004325,0.00012347031,0.00056349573,0.32240972],"genre_scores_gemma":[0.04795802,0.13851534,0.03693861,0.11752951,0.032028884,0.0020017205,0.00016166942,0.0011152267,0.623751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9711627,0.020455232,0.001326295,0.0015136229,0.0048706587,0.00067151274],"domain_scores_gemma":[0.95480597,0.032588407,0.0017179188,0.002989218,0.004746584,0.0031518992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029965667,0.001712348,0.002483128,0.0032120687,0.005189521,0.021767713,0.002991166,0.019437434,0.023859242],"category_scores_gemma":[0.049403988,0.0013505155,0.00041232834,0.0044099125,0.023009881,0.03413997,0.007910083,0.017694496,0.020199805],"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":[0.000022368557,0.000042942775,0.00011864051,0.00086996116,0.00000684723,0.00013173552,0.01225863,0.00008455599,0.0001547088,0.52347434,0.31578317,0.14705206],"study_design_scores_gemma":[0.000015873495,0.00002879062,0.00011778965,0.001659627,0.000007226446,0.00035720973,0.0039988924,0.00030755982,0.00007607958,0.17102504,0.8223844,0.000021499689],"about_ca_topic_score_codex":0.002362064,"about_ca_topic_score_gemma":0.005769766,"teacher_disagreement_score":0.029965667,"about_ca_system_score_codex":0.0071251923,"about_ca_system_score_gemma":0.019158889,"threshold_uncertainty_score":0.15847552},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018001452,0.0043900483,0.8919168,0.013348863,0.0005453189,0.0004550113,0.00037963782,0.0010692283,0.06989354],"genre_scores_gemma":[0.34261343,0.0049750796,0.61144894,0.0020972942,0.0004376365,0.0007243746,0.0006777335,0.00036213777,0.03666334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853817,0.0076244157,0.00057974044,0.0015537684,0.0043018768,0.0005584888],"domain_scores_gemma":[0.9907341,0.005007122,0.00063951,0.00083099096,0.0024432396,0.00034501016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013948488,0.0034092064,0.0016451159,0.0028755988,0.0014095315,0.01102283,0.0012346931,0.0029765747,0.0092739435],"category_scores_gemma":[0.017076071,0.0007922986,0.0016982195,0.004098368,0.0038036394,0.0070425593,0.002756567,0.004651885,0.001813065],"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":[0.00019716461,0.00017786562,0.0029393274,0.0011298325,0.0002496549,0.00019568045,0.0012030997,0.09795367,0.004066094,0.57224816,0.012586609,0.30705285],"study_design_scores_gemma":[0.0001992325,0.00081337686,0.005620841,0.0013288964,0.0003763411,0.0004263227,0.0021323555,0.25876597,0.011680067,0.5170348,0.20140484,0.00021695624],"about_ca_topic_score_codex":0.029724572,"about_ca_topic_score_gemma":0.03164405,"teacher_disagreement_score":0.029724572,"about_ca_system_score_codex":0.0084671015,"about_ca_system_score_gemma":0.015140501,"threshold_uncertainty_score":0.07376754},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077384914,0.0041597537,0.97211266,0.009732466,0.00048709847,0.0031577062,0.0005643852,0.000621529,0.008390605],"genre_scores_gemma":[0.008065338,0.0029735665,0.9826912,0.00067263894,0.00023314651,0.0023589397,0.0006393563,0.00017600752,0.0021896595],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84896636,0.088116124,0.02019597,0.0032099334,0.038174585,0.0013369367],"domain_scores_gemma":[0.71282685,0.17857847,0.012314556,0.022112641,0.07186645,0.0023009682],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20532173,0.0031702872,0.0028958102,0.010700727,0.00226223,0.010278013,0.0047679557,0.00620599,0.013702077],"category_scores_gemma":[0.33883458,0.0024709972,0.0046137613,0.0064478186,0.003494766,0.009166517,0.008579923,0.0062708505,0.009770391],"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":[0.00016900004,0.0004849893,0.0021339406,0.0066157044,0.00067994907,0.00030304707,0.0017930979,0.013976263,0.0016412062,0.21421912,0.12351426,0.63446933],"study_design_scores_gemma":[0.00032948682,0.00056948274,0.004165086,0.020379968,0.0013127497,0.000988027,0.0014645996,0.04559298,0.011161783,0.5103879,0.40327495,0.0003729475],"about_ca_topic_score_codex":0.0043492485,"about_ca_topic_score_gemma":0.005841093,"teacher_disagreement_score":0.7946783,"about_ca_system_score_codex":0.00509887,"about_ca_system_score_gemma":0.02382791,"threshold_uncertainty_score":0.9799798},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013565535,0.00081303803,0.0010595862,0.002080407,0.004587582,0.00025210355,0.0050430885,0.0013079148,0.9847206],"genre_scores_gemma":[0.00075613026,0.0008536029,0.00048159188,0.00084867026,0.00091313286,0.00012440197,0.003430614,0.0006148307,0.99197716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880624,0.00017193801,0.00009084931,0.00021548344,0.00057671603,0.00013875052],"domain_scores_gemma":[0.9975381,0.00038288653,0.00008615715,0.00031465903,0.0012181461,0.00045999413],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009583023,0.0017835872,0.0013654538,0.0033943146,0.0019121824,0.008163755,0.0023707738,0.0025109653,0.90616775],"category_scores_gemma":[0.0060774907,0.0006277412,0.0012938036,0.0048336745,0.00078699115,0.0048662024,0.0034088336,0.0022748348,0.8762172],"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":[0.000010086652,0.000019323525,0.000071369686,0.00009431235,0.0000012879972,0.000013437375,0.000017551902,0.000052140684,0.000045884895,0.0030381652,0.962272,0.034364533],"study_design_scores_gemma":[0.0000058344976,0.000008901732,0.00018774139,0.00011371334,0.0000011059864,0.000021763466,0.000031188047,0.000053973024,0.000025360587,0.001515213,0.99803096,0.000004280501],"about_ca_topic_score_codex":0.0059686317,"about_ca_topic_score_gemma":0.006953354,"teacher_disagreement_score":0.093832254,"about_ca_system_score_codex":0.0026714557,"about_ca_system_score_gemma":0.003537634,"threshold_uncertainty_score":0.13384026},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007502054,0.9483623,0.00039854227,0.021663243,0.013105926,0.00007883506,0.0007868946,0.00006282653,0.015466425],"genre_scores_gemma":[0.0010538425,0.9314877,0.00090644736,0.012238908,0.0058767064,0.00013098762,0.0009810927,0.00006255423,0.04726181],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845576,0.00020141639,0.00019119799,0.00019203383,0.0008472316,0.000112430156],"domain_scores_gemma":[0.9922346,0.002979505,0.00068278925,0.00016092011,0.0035425276,0.00039985523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018210781,0.0015461259,0.0022633031,0.007722797,0.000960357,0.0032028302,0.002456212,0.0031159043,0.054435484],"category_scores_gemma":[0.009368547,0.0007070319,0.0010343234,0.01048166,0.0012100016,0.003113954,0.0016721046,0.0031656208,0.043614786],"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":[0.000011612313,0.0000066904113,0.00005630778,0.0034669586,0.0000147539895,0.000046327506,0.000041645737,0.000042411026,0.000058537767,0.00048395788,0.8892758,0.106495],"study_design_scores_gemma":[0.0000073777637,0.0000064088363,0.00031066418,0.0055690794,0.00002024398,0.0002691825,0.000041446547,0.000014431948,0.000033565684,0.0004123358,0.9933035,0.000011686801],"about_ca_topic_score_codex":0.031359557,"about_ca_topic_score_gemma":0.07317787,"teacher_disagreement_score":0.96864045,"about_ca_system_score_codex":0.004082841,"about_ca_system_score_gemma":0.00832869,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068042224,0.2653338,0.013867716,0.4468581,0.25755912,0.0004063132,0.00031685573,0.00023799334,0.014739747],"genre_scores_gemma":[0.011152243,0.29891452,0.025584355,0.17578146,0.46896628,0.0011945398,0.0004995579,0.0008093244,0.01709765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96693414,0.01916705,0.0042415475,0.001432509,0.0074804747,0.0007442643],"domain_scores_gemma":[0.7312951,0.22981855,0.0050827693,0.0041468567,0.026716912,0.0029398133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042549577,0.0017812202,0.0025595205,0.0052839145,0.0033034207,0.010026753,0.0025382482,0.007925987,0.016567225],"category_scores_gemma":[0.18684736,0.0012724167,0.002674799,0.0045913635,0.006864818,0.01451959,0.005983528,0.013165034,0.004305988],"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":[0.00006759579,0.00008112763,0.0008731547,0.0019269285,0.000076663084,0.000083655344,0.0005341012,0.0002661448,0.000116926,0.014780044,0.800094,0.18109961],"study_design_scores_gemma":[0.0000402676,0.00013473885,0.0018367909,0.0070334855,0.0001351365,0.00046002024,0.0005289413,0.00060528493,0.00016854955,0.044383027,0.9445835,0.000090222806],"about_ca_topic_score_codex":0.0048361984,"about_ca_topic_score_gemma":0.008294363,"teacher_disagreement_score":0.95745045,"about_ca_system_score_codex":0.005848566,"about_ca_system_score_gemma":0.0071114763,"threshold_uncertainty_score":0.22502637},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017151207,0.012331274,0.09226482,0.79667056,0.0021287813,0.0049639875,0.00014628228,0.00046294494,0.07388007],"genre_scores_gemma":[0.35810027,0.01608999,0.5506514,0.044905867,0.0013265685,0.01198101,0.00044426383,0.00019713769,0.016303547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9153503,0.063850895,0.0030199327,0.0018634786,0.010666162,0.0052491752],"domain_scores_gemma":[0.79499954,0.088897966,0.011397217,0.009640966,0.04581149,0.049252816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13856569,0.00088913366,0.0009316119,0.0019219081,0.012431984,0.018997746,0.0042775646,0.009780518,0.015448271],"category_scores_gemma":[0.10843566,0.0010336756,0.0013682897,0.0020239034,0.013077535,0.020842675,0.012656354,0.011499089,0.0021294127],"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":[0.00034329953,0.0016645524,0.005828464,0.0033289334,0.000119120035,0.0008299728,0.016949754,0.006859917,0.001024612,0.46621135,0.13353948,0.36330044],"study_design_scores_gemma":[0.00036334156,0.0008375866,0.005285886,0.0059165955,0.00009728306,0.0004624635,0.05599458,0.005999437,0.0011447364,0.50917083,0.41439956,0.00032778067],"about_ca_topic_score_codex":0.0111898435,"about_ca_topic_score_gemma":0.0365006,"teacher_disagreement_score":0.13856569,"about_ca_system_score_codex":0.01731109,"about_ca_system_score_gemma":0.124813035,"threshold_uncertainty_score":0.7328142},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39587346,0.004366447,0.081924915,0.031796522,0.0007360032,0.00019411232,0.00036219263,0.0002619511,0.4844844],"genre_scores_gemma":[0.9127123,0.0018020786,0.021091728,0.0008302255,0.0001846076,0.0001412698,0.00016528861,0.00006253446,0.06301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955995,0.0020971233,0.00019222568,0.00034901942,0.0013152274,0.00044674717],"domain_scores_gemma":[0.9811721,0.006663464,0.0021019834,0.002346462,0.003286312,0.004429643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007752202,0.00039553992,0.00027128056,0.0012407936,0.0016340674,0.008082552,0.00068964576,0.0011776962,0.015299069],"category_scores_gemma":[0.019102206,0.00021708547,0.0003009249,0.00090468425,0.0037821091,0.0045548812,0.003504551,0.0018117797,0.0011121973],"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":[0.00018293131,0.0004387361,0.029563002,0.00046849265,0.0000648328,0.00042287906,0.013755576,0.0028090868,0.0052462737,0.58774793,0.00822084,0.35107931],"study_design_scores_gemma":[0.000040662075,0.0009015702,0.09709502,0.0012561657,0.000039444345,0.0006891151,0.026951332,0.0030388688,0.009309151,0.2416532,0.6189144,0.000110948764],"about_ca_topic_score_codex":0.0057723024,"about_ca_topic_score_gemma":0.010057443,"teacher_disagreement_score":0.015299069,"about_ca_system_score_codex":0.0039917245,"about_ca_system_score_gemma":0.0064094365,"threshold_uncertainty_score":0.05118054},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.598205,0.038892623,0.08352863,0.15621442,0.0011557431,0.027633687,0.0010702274,0.0005971629,0.09270249],"genre_scores_gemma":[0.89488775,0.004978487,0.089421496,0.002982063,0.000088721165,0.0057663433,0.00017204738,0.000042609332,0.0016604644],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.81574696,0.15791161,0.0058326935,0.002174211,0.014252619,0.004081822],"domain_scores_gemma":[0.79879075,0.10864821,0.009706885,0.005544904,0.06609948,0.011209831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13082717,0.001249748,0.0013872286,0.003211251,0.010124742,0.012213716,0.005614515,0.0027602292,0.0029865112],"category_scores_gemma":[0.14116055,0.0006041509,0.00087154796,0.0032863847,0.0046349927,0.0048472816,0.006351293,0.0046016634,0.000323091],"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":[0.0009224463,0.008547049,0.08617772,0.013144966,0.0009741028,0.0010765613,0.061822265,0.015651891,0.0019141224,0.036862493,0.025253316,0.7476532],"study_design_scores_gemma":[0.0015175379,0.013781755,0.27264267,0.061487,0.0015136953,0.0014647101,0.353827,0.0638443,0.009689539,0.080313064,0.13879494,0.0011238015],"about_ca_topic_score_codex":0.22797306,"about_ca_topic_score_gemma":0.35811654,"teacher_disagreement_score":0.22797306,"about_ca_system_score_codex":0.05813849,"about_ca_system_score_gemma":0.13171166,"threshold_uncertainty_score":0.69188845},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08741507,0.011742226,0.044208188,0.07333392,0.00038923253,0.00047694906,0.00032818515,0.00012006042,0.7819862],"genre_scores_gemma":[0.9076757,0.0037573806,0.026106432,0.0024722018,0.000056360142,0.00013717037,0.00008549948,0.00008663942,0.059622664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99089456,0.004285747,0.00016615863,0.00036145136,0.0026132881,0.0016788453],"domain_scores_gemma":[0.993086,0.0034679326,0.00017607206,0.0002204964,0.002335395,0.0007141447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007525838,0.0006183102,0.00051466364,0.002077724,0.008435491,0.016396163,0.0022623085,0.002442363,0.0036485305],"category_scores_gemma":[0.011772865,0.0003393264,0.0003789598,0.004485222,0.011743699,0.0038183955,0.002963563,0.003308439,0.00029810477],"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":[0.000043710268,0.00011510544,0.00414477,0.00023044867,0.000030748673,0.00066197244,0.015960567,0.010482165,0.0003370317,0.7946963,0.034269705,0.13902755],"study_design_scores_gemma":[0.00008064651,0.00009662789,0.017257525,0.0014229581,0.00008004738,0.0003389764,0.08036248,0.02805373,0.0011047708,0.5150103,0.3560079,0.00018412803],"about_ca_topic_score_codex":0.92191786,"about_ca_topic_score_gemma":0.9633511,"teacher_disagreement_score":0.892954,"about_ca_system_score_codex":0.10704603,"about_ca_system_score_gemma":0.111885965,"threshold_uncertainty_score":0.77667695},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007156241,0.02640547,0.040409278,0.13488701,0.0048876503,0.0014140584,0.000126174,0.00044376327,0.7842703],"genre_scores_gemma":[0.3213711,0.045687947,0.16726555,0.10199602,0.0032344458,0.005372795,0.0004370585,0.00055818696,0.35407686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9767898,0.014942052,0.00095808634,0.0017412908,0.004667152,0.0009016703],"domain_scores_gemma":[0.9864955,0.0051941015,0.0008390073,0.0016500793,0.0026025155,0.0032189346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01734977,0.0008547336,0.0006034157,0.0019640669,0.0047573172,0.012558792,0.0022538032,0.0047963257,0.021099128],"category_scores_gemma":[0.03161157,0.00041787527,0.00038228315,0.0019687917,0.015632713,0.007955573,0.00870231,0.0067426325,0.010429105],"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":[0.000031050553,0.00028175532,0.001212452,0.0016937617,0.000012941648,0.00042257996,0.036518395,0.00039559993,0.0003544024,0.32433924,0.33088344,0.30385447],"study_design_scores_gemma":[0.00001987824,0.000051540566,0.00053174084,0.0023262568,0.0000032360742,0.00043960815,0.012459182,0.00014668098,0.00009600694,0.08526517,0.89864534,0.000015355075],"about_ca_topic_score_codex":0.001838975,"about_ca_topic_score_gemma":0.0029800392,"teacher_disagreement_score":0.021099128,"about_ca_system_score_codex":0.0086485185,"about_ca_system_score_gemma":0.02039643,"threshold_uncertainty_score":0.09175545},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001713903,0.1488837,0.04549523,0.17322265,0.003730881,0.0005276835,0.00032761865,0.00025432755,0.62584394],"genre_scores_gemma":[0.30941388,0.24158879,0.1788994,0.029559806,0.0034928888,0.0036599191,0.00083027454,0.00057672884,0.2319783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97354186,0.018958416,0.00069555483,0.001512551,0.003996539,0.0012950323],"domain_scores_gemma":[0.96213305,0.030353267,0.00074616435,0.0029892991,0.002625563,0.0011525435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0404771,0.0018531695,0.0021296416,0.005515456,0.0064560254,0.016766394,0.003916959,0.0077749314,0.018991278],"category_scores_gemma":[0.033175617,0.00063741475,0.0009262114,0.010129866,0.0383115,0.013885936,0.006702263,0.0074042617,0.0030321404],"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":[0.000003878776,0.000017716862,0.00006940581,0.00036583396,0.0000107926635,0.000025075296,0.001581287,0.0004477534,0.000033358298,0.9444477,0.02608605,0.026911216],"study_design_scores_gemma":[0.000011974883,0.000007987756,0.0001508843,0.0013224093,0.000007368757,0.000021795582,0.0016013198,0.0006957385,0.00007484852,0.70023537,0.29585484,0.000015447928],"about_ca_topic_score_codex":0.08423152,"about_ca_topic_score_gemma":0.10116608,"teacher_disagreement_score":0.08423152,"about_ca_system_score_codex":0.049871348,"about_ca_system_score_gemma":0.055308048,"threshold_uncertainty_score":0.36184365},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06826082,0.8293675,0.028096672,0.057735905,0.00057973684,0.0008650905,0.0003466547,0.00012585366,0.0146217365],"genre_scores_gemma":[0.75316703,0.20113952,0.038445365,0.00468348,0.0003947509,0.0013737868,0.00027103422,0.000077551435,0.00044738987],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7967174,0.15107365,0.02251203,0.0063629644,0.02097048,0.0023635225],"domain_scores_gemma":[0.3580594,0.5296283,0.02825192,0.012997244,0.068646014,0.0024172103],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29667005,0.0007890993,0.003038186,0.013681292,0.0022150362,0.013717333,0.0021385269,0.0023378846,0.0020196931],"category_scores_gemma":[0.33583447,0.00085061596,0.0019091025,0.021616735,0.0052819275,0.020282008,0.004833411,0.00287427,0.0002036785],"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":[0.00071009644,0.0004460396,0.047461703,0.046090066,0.0017925402,0.000065813845,0.011865834,0.00094358134,0.00039424602,0.03165821,0.002791825,0.8557802],"study_design_scores_gemma":[0.00054917025,0.0036337834,0.13294227,0.49061608,0.00843725,0.0008687084,0.07140439,0.015209773,0.0053369803,0.105947465,0.16445906,0.00059495604],"about_ca_topic_score_codex":0.008416909,"about_ca_topic_score_gemma":0.012472162,"teacher_disagreement_score":0.7033299,"about_ca_system_score_codex":0.016424326,"about_ca_system_score_gemma":0.031079093,"threshold_uncertainty_score":0.867331},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40115213,0.099906735,0.0057741827,0.22175606,0.0029162122,0.00026970616,0.0037698068,0.0004636696,0.26399145],"genre_scores_gemma":[0.8367844,0.01044534,0.0035589132,0.005523182,0.00021808858,0.00005989199,0.0006678648,0.00007456814,0.14266777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982526,0.00047239283,0.000048914255,0.00017567171,0.00047801711,0.0005724164],"domain_scores_gemma":[0.9924039,0.0011743065,0.00047269862,0.00018114402,0.0026598123,0.0031080896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023487448,0.00031515525,0.00031081846,0.0014853665,0.0054044644,0.003725974,0.0007360251,0.0010180818,0.020850565],"category_scores_gemma":[0.004186703,0.00021706417,0.00027933446,0.0021763295,0.0026058077,0.00088593154,0.0009064357,0.0016359307,0.0010581274],"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":[0.00026413414,0.00030998583,0.16651799,0.0006742445,0.000091753536,0.0011062139,0.011016064,0.0011786084,0.0020778573,0.085341364,0.30121416,0.4302076],"study_design_scores_gemma":[0.00003513772,0.000064648506,0.44793862,0.00068639923,0.000026473888,0.00031189388,0.0084857615,0.00093172136,0.0005341282,0.001371063,0.53955054,0.000063537904],"about_ca_topic_score_codex":0.9903134,"about_ca_topic_score_gemma":0.99531364,"teacher_disagreement_score":0.9903134,"about_ca_system_score_codex":0.086575754,"about_ca_system_score_gemma":0.11071895,"threshold_uncertainty_score":0.62815404},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33952433,0.006565087,0.0807158,0.03788189,0.00043952352,0.0026912324,0.00039336123,0.0006576902,0.53113097],"genre_scores_gemma":[0.9144945,0.0020641345,0.051898424,0.0016184452,0.000040341587,0.00050904055,0.00010484509,0.00018081517,0.029089414],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97078,0.01816251,0.00073060486,0.0009622065,0.0063113756,0.0030534097],"domain_scores_gemma":[0.94634604,0.03665946,0.0008083702,0.0030030971,0.010287296,0.0028956318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044464808,0.000603693,0.00091734406,0.00412707,0.019972697,0.014712409,0.004242959,0.0030525618,0.003149088],"category_scores_gemma":[0.031953465,0.0005727032,0.00064993877,0.008105272,0.015631957,0.002784532,0.008505606,0.003777963,0.00033815557],"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":[0.0007924507,0.001035268,0.035329763,0.0010939615,0.00014613834,0.0029880777,0.11655024,0.008727559,0.0037562046,0.2504711,0.017671129,0.56143814],"study_design_scores_gemma":[0.00073005044,0.0013967421,0.12878922,0.0030124963,0.0005391953,0.0011632626,0.30852395,0.01572301,0.009670158,0.1663406,0.36341706,0.00069417915],"about_ca_topic_score_codex":0.88459396,"about_ca_topic_score_gemma":0.95955783,"teacher_disagreement_score":0.11540604,"about_ca_system_score_codex":0.073592775,"about_ca_system_score_gemma":0.13183343,"threshold_uncertainty_score":0.53395545},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07711542,0.0048378734,0.7042537,0.03774266,0.0008715362,0.010024971,0.0001730237,0.00034708422,0.16463369],"genre_scores_gemma":[0.61621565,0.0015355211,0.3626065,0.0032122303,0.000121828714,0.011529865,0.00005177429,0.0001345443,0.004592095],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5729653,0.41048586,0.003908968,0.0021322975,0.008984399,0.0015231519],"domain_scores_gemma":[0.58704805,0.37229666,0.006822057,0.017062064,0.013434644,0.0033364939],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26802912,0.00077311305,0.0009333618,0.0047971653,0.007208105,0.014321816,0.0027354872,0.0022629318,0.0050840513],"category_scores_gemma":[0.20221859,0.0007319221,0.00082458503,0.0034642597,0.03967156,0.01184891,0.016239518,0.004503148,0.00062753906],"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":[0.0002273593,0.0004358784,0.0029008973,0.0025594125,0.000055710636,0.0004251846,0.44746536,0.0016314777,0.0014196399,0.32383648,0.0051414263,0.21390115],"study_design_scores_gemma":[0.00043568396,0.00081169663,0.0030108043,0.0105257975,0.00012822711,0.00084622967,0.3244747,0.0067992024,0.0053194687,0.44776228,0.19965795,0.00022802911],"about_ca_topic_score_codex":0.003978803,"about_ca_topic_score_gemma":0.006439328,"teacher_disagreement_score":0.7319709,"about_ca_system_score_codex":0.011522858,"about_ca_system_score_gemma":0.026160771,"threshold_uncertainty_score":0.9026504},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46258307,0.088334225,0.006682456,0.07375335,0.0007304374,0.0005667977,0.00097519637,0.00006148454,0.36631304],"genre_scores_gemma":[0.98703104,0.008321774,0.0015786974,0.00057978166,0.00007299882,0.00010567101,0.00011070953,0.000008467466,0.0021909424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9598889,0.02119198,0.0010433259,0.0013999356,0.008942668,0.007533225],"domain_scores_gemma":[0.8430942,0.10977529,0.01007672,0.0042840536,0.027864804,0.0049049165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03897141,0.000399747,0.0012413793,0.013540834,0.009542412,0.019197596,0.0020810438,0.0020546184,0.007970436],"category_scores_gemma":[0.08104776,0.00040210612,0.0005885305,0.036983002,0.0188489,0.011472014,0.005520857,0.0022519736,0.00018932961],"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":[0.00015247236,0.00015272207,0.051213462,0.0013177608,0.000111701054,0.00023688168,0.048786014,0.0012895374,0.000108815875,0.81244653,0.00829937,0.07588471],"study_design_scores_gemma":[0.00007610429,0.00010735026,0.1726495,0.0039506042,0.00020984342,0.00019820216,0.5565691,0.0034037926,0.00043495436,0.10125655,0.16101314,0.00013099064],"about_ca_topic_score_codex":0.7288929,"about_ca_topic_score_gemma":0.7290624,"teacher_disagreement_score":0.8753669,"about_ca_system_score_codex":0.12463308,"about_ca_system_score_gemma":0.10398445,"threshold_uncertainty_score":0.90428054},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033057895,0.46569833,0.1087729,0.26320583,0.011136681,0.0006648403,0.0029790308,0.002218234,0.14201845],"genre_scores_gemma":[0.11835058,0.4937855,0.19964938,0.0331784,0.004293473,0.0017962761,0.002239255,0.0012412705,0.14546587],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99487007,0.002426178,0.00038866056,0.00029253346,0.001867201,0.00015540337],"domain_scores_gemma":[0.9581345,0.026209472,0.0017700933,0.00083958195,0.011686539,0.0013599191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016567543,0.0010610386,0.00072580867,0.0042410535,0.0017719748,0.0042996067,0.001712489,0.0026147445,0.025053088],"category_scores_gemma":[0.045215737,0.00082694844,0.00053795404,0.0049007875,0.002764501,0.005420037,0.0019929279,0.0047947187,0.008304021],"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":[0.000049602106,0.000026181631,0.0011020115,0.0010396442,0.00002418225,0.00007038964,0.0013665904,0.000465667,0.00021710584,0.012020522,0.53152,0.4520982],"study_design_scores_gemma":[0.00005568805,0.00012190551,0.007470852,0.00929559,0.0001460371,0.00024186925,0.002358617,0.0016752396,0.0020248136,0.05656744,0.9199017,0.00014016501],"about_ca_topic_score_codex":0.06594884,"about_ca_topic_score_gemma":0.12723269,"teacher_disagreement_score":0.06594884,"about_ca_system_score_codex":0.0072329794,"about_ca_system_score_gemma":0.018671878,"threshold_uncertainty_score":0.13112998},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5441722,0.002854602,0.16903847,0.0112076895,0.00049336127,0.005138678,0.0011169686,0.0009138272,0.2650642],"genre_scores_gemma":[0.8168218,0.0011661592,0.120755136,0.00062371977,0.000049686292,0.0018149092,0.0006908098,0.00038332198,0.057694547],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96768606,0.014526256,0.0016692686,0.002827947,0.011544219,0.0017462455],"domain_scores_gemma":[0.92171943,0.026523234,0.004999601,0.0061420067,0.034997083,0.005618598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03324935,0.0011437709,0.0007773504,0.0061074416,0.007301565,0.013649748,0.0019387255,0.0016132678,0.01026851],"category_scores_gemma":[0.06547961,0.00067373546,0.0007803169,0.004528926,0.0069997907,0.00463558,0.008301968,0.0021811405,0.0025316484],"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":[0.00030904604,0.00032605082,0.05394293,0.0013785429,0.00011607742,0.0008894521,0.33554617,0.0018516856,0.016298106,0.13982825,0.013212423,0.4363012],"study_design_scores_gemma":[0.00006869698,0.0006608209,0.13384335,0.0028466233,0.00020304475,0.0005062184,0.2567628,0.0062758955,0.02973857,0.042259503,0.5264946,0.00033991763],"about_ca_topic_score_codex":0.09474706,"about_ca_topic_score_gemma":0.15539846,"teacher_disagreement_score":0.09474706,"about_ca_system_score_codex":0.026221348,"about_ca_system_score_gemma":0.051502842,"threshold_uncertainty_score":0.1902501},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001393629,0.005160247,0.9205482,0.018597467,0.0009910028,0.0092871385,0.00016140612,0.0004931944,0.04336765],"genre_scores_gemma":[0.03559069,0.0019513073,0.9354319,0.0025623695,0.00025618743,0.02266159,0.00012614625,0.00011818664,0.0013015831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23614118,0.7070274,0.021887388,0.011013775,0.020667756,0.0032625224],"domain_scores_gemma":[0.3470417,0.56398624,0.014390763,0.036962334,0.031856317,0.005762597],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6014476,0.004504333,0.0057790517,0.020236857,0.012759392,0.041246656,0.010639754,0.0127560105,0.0074013467],"category_scores_gemma":[0.36354503,0.0029473477,0.006191455,0.013286917,0.09486817,0.035824124,0.023970298,0.019816032,0.0029520541],"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":[0.00004676562,0.000093001,0.00043569886,0.0026672843,0.00010153578,0.00012499982,0.01592839,0.0018061644,0.00020630301,0.93878937,0.0023205858,0.03747981],"study_design_scores_gemma":[0.00017316978,0.00032539453,0.0004973001,0.010021529,0.00011170194,0.00023364693,0.012012178,0.004704842,0.0005764663,0.85380644,0.11739817,0.00013913987],"about_ca_topic_score_codex":0.008818341,"about_ca_topic_score_gemma":0.009407731,"teacher_disagreement_score":0.39855242,"about_ca_system_score_codex":0.042137798,"about_ca_system_score_gemma":0.0676499,"threshold_uncertainty_score":0.49148613},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06480702,0.021459285,0.0026557422,0.8479643,0.0020137555,0.00050472864,0.00055402674,0.00019646909,0.059844643],"genre_scores_gemma":[0.88864547,0.0113769425,0.013741325,0.0707855,0.0004347396,0.00036799582,0.00048496758,0.00012428348,0.014038713],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8912494,0.03333455,0.007339324,0.0046569617,0.04462409,0.01879568],"domain_scores_gemma":[0.7346474,0.09505136,0.011008303,0.008082443,0.1023621,0.048848372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.091161974,0.0004943181,0.0011442003,0.0038065764,0.013485913,0.017285265,0.0043427655,0.0060566436,0.0035251416],"category_scores_gemma":[0.20701204,0.0007010351,0.0009721298,0.006217685,0.011365271,0.0053548752,0.009112501,0.009401197,0.00029313046],"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":[0.00066497707,0.00047057393,0.049578696,0.00448517,0.0006106451,0.00084710016,0.015746942,0.008256629,0.0010318281,0.2626284,0.19279473,0.4628843],"study_design_scores_gemma":[0.00048744862,0.00086440786,0.1744298,0.00921247,0.00048475474,0.00041481308,0.03298005,0.009301675,0.0022570197,0.05518423,0.7137864,0.00059685763],"about_ca_topic_score_codex":0.9845642,"about_ca_topic_score_gemma":0.98767614,"teacher_disagreement_score":0.76187515,"about_ca_system_score_codex":0.23812483,"about_ca_system_score_gemma":0.65236217,"threshold_uncertainty_score":0.88366723},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061791465,0.0031664483,0.046655804,0.40023,0.0027439245,0.0008036566,0.00007478529,0.00033765787,0.48419625],"genre_scores_gemma":[0.7747942,0.0027005458,0.08674372,0.039013136,0.0004041151,0.00055232615,0.00008958946,0.00030906848,0.09539332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97603685,0.014646437,0.0006776058,0.00081777823,0.0041728946,0.0036484662],"domain_scores_gemma":[0.9802494,0.0065621743,0.0011092087,0.0014678148,0.0048873858,0.0057240883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02432379,0.00072612305,0.00044532557,0.001907278,0.013502849,0.01144018,0.002756668,0.008185374,0.007420649],"category_scores_gemma":[0.034093123,0.00048759257,0.0008466387,0.0011078175,0.018392622,0.011545153,0.015476495,0.013473206,0.0018626464],"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":[0.000068605426,0.0005099816,0.0080609545,0.00025696962,0.000017233731,0.055862807,0.07622306,0.00076020695,0.0012677339,0.6150978,0.15448357,0.08739106],"study_design_scores_gemma":[0.00004069076,0.00015674027,0.0027269525,0.0020634315,0.000025039726,0.03986606,0.11457349,0.0035706356,0.002155437,0.12396989,0.7107332,0.000118396376],"about_ca_topic_score_codex":0.019534128,"about_ca_topic_score_gemma":0.052952055,"teacher_disagreement_score":0.02432379,"about_ca_system_score_codex":0.01180776,"about_ca_system_score_gemma":0.023964487,"threshold_uncertainty_score":0.12863803},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43604365,0.0049680946,0.00282729,0.08030914,0.00025264185,0.000088574976,0.00018138046,0.000025368132,0.4753039],"genre_scores_gemma":[0.9822859,0.0012646408,0.0002637791,0.0010084404,0.000027404749,0.000015852787,0.000024237203,0.0000089037585,0.015100777],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931235,0.0016405197,0.00017502646,0.0004436567,0.0023741922,0.0022431833],"domain_scores_gemma":[0.9934957,0.001675334,0.00089835376,0.00025910494,0.0016296487,0.0020418116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004254884,0.00037948802,0.00033781948,0.0012126953,0.022421682,0.01050321,0.0014987056,0.0020384078,0.0038377156],"category_scores_gemma":[0.004941991,0.00035144665,0.00037954858,0.0019046929,0.027174601,0.0031280748,0.0045525576,0.002627727,0.0001902527],"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":[0.00007561559,0.000060239166,0.027124502,0.00021129902,0.000023191356,0.0015929402,0.49486324,0.0009366573,0.0007484548,0.43572018,0.011083207,0.027560474],"study_design_scores_gemma":[0.00006504441,0.00009205174,0.07108866,0.00048646814,0.00003873149,0.00046397076,0.45966813,0.0013562866,0.0004818711,0.06703768,0.39905316,0.0001680172],"about_ca_topic_score_codex":0.9780171,"about_ca_topic_score_gemma":0.9861269,"teacher_disagreement_score":0.17331944,"about_ca_system_score_codex":0.17331944,"about_ca_system_score_gemma":0.13652138,"threshold_uncertainty_score":0.95883226},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20115109,0.0014864795,0.46654522,0.051125403,0.00043878696,0.004961348,0.00013405543,0.0012711951,0.2728865],"genre_scores_gemma":[0.8337615,0.00047604044,0.15752904,0.0011703321,0.000073762276,0.0016939908,0.000074406904,0.000106927284,0.00511397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.88506323,0.098992236,0.0018023064,0.002573375,0.008637002,0.0029319385],"domain_scores_gemma":[0.8364749,0.12361313,0.004166293,0.014695226,0.013082763,0.007967575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08931211,0.000736178,0.00073853164,0.005123136,0.006891178,0.014517279,0.0034402334,0.0026404308,0.0074406667],"category_scores_gemma":[0.10429899,0.0006946943,0.0008111704,0.0022161228,0.02695804,0.016351221,0.019349283,0.003219095,0.0008213714],"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":[0.0002058944,0.0011712381,0.009489201,0.0008384563,0.00008535632,0.00041202133,0.08412867,0.006040373,0.00124859,0.58212626,0.014827872,0.29942614],"study_design_scores_gemma":[0.000324463,0.00093908067,0.0047480995,0.0024849735,0.00008651006,0.0004525713,0.106740445,0.03103945,0.0036366337,0.69227666,0.1570551,0.00021601551],"about_ca_topic_score_codex":0.0040634014,"about_ca_topic_score_gemma":0.0045992546,"teacher_disagreement_score":0.08931211,"about_ca_system_score_codex":0.009246946,"about_ca_system_score_gemma":0.023426125,"threshold_uncertainty_score":0.4723332},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90155375,0.0029609234,0.029601693,0.007540241,0.00013981378,0.0005376945,0.00012216064,0.00015039505,0.057393305],"genre_scores_gemma":[0.98190546,0.0008281082,0.012270054,0.00027384327,0.00002306991,0.0003642806,0.000045576693,0.000028672086,0.004260956],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.938608,0.043167725,0.003231099,0.003474489,0.00931114,0.0022076438],"domain_scores_gemma":[0.797301,0.1448776,0.014285216,0.008322291,0.027625708,0.0075882613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058722276,0.00053205405,0.0009272405,0.0028361252,0.0036196175,0.010163007,0.0015474742,0.001498271,0.007304454],"category_scores_gemma":[0.13581257,0.0004938782,0.00076109805,0.0024811022,0.0063785547,0.0076719495,0.008574984,0.0029660915,0.0010024632],"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":[0.00062324014,0.00093050575,0.13971657,0.0023875213,0.0002266894,0.00023505342,0.4545955,0.0014722587,0.0024963948,0.051568106,0.0022923297,0.34345582],"study_design_scores_gemma":[0.00012654118,0.002203315,0.34138006,0.004055834,0.00027435555,0.00040331614,0.51071906,0.004257473,0.0072344127,0.041113615,0.0878638,0.000368246],"about_ca_topic_score_codex":0.0087818485,"about_ca_topic_score_gemma":0.009915644,"teacher_disagreement_score":0.058722276,"about_ca_system_score_codex":0.009011874,"about_ca_system_score_gemma":0.017161123,"threshold_uncertainty_score":0.31055677},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92067695,0.0007372163,0.024109175,0.0058440184,0.00014144069,0.0006907444,0.0004918897,0.00024466275,0.047063794],"genre_scores_gemma":[0.97571075,0.00021479938,0.014515913,0.00018091836,0.000034347613,0.00015651193,0.00022860411,0.000028288086,0.008929845],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99238974,0.004094574,0.0005194414,0.00049531605,0.0014636741,0.0010373206],"domain_scores_gemma":[0.9921483,0.0024197723,0.00084222393,0.0009983046,0.002259394,0.0013319814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008489718,0.0003369989,0.00026892373,0.0031464428,0.0039621233,0.004847376,0.0017774116,0.0020515996,0.0049855895],"category_scores_gemma":[0.00971731,0.00025267867,0.00033453875,0.0020665526,0.0017917304,0.0028577338,0.004300268,0.0009753188,0.00080108637],"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":[0.0006416357,0.002943196,0.23442143,0.0011954233,0.00010891934,0.056322094,0.15145232,0.022434765,0.011049903,0.17784908,0.021530654,0.3200506],"study_design_scores_gemma":[0.00016579828,0.0012752314,0.2185658,0.0019531946,0.00015748102,0.016434936,0.23361757,0.078278035,0.018529879,0.020676218,0.409963,0.0003828919],"about_ca_topic_score_codex":0.019080104,"about_ca_topic_score_gemma":0.01559319,"teacher_disagreement_score":0.019080104,"about_ca_system_score_codex":0.008944069,"about_ca_system_score_gemma":0.0062997662,"threshold_uncertainty_score":0.06489402},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059199192,0.95108265,0.00041038534,0.018404927,0.01489989,0.00008927659,0.00070904515,0.00007866304,0.01426602],"genre_scores_gemma":[0.0010829512,0.9260373,0.0008353165,0.012456534,0.008296781,0.00017953939,0.0008876465,0.000081458245,0.050142515],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787164,0.00032320432,0.00027946202,0.00024573857,0.0011493072,0.00013061275],"domain_scores_gemma":[0.9906674,0.003792887,0.0009133136,0.00019328202,0.0039400025,0.00049311784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021960742,0.0020637284,0.0026516558,0.00639795,0.0009056381,0.0038157606,0.0028630868,0.0035351368,0.055404898],"category_scores_gemma":[0.010672778,0.0009044015,0.0011448882,0.008118506,0.0012746503,0.003528627,0.0017201746,0.0047991234,0.062727235],"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":[0.00002004948,0.000008653152,0.00004779005,0.0031332097,0.00001810356,0.00003523938,0.000031148214,0.000036244965,0.00005361023,0.00041002696,0.9018986,0.09430737],"study_design_scores_gemma":[0.000016183907,0.000011409455,0.00032215408,0.0053875363,0.000030120918,0.0002665845,0.000032115757,0.000018995685,0.00004709716,0.00045200923,0.99340254,0.000013297611],"about_ca_topic_score_codex":0.012097564,"about_ca_topic_score_gemma":0.02824809,"teacher_disagreement_score":0.055404898,"about_ca_system_score_codex":0.0032383022,"about_ca_system_score_gemma":0.0061325035,"threshold_uncertainty_score":0.18534786},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20170553,0.0044811876,0.0038811308,0.53836966,0.0012190026,0.00028242558,0.00011848576,0.00007279361,0.24986982],"genre_scores_gemma":[0.9325216,0.0040288805,0.0026444618,0.019483984,0.0001263739,0.00009943997,0.000036853722,0.000046404333,0.041011952],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9912725,0.0043478645,0.0001892702,0.00039399398,0.0010426971,0.0027536408],"domain_scores_gemma":[0.9932969,0.0022666613,0.0003110882,0.00014504795,0.0012689197,0.002711436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062189223,0.0003509697,0.00039016994,0.00096225285,0.032689646,0.010992271,0.0029705327,0.0050802296,0.0041201278],"category_scores_gemma":[0.007988501,0.0004563109,0.0005337758,0.0017280236,0.022554364,0.004792235,0.005834941,0.0059430744,0.00040607053],"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":[0.000045478617,0.00022388605,0.012090215,0.00018465854,0.000013043168,0.0049479245,0.7113236,0.0010548894,0.00023826298,0.17843652,0.06295875,0.028482758],"study_design_scores_gemma":[0.000022762304,0.000064049695,0.005463661,0.00031007684,0.000015035639,0.00048392435,0.6462573,0.0007502482,0.00013491267,0.010891715,0.33554268,0.00006361105],"about_ca_topic_score_codex":0.93360156,"about_ca_topic_score_gemma":0.9683832,"teacher_disagreement_score":0.10065002,"about_ca_system_score_codex":0.10065002,"about_ca_system_score_gemma":0.11296924,"threshold_uncertainty_score":0.7302704},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019171418,0.019673046,0.03432642,0.047176354,0.014464041,0.00028753877,0.0001523514,0.00042050486,0.8815827],"genre_scores_gemma":[0.07919839,0.01728674,0.027369859,0.017546182,0.004412363,0.0007884502,0.0002706937,0.0011323653,0.85199505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9805659,0.010824506,0.0008128543,0.0011676628,0.006027699,0.0006013752],"domain_scores_gemma":[0.97776175,0.014884748,0.0006131339,0.0030896508,0.0030681107,0.0005825783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016079018,0.0009099654,0.0008442103,0.002502181,0.0033806937,0.015808603,0.002136755,0.0031062814,0.023890119],"category_scores_gemma":[0.036480054,0.00067743147,0.0007789888,0.0024469062,0.014398905,0.011990945,0.007896125,0.007328642,0.009235809],"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":[0.000024167883,0.000028759772,0.00009402801,0.00042987437,0.000010055273,0.00011428163,0.025110207,0.00025389768,0.0003050773,0.63459724,0.2289314,0.11010091],"study_design_scores_gemma":[0.000005731436,0.000010956119,0.000052165142,0.0005411082,0.0000025362874,0.00012219213,0.003193705,0.00010902582,0.0001328198,0.07216914,0.92365134,0.0000092949695],"about_ca_topic_score_codex":0.0011155263,"about_ca_topic_score_gemma":0.0018842805,"teacher_disagreement_score":0.023890119,"about_ca_system_score_codex":0.0050493004,"about_ca_system_score_gemma":0.0070572332,"threshold_uncertainty_score":0.085035026},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01880953,0.084445015,0.5814845,0.23080492,0.00345205,0.0015118611,0.00026925773,0.0017161792,0.07750673],"genre_scores_gemma":[0.21675561,0.07737174,0.6877426,0.009848426,0.0014468009,0.0015352636,0.0002763631,0.00045327866,0.0045699417],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9658653,0.026629541,0.0011976749,0.0011456038,0.0044707325,0.0006910809],"domain_scores_gemma":[0.8944938,0.08503431,0.0013758027,0.004416412,0.012949534,0.0017302029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05790224,0.0020918685,0.0012840788,0.0038554093,0.0023804894,0.010243819,0.0038302322,0.003817135,0.006737927],"category_scores_gemma":[0.080268055,0.00066439883,0.0015123384,0.004338067,0.0063279714,0.01546131,0.004928042,0.006229623,0.0012326497],"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":[0.00011159662,0.00043101373,0.0023505457,0.004690605,0.00008348911,0.00014910594,0.0043193055,0.007314324,0.0003942028,0.16563478,0.016370151,0.7981509],"study_design_scores_gemma":[0.00021171062,0.0006913652,0.00425074,0.0228016,0.00015155881,0.00045803777,0.013225417,0.03417471,0.0041503813,0.6690505,0.2506117,0.00022236757],"about_ca_topic_score_codex":0.014929599,"about_ca_topic_score_gemma":0.01094337,"teacher_disagreement_score":0.05790224,"about_ca_system_score_codex":0.00787459,"about_ca_system_score_gemma":0.018454447,"threshold_uncertainty_score":0.30621994},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026954476,0.02873369,0.66362417,0.19707644,0.0052183564,0.017784268,0.0018402234,0.0009831153,0.05778528],"genre_scores_gemma":[0.38445637,0.01022684,0.5555944,0.021288546,0.0018611018,0.020291097,0.0010348334,0.0004729253,0.004773924],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.19653402,0.6873311,0.054874677,0.0045237676,0.05486862,0.0018678294],"domain_scores_gemma":[0.06681586,0.63073397,0.0431126,0.05556329,0.20056818,0.0032060938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6795222,0.00093397923,0.0029215463,0.009125547,0.0042754086,0.0154440375,0.0046321973,0.0035882366,0.005775798],"category_scores_gemma":[0.7974698,0.0007566596,0.002605198,0.0089602545,0.0097932955,0.008244547,0.008508016,0.008663053,0.0012593272],"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":[0.0013254154,0.00043443925,0.028313048,0.014157557,0.0014799888,0.0001296372,0.010454312,0.0034283255,0.000956168,0.19462249,0.049368948,0.69532967],"study_design_scores_gemma":[0.0018676316,0.0030117922,0.039498996,0.0896488,0.0027579884,0.00064232724,0.013426994,0.026203657,0.015284038,0.36710688,0.43985075,0.0007001094],"about_ca_topic_score_codex":0.007094366,"about_ca_topic_score_gemma":0.0052776854,"teacher_disagreement_score":0.6795222,"about_ca_system_score_codex":0.01893633,"about_ca_system_score_gemma":0.061725397,"threshold_uncertainty_score":0.3952062},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015111738,0.010774797,0.70047987,0.18562904,0.0051490692,0.0044767475,0.0000986639,0.00094007415,0.07733988],"genre_scores_gemma":[0.44650272,0.0048061633,0.50606793,0.02285674,0.0019722988,0.011696885,0.000076806886,0.0006485169,0.0053719557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.17608705,0.76140606,0.020047734,0.014837955,0.02403522,0.0035858783],"domain_scores_gemma":[0.1790014,0.70258856,0.02003249,0.05233655,0.04006831,0.0059727733],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6363066,0.0023923852,0.004010295,0.011745642,0.0107399635,0.035169918,0.008170935,0.012264353,0.005727237],"category_scores_gemma":[0.6249049,0.002773824,0.0033291471,0.0049712635,0.13846008,0.04205873,0.032209393,0.023065591,0.0015263923],"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":[0.00020513945,0.00018430207,0.001518221,0.0042971605,0.00026610892,0.00046610238,0.20699854,0.0014064319,0.00073608145,0.67878205,0.008746704,0.096393146],"study_design_scores_gemma":[0.00027745092,0.00027323383,0.0004969805,0.009680139,0.00008800164,0.0003592958,0.04204626,0.0023158835,0.0016286368,0.8379896,0.10467662,0.0001678459],"about_ca_topic_score_codex":0.0024364695,"about_ca_topic_score_gemma":0.0018928031,"teacher_disagreement_score":0.36369342,"about_ca_system_score_codex":0.020911653,"about_ca_system_score_gemma":0.044426695,"threshold_uncertainty_score":0.4484988},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047891038,0.013772107,0.03383259,0.85361826,0.08375966,0.0017931013,0.0001565975,0.00016477096,0.008113885],"genre_scores_gemma":[0.1648271,0.025643531,0.27805835,0.3998846,0.10469887,0.011924073,0.0003514141,0.00064060866,0.013971598],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.47667432,0.41130263,0.04960708,0.011801216,0.04561294,0.0050019077],"domain_scores_gemma":[0.10734575,0.7276478,0.038440797,0.032162167,0.06858927,0.025814243],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38869554,0.0016437648,0.0032146168,0.005412452,0.011268432,0.030498274,0.005377348,0.020615356,0.005449567],"category_scores_gemma":[0.7379322,0.0017145509,0.0027135669,0.0031886976,0.01844388,0.019718396,0.011014299,0.0272956,0.0037411137],"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":[0.0004002218,0.0009359731,0.0039382232,0.011598932,0.001094398,0.0020733275,0.042204615,0.00084932474,0.0013539225,0.06924542,0.5178115,0.34849408],"study_design_scores_gemma":[0.00078595395,0.0011762704,0.0026162274,0.028754823,0.0011269173,0.0031779709,0.055998817,0.0023814673,0.003514003,0.23163791,0.6683241,0.00050542346],"about_ca_topic_score_codex":0.00065462984,"about_ca_topic_score_gemma":0.001407453,"teacher_disagreement_score":0.61130446,"about_ca_system_score_codex":0.008142358,"about_ca_system_score_gemma":0.046758875,"threshold_uncertainty_score":0.75384724},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004567851,0.007060954,0.8363951,0.0689812,0.0020275612,0.0047350577,0.0011041703,0.0008019355,0.074326225],"genre_scores_gemma":[0.1488713,0.0036586837,0.80370975,0.009664468,0.00074488024,0.025765633,0.00030740863,0.0004720061,0.006805806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.4189082,0.53687626,0.012440527,0.0060024783,0.024366416,0.0014060416],"domain_scores_gemma":[0.20884126,0.6983519,0.01401523,0.054144766,0.021860417,0.0027864666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4073342,0.002528089,0.0033899203,0.017861549,0.0070837997,0.021748796,0.0057923384,0.005583623,0.014557322],"category_scores_gemma":[0.50845295,0.0023464742,0.0022404864,0.008550877,0.059733175,0.023642149,0.021627095,0.0084700845,0.0036975855],"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":[0.00010420349,0.000120776764,0.0011712573,0.0030879278,0.000110828034,0.00008758043,0.025662562,0.0008244312,0.0004310256,0.8361864,0.010529637,0.12168324],"study_design_scores_gemma":[0.00014427533,0.000114050774,0.0005831205,0.004869437,0.00004857954,0.0002131139,0.012504937,0.0025044577,0.00076647475,0.90330946,0.07483998,0.0001021296],"about_ca_topic_score_codex":0.003213503,"about_ca_topic_score_gemma":0.0036460578,"teacher_disagreement_score":0.5926658,"about_ca_system_score_codex":0.013495064,"about_ca_system_score_gemma":0.023295628,"threshold_uncertainty_score":0.73086244},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34874302,0.027891034,0.44427046,0.019915527,0.0009526458,0.003836915,0.0007357002,0.0007123551,0.15294239],"genre_scores_gemma":[0.8780047,0.0028673636,0.11315494,0.00048871204,0.00022609865,0.0025017879,0.00018869965,0.00015475348,0.0024129048],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5580021,0.3496925,0.017381322,0.0056440006,0.06735093,0.0019291677],"domain_scores_gemma":[0.25023207,0.6509695,0.022227988,0.019171905,0.0555921,0.001806373],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34010202,0.0016997164,0.0016568147,0.012293181,0.0025041634,0.01681311,0.0026973472,0.0028277135,0.0047698137],"category_scores_gemma":[0.5485969,0.00094392453,0.002459351,0.009608186,0.0069843098,0.010517954,0.0054842005,0.0041687973,0.00051591464],"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":[0.00086502335,0.00077731546,0.051662207,0.0079587195,0.0014599763,0.0002719583,0.041831926,0.010004262,0.0026161682,0.10597092,0.0036409104,0.7729406],"study_design_scores_gemma":[0.0008180488,0.005415685,0.29436943,0.035051756,0.002915676,0.0025422298,0.03876358,0.14004868,0.025665997,0.2682886,0.18497254,0.00114772],"about_ca_topic_score_codex":0.008412727,"about_ca_topic_score_gemma":0.00769343,"teacher_disagreement_score":0.659898,"about_ca_system_score_codex":0.012037493,"about_ca_system_score_gemma":0.011473902,"threshold_uncertainty_score":0.8137717},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15275049,0.013870631,0.018269217,0.55071074,0.0011498809,0.00016368621,0.00035729248,0.00013261163,0.26259544],"genre_scores_gemma":[0.96385294,0.0028253864,0.0032502387,0.019367449,0.0005897372,0.00013566433,0.00007652005,0.00007659978,0.009825431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88804907,0.04641452,0.0038672786,0.007944231,0.048396528,0.0053283875],"domain_scores_gemma":[0.8760252,0.068846025,0.014943357,0.017281188,0.020394944,0.0025092985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07216419,0.00032941953,0.00061415223,0.0030606976,0.0064484566,0.011568172,0.003346057,0.0030740646,0.0058979816],"category_scores_gemma":[0.12776059,0.000500174,0.00039313722,0.0064744065,0.063175924,0.008495753,0.009241439,0.0048032496,0.00034200755],"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":[0.000070856215,0.00002593945,0.018941335,0.00044299915,0.000037236183,0.0001573578,0.046481937,0.00021499833,0.00036834375,0.8200205,0.012820948,0.100417525],"study_design_scores_gemma":[0.00013258235,0.00017132072,0.10059356,0.0051778504,0.0001284596,0.00033118523,0.079125434,0.0010247091,0.0014315946,0.23115686,0.58060485,0.00012164074],"about_ca_topic_score_codex":0.369699,"about_ca_topic_score_gemma":0.44147658,"teacher_disagreement_score":0.369699,"about_ca_system_score_codex":0.047663223,"about_ca_system_score_gemma":0.04427642,"threshold_uncertainty_score":0.7350942},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58395606,0.10465621,0.0314854,0.050088394,0.001446468,0.0032048186,0.009015874,0.0008608863,0.21528582],"genre_scores_gemma":[0.9350828,0.01315251,0.029951034,0.00173176,0.00017687137,0.00078109,0.0022616487,0.0000900034,0.01677232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9548737,0.017786367,0.002341983,0.0016305111,0.021402588,0.0019649589],"domain_scores_gemma":[0.8851855,0.033789974,0.0044173812,0.0022462942,0.07234876,0.0020121553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054058,0.0012097463,0.0012779891,0.008529728,0.003085729,0.009845151,0.0025722256,0.0017892809,0.0072730887],"category_scores_gemma":[0.09728009,0.00047386062,0.0015069268,0.013110168,0.0016397006,0.0030139878,0.0018304967,0.001504783,0.00077421294],"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":[0.0011660766,0.00060110836,0.19321649,0.008236288,0.0014250152,0.0001274825,0.007461524,0.01263177,0.0024362286,0.024394449,0.032369774,0.7159338],"study_design_scores_gemma":[0.0006142229,0.002855021,0.76862603,0.013445616,0.00218247,0.0001590843,0.011842359,0.025903659,0.01185493,0.003978944,0.15811028,0.00042735718],"about_ca_topic_score_codex":0.92174065,"about_ca_topic_score_gemma":0.90802586,"teacher_disagreement_score":0.9050044,"about_ca_system_score_codex":0.094995625,"about_ca_system_score_gemma":0.09122834,"threshold_uncertainty_score":0.68924475},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010888329,0.5981587,0.0013366519,0.23116636,0.06490395,0.00021124724,0.0028402712,0.00043516318,0.09985878],"genre_scores_gemma":[0.015898759,0.7898116,0.005874269,0.09985958,0.017559372,0.00021037548,0.0038442959,0.000379633,0.066562116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9825486,0.0019090916,0.0019878512,0.00063805934,0.011308471,0.0016079728],"domain_scores_gemma":[0.91285443,0.006404004,0.0013973383,0.0010235627,0.072917275,0.005403363],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015242437,0.0012056069,0.0018902214,0.011643552,0.0045755557,0.008497331,0.0033927616,0.005726295,0.012657087],"category_scores_gemma":[0.035195258,0.00073242374,0.0012098518,0.019257165,0.0029918884,0.0035710705,0.0026330396,0.006461239,0.004096049],"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":[0.00002402288,0.000020322126,0.0004735159,0.0007428108,0.000012909316,0.000112565125,0.00013448007,0.00009295558,0.000045715107,0.0016569055,0.8903769,0.10630684],"study_design_scores_gemma":[0.000011152939,0.000013028988,0.002248667,0.0020493902,0.00002320297,0.00015082005,0.00015655355,0.00003593695,0.000038049693,0.00039289828,0.99485695,0.000023283681],"about_ca_topic_score_codex":0.8982656,"about_ca_topic_score_gemma":0.95317596,"teacher_disagreement_score":0.98475754,"about_ca_system_score_codex":0.061856307,"about_ca_system_score_gemma":0.19070685,"threshold_uncertainty_score":0.44880104},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020104279,0.42543676,0.15744053,0.2083274,0.07170861,0.01437602,0.006705101,0.011221716,0.10277347],"genre_scores_gemma":[0.0052486337,0.31875074,0.31833637,0.034140114,0.021270096,0.016370399,0.0043113087,0.0038784945,0.27769384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889537,0.0051420415,0.0014904191,0.00045492034,0.0037682313,0.0001906876],"domain_scores_gemma":[0.89600205,0.06436069,0.004441578,0.0035500578,0.026214128,0.0054314667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021818526,0.0019623132,0.0039672395,0.0093887225,0.001984963,0.0047558565,0.0026649246,0.0028910886,0.051395237],"category_scores_gemma":[0.0690283,0.002082159,0.0013668597,0.0082544675,0.0031139113,0.0058777053,0.0026862936,0.0058039846,0.06891316],"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":[0.000015704638,0.00004286252,0.000063665626,0.0011339381,0.000011392141,0.000057052526,0.00037978074,0.00010515013,0.00041319057,0.0010350468,0.8814906,0.11525164],"study_design_scores_gemma":[0.000017073002,0.000060148053,0.00043302387,0.0015429115,0.00001244201,0.00031514786,0.00041185744,0.00012145862,0.00015163675,0.0036861266,0.993212,0.00003618003],"about_ca_topic_score_codex":0.0049308045,"about_ca_topic_score_gemma":0.019007448,"teacher_disagreement_score":0.051395237,"about_ca_system_score_codex":0.002242661,"about_ca_system_score_gemma":0.012237798,"threshold_uncertainty_score":0.17193419},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011229881,0.04408596,0.00463454,0.048814457,0.0012974067,0.00010499052,0.00039260296,0.00012538594,0.8893147],"genre_scores_gemma":[0.580921,0.08146534,0.017010625,0.0107673155,0.00040528158,0.00023927557,0.00053304917,0.00024665295,0.3084115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99114907,0.00243139,0.0002278939,0.00077795837,0.0034599693,0.0019536898],"domain_scores_gemma":[0.99524695,0.0015886223,0.00013847867,0.00020759465,0.0018865493,0.00093179365],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0061214175,0.0008532522,0.0007161576,0.003672038,0.022837993,0.01767012,0.0025109237,0.0024933338,0.011964767],"category_scores_gemma":[0.006862816,0.00049173663,0.00038522703,0.009247558,0.02678699,0.004176695,0.004944923,0.0038234373,0.0010905656],"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":true,"study_design_scores_codex":[0.000011961715,0.000011295139,0.00052860175,0.00021509346,0.0000063116704,0.00021283967,0.027441591,0.00046182654,0.00011075304,0.8762408,0.05116402,0.043594867],"study_design_scores_gemma":[0.0000051147663,0.0000072223447,0.00165196,0.0006898383,0.000009445666,0.00007793114,0.021842472,0.00022181343,0.00009063418,0.03211748,0.94325125,0.000034819772],"about_ca_topic_score_codex":0.9912947,"about_ca_topic_score_gemma":0.9962877,"teacher_disagreement_score":0.9938786,"about_ca_system_score_codex":0.24790007,"about_ca_system_score_gemma":0.31285253,"threshold_uncertainty_score":0.8723293},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009204209,0.5590852,0.15804443,0.1284953,0.009448757,0.0011363649,0.004959189,0.0029728997,0.12665364],"genre_scores_gemma":[0.27269983,0.27209628,0.29876667,0.011057904,0.0020693163,0.0025992459,0.0033303008,0.0022305064,0.13514994],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9721181,0.009500567,0.0022561585,0.0013526086,0.013928759,0.0008438391],"domain_scores_gemma":[0.8683654,0.058467325,0.005744045,0.0063582147,0.05735626,0.0037086308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053904302,0.0015391631,0.001219177,0.005820936,0.004512328,0.0106607415,0.002664604,0.0034801753,0.013924407],"category_scores_gemma":[0.120573066,0.0017818325,0.00088762265,0.006626235,0.010139017,0.007803382,0.0031162645,0.0077249203,0.008799793],"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":[0.00020860642,0.000075208685,0.0061712097,0.0017980571,0.000048509362,0.00011813349,0.0042810873,0.00081320794,0.0015902853,0.024181843,0.3270421,0.63367176],"study_design_scores_gemma":[0.000062795414,0.000119706936,0.045631457,0.004920699,0.000084175845,0.00038397327,0.0027669868,0.00083423394,0.002344542,0.014039434,0.9285591,0.00025291377],"about_ca_topic_score_codex":0.5383365,"about_ca_topic_score_gemma":0.6527193,"teacher_disagreement_score":0.5383365,"about_ca_system_score_codex":0.029230108,"about_ca_system_score_gemma":0.0446307,"threshold_uncertainty_score":0.92876464},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0111059,0.45985985,0.021971153,0.45167434,0.0037382075,0.00066163024,0.00013534681,0.0000547305,0.05079885],"genre_scores_gemma":[0.4421605,0.4345737,0.06058213,0.055253416,0.0020355757,0.0012878638,0.00020542387,0.00010150025,0.0037998185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.89303803,0.079456456,0.0042898823,0.0027575463,0.015529738,0.004928434],"domain_scores_gemma":[0.9064334,0.07134603,0.0071511543,0.0022523727,0.009205249,0.0036117095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.086938195,0.001599481,0.0035081296,0.005992156,0.0068559,0.01981843,0.0045309793,0.011909874,0.003708863],"category_scores_gemma":[0.10455287,0.0011624593,0.0014581499,0.006557151,0.025551558,0.025278553,0.0060816254,0.010157224,0.00078685005],"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":[0.00009655951,0.0002709998,0.0016193886,0.01393103,0.0002223752,0.00015810822,0.019251663,0.0019536768,0.00019859895,0.5479312,0.020892143,0.39347425],"study_design_scores_gemma":[0.0001958149,0.00030214922,0.0031004113,0.1200601,0.0004272392,0.00034700995,0.056485657,0.0018030878,0.000982629,0.4067375,0.40934572,0.00021264447],"about_ca_topic_score_codex":0.044623297,"about_ca_topic_score_gemma":0.04699173,"teacher_disagreement_score":0.086938195,"about_ca_system_score_codex":0.033492196,"about_ca_system_score_gemma":0.07685346,"threshold_uncertainty_score":0.4597786},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7578648,0.007130984,0.10741873,0.053135514,0.0014240494,0.0015957641,0.0004652975,0.00030006145,0.070664845],"genre_scores_gemma":[0.9761997,0.0017286222,0.01229538,0.0025426666,0.00014991414,0.0007377716,0.000090978516,0.00022103301,0.0060338993],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.844342,0.13882127,0.0023030536,0.0031256385,0.0070742713,0.0043338514],"domain_scores_gemma":[0.8917132,0.08448231,0.0067380997,0.003986778,0.0077763097,0.0053034024],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047560845,0.0022217974,0.0014122173,0.004740419,0.021295823,0.012502068,0.004025758,0.004919998,0.0027448693],"category_scores_gemma":[0.108741,0.0016915881,0.0011271884,0.003043594,0.050566662,0.017704038,0.018858025,0.010419095,0.00069772784],"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":[0.000022193874,0.000009363767,0.00047132955,0.00008728462,0.000006415279,0.00050659926,0.9908366,0.000046654328,0.00033885086,0.004512028,0.00082039967,0.0023422663],"study_design_scores_gemma":[0.0000037022583,0.00002305297,0.00018764906,0.00022083487,0.0000044189283,0.00046890235,0.968174,0.00017583052,0.00040822208,0.0025618966,0.027751358,0.000020128455],"about_ca_topic_score_codex":0.006772689,"about_ca_topic_score_gemma":0.00820781,"teacher_disagreement_score":0.9524391,"about_ca_system_score_codex":0.010382581,"about_ca_system_score_gemma":0.0062895473,"threshold_uncertainty_score":0.2515288},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23073779,0.04935253,0.2206272,0.35049844,0.006136649,0.001532016,0.0021321317,0.0008677913,0.13811551],"genre_scores_gemma":[0.78396237,0.009121634,0.18843336,0.006674055,0.0005608026,0.0004918378,0.00046118087,0.00023325483,0.010061437],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944125,0.0034381542,0.00030414914,0.00034858004,0.0007901083,0.0007065383],"domain_scores_gemma":[0.9787692,0.0071306312,0.002296619,0.0005619199,0.0058835256,0.0053581377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014176124,0.0007723299,0.0012531308,0.0038901896,0.003917783,0.009017377,0.0018090173,0.0035536657,0.017149586],"category_scores_gemma":[0.047996324,0.00047585546,0.0003767948,0.0027556575,0.0021351746,0.013139438,0.0025725658,0.003323336,0.0040358403],"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":[0.0006772621,0.00046689386,0.032237127,0.0016371085,0.00013328547,0.00034408606,0.0044536586,0.0030134416,0.0020014332,0.07328478,0.090826586,0.7909243],"study_design_scores_gemma":[0.0005244726,0.0013234878,0.06730748,0.006798404,0.0004977014,0.0010781697,0.09496704,0.023968052,0.004870337,0.52707285,0.27102402,0.00056797214],"about_ca_topic_score_codex":0.013602795,"about_ca_topic_score_gemma":0.03681329,"teacher_disagreement_score":0.017149586,"about_ca_system_score_codex":0.004580547,"about_ca_system_score_gemma":0.0097615095,"threshold_uncertainty_score":0.07497144},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91667515,0.0049094227,0.003010296,0.011457919,0.000094970506,0.000291812,0.00043780147,0.000033343633,0.06308933],"genre_scores_gemma":[0.9957768,0.00067656324,0.0011230935,0.00019414758,0.0000033788936,0.00006716885,0.000069345966,0.0000093317285,0.0020803763],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97742015,0.015057355,0.0005408812,0.0013479536,0.0018373762,0.003796284],"domain_scores_gemma":[0.97812974,0.01254898,0.001534231,0.00093219685,0.003610699,0.0032441283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021753244,0.00036360274,0.0005333412,0.0021962696,0.014895556,0.009283723,0.0020479115,0.0012924039,0.0036636058],"category_scores_gemma":[0.02167347,0.00032203743,0.0003437616,0.0037231392,0.013399575,0.0043241936,0.007769585,0.0011098213,0.00017350841],"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":[0.00025275955,0.00013597762,0.117048286,0.00061223813,0.00011179157,0.0011710584,0.7321019,0.0023315155,0.00078335777,0.04907779,0.0069897566,0.089383595],"study_design_scores_gemma":[0.000032400105,0.000064693355,0.0684656,0.0011806122,0.000052634463,0.0000905715,0.8644076,0.0011306424,0.0003336927,0.0037021602,0.060465265,0.00007411395],"about_ca_topic_score_codex":0.9679423,"about_ca_topic_score_gemma":0.9782508,"teacher_disagreement_score":0.100331016,"about_ca_system_score_codex":0.100331016,"about_ca_system_score_gemma":0.11292318,"threshold_uncertainty_score":0.7279559},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003169961,0.81088233,0.04582564,0.07278836,0.01081873,0.00019082529,0.0003453795,0.000829233,0.05800248],"genre_scores_gemma":[0.020359527,0.6854475,0.11535963,0.03215001,0.0112634795,0.0014857192,0.00062976085,0.0010997197,0.13220471],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98243445,0.0072532794,0.0017690758,0.00063280005,0.0074732103,0.00043718432],"domain_scores_gemma":[0.95169187,0.03322371,0.0013336069,0.001903407,0.010375143,0.0014722775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0236915,0.0025047746,0.0026676902,0.006826279,0.0029090617,0.011432541,0.0023344783,0.006082989,0.0083241975],"category_scores_gemma":[0.031877067,0.0023282873,0.0010368016,0.005025819,0.0154826725,0.011639229,0.0036992254,0.009082286,0.006522663],"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":[0.000019552805,0.00005279705,0.0003152922,0.0010634463,0.000015408503,0.000053569034,0.001306329,0.00038015906,0.00020296266,0.03775091,0.5962988,0.36254078],"study_design_scores_gemma":[0.000017847382,0.000038166025,0.0008669805,0.0038583837,0.000018596078,0.00036510173,0.0011770907,0.000335102,0.00023647267,0.08736873,0.90566176,0.00005578821],"about_ca_topic_score_codex":0.02332707,"about_ca_topic_score_gemma":0.05148462,"teacher_disagreement_score":0.0236915,"about_ca_system_score_codex":0.006475783,"about_ca_system_score_gemma":0.017480092,"threshold_uncertainty_score":0.12529415},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058639217,0.13959809,0.48859835,0.058457945,0.005424008,0.012435188,0.00054278545,0.0005192134,0.23578514],"genre_scores_gemma":[0.7536233,0.026844192,0.19906977,0.005017719,0.00085779873,0.012430354,0.00019604868,0.00022856981,0.0017322442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27923164,0.66304797,0.013714479,0.005158071,0.0366786,0.0021691925],"domain_scores_gemma":[0.18607923,0.76857775,0.01074809,0.012699552,0.01993686,0.001958478],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43579936,0.002047706,0.0037726525,0.021183388,0.005001831,0.01900191,0.00420043,0.004334162,0.0059699025],"category_scores_gemma":[0.65571606,0.0011277781,0.0022572714,0.015762448,0.031021692,0.02058385,0.012860647,0.0064153452,0.0005363947],"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":[0.00074858154,0.0005193882,0.01311288,0.012289218,0.0012617987,0.00011138058,0.013943018,0.00802108,0.00010738143,0.5762841,0.006083447,0.36751783],"study_design_scores_gemma":[0.00097035477,0.0033027288,0.016869042,0.056575403,0.0012170012,0.00039431534,0.03676134,0.02421399,0.0014813001,0.771741,0.086116865,0.0003566811],"about_ca_topic_score_codex":0.0072548813,"about_ca_topic_score_gemma":0.0056749536,"teacher_disagreement_score":0.43579936,"about_ca_system_score_codex":0.035733208,"about_ca_system_score_gemma":0.035020877,"threshold_uncertainty_score":0.6957599},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8616684,0.0035436677,0.055086203,0.0067743533,0.00048452,0.0106969355,0.0006825109,0.00024979727,0.060813602],"genre_scores_gemma":[0.974739,0.00034126558,0.02144892,0.00035929444,0.000054526463,0.002302056,0.0001709236,0.000014525553,0.0005694509],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6875693,0.25875446,0.009106302,0.0033927492,0.03528638,0.0058907685],"domain_scores_gemma":[0.6770677,0.2241314,0.03359898,0.009731686,0.04959907,0.005871247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15713423,0.00115423,0.0011619775,0.003656958,0.0020232766,0.005635842,0.0014086853,0.0019071518,0.0029370904],"category_scores_gemma":[0.25740433,0.0002906135,0.0016546542,0.0038592494,0.0033163796,0.0057105166,0.0041531166,0.0019318986,0.0003523227],"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":[0.0067956233,0.013070182,0.2050275,0.0044768853,0.0024091185,0.00024092586,0.0071693687,0.05164378,0.0027654734,0.095619895,0.009623979,0.6011573],"study_design_scores_gemma":[0.0060529266,0.09434843,0.4418052,0.007555476,0.0035592555,0.0003949749,0.020962596,0.194461,0.042738434,0.14081901,0.046415124,0.0008876204],"about_ca_topic_score_codex":0.007915424,"about_ca_topic_score_gemma":0.0069001545,"teacher_disagreement_score":0.15713423,"about_ca_system_score_codex":0.02033414,"about_ca_system_score_gemma":0.031133646,"threshold_uncertainty_score":0.8310152},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79842913,0.0015087752,0.0069035203,0.028383348,0.0001519264,0.0008190748,0.000077418874,0.000050847542,0.16367601],"genre_scores_gemma":[0.9838935,0.0005041693,0.0032912344,0.0012109154,0.000033302065,0.00017121855,0.000026133705,0.000013429137,0.010856042],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9645171,0.02635456,0.00054725015,0.0008073287,0.0027164593,0.005057229],"domain_scores_gemma":[0.92922014,0.04964415,0.0041718488,0.0013522258,0.0070530386,0.00855854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025700733,0.0002931964,0.00028464192,0.002298546,0.025386833,0.008344171,0.0021560602,0.0034298908,0.005659194],"category_scores_gemma":[0.04525903,0.00044373146,0.0002494327,0.0024113446,0.0067946576,0.0036519938,0.006139654,0.003402252,0.00059208093],"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":[0.00086375425,0.001579008,0.13019645,0.0007070036,0.00008845028,0.014795834,0.434486,0.011523458,0.0039577396,0.138168,0.028587863,0.23504646],"study_design_scores_gemma":[0.00014043714,0.00050152815,0.05289265,0.00079693034,0.000066497494,0.0015235014,0.68702257,0.0060726996,0.0017254595,0.011949476,0.2372079,0.00010030543],"about_ca_topic_score_codex":0.19632918,"about_ca_topic_score_gemma":0.4335241,"teacher_disagreement_score":0.8036708,"about_ca_system_score_codex":0.018170219,"about_ca_system_score_gemma":0.031763013,"threshold_uncertainty_score":0.3903728},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25165746,0.0058149933,0.014368685,0.14690578,0.00043079053,0.00075003237,0.00036714593,0.000094193056,0.5796109],"genre_scores_gemma":[0.98437977,0.0009487437,0.0037110932,0.0021268695,0.00003057313,0.00009487907,0.000039419385,0.000025068746,0.008643482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9675189,0.02066538,0.0009902489,0.0013365976,0.0044933725,0.0049953675],"domain_scores_gemma":[0.968952,0.012781636,0.0020858673,0.0012467171,0.009614746,0.00531906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028767621,0.00030360464,0.000527158,0.002379648,0.018128684,0.021602081,0.0022081356,0.0023282797,0.0041957838],"category_scores_gemma":[0.025499403,0.00039492088,0.00032054418,0.0035399694,0.028043648,0.0052152644,0.009211123,0.0036795838,0.00020337343],"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":[0.00012583556,0.00017222678,0.028273765,0.0005768781,0.000029778745,0.005556827,0.11372041,0.0025423253,0.0011596822,0.7544316,0.019947872,0.07346283],"study_design_scores_gemma":[0.000061012288,0.00014221773,0.037934188,0.0024805306,0.000057455673,0.0008202071,0.33204636,0.0018536134,0.0017736601,0.06199967,0.56066525,0.00016585112],"about_ca_topic_score_codex":0.7188526,"about_ca_topic_score_gemma":0.8475254,"teacher_disagreement_score":0.8105787,"about_ca_system_score_codex":0.18942133,"about_ca_system_score_gemma":0.151056,"threshold_uncertainty_score":0.94015634},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02761912,0.15856631,0.34784797,0.36786798,0.008716635,0.0067819846,0.0020411727,0.0006079742,0.07995095],"genre_scores_gemma":[0.28675234,0.07308248,0.5763091,0.040183704,0.0027113664,0.016052872,0.00063304004,0.0006197004,0.003655506],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.51950103,0.36972407,0.041056406,0.009683604,0.055810295,0.0042245337],"domain_scores_gemma":[0.21259227,0.6289802,0.028408788,0.02826151,0.09809104,0.0036661576],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5207908,0.0016830564,0.0038905863,0.010149499,0.0042659873,0.020789428,0.010408029,0.008739012,0.0063892077],"category_scores_gemma":[0.58966106,0.0015715364,0.003876295,0.012900098,0.019757232,0.024901228,0.008858263,0.014576735,0.0023278212],"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":[0.0006470837,0.00063685473,0.012473622,0.028186109,0.0007620769,0.00020188646,0.02280259,0.002748099,0.0010536644,0.33733472,0.039879892,0.5532735],"study_design_scores_gemma":[0.00065741944,0.0010030149,0.017488744,0.14940059,0.0011192512,0.00069577195,0.049984656,0.005487356,0.0047333795,0.4158615,0.35286838,0.00070005096],"about_ca_topic_score_codex":0.0054979003,"about_ca_topic_score_gemma":0.0071544275,"teacher_disagreement_score":0.47920918,"about_ca_system_score_codex":0.01344455,"about_ca_system_score_gemma":0.03601678,"threshold_uncertainty_score":0.59095025},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69161236,0.0068714954,0.0045259213,0.10695091,0.00054597144,0.0009444059,0.00022000866,0.00018372913,0.18814518],"genre_scores_gemma":[0.9155887,0.0071485317,0.014793474,0.015971566,0.00019613434,0.0005815365,0.00018941297,0.00023873382,0.04529196],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98759204,0.007135133,0.0003803842,0.00062141655,0.0022497657,0.0020212247],"domain_scores_gemma":[0.9874456,0.0055783857,0.0007461388,0.00079640525,0.0025821943,0.002851335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031462613,0.00037947425,0.00037232556,0.0008258255,0.0065287594,0.007008171,0.0020601253,0.0027817753,0.005224991],"category_scores_gemma":[0.015527503,0.00044563625,0.00047268972,0.001123815,0.0046839938,0.0038934445,0.0061720978,0.005023216,0.00061528356],"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":[0.00088192173,0.00533034,0.025107684,0.0013563723,0.000080355385,0.009553501,0.24934983,0.002996151,0.0070594293,0.104221486,0.0998182,0.49424484],"study_design_scores_gemma":[0.0001269174,0.0016082238,0.030234639,0.0015912626,0.000022395012,0.0027949484,0.09553244,0.002935798,0.0017904139,0.0041306145,0.85904723,0.00018516544],"about_ca_topic_score_codex":0.062140863,"about_ca_topic_score_gemma":0.10110878,"teacher_disagreement_score":0.062140863,"about_ca_system_score_codex":0.008473448,"about_ca_system_score_gemma":0.018061414,"threshold_uncertainty_score":0.16639215},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.704709,0.004183885,0.0006581219,0.03678993,0.00035845555,0.00019938065,0.0006432883,0.000052585463,0.25240532],"genre_scores_gemma":[0.9407372,0.0026049088,0.00024129282,0.0024798962,0.00008945877,0.000085500506,0.00019731757,0.000027216804,0.053537108],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9898617,0.0014327478,0.000397792,0.0006226538,0.0046429774,0.003042106],"domain_scores_gemma":[0.98304623,0.004442699,0.002849167,0.00062835345,0.0057346253,0.0032988864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045703505,0.00022844785,0.00033521873,0.002268169,0.020558774,0.0045285053,0.0015969176,0.0016619294,0.0047147386],"category_scores_gemma":[0.017481705,0.00048528786,0.00026795478,0.004547832,0.020220138,0.0018334987,0.0055225277,0.0033546968,0.00031867452],"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":[0.00016596768,0.00013504703,0.09285894,0.00031180153,0.000021174203,0.0014792362,0.72824705,0.00021395794,0.0007333167,0.04661943,0.023038004,0.10617605],"study_design_scores_gemma":[0.000015345544,0.00006713028,0.25856742,0.0004346428,0.000015239271,0.0002188767,0.17174448,0.00011375072,0.00047653526,0.0016675153,0.5665966,0.00008243789],"about_ca_topic_score_codex":0.9795629,"about_ca_topic_score_gemma":0.99057806,"teacher_disagreement_score":0.15287319,"about_ca_system_score_codex":0.15287319,"about_ca_system_score_gemma":0.1342335,"threshold_uncertainty_score":0.98254704},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99169827,0.00045754088,0.00016149759,0.00090093433,0.000011126629,0.00010052699,0.00003020876,0.000007238033,0.006632653],"genre_scores_gemma":[0.99740773,0.00023612857,0.00015404838,0.00010991129,0.0000057049706,0.00005128586,0.000023696743,0.0000036317058,0.0020078346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98932624,0.008176996,0.00025042353,0.00022302846,0.0006509159,0.0013724073],"domain_scores_gemma":[0.9762263,0.012360047,0.0027674555,0.00039471604,0.0026168954,0.0056345877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008799136,0.0002902671,0.00024303119,0.0010889703,0.0044163796,0.002733381,0.00068132364,0.00072500436,0.0063300016],"category_scores_gemma":[0.01293946,0.00023203304,0.00010540153,0.0008606013,0.0015980775,0.0012612874,0.0030885201,0.00086218875,0.0004251676],"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":[0.0012650322,0.0024326195,0.42474082,0.0014986584,0.000060893075,0.006508429,0.40379944,0.00069011166,0.0029554537,0.0033846854,0.006974182,0.14568968],"study_design_scores_gemma":[0.000031272088,0.0006426847,0.2500632,0.0005211956,0.000022171429,0.0007605942,0.72549665,0.00055401033,0.0010804163,0.0004363345,0.020346936,0.000044517365],"about_ca_topic_score_codex":0.0063742925,"about_ca_topic_score_gemma":0.01811754,"teacher_disagreement_score":0.008799136,"about_ca_system_score_codex":0.004697973,"about_ca_system_score_gemma":0.0047386037,"threshold_uncertainty_score":0.046534836},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97265494,0.0005167004,0.00019842987,0.0017260789,0.00000908722,0.000040336163,0.00024614492,0.0000055273695,0.02460285],"genre_scores_gemma":[0.99797136,0.00021487336,0.00026931503,0.00013717197,0.000004263229,0.000017852717,0.00011287032,0.0000028477689,0.0012693674],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99786645,0.00048224194,0.0000528846,0.000120942575,0.00066053285,0.0008168862],"domain_scores_gemma":[0.9938074,0.00139856,0.00057094044,0.00017683426,0.0023277157,0.0017185382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025196606,0.0000918638,0.00021794076,0.0027355456,0.0019652785,0.0020638255,0.0004311245,0.00025749355,0.0028124712],"category_scores_gemma":[0.0076776906,0.000110233384,0.00012817589,0.0052382257,0.0019497613,0.00095911894,0.0018217006,0.00079406914,0.00010635877],"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":[0.00022391588,0.0003817447,0.8602886,0.00015792537,0.00012389428,0.00026307962,0.012208358,0.0020619975,0.00046632174,0.0341995,0.0036400028,0.08598464],"study_design_scores_gemma":[0.000012659414,0.00005828759,0.9702041,0.00010594726,0.0000330617,0.000031557083,0.01801564,0.0014275246,0.0002869738,0.0013139991,0.00849597,0.000014299949],"about_ca_topic_score_codex":0.8198313,"about_ca_topic_score_gemma":0.89966404,"teacher_disagreement_score":0.9891218,"about_ca_system_score_codex":0.010878202,"about_ca_system_score_gemma":0.01643344,"threshold_uncertainty_score":0.36245942},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076106116,0.0058463993,0.5592641,0.02100179,0.0028648165,0.16480939,0.03915942,0.0015140887,0.12943375],"genre_scores_gemma":[0.19891879,0.0026718457,0.41352144,0.004324404,0.00034678707,0.36075735,0.0116162,0.0010380427,0.006805157],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.3988022,0.50759655,0.037410904,0.008162021,0.044316176,0.0037120315],"domain_scores_gemma":[0.32244122,0.45857552,0.03647369,0.05700524,0.12159998,0.0039043983],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3508638,0.001884216,0.0031703988,0.021118142,0.0063311863,0.010658625,0.0048717177,0.0025714452,0.016597178],"category_scores_gemma":[0.5827878,0.0018305889,0.002386125,0.022384034,0.00906958,0.012100328,0.015293265,0.0060462523,0.0037605034],"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":[0.0013563682,0.00068332197,0.01219248,0.028420182,0.0004961143,0.00047570316,0.30288973,0.0038839167,0.0020366907,0.15120779,0.072395906,0.4239618],"study_design_scores_gemma":[0.0010176101,0.0013681764,0.016628046,0.05437246,0.00042371257,0.00031517431,0.12811027,0.0054979674,0.008131589,0.17174587,0.61174613,0.00064305065],"about_ca_topic_score_codex":0.006958232,"about_ca_topic_score_gemma":0.007130477,"teacher_disagreement_score":0.6491362,"about_ca_system_score_codex":0.017125394,"about_ca_system_score_gemma":0.03100952,"threshold_uncertainty_score":0.8005005},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889774,0.0002908518,0.0035959017,0.0002629768,0.00003180046,0.003304367,0.0001418924,0.000047646587,0.0033471843],"genre_scores_gemma":[0.98510355,0.0002448507,0.009203828,0.000099127705,0.000016191707,0.004065707,0.00017393556,0.000012520123,0.0010802444],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96194017,0.028538264,0.0018365539,0.0015479161,0.004434875,0.001702202],"domain_scores_gemma":[0.9402554,0.038369272,0.0042318264,0.0022350622,0.013258587,0.0016498491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052316137,0.00084773253,0.0007875016,0.0012651689,0.0017357972,0.0016042015,0.0011287734,0.00076005905,0.0023380027],"category_scores_gemma":[0.07957215,0.00044109437,0.001306177,0.0009219044,0.0014681121,0.0011929106,0.001364271,0.0009920151,0.00025243475],"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":[0.021291487,0.033388864,0.14482106,0.0038140318,0.0011661897,0.00037833964,0.070230216,0.0048750634,0.006737896,0.0014041495,0.0014344269,0.7104584],"study_design_scores_gemma":[0.008228663,0.13587564,0.74387765,0.0025054384,0.0028365627,0.0002490954,0.037162844,0.016888546,0.029587869,0.0012499356,0.021267425,0.00027039257],"about_ca_topic_score_codex":0.10551654,"about_ca_topic_score_gemma":0.12521845,"teacher_disagreement_score":0.10551654,"about_ca_system_score_codex":0.012291237,"about_ca_system_score_gemma":0.016878929,"threshold_uncertainty_score":0.27667755},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05835407,0.033971675,0.26203543,0.57079524,0.0042926623,0.010759934,0.00053752854,0.0015131923,0.057740293],"genre_scores_gemma":[0.31713146,0.010906192,0.64103436,0.020611065,0.0007077777,0.007959807,0.00024124206,0.00038472272,0.0010233304],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.25647953,0.6191784,0.035450578,0.011686977,0.069571525,0.0076329876],"domain_scores_gemma":[0.112337284,0.67337745,0.028175466,0.056362566,0.116706036,0.01304124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7318178,0.0021897014,0.004107465,0.012356578,0.011986404,0.038825758,0.012174281,0.008762613,0.004124697],"category_scores_gemma":[0.7413005,0.0023090644,0.0022534966,0.009614414,0.02648786,0.032696262,0.029931394,0.021373266,0.0011414172],"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":[0.0003388354,0.0012340868,0.029797398,0.010590854,0.000527945,0.00029446307,0.06842017,0.006877442,0.0010222463,0.07282558,0.024233988,0.783837],"study_design_scores_gemma":[0.0014350045,0.0026348983,0.055037048,0.10390942,0.0008010029,0.000840769,0.2088015,0.019698944,0.005993649,0.30966634,0.28971872,0.0014628011],"about_ca_topic_score_codex":0.06345379,"about_ca_topic_score_gemma":0.0763068,"teacher_disagreement_score":0.7318178,"about_ca_system_score_codex":0.06421482,"about_ca_system_score_gemma":0.26154876,"threshold_uncertainty_score":0.4659133},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20791298,0.017627785,0.535782,0.05096101,0.0008928012,0.001884265,0.00029740704,0.0003791692,0.18426257],"genre_scores_gemma":[0.8939101,0.0045177955,0.09423836,0.001320826,0.000104415405,0.0023228189,0.00011036294,0.00015497846,0.0033202253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8409586,0.13035797,0.0031569644,0.0038555658,0.018910637,0.0027602077],"domain_scores_gemma":[0.7116935,0.2585535,0.005747995,0.011682511,0.011205952,0.0011163818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12767489,0.0014936627,0.0014683093,0.008059811,0.009121158,0.019340852,0.003922622,0.00583462,0.0063812113],"category_scores_gemma":[0.16074905,0.0012383048,0.001884693,0.011380089,0.043153524,0.025444353,0.00941098,0.0074486616,0.0006744337],"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":[0.00011862711,0.0002561947,0.005265126,0.0019575183,0.00006723847,0.0008644099,0.1174432,0.0017651982,0.00036631047,0.7989216,0.0019769035,0.07099774],"study_design_scores_gemma":[0.00024817802,0.0004179267,0.009358187,0.012246746,0.0003110746,0.0026748036,0.1810997,0.02300521,0.0050243307,0.58045,0.18492888,0.00023497183],"about_ca_topic_score_codex":0.022053497,"about_ca_topic_score_gemma":0.012159547,"teacher_disagreement_score":0.12767489,"about_ca_system_score_codex":0.02582543,"about_ca_system_score_gemma":0.027310684,"threshold_uncertainty_score":0.67521745},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028264866,0.93113476,0.0020920471,0.04724912,0.004837287,0.000029303472,0.00034080198,0.00011237498,0.013921718],"genre_scores_gemma":[0.0038600261,0.9787662,0.0026881192,0.0025070081,0.0018935056,0.00003196761,0.00019565436,0.000050861945,0.010006652],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722147,0.0009371364,0.00029006804,0.0001966082,0.0012210703,0.00013356569],"domain_scores_gemma":[0.98894346,0.0063438243,0.0008480346,0.00022733843,0.0026056054,0.0010317252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007040726,0.0019059387,0.0014734673,0.003810702,0.0013739328,0.006714528,0.0017977093,0.003226983,0.013222872],"category_scores_gemma":[0.010925748,0.0014447488,0.0006118145,0.006736242,0.002421347,0.0065745935,0.0019200642,0.004497274,0.012498701],"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":[0.000054508542,0.000023374112,0.0005368604,0.0015141509,0.000024583433,0.000039234194,0.00053473655,0.00031839474,0.00008750355,0.0039718505,0.6941663,0.29872847],"study_design_scores_gemma":[0.000034531775,0.000035184115,0.0029562814,0.0065051,0.00008150268,0.00026379683,0.0014439967,0.00039521142,0.00040682184,0.012777648,0.97503453,0.00006553767],"about_ca_topic_score_codex":0.06488541,"about_ca_topic_score_gemma":0.1637328,"teacher_disagreement_score":0.06488541,"about_ca_system_score_codex":0.0045916443,"about_ca_system_score_gemma":0.015339291,"threshold_uncertainty_score":0.12901545},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904447,0.00034973558,0.0005609811,0.0009344448,0.000014330495,0.00037451775,0.00028898678,0.000026536538,0.007005837],"genre_scores_gemma":[0.9980913,0.00014609848,0.00073368795,0.000070411246,0.000004935684,0.00014623368,0.00013428029,0.0000050127546,0.00066811277],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9809694,0.007104488,0.0011063534,0.0010885898,0.0057410332,0.0039899857],"domain_scores_gemma":[0.9435164,0.013109086,0.008763645,0.0023340983,0.023643818,0.008632962],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018155634,0.0003447365,0.00047068574,0.002360853,0.005689996,0.0033927874,0.0025440473,0.00054980477,0.0029723437],"category_scores_gemma":[0.03643117,0.00059126556,0.00034958005,0.003297391,0.0038200514,0.0013325752,0.0048578023,0.00081373716,0.00023380031],"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":[0.00041945765,0.00050194556,0.85818917,0.00060925883,0.000111465575,0.00023814771,0.07226549,0.0015340284,0.0015166207,0.0013461013,0.003927798,0.059340596],"study_design_scores_gemma":[0.00003291716,0.00023692512,0.9336769,0.00023187972,0.000027197699,0.00003351982,0.055128947,0.0010922456,0.00067455857,0.00024876895,0.008577416,0.000038719],"about_ca_topic_score_codex":0.88446397,"about_ca_topic_score_gemma":0.915966,"teacher_disagreement_score":0.98184437,"about_ca_system_score_codex":0.069190465,"about_ca_system_score_gemma":0.108065434,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025209345,0.8871961,0.0024291151,0.081662714,0.013102807,0.000019368967,0.00020887387,0.000067755114,0.015061194],"genre_scores_gemma":[0.003983376,0.96440756,0.0031505586,0.0059926636,0.004522324,0.000028454862,0.00013842853,0.000065961394,0.017710602],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981939,0.00046119577,0.00023665049,0.00016061745,0.0008689624,0.00007862802],"domain_scores_gemma":[0.9860225,0.007443171,0.0006104928,0.00024357991,0.0045498996,0.001130361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008110211,0.0013693247,0.0010299246,0.0031048479,0.0011229246,0.0047436305,0.0015231551,0.0022153503,0.010369175],"category_scores_gemma":[0.012075341,0.0007486206,0.00041646196,0.0049070073,0.0021199298,0.0060168994,0.0014562183,0.0057183756,0.009543336],"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":[0.00003835234,0.000018874145,0.0003579029,0.0014736257,0.00001555871,0.00007088589,0.00092334166,0.00019198055,0.00010795394,0.004729029,0.74875724,0.24331525],"study_design_scores_gemma":[0.0000072228445,0.0000138729865,0.00088324863,0.0031175904,0.000030020026,0.00023376466,0.0010747915,0.00009396915,0.00022832229,0.0052394844,0.98905396,0.000023790388],"about_ca_topic_score_codex":0.022603167,"about_ca_topic_score_gemma":0.05980334,"teacher_disagreement_score":0.022603167,"about_ca_system_score_codex":0.002640437,"about_ca_system_score_gemma":0.009934665,"threshold_uncertainty_score":0.044943154},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052478604,0.01089937,0.025065107,0.7579001,0.005481671,0.004175614,0.0039831204,0.0016102464,0.13840614],"genre_scores_gemma":[0.734339,0.010729163,0.1709172,0.052584514,0.00089452334,0.0048468704,0.003384277,0.0009403796,0.021364072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8335755,0.059367765,0.0076449495,0.0031999645,0.08756476,0.008647007],"domain_scores_gemma":[0.6479455,0.043880187,0.013664961,0.011248534,0.2538457,0.029415082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15332893,0.0009297596,0.0017259151,0.0041604084,0.010996823,0.01861532,0.0047130072,0.002587939,0.0059443624],"category_scores_gemma":[0.232121,0.0005592491,0.0008092722,0.0059477556,0.006235258,0.008441439,0.005971014,0.005400947,0.0012488835],"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":[0.00035392176,0.00038567823,0.031266063,0.0017447934,0.00023194593,0.000092577255,0.010565499,0.001912371,0.0007659853,0.020658718,0.3891376,0.5428849],"study_design_scores_gemma":[0.00044446363,0.0013952418,0.14221847,0.015123983,0.0003912489,0.00011288156,0.054069847,0.007581358,0.005469669,0.026416121,0.7459708,0.00080598675],"about_ca_topic_score_codex":0.87025553,"about_ca_topic_score_gemma":0.9315767,"teacher_disagreement_score":0.15332893,"about_ca_system_score_codex":0.11779499,"about_ca_system_score_gemma":0.334031,"threshold_uncertainty_score":0.8546665},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026442068,0.0050958483,0.071331516,0.040459845,0.0010893558,0.00052089593,0.00012427362,0.0003408384,0.85459536],"genre_scores_gemma":[0.54335386,0.010503065,0.09537768,0.010642227,0.00033485447,0.0012248259,0.0002658359,0.00025215856,0.33804545],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9971048,0.001725326,0.000053861062,0.00017029654,0.00070685183,0.00023884077],"domain_scores_gemma":[0.9987639,0.0004982364,0.0000656043,0.00012292949,0.00028273012,0.00026653623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042366376,0.00056566886,0.00037261567,0.0010283089,0.002828191,0.005615982,0.0011975738,0.0016615071,0.009508419],"category_scores_gemma":[0.0029027741,0.00024311809,0.0004607078,0.0013839377,0.0035798484,0.0031337852,0.0057398477,0.0030731456,0.0016865019],"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":[0.00004483041,0.0013052553,0.002315585,0.0006152004,0.00004432608,0.00021734659,0.022140263,0.0007987534,0.0013426682,0.43642142,0.081509,0.4532453],"study_design_scores_gemma":[0.000029036297,0.00026040818,0.0039982316,0.0010619456,0.00003396825,0.00030551164,0.016308686,0.0011634823,0.0016355411,0.20768757,0.7674776,0.000038061356],"about_ca_topic_score_codex":0.0041540437,"about_ca_topic_score_gemma":0.017007066,"teacher_disagreement_score":0.009508419,"about_ca_system_score_codex":0.0027831818,"about_ca_system_score_gemma":0.009758353,"threshold_uncertainty_score":0.031808853},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769557,0.00016278532,0.0030521126,0.0063988455,0.000043227457,0.000199897,0.000028504164,0.000031130465,0.013127706],"genre_scores_gemma":[0.993911,0.00016459178,0.0022585005,0.00037461074,0.000017053682,0.00006371052,0.000015149079,0.000018988794,0.0031762875],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98329884,0.011578292,0.00026525022,0.00045464796,0.0010329253,0.003369978],"domain_scores_gemma":[0.96512735,0.018049518,0.0022437451,0.0016010125,0.0029984738,0.009979873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015580634,0.00049916236,0.0004783967,0.0016259924,0.031430632,0.006656705,0.0023614708,0.0037231355,0.004695078],"category_scores_gemma":[0.021451905,0.00085223606,0.00047582804,0.0014913334,0.010984938,0.0045743375,0.007946797,0.0076744035,0.0005210618],"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":[0.00026061432,0.0031664595,0.020176373,0.0002597709,0.000043312244,0.027045436,0.8653645,0.002207944,0.0019962632,0.025195342,0.0090229465,0.045261145],"study_design_scores_gemma":[0.000027894828,0.00047135868,0.0056632613,0.00021883639,0.000015658268,0.002975573,0.9513671,0.001365202,0.00088102504,0.0019227519,0.03504163,0.000049755563],"about_ca_topic_score_codex":0.025576364,"about_ca_topic_score_gemma":0.07725015,"teacher_disagreement_score":0.031430632,"about_ca_system_score_codex":0.012472931,"about_ca_system_score_gemma":0.016586138,"threshold_uncertainty_score":0.09049785},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017472476,0.04895749,0.036583014,0.42189538,0.0040366203,0.00011012467,0.00008663459,0.00011038733,0.48647317],"genre_scores_gemma":[0.52892745,0.083618045,0.052977268,0.13854645,0.012762215,0.0013115377,0.000232102,0.00068167126,0.18094338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87474084,0.09752907,0.0021042232,0.00394527,0.019689016,0.00199166],"domain_scores_gemma":[0.8788681,0.106651895,0.0012004289,0.0036427802,0.008595027,0.0010416734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.083203636,0.0007773145,0.0013145688,0.0034758416,0.0045402697,0.019536398,0.001872035,0.0070865275,0.006843463],"category_scores_gemma":[0.08571157,0.0006389228,0.0006645958,0.0025854423,0.03379374,0.014782825,0.0050039673,0.016680753,0.0018357018],"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":[0.000004924472,0.0000051733186,0.000032879176,0.000055044202,0.00000345848,0.000008959414,0.00026452073,0.00025729174,0.000017643406,0.97517914,0.011435091,0.0127358455],"study_design_scores_gemma":[0.000011765244,0.000010200105,0.00011032326,0.0007263401,0.0000054808675,0.000029177803,0.00044051808,0.0008247114,0.0001460909,0.8156037,0.18207455,0.000017110642],"about_ca_topic_score_codex":0.004124264,"about_ca_topic_score_gemma":0.0022057141,"teacher_disagreement_score":0.083203636,"about_ca_system_score_codex":0.014880283,"about_ca_system_score_gemma":0.011982864,"threshold_uncertainty_score":0.44002813},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9807869,0.00029958456,0.0009130223,0.004929721,0.000108771084,0.0002101963,0.000046223253,0.000027438395,0.012678242],"genre_scores_gemma":[0.9902547,0.00049212715,0.0010113295,0.0015557518,0.000070605,0.00016022775,0.000049894752,0.000042017477,0.0063633802],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97724676,0.014541289,0.00036434125,0.00095093006,0.0018119756,0.0050848005],"domain_scores_gemma":[0.96632916,0.012545583,0.0013253291,0.00091630337,0.0027755345,0.016108071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020595964,0.0009394895,0.0011003079,0.0013925359,0.020298041,0.009915809,0.003302344,0.0036238576,0.003712544],"category_scores_gemma":[0.029306805,0.0006799381,0.0004722819,0.0011965819,0.01675027,0.0055026785,0.017679326,0.0068244166,0.0008168443],"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":[0.0001060369,0.0016291252,0.0045529464,0.00014103812,0.000012106601,0.0010647563,0.9649102,0.00021011112,0.00051652075,0.0020515104,0.0053167567,0.01948883],"study_design_scores_gemma":[0.000036974307,0.0006142427,0.0040183393,0.00016769409,0.000010015748,0.00028565282,0.955024,0.00023715867,0.00046455808,0.0012023713,0.03788946,0.000049564605],"about_ca_topic_score_codex":0.017968388,"about_ca_topic_score_gemma":0.048588883,"teacher_disagreement_score":0.020595964,"about_ca_system_score_codex":0.007837405,"about_ca_system_score_gemma":0.009911082,"threshold_uncertainty_score":0.1089232},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00468411,0.044488106,0.00575066,0.08988424,0.0060127727,0.00081525964,0.0031687503,0.0008016021,0.84439445],"genre_scores_gemma":[0.2051009,0.07015548,0.02292701,0.037858535,0.0012013146,0.0010503047,0.004955274,0.0008170629,0.6559341],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97593,0.004343895,0.0013872762,0.0015074174,0.012359166,0.004472293],"domain_scores_gemma":[0.91498667,0.0071197883,0.0013724072,0.0024612346,0.057297133,0.016762696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017554263,0.0008006022,0.0011387657,0.005013247,0.013975489,0.016023591,0.0028579931,0.0033828106,0.050472997],"category_scores_gemma":[0.051471613,0.0007189134,0.0008914338,0.0084727155,0.004749449,0.003534074,0.005289514,0.0044177677,0.007982378],"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":[0.00006793323,0.000056277815,0.0019017998,0.000642891,0.000025149895,0.0002163262,0.0009852045,0.0005612654,0.0001650797,0.09267406,0.7407422,0.16196172],"study_design_scores_gemma":[0.000024618332,0.000020115807,0.0056367754,0.0008553692,0.00001335567,0.00007144608,0.0009556572,0.0003439921,0.00011777938,0.0058178944,0.9860952,0.000047885726],"about_ca_topic_score_codex":0.9744611,"about_ca_topic_score_gemma":0.9822066,"teacher_disagreement_score":0.9824457,"about_ca_system_score_codex":0.15570463,"about_ca_system_score_gemma":0.5194822,"threshold_uncertainty_score":0.97926295},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.404079,0.0030594398,0.084814735,0.30112946,0.001481009,0.005850288,0.0017575235,0.002272842,0.19555575],"genre_scores_gemma":[0.92487746,0.0012710994,0.048625726,0.009073118,0.000047753478,0.0014618007,0.00033421323,0.00018241472,0.014126406],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9853931,0.007857298,0.0002870282,0.0007505684,0.0036999893,0.002012014],"domain_scores_gemma":[0.968384,0.008251592,0.0012938816,0.0017764714,0.012188435,0.008105599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018631162,0.00089234556,0.00068145,0.0016880769,0.010305737,0.007242995,0.0037000757,0.0021337576,0.0075134104],"category_scores_gemma":[0.040006187,0.00053213973,0.00052542955,0.001606586,0.00464124,0.0043153497,0.005539153,0.0035325277,0.0010535261],"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":[0.0012121574,0.0022169277,0.13041644,0.0011957844,0.00023005588,0.00081660115,0.08642723,0.0060361912,0.0017792243,0.06952084,0.23801962,0.46212906],"study_design_scores_gemma":[0.00096783094,0.0020545668,0.15935707,0.0055060433,0.000965443,0.000870741,0.2724228,0.04087479,0.0070885704,0.08562559,0.42323592,0.0010307234],"about_ca_topic_score_codex":0.9072894,"about_ca_topic_score_gemma":0.96812147,"teacher_disagreement_score":0.9435885,"about_ca_system_score_codex":0.0564115,"about_ca_system_score_gemma":0.28627434,"threshold_uncertainty_score":0.40929604},"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":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014988329,0.014913829,0.042379137,0.058971766,0.01096143,0.0012700005,0.03131375,0.004966431,0.8202353],"genre_scores_gemma":[0.021401979,0.004643867,0.02360793,0.0011740712,0.00031852396,0.00018612875,0.0059731877,0.00076801144,0.9419262],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99613476,0.00039923927,0.00023863777,0.0006279161,0.0019668026,0.00063264236],"domain_scores_gemma":[0.99011314,0.00075417914,0.0002219454,0.0009113179,0.005970852,0.002028671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041963374,0.0014093322,0.0020195078,0.0027129103,0.010285806,0.011013955,0.003128832,0.0037657698,0.21975319],"category_scores_gemma":[0.006316172,0.0012852412,0.00137172,0.0043930225,0.0040740767,0.0026650361,0.0026007164,0.0026054073,0.05033918],"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":[0.00030219316,0.00012084799,0.0020676919,0.0005206892,0.0000664284,0.0003951831,0.00024482442,0.0033563622,0.0022852705,0.033050403,0.795041,0.1625491],"study_design_scores_gemma":[0.0000388171,0.000026369169,0.0022499491,0.00019438523,0.000013423815,0.000046549878,0.00028451206,0.0025172008,0.00117943,0.0031261235,0.9902772,0.00004617573],"about_ca_topic_score_codex":0.8582547,"about_ca_topic_score_gemma":0.9416919,"teacher_disagreement_score":0.21975319,"about_ca_system_score_codex":0.03874552,"about_ca_system_score_gemma":0.10833505,"threshold_uncertainty_score":0.73514766},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2359139,0.1127202,0.4826478,0.09118539,0.004267878,0.006359186,0.0020443765,0.0011431278,0.06371818],"genre_scores_gemma":[0.4550474,0.049159348,0.46598512,0.0075624646,0.0008637062,0.0063810125,0.0014007542,0.0005220597,0.013078162],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8449918,0.08813827,0.01910633,0.0036948659,0.0421353,0.0019334351],"domain_scores_gemma":[0.76456046,0.13643186,0.012917218,0.018191278,0.06602671,0.0018725282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1485854,0.0012118662,0.0018088046,0.008397093,0.002515624,0.012647902,0.0020570885,0.002107307,0.002752441],"category_scores_gemma":[0.20680135,0.00092139276,0.0025387083,0.0068377326,0.008655459,0.011488898,0.005838516,0.0069069904,0.00095222355],"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":[0.0004952923,0.00022768187,0.013322912,0.007933051,0.00033945698,0.00023701126,0.055286907,0.0013891174,0.006525081,0.0749721,0.007440545,0.83183086],"study_design_scores_gemma":[0.0002898615,0.0026478877,0.08526979,0.034061484,0.0011699257,0.0029294745,0.051379103,0.003994083,0.028021589,0.107392006,0.68224347,0.0006013325],"about_ca_topic_score_codex":0.007433275,"about_ca_topic_score_gemma":0.00903556,"teacher_disagreement_score":0.1485854,"about_ca_system_score_codex":0.009375131,"about_ca_system_score_gemma":0.020926679,"threshold_uncertainty_score":0.78580403},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020641623,0.010511695,0.32872882,0.0120258285,0.0021573238,0.0031672297,0.0010127105,0.0018088167,0.61994594],"genre_scores_gemma":[0.16179387,0.009954323,0.5719838,0.003945156,0.0005227843,0.0036554453,0.0018229573,0.0020382642,0.24428342],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.985293,0.010634396,0.0004423822,0.00087203155,0.002208387,0.0005498872],"domain_scores_gemma":[0.96437407,0.018210905,0.000888278,0.0064020553,0.0069240215,0.0032005406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0330553,0.001342968,0.00058865594,0.002953437,0.0019365398,0.00849527,0.002858371,0.0017372601,0.03492851],"category_scores_gemma":[0.021883624,0.0004995893,0.00091603916,0.0034467296,0.0032980416,0.0029297879,0.005586631,0.0024742915,0.0106825605],"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":[0.000053177457,0.00042383972,0.00093625707,0.0010687865,0.00003651332,0.00009868068,0.007687774,0.00083445094,0.004298742,0.086232066,0.055301037,0.84302866],"study_design_scores_gemma":[0.00006650044,0.00044560037,0.0032286819,0.0023175431,0.00004721482,0.00078126136,0.011912712,0.0028836818,0.0102448175,0.090431064,0.87757325,0.00006761508],"about_ca_topic_score_codex":0.0023251262,"about_ca_topic_score_gemma":0.003112115,"teacher_disagreement_score":0.03492851,"about_ca_system_score_codex":0.004512386,"about_ca_system_score_gemma":0.007857595,"threshold_uncertainty_score":0.17481524},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067061107,0.17774545,0.0035013454,0.14213146,0.024218211,0.00046657634,0.005465239,0.00081772055,0.6389479],"genre_scores_gemma":[0.13098547,0.1636256,0.013043425,0.019158568,0.003386589,0.00037846973,0.0056313598,0.00073482754,0.6630557],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907136,0.0010324229,0.00037088105,0.00024122748,0.0070877005,0.0005542655],"domain_scores_gemma":[0.97542965,0.0018717541,0.00044631463,0.00049390964,0.01901293,0.0027454593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00677045,0.00057222554,0.00094230345,0.0055502723,0.004851069,0.008117822,0.0014137594,0.001514604,0.0694944],"category_scores_gemma":[0.02393143,0.0006029986,0.00037705715,0.0072354726,0.0024962542,0.001737887,0.0015469445,0.0017314547,0.0066792625],"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":[0.00003804993,0.000050243158,0.0017499115,0.00034676227,0.000020370819,0.00002948622,0.00021716215,0.00012166646,0.0000855371,0.0068482077,0.89126587,0.09922676],"study_design_scores_gemma":[0.000019692377,0.00001766608,0.009314805,0.0005850224,0.000027538486,0.000056584147,0.0007302964,0.00016845239,0.0000975068,0.0023641223,0.98659307,0.000025232375],"about_ca_topic_score_codex":0.83883756,"about_ca_topic_score_gemma":0.93227357,"teacher_disagreement_score":0.83883756,"about_ca_system_score_codex":0.034656785,"about_ca_system_score_gemma":0.1172325,"threshold_uncertainty_score":0.32422304},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9289174,0.0030241308,0.03203069,0.0044940053,0.00044606824,0.015443534,0.000073421266,0.00010507747,0.015465698],"genre_scores_gemma":[0.9562989,0.00066444825,0.031467102,0.0009244489,0.00005879282,0.009662297,0.000044245524,0.00005635478,0.0008233706],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.32089594,0.6305783,0.019414846,0.0034496367,0.022044918,0.0036163554],"domain_scores_gemma":[0.422388,0.44366136,0.025024923,0.034145918,0.06902929,0.0057504973],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.518023,0.0011446422,0.0013568631,0.0027635612,0.0067737214,0.0062707462,0.0024513274,0.002898634,0.0015738372],"category_scores_gemma":[0.5154154,0.0012155095,0.0018172546,0.0024353515,0.0078083784,0.0065894597,0.010876689,0.0033219543,0.00025834463],"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":[0.010434277,0.013542144,0.088848755,0.0072507598,0.0019805902,0.0017445383,0.36557862,0.004662613,0.0069422233,0.015456497,0.0039068796,0.47965205],"study_design_scores_gemma":[0.009011776,0.08566609,0.19722854,0.020233378,0.0030753228,0.0027238538,0.52650476,0.015148955,0.037719402,0.023376208,0.07802948,0.0012821425],"about_ca_topic_score_codex":0.002576016,"about_ca_topic_score_gemma":0.005878691,"teacher_disagreement_score":0.518023,"about_ca_system_score_codex":0.011843021,"about_ca_system_score_gemma":0.01155144,"threshold_uncertainty_score":0.59436345},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35176015,0.003806721,0.0660307,0.014096669,0.00044210206,0.0014362531,0.00078885024,0.00032239247,0.56131613],"genre_scores_gemma":[0.8806772,0.0025921047,0.05073595,0.0010374824,0.00008432557,0.001739463,0.0005668582,0.00020508248,0.062361605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98758554,0.006273797,0.00059886347,0.0011662558,0.0030427026,0.0013328029],"domain_scores_gemma":[0.98122,0.008234271,0.002409587,0.0018098904,0.0035650516,0.0027611342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011170397,0.0005366016,0.0003627033,0.0030934042,0.003578238,0.007911793,0.0016129982,0.0013136169,0.015691133],"category_scores_gemma":[0.019309793,0.00043918221,0.00062310137,0.0065171686,0.0044926372,0.005382321,0.0059760823,0.003240408,0.0023361314],"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":[0.00022611901,0.0004944928,0.05757929,0.0019023062,0.000100174766,0.00060126506,0.23204808,0.0018901981,0.0046850736,0.36945146,0.00864576,0.32237583],"study_design_scores_gemma":[0.000058942347,0.0006208158,0.120304376,0.0020507076,0.00008150086,0.0005527261,0.20546204,0.0015485606,0.0040014936,0.047690745,0.6175222,0.000105899104],"about_ca_topic_score_codex":0.011114836,"about_ca_topic_score_gemma":0.016695667,"teacher_disagreement_score":0.015691133,"about_ca_system_score_codex":0.010454958,"about_ca_system_score_gemma":0.022094525,"threshold_uncertainty_score":0.07585633},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76870894,0.0040015047,0.0004245357,0.08937425,0.0007233458,0.00041620198,0.000537467,0.00009166294,0.13572204],"genre_scores_gemma":[0.95736396,0.0018154158,0.0006318402,0.0063903336,0.00004957784,0.00014283492,0.00032489968,0.000024169545,0.03325693],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98966646,0.002399073,0.00014292201,0.00032974596,0.0015343695,0.0059273946],"domain_scores_gemma":[0.9694308,0.0022628005,0.0010099993,0.00026154015,0.006979228,0.02005562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075525073,0.00038649645,0.00037719877,0.0012733848,0.010851042,0.011180492,0.0018591956,0.001854668,0.008532443],"category_scores_gemma":[0.018752545,0.00027148676,0.00025805907,0.0026419056,0.0031479702,0.0021983185,0.005541142,0.0051599853,0.0011856373],"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":[0.00085560995,0.0022292135,0.22361015,0.00058119436,0.00010039783,0.0005669808,0.03594308,0.0011491736,0.0006353458,0.01360856,0.20681271,0.51390755],"study_design_scores_gemma":[0.00019038942,0.0008323207,0.57557344,0.0023886766,0.0000941946,0.00009341738,0.29594946,0.0013028648,0.0008574116,0.0032467134,0.11932144,0.00014973182],"about_ca_topic_score_codex":0.88567716,"about_ca_topic_score_gemma":0.966243,"teacher_disagreement_score":0.11432284,"about_ca_system_score_codex":0.055579342,"about_ca_system_score_gemma":0.19885023,"threshold_uncertainty_score":0.40325826},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043465225,0.026916793,0.17966156,0.6623492,0.016356705,0.002276316,0.00022521273,0.00059932657,0.10726836],"genre_scores_gemma":[0.43792182,0.028461536,0.3640393,0.11277702,0.0059110387,0.013806882,0.00035292553,0.0009903584,0.035739042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5880084,0.35430795,0.009029056,0.015123458,0.02792082,0.005610269],"domain_scores_gemma":[0.6425675,0.2646905,0.008640721,0.044696216,0.02870848,0.01069659],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2713506,0.0023934995,0.004517761,0.00529628,0.015434375,0.030172335,0.0057194466,0.017328255,0.011127521],"category_scores_gemma":[0.2706375,0.0021490434,0.0022086925,0.00526409,0.07809969,0.03151441,0.022205703,0.02424492,0.0037202062],"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":[0.000079449135,0.00016556712,0.0010141287,0.0025640663,0.00021934893,0.00024851484,0.05490996,0.0008013074,0.00027899846,0.7798197,0.049213115,0.110685915],"study_design_scores_gemma":[0.000093117844,0.00013003511,0.0003687824,0.006001609,0.000059845675,0.00014481957,0.029021565,0.000647074,0.0003176212,0.7162311,0.24690919,0.00007526479],"about_ca_topic_score_codex":0.0077156276,"about_ca_topic_score_gemma":0.0073715732,"teacher_disagreement_score":0.2713506,"about_ca_system_score_codex":0.013543867,"about_ca_system_score_gemma":0.061028197,"threshold_uncertainty_score":0.89855444},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004005704,0.0047980514,0.7451871,0.15996929,0.0044109123,0.016249502,0.00058199133,0.0040673553,0.060730036],"genre_scores_gemma":[0.017100131,0.0032029562,0.95695233,0.0055609895,0.0004884327,0.007588587,0.00023322576,0.0004482273,0.008425168],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.76656765,0.17042221,0.020248335,0.0039341473,0.033497185,0.005330452],"domain_scores_gemma":[0.7436524,0.15515886,0.012318787,0.01816646,0.057964407,0.01273909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15140171,0.0028417746,0.0013792175,0.006893104,0.0071914247,0.009422959,0.0034616168,0.0063258517,0.012667281],"category_scores_gemma":[0.18354443,0.0022241815,0.002081763,0.005215035,0.010053346,0.011581291,0.01166373,0.015222409,0.007007478],"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":[0.00025119632,0.00069330144,0.0019129749,0.0037717954,0.00008800615,0.0009904563,0.022817977,0.0036967318,0.0031702525,0.091729686,0.2672613,0.6036163],"study_design_scores_gemma":[0.00021400071,0.00066941936,0.0029876379,0.008499588,0.0000948132,0.0012144864,0.022480322,0.003053667,0.0026793072,0.13113475,0.82657266,0.00039942522],"about_ca_topic_score_codex":0.0036111854,"about_ca_topic_score_gemma":0.010954404,"teacher_disagreement_score":0.15140171,"about_ca_system_score_codex":0.009669413,"about_ca_system_score_gemma":0.026987206,"threshold_uncertainty_score":0.80069834},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94158614,0.003559235,0.008796741,0.0023473967,0.00015896941,0.00019375813,0.0042483937,0.00026520342,0.038844205],"genre_scores_gemma":[0.95295584,0.001265328,0.003906509,0.00045248427,0.00006012813,0.0001271031,0.0018082644,0.00007736621,0.039347064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979818,0.0003609257,0.00006881251,0.0003697894,0.00075885485,0.0004598633],"domain_scores_gemma":[0.9927515,0.0033059348,0.0011475896,0.00040106132,0.0018725512,0.00052132306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037644282,0.00067809096,0.0006468034,0.0013272478,0.0011296414,0.0022841862,0.00057933864,0.00056483404,0.012283916],"category_scores_gemma":[0.0056584487,0.00029086438,0.0015657664,0.0020552718,0.00094825623,0.0012077091,0.0011368126,0.0009523101,0.0012040902],"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":[0.0005406673,0.00019191521,0.91257375,0.00065995497,0.00087996386,0.00024068762,0.0035681252,0.0011375855,0.009212312,0.0019398134,0.001840864,0.06721431],"study_design_scores_gemma":[0.0000047198405,0.00016704341,0.9915637,0.000039935418,0.00014056798,0.0000241415,0.0013525807,0.00024462264,0.001210795,0.0001676462,0.0050749797,0.000009380608],"about_ca_topic_score_codex":0.20884521,"about_ca_topic_score_gemma":0.42249322,"teacher_disagreement_score":0.7911548,"about_ca_system_score_codex":0.002481946,"about_ca_system_score_gemma":0.0074212956,"threshold_uncertainty_score":0.41525918},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7746625,0.003914983,0.018849105,0.060531195,0.0004608943,0.00016764492,0.00008227887,0.00010476384,0.14122663],"genre_scores_gemma":[0.9915503,0.0006399582,0.0026541522,0.0011604513,0.00004391953,0.000048893642,0.000018551176,0.00002547065,0.003858196],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9612941,0.022192253,0.0011506394,0.0020652083,0.010672272,0.0026255115],"domain_scores_gemma":[0.9536523,0.029586624,0.0064422376,0.0017039189,0.005125642,0.003489188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019094782,0.00045645665,0.0007783348,0.0028363666,0.028749615,0.016129488,0.0021504632,0.0038901137,0.0026269548],"category_scores_gemma":[0.030205926,0.0005013021,0.00044890982,0.0046354304,0.041970115,0.00853256,0.012435392,0.0049826526,0.00023713463],"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":[0.00004363145,0.000021375612,0.0047596702,0.00015036546,0.000012970108,0.00060920493,0.9461995,0.00013486104,0.00059352245,0.032807227,0.0014438718,0.013223847],"study_design_scores_gemma":[0.000012699858,0.000048096575,0.008913726,0.00045361836,0.000023892486,0.00045067715,0.8809324,0.00037826019,0.0004896614,0.008540527,0.099691205,0.000065248234],"about_ca_topic_score_codex":0.33553338,"about_ca_topic_score_gemma":0.4290295,"teacher_disagreement_score":0.33553338,"about_ca_system_score_codex":0.033994477,"about_ca_system_score_gemma":0.06952147,"threshold_uncertainty_score":0.66716075},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109007396,0.0072640553,0.5762058,0.22612111,0.001996736,0.001082584,0.00017350542,0.0005459473,0.077602886],"genre_scores_gemma":[0.8837839,0.0013129171,0.09831744,0.011965265,0.0004782321,0.0017520868,0.0000697932,0.00036705445,0.001953338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.457782,0.4425967,0.017361563,0.0149543425,0.06316677,0.0041385954],"domain_scores_gemma":[0.17830233,0.7125074,0.024968699,0.05396331,0.028698148,0.0015600654],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3749467,0.0016089948,0.0020105487,0.0099946,0.012171757,0.01316889,0.010526343,0.009182429,0.0029039958],"category_scores_gemma":[0.6757949,0.0017820445,0.0018229254,0.010584452,0.08423223,0.027423646,0.018873341,0.015188535,0.00055830483],"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":[0.00011433731,0.000039930845,0.004588838,0.0010997762,0.00010225474,0.0017922962,0.3066497,0.0008775399,0.0003801827,0.6029442,0.0066134813,0.074797496],"study_design_scores_gemma":[0.00009510249,0.000104283026,0.0017764256,0.0062187216,0.00009197812,0.004249346,0.113612145,0.01175071,0.0026035989,0.7730769,0.08619834,0.00022243227],"about_ca_topic_score_codex":0.00723427,"about_ca_topic_score_gemma":0.0035524433,"teacher_disagreement_score":0.6250533,"about_ca_system_score_codex":0.013929502,"about_ca_system_score_gemma":0.015886616,"threshold_uncertainty_score":0.770802},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.913169,0.0016003542,0.07886576,0.0005066688,0.000087969216,0.00036705227,0.00025064018,0.00042362724,0.0047288924],"genre_scores_gemma":[0.9367628,0.00036063016,0.06006134,0.000117784235,0.000027444416,0.000273937,0.00023958126,0.0001572134,0.0019992075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95947254,0.02635574,0.0021512283,0.0041732923,0.007165176,0.000682024],"domain_scores_gemma":[0.6861,0.26157644,0.015124728,0.015607482,0.02043591,0.0011554138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044000257,0.001409677,0.001323207,0.0015244198,0.00091142923,0.0023550123,0.0010391388,0.0017557383,0.0020144247],"category_scores_gemma":[0.1513228,0.00047967612,0.001868832,0.0018433337,0.002426227,0.0020306294,0.0025260204,0.0017899581,0.00042300153],"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":[0.008939767,0.00094496674,0.25160673,0.0026316678,0.003963668,0.00026534605,0.00668802,0.094964854,0.048564974,0.0043764464,0.0011748776,0.57587856],"study_design_scores_gemma":[0.00070477265,0.019184237,0.7372855,0.00095636235,0.0022348438,0.00042728364,0.0054406263,0.10673496,0.10286809,0.01071913,0.012689109,0.0007551047],"about_ca_topic_score_codex":0.012471263,"about_ca_topic_score_gemma":0.014349333,"teacher_disagreement_score":0.044000257,"about_ca_system_score_codex":0.0017774642,"about_ca_system_score_gemma":0.0014774906,"threshold_uncertainty_score":0.23269838},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014368983,0.93620294,0.0068427986,0.015031138,0.0037615655,0.00008341002,0.0009935834,0.00023909876,0.035408605],"genre_scores_gemma":[0.013793244,0.89210385,0.0097484905,0.0015965651,0.0017228841,0.0001551262,0.0014987753,0.00036584656,0.07901516],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975811,0.0006458409,0.000297448,0.0003157262,0.0010145626,0.0001453343],"domain_scores_gemma":[0.99341387,0.004582538,0.00050453655,0.000222126,0.0009408897,0.0003360925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037867595,0.0030378208,0.002336306,0.0037461217,0.0008841029,0.0075030355,0.0014254948,0.0028548094,0.07728761],"category_scores_gemma":[0.0075006774,0.0014008557,0.0007711146,0.0076867635,0.0019639519,0.010872991,0.0020374719,0.002882506,0.040823307],"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":[0.000122687,0.000094767376,0.000755304,0.0040871557,0.000040811217,0.00018121625,0.000950433,0.0006180181,0.00053790957,0.008121677,0.4173935,0.5670965],"study_design_scores_gemma":[0.000030545776,0.00006390953,0.0040034624,0.0054986565,0.00006622656,0.0005821463,0.0014154732,0.000742661,0.00074723625,0.01819691,0.9685994,0.000053329964],"about_ca_topic_score_codex":0.01758675,"about_ca_topic_score_gemma":0.030083844,"teacher_disagreement_score":0.07728761,"about_ca_system_score_codex":0.0024936087,"about_ca_system_score_gemma":0.006905274,"threshold_uncertainty_score":0.25855285},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86864024,0.0034964238,0.008592561,0.011424944,0.0004207423,0.031277843,0.006296553,0.00020110267,0.06964963],"genre_scores_gemma":[0.9285269,0.0026059744,0.022960495,0.0026885509,0.000041027302,0.016951613,0.0015473474,0.0001035163,0.024574487],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9908289,0.0051130042,0.00021763699,0.0005646576,0.0014199241,0.0018558534],"domain_scores_gemma":[0.990473,0.0019053175,0.00029414546,0.00029778283,0.0041464847,0.002883301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013087817,0.0005130092,0.00057684205,0.0011749918,0.010710892,0.0034962278,0.0020419552,0.000681986,0.0058115125],"category_scores_gemma":[0.010902152,0.0004450648,0.00028083174,0.0024433206,0.003132926,0.00066414906,0.0046871165,0.0010054255,0.00035206284],"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":[0.00047591885,0.0007414245,0.020479735,0.0021988475,0.00003796935,0.0027644178,0.815328,0.00075913355,0.0032193484,0.008261362,0.033794515,0.111939326],"study_design_scores_gemma":[0.00023808217,0.0004011555,0.035412654,0.0016750364,0.000054332235,0.00028495572,0.7951615,0.0006214965,0.0015566744,0.001023961,0.16350126,0.00006888134],"about_ca_topic_score_codex":0.89159524,"about_ca_topic_score_gemma":0.9424996,"teacher_disagreement_score":0.108404756,"about_ca_system_score_codex":0.06295,"about_ca_system_score_gemma":0.14465007,"threshold_uncertainty_score":0.4567364},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013352228,0.011437889,0.0080013415,0.3773967,0.055793658,0.002870846,0.008847561,0.0020424908,0.5202573],"genre_scores_gemma":[0.02369839,0.003486989,0.004353844,0.01664284,0.007932503,0.00057111756,0.0023101415,0.00047371243,0.94053054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976857,0.0004480927,0.00007869253,0.00025501027,0.0007509865,0.00078149384],"domain_scores_gemma":[0.9790942,0.0006686798,0.0004158876,0.00022821416,0.0036941306,0.01589898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074554086,0.0015285835,0.000764332,0.001150911,0.0046181083,0.0052304366,0.002239017,0.0049278038,0.17107648],"category_scores_gemma":[0.007849046,0.0006636154,0.0006341013,0.0010311371,0.0021418312,0.0019273721,0.0040585627,0.0046295947,0.0649298],"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":[0.00009442747,0.00009685943,0.00040985201,0.00009349305,0.0000036364313,0.000073367926,0.00028451523,0.00010203775,0.00047735826,0.0010741672,0.9787483,0.018541856],"study_design_scores_gemma":[0.00005731995,0.00010012577,0.0051210835,0.0002652187,0.000006026344,0.00006984421,0.0010764396,0.00017623791,0.00034587528,0.0019815292,0.9907742,0.000026020938],"about_ca_topic_score_codex":0.24879862,"about_ca_topic_score_gemma":0.5669703,"teacher_disagreement_score":0.98045665,"about_ca_system_score_codex":0.019543337,"about_ca_system_score_gemma":0.051163547,"threshold_uncertainty_score":0.5723078},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032086305,0.0030036164,0.040930994,0.9031468,0.005453397,0.0016624825,0.00010663255,0.00021729154,0.013392449],"genre_scores_gemma":[0.67788845,0.0033942421,0.07013088,0.22919704,0.0031094975,0.0071617,0.00012052554,0.0002801752,0.008717501],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66313523,0.26963514,0.0185441,0.005895678,0.035974238,0.0068156924],"domain_scores_gemma":[0.6072977,0.27598467,0.022793205,0.01414241,0.068302125,0.011479894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25558,0.0008131659,0.0010545342,0.0020126414,0.009816749,0.013397797,0.005769829,0.015029826,0.0055593834],"category_scores_gemma":[0.32276607,0.00064265303,0.0013788417,0.0021970922,0.011480523,0.013733056,0.012220092,0.018949272,0.0006835922],"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":[0.00075915194,0.00072543556,0.012988457,0.011479196,0.00019360043,0.0018166095,0.2836115,0.0025249342,0.0045697526,0.27001044,0.1392341,0.27208683],"study_design_scores_gemma":[0.00035463824,0.00084522134,0.008185137,0.020211676,0.00013914666,0.0018650342,0.27384526,0.005911754,0.0059307697,0.10604169,0.57631785,0.00035177072],"about_ca_topic_score_codex":0.0047884043,"about_ca_topic_score_gemma":0.0061391243,"teacher_disagreement_score":0.25558,"about_ca_system_score_codex":0.018004792,"about_ca_system_score_gemma":0.038125463,"threshold_uncertainty_score":0.91800237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5490887,0.012301444,0.012097399,0.0656968,0.0017911376,0.000587982,0.00015732259,0.00020555742,0.35807362],"genre_scores_gemma":[0.99092835,0.0011691664,0.0027165497,0.00051674235,0.00037546863,0.000062088686,0.00003651078,0.000012587645,0.0041825706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9296484,0.036759574,0.0035088053,0.0016066489,0.024618302,0.0038584014],"domain_scores_gemma":[0.84234726,0.051010534,0.027973708,0.006166776,0.04545106,0.0270507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034212332,0.00032163275,0.00085440703,0.002951023,0.00399232,0.011690998,0.0015475434,0.002037177,0.0040527727],"category_scores_gemma":[0.14325781,0.00018763222,0.00062745827,0.0019485506,0.0059361598,0.0039739776,0.0075281137,0.0024881044,0.0012166041],"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":[0.0005284417,0.0014441165,0.24177922,0.0011311859,0.0003799267,0.0007236925,0.014074044,0.001137086,0.0011609121,0.093210734,0.019796817,0.62463385],"study_design_scores_gemma":[0.00015476617,0.0031665277,0.7015923,0.0014374171,0.0002971057,0.003261713,0.04152768,0.005795154,0.004270927,0.12549025,0.11270144,0.00030474004],"about_ca_topic_score_codex":0.0070709563,"about_ca_topic_score_gemma":0.013602974,"teacher_disagreement_score":0.034212332,"about_ca_system_score_codex":0.0050910385,"about_ca_system_score_gemma":0.021011427,"threshold_uncertainty_score":0.18093431},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029776042,0.3923851,0.008953913,0.40273476,0.0063427133,0.00018001045,0.0002911568,0.0002685783,0.15906784],"genre_scores_gemma":[0.31978357,0.22790287,0.013148774,0.039399642,0.0017490818,0.0002738094,0.00036837175,0.00026967598,0.3971043],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99423414,0.0017497048,0.00020499623,0.00035800424,0.002539719,0.0009134708],"domain_scores_gemma":[0.98628473,0.0037783715,0.00039317255,0.00023436312,0.0068919393,0.0024174163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012535727,0.0007003272,0.0006834949,0.0025406254,0.009136743,0.010933021,0.0017366217,0.0042271554,0.006759781],"category_scores_gemma":[0.014270593,0.0005105116,0.0003607938,0.006090428,0.010185952,0.0038956108,0.0029632784,0.0041397633,0.0008177649],"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":[0.000094119685,0.00016045148,0.006872042,0.0007118426,0.000029497178,0.0005225449,0.0359969,0.000997452,0.0006667529,0.06375376,0.43803662,0.45215794],"study_design_scores_gemma":[0.00002230748,0.000052635613,0.023566531,0.001462371,0.000019007226,0.0003690293,0.020305185,0.0005327712,0.0002710696,0.0071825585,0.9461492,0.000067309906],"about_ca_topic_score_codex":0.96103376,"about_ca_topic_score_gemma":0.98298246,"teacher_disagreement_score":0.96103376,"about_ca_system_score_codex":0.07724938,"about_ca_system_score_gemma":0.15382159,"threshold_uncertainty_score":0.5604861},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021749802,0.010399434,0.00079056,0.21851458,0.0025934544,0.0006261507,0.024182245,0.0003004599,0.7208433],"genre_scores_gemma":[0.09200799,0.009293124,0.0023849949,0.008213861,0.00034971948,0.0002274505,0.004499631,0.00017050112,0.88285273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960735,0.00036217805,0.00011638004,0.000116001516,0.0024575493,0.0008743692],"domain_scores_gemma":[0.99279517,0.00054993376,0.0002160611,0.0001902174,0.004228716,0.0020198843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030376809,0.0004139111,0.00038959848,0.001399673,0.0059824907,0.005100256,0.0009466549,0.001971783,0.05853387],"category_scores_gemma":[0.008819938,0.0004849198,0.0003217833,0.002299303,0.0012991818,0.0012696317,0.0014256672,0.0014155167,0.005849997],"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":[0.000040363786,0.000021687316,0.003425986,0.00009842982,0.000009793818,0.00005811631,0.00030090124,0.00021739904,0.0001062781,0.01580713,0.95115125,0.02876268],"study_design_scores_gemma":[0.000017670474,0.000015737895,0.020615743,0.00013435075,0.000011154156,0.000022900767,0.0007532158,0.00019768687,0.00013284276,0.0010859359,0.9769949,0.000017889257],"about_ca_topic_score_codex":0.98011816,"about_ca_topic_score_gemma":0.99561405,"teacher_disagreement_score":0.9399091,"about_ca_system_score_codex":0.060090892,"about_ca_system_score_gemma":0.23686685,"threshold_uncertainty_score":0.435992},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026553985,0.033757575,0.27728575,0.21858135,0.004867349,0.0016951322,0.00016316563,0.0002486826,0.436847],"genre_scores_gemma":[0.7817362,0.017149514,0.15918846,0.016145088,0.002083873,0.0031069021,0.00019788572,0.0001834836,0.020208467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87056714,0.11338249,0.002070675,0.004177361,0.007572357,0.002229909],"domain_scores_gemma":[0.9152977,0.06600637,0.004896367,0.0059647197,0.0040127886,0.0038220217],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09324102,0.0018281065,0.0013914813,0.010572653,0.012187007,0.029187262,0.0033478388,0.01133223,0.0053686686],"category_scores_gemma":[0.03838453,0.0010185767,0.0016246182,0.005749854,0.1191322,0.027902398,0.019337153,0.01027264,0.0009858923],"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":[0.000013376469,0.000058341604,0.00041428907,0.00043387254,0.000017632507,0.00020573844,0.107221484,0.00029496974,0.00018455752,0.8717782,0.002567141,0.01681042],"study_design_scores_gemma":[0.000031986256,0.00006200833,0.00045377712,0.0015659874,0.000024460665,0.0002477721,0.07981251,0.0005736187,0.00027045177,0.79761195,0.11930657,0.000038856448],"about_ca_topic_score_codex":0.0033818271,"about_ca_topic_score_gemma":0.0034802062,"teacher_disagreement_score":0.90675896,"about_ca_system_score_codex":0.015055535,"about_ca_system_score_gemma":0.018471416,"threshold_uncertainty_score":0.49311155},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8554425,0.0022310568,0.03103664,0.015167389,0.0002617701,0.016502015,0.00030738386,0.00011214484,0.07893906],"genre_scores_gemma":[0.95691276,0.00084505446,0.025696777,0.0010552321,0.000024833813,0.003992025,0.00012239191,0.000022843053,0.011328128],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96207094,0.023212107,0.0008523536,0.0020517367,0.004963531,0.0068493136],"domain_scores_gemma":[0.976398,0.009827195,0.0010835257,0.0008897044,0.0069452696,0.0048564286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048268177,0.0006847803,0.00069109746,0.002376251,0.027672369,0.006728029,0.0033269024,0.0016926724,0.0024251149],"category_scores_gemma":[0.03027908,0.0006172933,0.00058312423,0.002935418,0.008476402,0.0015496897,0.01129991,0.0027002823,0.00018935687],"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":[0.00028611437,0.0006049859,0.017146446,0.0007719034,0.000034893143,0.0021185533,0.8130972,0.0019249631,0.0022977781,0.016934987,0.00400397,0.14077815],"study_design_scores_gemma":[0.00013939138,0.00048099866,0.022112839,0.0010758089,0.000053749798,0.00021084337,0.86594516,0.0023627977,0.0019738092,0.0049319174,0.100594275,0.000118385935],"about_ca_topic_score_codex":0.8563378,"about_ca_topic_score_gemma":0.9375903,"teacher_disagreement_score":0.14366221,"about_ca_system_score_codex":0.0940581,"about_ca_system_score_gemma":0.3366741,"threshold_uncertainty_score":0.6824424},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058712307,0.036698665,0.008817443,0.2136466,0.0011414908,0.000091900445,0.000095583855,0.000045089815,0.680751],"genre_scores_gemma":[0.96859556,0.0079338625,0.0025689076,0.004378135,0.00045149474,0.00011096553,0.000046824724,0.000027756916,0.015886417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98321277,0.012265645,0.0004713739,0.0010008574,0.0016400462,0.0014092192],"domain_scores_gemma":[0.99252397,0.004604906,0.0007649027,0.0005780372,0.0006736705,0.00085443765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016483985,0.0005348978,0.0007877639,0.0031784049,0.010962442,0.025446765,0.0015584609,0.0060744095,0.0063877273],"category_scores_gemma":[0.016469628,0.00027776812,0.00027636177,0.0036240038,0.050154403,0.014296017,0.009473083,0.0034125051,0.0007424364],"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":[0.000009128239,0.000019994346,0.00031162894,0.000041135587,0.0000037147013,0.00003347605,0.0115729,0.000103453625,0.000034274526,0.9787259,0.0021365096,0.0070079817],"study_design_scores_gemma":[0.00001233747,0.000024237304,0.0005974688,0.00048845506,0.000009116116,0.000052601754,0.035900988,0.0002857243,0.00022054672,0.8267271,0.13566534,0.000016063068],"about_ca_topic_score_codex":0.009740597,"about_ca_topic_score_gemma":0.0064064916,"teacher_disagreement_score":0.025446765,"about_ca_system_score_codex":0.014284713,"about_ca_system_score_gemma":0.013217143,"threshold_uncertainty_score":0.10364336},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047851462,0.048578963,0.002779726,0.9196761,0.0041906335,0.000036426532,0.00007368199,0.000048843853,0.024136998],"genre_scores_gemma":[0.17949596,0.2491021,0.046730865,0.47587156,0.026768718,0.00077508134,0.0008187564,0.00046318912,0.019973747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8426312,0.10651751,0.015785636,0.0035722295,0.021358453,0.010134898],"domain_scores_gemma":[0.52191913,0.37164155,0.01258228,0.012682911,0.055534367,0.02563973],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25341347,0.0016966542,0.0026893306,0.005141674,0.005708835,0.055835407,0.005254383,0.044410747,0.029882379],"category_scores_gemma":[0.19535138,0.0010379461,0.0018286784,0.008433955,0.026272802,0.03311322,0.017105397,0.028690828,0.0050034686],"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":[0.0003454279,0.00038761424,0.0014242183,0.006682145,0.00017138751,0.00037458277,0.0061827535,0.0008444549,0.00048051073,0.48335096,0.24587159,0.25388435],"study_design_scores_gemma":[0.00026920115,0.0002839777,0.002830041,0.03279496,0.00017016851,0.0005918662,0.022429066,0.0008756463,0.0006598181,0.30098718,0.63795316,0.00015490828],"about_ca_topic_score_codex":0.010675411,"about_ca_topic_score_gemma":0.013450656,"teacher_disagreement_score":0.25341347,"about_ca_system_score_codex":0.017040731,"about_ca_system_score_gemma":0.070081584,"threshold_uncertainty_score":0.9206741},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58330315,0.00055354944,0.308514,0.004317927,0.00023061987,0.004483503,0.00011759112,0.00029931852,0.09818029],"genre_scores_gemma":[0.70956916,0.00036611082,0.28138867,0.00034093435,0.000041575837,0.001943779,0.000055581793,0.000101878046,0.0061923163],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8663348,0.120992035,0.0015789274,0.0011080076,0.008172445,0.0018137693],"domain_scores_gemma":[0.86671305,0.12026838,0.0014306199,0.0035390866,0.0062533705,0.0017955103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.084119394,0.00078865775,0.0004856016,0.0031111313,0.004664102,0.006211047,0.0022712543,0.0017978761,0.00468176],"category_scores_gemma":[0.08281212,0.0005438422,0.0005604965,0.0021421695,0.0033847548,0.0053445636,0.0062589045,0.0018757256,0.0008018868],"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":[0.0012458607,0.0032484957,0.0126850065,0.0024105273,0.00009173947,0.001557136,0.21462992,0.0037084697,0.011936584,0.07080976,0.002495166,0.6751813],"study_design_scores_gemma":[0.0008377844,0.010240788,0.04467427,0.00657183,0.00040227646,0.0047468967,0.46671373,0.08845586,0.03975762,0.105897136,0.23090684,0.000795042],"about_ca_topic_score_codex":0.0022299828,"about_ca_topic_score_gemma":0.0057264417,"teacher_disagreement_score":0.084119394,"about_ca_system_score_codex":0.0033785547,"about_ca_system_score_gemma":0.0062825475,"threshold_uncertainty_score":0.4448712},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11062844,0.10585745,0.22172503,0.40710717,0.010847408,0.005167214,0.0005105356,0.0013086031,0.13684826],"genre_scores_gemma":[0.50637406,0.05429935,0.39965692,0.02222247,0.0018986798,0.002956845,0.00029271693,0.00040500416,0.011893991],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9426575,0.040353592,0.0038932336,0.0022110308,0.009514125,0.0013706031],"domain_scores_gemma":[0.89473855,0.08150499,0.0025725495,0.010747519,0.008590353,0.0018459226],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0830298,0.00137267,0.0023123005,0.0031269318,0.0025477344,0.009177641,0.004276842,0.0052324394,0.007355555],"category_scores_gemma":[0.10703552,0.00076745875,0.0024073012,0.0032894006,0.014400137,0.011217407,0.0055090934,0.0069600404,0.0012413097],"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":[0.00021596588,0.0010696282,0.0015498679,0.007296586,0.00014779074,0.0003128885,0.019715358,0.0008476752,0.0011859979,0.06979007,0.009861308,0.8880068],"study_design_scores_gemma":[0.0016369644,0.0026390455,0.025355777,0.06970482,0.0010307579,0.0028848706,0.06556972,0.007696125,0.015775159,0.49417862,0.3129384,0.0005897603],"about_ca_topic_score_codex":0.016810471,"about_ca_topic_score_gemma":0.019022163,"teacher_disagreement_score":0.9169702,"about_ca_system_score_codex":0.009113986,"about_ca_system_score_gemma":0.03611079,"threshold_uncertainty_score":0.4391088},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30623323,0.059895966,0.034595728,0.14994814,0.0014847887,0.002436869,0.0018197383,0.00029451278,0.44329113],"genre_scores_gemma":[0.90228564,0.022556525,0.028880281,0.005210551,0.00026946925,0.0011315679,0.0004800425,0.00008575358,0.03910022],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94096255,0.03817007,0.0015546505,0.001798236,0.014083283,0.0034311346],"domain_scores_gemma":[0.93386286,0.031894006,0.0039282776,0.0018695503,0.024456963,0.00398821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043594137,0.0008725459,0.0010601681,0.0030411237,0.006165014,0.008450116,0.0017960302,0.002472775,0.008119531],"category_scores_gemma":[0.0570852,0.00027115332,0.00080544554,0.0033900782,0.0065581547,0.0034720714,0.004192291,0.003395431,0.00073428976],"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":[0.0005013853,0.00074573536,0.05334895,0.004916794,0.00052767585,0.00053990097,0.06590865,0.0055615306,0.0024180256,0.12338642,0.039543297,0.70260173],"study_design_scores_gemma":[0.00017344086,0.0023082837,0.26422238,0.015320006,0.0005025488,0.0003805979,0.12451988,0.0034641693,0.005444804,0.027783653,0.55552053,0.00035970495],"about_ca_topic_score_codex":0.53423333,"about_ca_topic_score_gemma":0.66096604,"teacher_disagreement_score":0.53423333,"about_ca_system_score_codex":0.052397806,"about_ca_system_score_gemma":0.09479765,"threshold_uncertainty_score":0.93701935},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007909399,0.16551729,0.6139954,0.16114385,0.010231556,0.00924834,0.0008185065,0.0006393542,0.030496307],"genre_scores_gemma":[0.07371338,0.053751368,0.8038382,0.024203537,0.0045078546,0.03683049,0.0003264532,0.0004595208,0.0023690767],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.22394818,0.7255092,0.014404521,0.00687155,0.027872864,0.0013937182],"domain_scores_gemma":[0.10445419,0.8374861,0.009034869,0.028787512,0.01730715,0.002930148],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.63094014,0.0029848062,0.0069232094,0.013399971,0.012269616,0.02841857,0.008837926,0.008838198,0.009844124],"category_scores_gemma":[0.5844912,0.0025817428,0.003143069,0.016247595,0.028446743,0.021507725,0.023797141,0.012706116,0.002526137],"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":[0.00034330736,0.00049994484,0.005363482,0.021912502,0.0011721436,0.0004715635,0.041415233,0.001286792,0.0005975299,0.34186026,0.022108398,0.5629688],"study_design_scores_gemma":[0.000354647,0.0007837321,0.0023161566,0.044007037,0.00037857323,0.0011526237,0.035021596,0.0049028364,0.00085384055,0.6859458,0.22391579,0.00036743615],"about_ca_topic_score_codex":0.0066264574,"about_ca_topic_score_gemma":0.012564563,"teacher_disagreement_score":0.36905986,"about_ca_system_score_codex":0.012214217,"about_ca_system_score_gemma":0.03466404,"threshold_uncertainty_score":0.45511657},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08872103,0.00860916,0.72683316,0.06288297,0.0016794661,0.03987367,0.0008572566,0.0013335558,0.06920973],"genre_scores_gemma":[0.4266303,0.0025908907,0.54689103,0.001541287,0.0001904569,0.020925606,0.00030474545,0.00019083664,0.00073496933],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.16762653,0.7689781,0.022316087,0.0055877184,0.03233335,0.003158225],"domain_scores_gemma":[0.106159136,0.789285,0.018327996,0.0373038,0.045313843,0.0036102734],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7110554,0.003668964,0.0054078386,0.016075209,0.007353188,0.027828604,0.0106148105,0.00636611,0.004268277],"category_scores_gemma":[0.72380096,0.0021661546,0.00472287,0.014129538,0.023529673,0.029260278,0.018323638,0.010054761,0.0007414218],"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":[0.0010626514,0.0047678035,0.014275972,0.01156523,0.001242127,0.0003863083,0.05449764,0.037546523,0.0006122676,0.2757766,0.0067369607,0.59152997],"study_design_scores_gemma":[0.0017216622,0.004499488,0.011162422,0.03242859,0.0010816932,0.00022659362,0.041468743,0.1025873,0.0051201247,0.76024556,0.038803812,0.0006540027],"about_ca_topic_score_codex":0.008281187,"about_ca_topic_score_gemma":0.009509402,"teacher_disagreement_score":0.2889446,"about_ca_system_score_codex":0.05470282,"about_ca_system_score_gemma":0.07517601,"threshold_uncertainty_score":0.39689857},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83382714,0.0010520912,0.06588591,0.011221514,0.00021001366,0.011864076,0.00023796032,0.00013604149,0.07556521],"genre_scores_gemma":[0.97036386,0.00023406302,0.022955209,0.0005180095,0.000029400988,0.0041176337,0.00009634901,0.000045125154,0.0016403873],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.69410044,0.25325117,0.012141096,0.0051458594,0.027792258,0.0075691296],"domain_scores_gemma":[0.5683558,0.29229105,0.026843525,0.018267216,0.08294067,0.011301702],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.29702115,0.0006463114,0.0006238222,0.004436094,0.008569509,0.008420805,0.0023052655,0.0015355685,0.0031225695],"category_scores_gemma":[0.34518138,0.0004760814,0.0006635579,0.0032708817,0.008914454,0.0070521794,0.010156864,0.0018279256,0.0003238453],"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":[0.0013810945,0.0023364888,0.097398974,0.004667419,0.00021730234,0.002097357,0.50763196,0.0044082017,0.0075299772,0.03184525,0.0053571686,0.33512887],"study_design_scores_gemma":[0.0005626586,0.004919843,0.11655398,0.005615021,0.00035021952,0.00082681794,0.6634664,0.010267944,0.019357128,0.04074822,0.13698013,0.0003515466],"about_ca_topic_score_codex":0.0112557635,"about_ca_topic_score_gemma":0.01663321,"teacher_disagreement_score":0.29702115,"about_ca_system_score_codex":0.02323461,"about_ca_system_score_gemma":0.03236695,"threshold_uncertainty_score":0.86689806},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03479146,0.010933576,0.2768572,0.33914617,0.0011904746,0.002170295,0.00023191662,0.00034079037,0.33433816],"genre_scores_gemma":[0.83816355,0.0051598074,0.13066134,0.010863628,0.0003283245,0.0012917134,0.00012416938,0.00012827465,0.013279283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.83789206,0.12390313,0.002807336,0.005124867,0.02331929,0.0069534136],"domain_scores_gemma":[0.80867356,0.10034373,0.007999537,0.014207652,0.04178831,0.026987147],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13075894,0.0008516423,0.0012580821,0.009882393,0.022371706,0.038095217,0.00588737,0.007342062,0.00789415],"category_scores_gemma":[0.102137014,0.0009161661,0.000970171,0.009329375,0.057154506,0.021466706,0.02897912,0.009232022,0.0012439383],"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":[0.00003482413,0.00016761653,0.0027870242,0.00068614003,0.000059807593,0.00034580968,0.054555293,0.001091824,0.00028897228,0.8703059,0.0108459005,0.058830887],"study_design_scores_gemma":[0.00007015771,0.00011066785,0.0025149481,0.0021248034,0.00005270122,0.00026544268,0.06368544,0.002957681,0.00050217146,0.6565051,0.27113193,0.00007893115],"about_ca_topic_score_codex":0.16036484,"about_ca_topic_score_gemma":0.20179984,"teacher_disagreement_score":0.9400523,"about_ca_system_score_codex":0.059947733,"about_ca_system_score_gemma":0.20742457,"threshold_uncertainty_score":0.6915276},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92560273,0.0015708817,0.015049661,0.017553505,0.0002908969,0.0006079757,0.000049615144,0.000244348,0.039030366],"genre_scores_gemma":[0.98960006,0.0004227625,0.007258703,0.00036458485,0.000026052934,0.000082312254,0.000017102624,0.00002433185,0.002204149],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9677573,0.022129947,0.00073680223,0.0009181132,0.0054865177,0.0029713314],"domain_scores_gemma":[0.9465192,0.023849921,0.004473065,0.0031168119,0.009571591,0.012469412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02780518,0.00044590715,0.00025398802,0.0014536682,0.009661184,0.006755524,0.0019159447,0.0013644001,0.0018649243],"category_scores_gemma":[0.07178795,0.00037534288,0.0003934865,0.000883606,0.0042764354,0.0019548128,0.0067561255,0.0029430015,0.0002370137],"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":[0.0002707432,0.0009902271,0.09785468,0.0004935307,0.00008413093,0.002687952,0.49373302,0.00091587147,0.005608162,0.007250431,0.017882658,0.3722286],"study_design_scores_gemma":[0.000055454006,0.00079712895,0.10928114,0.0012440017,0.00012744189,0.0022082978,0.73500234,0.002683737,0.0050914907,0.0054804706,0.1377925,0.00023606181],"about_ca_topic_score_codex":0.03602295,"about_ca_topic_score_gemma":0.16637553,"teacher_disagreement_score":0.03602295,"about_ca_system_score_codex":0.0105085345,"about_ca_system_score_gemma":0.03241084,"threshold_uncertainty_score":0.1470496},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039108354,0.001938795,0.00069271424,0.9644835,0.029654942,0.000024640865,0.000024365687,0.000052428244,0.0027375296],"genre_scores_gemma":[0.035597615,0.0031183446,0.0030955574,0.89137024,0.023752013,0.00021763875,0.000036658723,0.0003961707,0.042415705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9645269,0.015695116,0.0020458824,0.004438471,0.011246035,0.0020477076],"domain_scores_gemma":[0.86108065,0.050227053,0.0045471466,0.00445884,0.059447315,0.020239022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025276612,0.00092979503,0.0020641005,0.0012263814,0.016439723,0.01878328,0.0043098726,0.013702315,0.009158469],"category_scores_gemma":[0.18917994,0.00078492204,0.00087992306,0.0014045916,0.02058706,0.013178311,0.007559484,0.055676576,0.0055313758],"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":[0.00003474141,0.00001098673,0.00023529858,0.00010843204,0.000011589214,0.00022463483,0.005325533,0.000041175983,0.00012431748,0.010278542,0.97759455,0.006010224],"study_design_scores_gemma":[0.000017624445,0.000027756774,0.00034686888,0.00070977316,0.000017563587,0.00029669236,0.014560803,0.00025328677,0.00030310033,0.009598447,0.97375315,0.00011498282],"about_ca_topic_score_codex":0.042465452,"about_ca_topic_score_gemma":0.061543193,"teacher_disagreement_score":0.042465452,"about_ca_system_score_codex":0.012627559,"about_ca_system_score_gemma":0.027908187,"threshold_uncertainty_score":0.13367712},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6735707,0.0058332356,0.007584834,0.21986884,0.0020133827,0.001430295,0.00022564361,0.0002010061,0.08927202],"genre_scores_gemma":[0.9534363,0.0026797806,0.003310863,0.01579348,0.00020104536,0.00048038506,0.00006105612,0.00011580891,0.023921233],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9748556,0.018576937,0.0007309073,0.00081106316,0.0028696689,0.002155973],"domain_scores_gemma":[0.95532084,0.024499686,0.002401583,0.0008322552,0.008860012,0.008085717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021561867,0.000436783,0.0010174575,0.0021244192,0.024701342,0.0079451585,0.0017188075,0.0048613884,0.00601392],"category_scores_gemma":[0.060704272,0.0011311275,0.000465611,0.0019480491,0.0141149815,0.005937162,0.006680461,0.011554718,0.0011162147],"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":[0.00003349027,0.00005445461,0.0011250019,0.000066941866,0.000001913259,0.0014797082,0.9786663,0.00005016206,0.00074591406,0.0016836866,0.009644457,0.0064479895],"study_design_scores_gemma":[0.0000039696424,0.000054835615,0.0008805871,0.000223423,0.0000030199133,0.00042309982,0.9406583,0.000088618224,0.00019794842,0.00042930548,0.057000954,0.000035987323],"about_ca_topic_score_codex":0.08886941,"about_ca_topic_score_gemma":0.12481836,"teacher_disagreement_score":0.08886941,"about_ca_system_score_codex":0.018462157,"about_ca_system_score_gemma":0.023658428,"threshold_uncertainty_score":0.17670423},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022426443,0.0062585855,0.5160107,0.32374218,0.0029410934,0.0032622316,0.00019778973,0.0006687089,0.12449233],"genre_scores_gemma":[0.37433374,0.004941309,0.5959925,0.0057517015,0.0010076296,0.0016742579,0.00031830385,0.0004061657,0.015574448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.713895,0.17218304,0.018315507,0.006876738,0.08422773,0.0045019593],"domain_scores_gemma":[0.46827412,0.25690657,0.016288022,0.063795365,0.17914796,0.015587885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37700397,0.000792331,0.0010522703,0.012446851,0.0123450495,0.026782785,0.005688598,0.005127583,0.0031355463],"category_scores_gemma":[0.40130606,0.001271714,0.00092333544,0.008752666,0.024682663,0.01348373,0.018226333,0.014887834,0.0008335651],"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":[0.000022440086,0.0003535495,0.0032721132,0.00036307453,0.00003005546,0.00010494479,0.01546347,0.0028141988,0.00042815635,0.67384994,0.032660525,0.27063754],"study_design_scores_gemma":[0.00007441109,0.00018739511,0.0054954486,0.004798777,0.000054735796,0.00017198738,0.02241772,0.011400901,0.0031247984,0.56858295,0.38345018,0.00024070549],"about_ca_topic_score_codex":0.04564105,"about_ca_topic_score_gemma":0.052407388,"teacher_disagreement_score":0.95771325,"about_ca_system_score_codex":0.042286772,"about_ca_system_score_gemma":0.2122281,"threshold_uncertainty_score":0.768265},"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":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05875573,0.02527429,0.18688881,0.3317912,0.01350638,0.0069511067,0.007435831,0.0012432837,0.3681534],"genre_scores_gemma":[0.6370291,0.010106807,0.22567157,0.06867079,0.005817644,0.008283191,0.002171109,0.0007154684,0.041534342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98508644,0.007198579,0.0012851359,0.0022018894,0.002723756,0.0015042641],"domain_scores_gemma":[0.9753607,0.01122677,0.0015552385,0.0010544256,0.008146269,0.0026566517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016671738,0.00073678023,0.0009046541,0.0029710976,0.007997678,0.014452972,0.0023386956,0.005339504,0.018965797],"category_scores_gemma":[0.033867538,0.0010363355,0.00091372046,0.0032075378,0.0077173463,0.008596561,0.007190373,0.009560519,0.0026854326],"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":[0.00029783678,0.00037434333,0.013085245,0.0031560455,0.00003512804,0.00068819197,0.020135194,0.0010283575,0.0041568843,0.6657079,0.13364361,0.15769121],"study_design_scores_gemma":[0.000090463574,0.000156472,0.022111274,0.0057663275,0.00006914664,0.00035760005,0.024525588,0.0012764474,0.0037839117,0.115789704,0.8258663,0.0002066794],"about_ca_topic_score_codex":0.040430572,"about_ca_topic_score_gemma":0.07358474,"teacher_disagreement_score":0.040430572,"about_ca_system_score_codex":0.016825333,"about_ca_system_score_gemma":0.022937695,"threshold_uncertainty_score":0.12207693},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516801,0.000872189,0.01054453,0.012909729,0.00007259157,0.00036468887,0.000027119771,0.00002361761,0.023505453],"genre_scores_gemma":[0.99774796,0.00015547524,0.0012814928,0.00036876363,0.00001159243,0.00012029788,0.0000041271055,0.000011315623,0.00029901063],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.73054343,0.22546901,0.008292402,0.004628813,0.024310991,0.006755339],"domain_scores_gemma":[0.32420307,0.60768783,0.019597795,0.01191981,0.030644914,0.0059466003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21439151,0.0006576192,0.0011378,0.0048573483,0.012949361,0.018863903,0.003264421,0.0042146454,0.0026693437],"category_scores_gemma":[0.41139472,0.000809231,0.0006685561,0.005269391,0.035257187,0.016130306,0.017134957,0.008345946,0.0002712169],"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":[0.00007396444,0.00027987512,0.015859006,0.00021823673,0.000018270888,0.00028991434,0.9446747,0.00013513306,0.00024202123,0.01733546,0.00071612024,0.020157443],"study_design_scores_gemma":[0.000020947846,0.000112131456,0.00952888,0.00051589304,0.000017490565,0.00014317453,0.9776487,0.0006209339,0.0005170054,0.0057879416,0.00504827,0.000038563907],"about_ca_topic_score_codex":0.008470981,"about_ca_topic_score_gemma":0.0071483403,"teacher_disagreement_score":0.21439151,"about_ca_system_score_codex":0.013353114,"about_ca_system_score_gemma":0.01685745,"threshold_uncertainty_score":0.9687951},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14177392,0.019129189,0.48417675,0.10046853,0.00092707464,0.003006241,0.0001656338,0.0009503132,0.24940239],"genre_scores_gemma":[0.6988131,0.007556878,0.28415686,0.0033013837,0.00030350738,0.0013308554,0.000118092314,0.00021693196,0.0042025116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82126707,0.14536351,0.006114154,0.004962644,0.01883654,0.0034561018],"domain_scores_gemma":[0.6311385,0.28286007,0.016182132,0.024577036,0.037721355,0.007520992],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15627845,0.001010181,0.0015462582,0.008398765,0.0058691264,0.020531705,0.0033163277,0.0029787633,0.005953831],"category_scores_gemma":[0.2221387,0.0007240218,0.001366438,0.00677998,0.014553806,0.017711585,0.017214922,0.0048883716,0.0009885362],"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":[0.00016813261,0.0009923268,0.015502801,0.0024081827,0.00012330148,0.00012638689,0.030755123,0.0025599732,0.000633655,0.1071852,0.006058046,0.8334869],"study_design_scores_gemma":[0.00034199865,0.0013522354,0.037787665,0.020901086,0.0004918083,0.00048284716,0.06421104,0.01718542,0.009912461,0.6263235,0.22063744,0.00037245025],"about_ca_topic_score_codex":0.012005981,"about_ca_topic_score_gemma":0.016137747,"teacher_disagreement_score":0.84372157,"about_ca_system_score_codex":0.02151689,"about_ca_system_score_gemma":0.049963325,"threshold_uncertainty_score":0.8264893},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5818985,0.00020085473,0.35839787,0.0008889216,0.00006382291,0.016333696,0.0031236287,0.00038735534,0.038705297],"genre_scores_gemma":[0.5784525,0.00012861953,0.38991168,0.00017967715,0.000017167367,0.025862101,0.0007517426,0.0000956598,0.00460084],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98280627,0.01373402,0.0005989298,0.00067787623,0.0015607474,0.00062219775],"domain_scores_gemma":[0.92428505,0.06412425,0.002555326,0.0035948348,0.0047915564,0.0006489471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022785254,0.001023996,0.0006393017,0.0048894617,0.003974404,0.002798532,0.002107314,0.0012357445,0.010540851],"category_scores_gemma":[0.05116747,0.0006709964,0.0008667145,0.0050941096,0.0024773448,0.002199527,0.0034559863,0.0011228246,0.0006080655],"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":[0.001579086,0.0033125177,0.11367976,0.0026578752,0.00032022252,0.0034305977,0.3377175,0.013427403,0.012352815,0.1169984,0.019138362,0.3753854],"study_design_scores_gemma":[0.0015788861,0.00483023,0.09691579,0.0021399457,0.0004878008,0.001971791,0.6492259,0.06776223,0.01667773,0.07161206,0.086401656,0.00039599513],"about_ca_topic_score_codex":0.016989777,"about_ca_topic_score_gemma":0.0380076,"teacher_disagreement_score":0.98301023,"about_ca_system_score_codex":0.003618538,"about_ca_system_score_gemma":0.007880587,"threshold_uncertainty_score":0.1205014},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857094,0.00042107955,0.00037898187,0.0032355366,0.000013161741,0.00019044887,0.000106873915,0.000013617967,0.009930822],"genre_scores_gemma":[0.99686325,0.00050363375,0.00059384824,0.0001254753,0.000005243416,0.00006434439,0.000048224643,0.0000050460562,0.0017909881],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98429537,0.005730233,0.00080137077,0.00066508487,0.004705159,0.0038028422],"domain_scores_gemma":[0.9661785,0.01482848,0.0069393655,0.0007912894,0.00754025,0.0037222311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013111062,0.00022622742,0.0004313345,0.0024744608,0.010562303,0.0054207677,0.0014784638,0.00069268263,0.001364627],"category_scores_gemma":[0.03238759,0.0006009432,0.00031772468,0.0048355213,0.005561698,0.0020217493,0.0030718923,0.001518164,0.000101143625],"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":[0.00013910994,0.00025079414,0.36748704,0.0005356555,0.000036148827,0.0012253496,0.56044614,0.0006028369,0.0011718181,0.0075918576,0.0030290391,0.057484217],"study_design_scores_gemma":[0.000016826329,0.00010827926,0.55267686,0.00026862998,0.000029308916,0.000053696516,0.42398912,0.0007218021,0.00047103694,0.00048630015,0.021140631,0.000037428515],"about_ca_topic_score_codex":0.9647964,"about_ca_topic_score_gemma":0.9844906,"teacher_disagreement_score":0.15743046,"about_ca_system_score_codex":0.15743046,"about_ca_system_score_gemma":0.21068347,"threshold_uncertainty_score":0.97726125},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43196672,0.04967567,0.17813896,0.2758902,0.0038371666,0.0014353357,0.00032877742,0.0009854612,0.057741694],"genre_scores_gemma":[0.9188734,0.011361973,0.046495363,0.016455946,0.00085853465,0.0012198351,0.0001535614,0.000304698,0.0042765858],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6022605,0.31843844,0.024269924,0.008586384,0.041398212,0.0050465153],"domain_scores_gemma":[0.4212664,0.39707822,0.03534288,0.024058988,0.10873376,0.013519732],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24527018,0.0004943068,0.0011237758,0.003310399,0.007811796,0.017017026,0.003137649,0.0030935146,0.002762221],"category_scores_gemma":[0.39821857,0.0007258491,0.0008027465,0.003908039,0.007964327,0.009752558,0.010815882,0.0052743945,0.00092047756],"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":[0.0003506411,0.0003913538,0.056305744,0.0049830033,0.00030254893,0.0012466743,0.3135026,0.001214463,0.0016283302,0.014965583,0.04265442,0.5624545],"study_design_scores_gemma":[0.00009710598,0.0010803243,0.035959564,0.015783641,0.00020597625,0.003927435,0.6229066,0.0034051393,0.004354419,0.03161595,0.2802938,0.0003700481],"about_ca_topic_score_codex":0.003094809,"about_ca_topic_score_gemma":0.007438128,"teacher_disagreement_score":0.24527018,"about_ca_system_score_codex":0.0063518886,"about_ca_system_score_gemma":0.018546259,"threshold_uncertainty_score":0.9307162},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6890697,0.003050071,0.038290307,0.030455478,0.0018929617,0.151565,0.01950684,0.0010282687,0.065141335],"genre_scores_gemma":[0.7651478,0.0026500558,0.09291533,0.010884803,0.00044851666,0.0806122,0.02517122,0.00030750377,0.021862598],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9387954,0.033100236,0.0036171938,0.0019825248,0.015648073,0.0068566515],"domain_scores_gemma":[0.8993003,0.020084277,0.0060836114,0.0070558945,0.053540442,0.013935655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.083756134,0.0013387997,0.0013925179,0.0014734989,0.003233365,0.0054879026,0.0039061923,0.005199878,0.0057402747],"category_scores_gemma":[0.057483874,0.0008190496,0.0035915116,0.0016319925,0.0014755798,0.0029193345,0.0061862,0.0039961026,0.003446076],"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":[0.043258272,0.07586457,0.117964186,0.006836231,0.0014624412,0.0012897827,0.012445309,0.009697977,0.019838449,0.008361962,0.08490145,0.61807936],"study_design_scores_gemma":[0.031255413,0.29191044,0.3297999,0.005513288,0.0019958524,0.0009924079,0.027470233,0.0050354404,0.07081645,0.0067547574,0.22793554,0.00052035315],"about_ca_topic_score_codex":0.0314692,"about_ca_topic_score_gemma":0.03274648,"teacher_disagreement_score":0.083756134,"about_ca_system_score_codex":0.010212331,"about_ca_system_score_gemma":0.08019026,"threshold_uncertainty_score":0.44295007},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08347573,0.12775502,0.043207318,0.69960546,0.0034389491,0.00073379255,0.000056435205,0.00016615506,0.041561168],"genre_scores_gemma":[0.8887817,0.028244583,0.042418677,0.035159882,0.001357046,0.0012124563,0.000039774095,0.0000651596,0.002720687],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.65656435,0.29728088,0.011638484,0.0034192011,0.026581284,0.0045159096],"domain_scores_gemma":[0.41728637,0.52260196,0.018499045,0.0065751686,0.021717062,0.013320325],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.257811,0.00059610547,0.0017505425,0.005361287,0.004053791,0.021711083,0.0023211322,0.007148192,0.0023732134],"category_scores_gemma":[0.392563,0.00074308296,0.00094343,0.004384264,0.028498901,0.016933398,0.009721591,0.0071093384,0.00032859304],"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":[0.00063237204,0.0009614841,0.025419869,0.004299289,0.00023686331,0.00018168753,0.03631947,0.0007002995,0.00016886098,0.19468212,0.017302515,0.71909523],"study_design_scores_gemma":[0.000656753,0.0022288042,0.037415266,0.03128296,0.00049300346,0.0010020412,0.10585442,0.0064330418,0.0017903829,0.6844308,0.1279739,0.00043875616],"about_ca_topic_score_codex":0.0043378407,"about_ca_topic_score_gemma":0.006853897,"teacher_disagreement_score":0.257811,"about_ca_system_score_codex":0.014930722,"about_ca_system_score_gemma":0.025821075,"threshold_uncertainty_score":0.91525114},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14021243,0.0032809323,0.41551566,0.24897496,0.0020523418,0.0020330937,0.00016746989,0.00034163267,0.18742147],"genre_scores_gemma":[0.9159799,0.00074280915,0.07544098,0.0040321834,0.00016119405,0.0010011732,0.000032672848,0.000046596342,0.0025625743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95485395,0.0392013,0.00048774833,0.0012404267,0.0029860986,0.0012304356],"domain_scores_gemma":[0.92191523,0.06388782,0.0027688593,0.0032360551,0.0039509973,0.0042409734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036967885,0.00080422044,0.000716014,0.002435926,0.0039851894,0.00714379,0.0026543038,0.003464011,0.006309394],"category_scores_gemma":[0.085381135,0.00044438336,0.0009699626,0.0014796194,0.01911079,0.0076436815,0.005451273,0.0036153349,0.00035773052],"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":[0.00023375529,0.0010988417,0.0107213585,0.00059167587,0.00011980557,0.00017042653,0.0091937,0.010143066,0.00022680033,0.8410931,0.007824559,0.118582904],"study_design_scores_gemma":[0.00042331772,0.00095275417,0.006983461,0.0008662612,0.00015199232,0.0002465684,0.010386409,0.03428656,0.00066042674,0.91515636,0.029794397,0.00009155036],"about_ca_topic_score_codex":0.008916119,"about_ca_topic_score_gemma":0.008804819,"teacher_disagreement_score":0.036967885,"about_ca_system_score_codex":0.00924938,"about_ca_system_score_gemma":0.025850201,"threshold_uncertainty_score":0.19550723},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063379155,0.0014068476,0.00080957176,0.9802311,0.0011922898,0.000182964,0.000053559124,0.00003758396,0.009748207],"genre_scores_gemma":[0.34505183,0.0044047185,0.017295824,0.5888171,0.0024037655,0.001121211,0.00019992903,0.00034115947,0.040364467],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8805634,0.04139443,0.0046470314,0.004359273,0.026344817,0.042690992],"domain_scores_gemma":[0.6888088,0.12912807,0.006612103,0.006457434,0.061353914,0.10763974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15111096,0.0010858125,0.0016212936,0.00200202,0.045448843,0.033920035,0.011951313,0.032272868,0.008924144],"category_scores_gemma":[0.17057338,0.0019855686,0.0026705728,0.0026809105,0.040166184,0.01334385,0.024376856,0.05289032,0.00077880593],"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":[0.000264081,0.0005762125,0.006592233,0.00064427394,0.00020345418,0.0011954427,0.052550644,0.0024673815,0.0010773877,0.12186459,0.7505749,0.06198953],"study_design_scores_gemma":[0.0004778634,0.00026619865,0.023624709,0.0015921582,0.00010660347,0.00021340986,0.061280455,0.0013643708,0.00085812714,0.041190494,0.868431,0.0005945915],"about_ca_topic_score_codex":0.9131061,"about_ca_topic_score_gemma":0.9735719,"teacher_disagreement_score":0.9131061,"about_ca_system_score_codex":0.2340189,"about_ca_system_score_gemma":0.62713915,"threshold_uncertainty_score":0.8884295},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15091637,0.0064501823,0.25529101,0.4531416,0.0010046853,0.0016650236,0.00012124903,0.000310296,0.13109954],"genre_scores_gemma":[0.9009658,0.0024318881,0.086586185,0.0068869893,0.00013796748,0.00088879,0.000042034346,0.00011375323,0.0019465935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8859264,0.09456067,0.0025338412,0.0025721733,0.009635284,0.0047716377],"domain_scores_gemma":[0.8215261,0.12891643,0.009889216,0.00989447,0.013168926,0.016604878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12037245,0.0012039739,0.0017338878,0.0036462257,0.009862658,0.029518478,0.0042622825,0.005283554,0.006277156],"category_scores_gemma":[0.16365972,0.0008619923,0.0011700183,0.0024169693,0.04089179,0.03032019,0.02016496,0.011679738,0.00044749645],"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":[0.00015324315,0.0007554133,0.012148966,0.0014931225,0.00026157574,0.0003554366,0.07133068,0.0047841426,0.0015251562,0.70986325,0.009224082,0.18810493],"study_design_scores_gemma":[0.00005242539,0.0002384825,0.0057313913,0.0025859114,0.00012169777,0.000258064,0.04961939,0.0044701253,0.0020988996,0.89484966,0.039767914,0.00020606077],"about_ca_topic_score_codex":0.008544396,"about_ca_topic_score_gemma":0.013721133,"teacher_disagreement_score":0.12037245,"about_ca_system_score_codex":0.016595202,"about_ca_system_score_gemma":0.055388372,"threshold_uncertainty_score":0.636598},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5082411,0.0031321095,0.20677397,0.05081224,0.0002661648,0.010378438,0.00047959425,0.00023632223,0.21968007],"genre_scores_gemma":[0.9419576,0.00045370444,0.053207565,0.000947994,0.000014318024,0.0024146005,0.000090542075,0.000026596153,0.0008869262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.8274165,0.15535301,0.003540674,0.0016881006,0.0076263268,0.004375465],"domain_scores_gemma":[0.7241605,0.22800706,0.009196176,0.0065229186,0.029110717,0.0030025402],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14633423,0.0008791056,0.00078188523,0.006913935,0.0058575394,0.008442828,0.0020618476,0.0018498334,0.0021323205],"category_scores_gemma":[0.2022749,0.00061193283,0.00075736793,0.0063704457,0.006976714,0.008276814,0.006621923,0.0034495888,0.00016533102],"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":[0.00029799176,0.002263326,0.10106994,0.00250406,0.00021213786,0.00078387855,0.17411329,0.0162788,0.00063644967,0.3685107,0.014401086,0.3189284],"study_design_scores_gemma":[0.00047387535,0.0012542522,0.13369392,0.008688027,0.00031618378,0.00045313596,0.49467,0.082718074,0.004138494,0.20567124,0.067585416,0.00033747038],"about_ca_topic_score_codex":0.04818979,"about_ca_topic_score_gemma":0.048870377,"teacher_disagreement_score":0.85366577,"about_ca_system_score_codex":0.02951625,"about_ca_system_score_gemma":0.043961767,"threshold_uncertainty_score":0.7738986},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9075853,0.0008087826,0.0060201483,0.019120023,0.00026036584,0.008960474,0.0016254564,0.0002920072,0.055327307],"genre_scores_gemma":[0.9787274,0.0003686249,0.010092149,0.0009493611,0.00005129198,0.0023694462,0.0005248175,0.000033038552,0.006883869],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9688752,0.019494262,0.0010760988,0.0012834432,0.0037739025,0.005496995],"domain_scores_gemma":[0.88670033,0.05147571,0.006108131,0.008533935,0.026414266,0.020767584],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.044657156,0.0006466685,0.0005905598,0.001002426,0.012522576,0.0041126492,0.0036093432,0.0020273738,0.00634706],"category_scores_gemma":[0.06015854,0.0007527784,0.0009445182,0.0021823894,0.0053767385,0.0032718517,0.0056615914,0.0023813408,0.0005839546],"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":[0.025894143,0.035235472,0.3185602,0.00359605,0.00094818335,0.0020149422,0.05100383,0.050925195,0.015749324,0.060853142,0.0704585,0.36476102],"study_design_scores_gemma":[0.010924078,0.0163537,0.7027334,0.0015911052,0.00081469724,0.000314451,0.040307175,0.026476324,0.024172839,0.028784906,0.14691605,0.0006112814],"about_ca_topic_score_codex":0.91081774,"about_ca_topic_score_gemma":0.9608515,"teacher_disagreement_score":0.9553428,"about_ca_system_score_codex":0.10751377,"about_ca_system_score_gemma":0.2943771,"threshold_uncertainty_score":0.78007066},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26587662,0.003655532,0.013451421,0.62268925,0.011561477,0.001198905,0.000105127554,0.00016741695,0.081294276],"genre_scores_gemma":[0.8627296,0.0029781074,0.012819319,0.07224116,0.002347769,0.0009667167,0.0000882127,0.00019332508,0.04563579],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9608471,0.029536152,0.0008017002,0.0010993998,0.002237122,0.0054785535],"domain_scores_gemma":[0.94372797,0.02904319,0.0010534477,0.0013441145,0.0066685244,0.018162774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04375554,0.0009657315,0.0004938332,0.00071165885,0.019085398,0.011118594,0.005610856,0.011221676,0.008366544],"category_scores_gemma":[0.0669194,0.000740392,0.0011705518,0.0007022825,0.015237734,0.00718432,0.0152646685,0.0319314,0.0012898699],"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":[0.0004365209,0.008429722,0.0041059135,0.0007460827,0.00006692924,0.010455287,0.7142195,0.0015549536,0.002264022,0.027426515,0.104918525,0.12537605],"study_design_scores_gemma":[0.00011547913,0.0009293103,0.002805886,0.00083397224,0.000028910777,0.0014161386,0.73375577,0.0005243138,0.0012905365,0.011782808,0.24639954,0.00011736166],"about_ca_topic_score_codex":0.012060572,"about_ca_topic_score_gemma":0.030921018,"teacher_disagreement_score":0.04375554,"about_ca_system_score_codex":0.011687324,"about_ca_system_score_gemma":0.01844428,"threshold_uncertainty_score":0.23140419},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044948563,0.021167513,0.30962616,0.06289847,0.007314016,0.03509351,0.0019389966,0.0013713061,0.51564145],"genre_scores_gemma":[0.3996037,0.012480557,0.4305766,0.015045219,0.0025749842,0.038414173,0.0019859376,0.00061955233,0.09869919],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5192904,0.35618934,0.019275758,0.0065246373,0.09366148,0.0050583296],"domain_scores_gemma":[0.5998837,0.21922044,0.01598269,0.028068319,0.13113792,0.005706943],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2607118,0.0013586695,0.0018906533,0.005780323,0.0039307517,0.01691359,0.003536083,0.0045587765,0.021179892],"category_scores_gemma":[0.37387523,0.0008475395,0.0022711665,0.005795453,0.0049810996,0.008382546,0.007595676,0.005911809,0.004273866],"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":[0.0016536975,0.00095481746,0.0049412916,0.007125391,0.00041882662,0.00016799947,0.008197732,0.0052265073,0.0011646677,0.17896923,0.041575953,0.74960405],"study_design_scores_gemma":[0.0017938893,0.006203582,0.016524501,0.022835823,0.0010547919,0.0003763716,0.009277514,0.009567122,0.010314707,0.16749112,0.75419337,0.0003671862],"about_ca_topic_score_codex":0.0055338,"about_ca_topic_score_gemma":0.0058926996,"teacher_disagreement_score":0.7392882,"about_ca_system_score_codex":0.013749367,"about_ca_system_score_gemma":0.041704915,"threshold_uncertainty_score":0.91167396},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87942785,0.0018961692,0.0027118328,0.07022462,0.00036142478,0.00021117469,0.0006048361,0.000080123136,0.04448191],"genre_scores_gemma":[0.98879427,0.0008312973,0.00068392546,0.001518081,0.00012251934,0.000121832236,0.00020289472,0.00003698139,0.0076883016],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9877543,0.006990519,0.00040677906,0.0010097591,0.0018684161,0.0019702117],"domain_scores_gemma":[0.962173,0.022301797,0.002033365,0.00096360355,0.0057618576,0.0067663817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018864566,0.0002569376,0.00029880932,0.0013803106,0.0022706112,0.0038247507,0.0017895935,0.0017514277,0.008155265],"category_scores_gemma":[0.03587169,0.0003117527,0.00028543847,0.0018077708,0.0014030354,0.0051524104,0.0029782152,0.002584426,0.0006411536],"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":[0.0009246481,0.001739798,0.3267167,0.00085503043,0.000058977323,0.0006784385,0.11430054,0.0007165103,0.0016621872,0.015477426,0.01717542,0.51969445],"study_design_scores_gemma":[0.00006331473,0.0014848782,0.58275896,0.0012623084,0.000061149,0.00047287205,0.30371046,0.001882223,0.0025924712,0.0082874065,0.09733444,0.00008955637],"about_ca_topic_score_codex":0.025627753,"about_ca_topic_score_gemma":0.047074467,"teacher_disagreement_score":0.025627753,"about_ca_system_score_codex":0.004713857,"about_ca_system_score_gemma":0.00642409,"threshold_uncertainty_score":0.09976661},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3391432,0.016309831,0.09017048,0.17514971,0.0011621186,0.0004240609,0.00058693136,0.00022452051,0.37682915],"genre_scores_gemma":[0.99455523,0.00080607645,0.0033776,0.0006654176,0.00007607141,0.00004289996,0.000017742843,0.00001082515,0.00044806246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.946685,0.03898976,0.0021477845,0.0009832007,0.0092385225,0.0019556265],"domain_scores_gemma":[0.8476815,0.11101839,0.016248822,0.0067230905,0.013821171,0.0045069745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034041073,0.0004054134,0.0007060058,0.0034009102,0.0047639953,0.014406764,0.0015071371,0.0019814228,0.003941807],"category_scores_gemma":[0.10490742,0.00035191953,0.0004888815,0.0020474195,0.023010422,0.012963197,0.008219992,0.0036925513,0.00019952128],"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":[0.0005221245,0.0002474563,0.038668197,0.0019591427,0.00020576589,0.00033621813,0.15086402,0.0019265935,0.001076193,0.5429724,0.007750379,0.2534715],"study_design_scores_gemma":[0.00010856237,0.0007636911,0.05740435,0.00719758,0.0005013701,0.00081890187,0.2857933,0.006763058,0.003976892,0.5227328,0.113565266,0.00037428323],"about_ca_topic_score_codex":0.014823617,"about_ca_topic_score_gemma":0.021904124,"teacher_disagreement_score":0.034041073,"about_ca_system_score_codex":0.014938144,"about_ca_system_score_gemma":0.013633636,"threshold_uncertainty_score":0.18002856},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028077397,0.020682365,0.1630501,0.6070437,0.002328573,0.001308549,0.00023469214,0.00083075353,0.17644382],"genre_scores_gemma":[0.7282769,0.021201914,0.20367485,0.031740956,0.0018677813,0.0024753972,0.0002782113,0.0003245377,0.010159408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.87741274,0.09717279,0.0049133785,0.0055396226,0.010064268,0.0048972066],"domain_scores_gemma":[0.70681226,0.23662801,0.015176005,0.019375235,0.010587829,0.011420667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13998419,0.001056234,0.00137207,0.006715956,0.009862257,0.038875267,0.0054309983,0.014498768,0.015105013],"category_scores_gemma":[0.1661276,0.0014485022,0.0020896571,0.007493266,0.032045748,0.040573377,0.028464897,0.009645342,0.0028872602],"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":[0.00020334094,0.0003272563,0.0045449776,0.0036456275,0.00019789352,0.00091789354,0.054937247,0.0015523281,0.001159491,0.61582255,0.030411514,0.2862799],"study_design_scores_gemma":[0.00019738848,0.00013460315,0.0023589807,0.008513841,0.00015516933,0.00043012438,0.018618163,0.0030162027,0.0011037873,0.7892955,0.17604253,0.00013369149],"about_ca_topic_score_codex":0.009982967,"about_ca_topic_score_gemma":0.008360869,"teacher_disagreement_score":0.13998419,"about_ca_system_score_codex":0.014620341,"about_ca_system_score_gemma":0.06525558,"threshold_uncertainty_score":0.74031603},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24278644,0.09852039,0.0072809514,0.2625411,0.0031235893,0.00030814784,0.016224505,0.00054260273,0.36867234],"genre_scores_gemma":[0.8280914,0.033704966,0.007393952,0.012442741,0.00039604213,0.00019054918,0.0054048025,0.0002601683,0.11211544],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99100935,0.0011491047,0.00019581398,0.00049149577,0.0055049006,0.0016492533],"domain_scores_gemma":[0.9858892,0.0018821459,0.0009020633,0.00033605492,0.009501256,0.0014892735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072391042,0.00060575,0.00070623157,0.0036579778,0.005907932,0.011280663,0.0012151055,0.0014275672,0.010667643],"category_scores_gemma":[0.011734649,0.00032081536,0.0006854277,0.013364671,0.004699077,0.0038594932,0.0037138879,0.0028373701,0.0011645183],"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":[0.000755157,0.00015538024,0.110729545,0.002078802,0.00032382386,0.0009151476,0.015905848,0.003181518,0.0011899694,0.22186397,0.21118754,0.43171334],"study_design_scores_gemma":[0.000052906922,0.00013553281,0.21654502,0.0022075775,0.00019146941,0.00015767051,0.018371733,0.001144186,0.0014634599,0.007941097,0.75165015,0.00013922206],"about_ca_topic_score_codex":0.96982026,"about_ca_topic_score_gemma":0.97071046,"teacher_disagreement_score":0.07306798,"about_ca_system_score_codex":0.07306798,"about_ca_system_score_gemma":0.16616039,"threshold_uncertainty_score":0.5301478},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65281934,0.004745585,0.20419064,0.04494192,0.000576153,0.007495424,0.00016456116,0.00015398616,0.0849124],"genre_scores_gemma":[0.8871142,0.0011867865,0.105820306,0.0014320354,0.00004175797,0.0019074659,0.00003927751,0.000034227003,0.002423826],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7520316,0.22613081,0.0050547305,0.0026822067,0.009460728,0.00463991],"domain_scores_gemma":[0.8177432,0.140926,0.0069759837,0.008471324,0.01831669,0.007566898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14473827,0.0007205839,0.00074090547,0.0031019652,0.020585297,0.010036907,0.0037850763,0.0057830694,0.002136397],"category_scores_gemma":[0.12503244,0.00082811347,0.0011700701,0.0036790823,0.011362657,0.008499083,0.012349336,0.008813492,0.0003891419],"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":[0.0005688821,0.0047104876,0.0330016,0.0017028234,0.00011270104,0.026538327,0.5716545,0.0039473376,0.0020061964,0.15825392,0.010648246,0.18685496],"study_design_scores_gemma":[0.0004543808,0.002167401,0.014051635,0.0058344956,0.00018103683,0.014733547,0.714609,0.011513164,0.0066689793,0.058899857,0.17061485,0.000271656],"about_ca_topic_score_codex":0.008347312,"about_ca_topic_score_gemma":0.020760164,"teacher_disagreement_score":0.14473827,"about_ca_system_score_codex":0.013626897,"about_ca_system_score_gemma":0.020924844,"threshold_uncertainty_score":0},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5825946,0.0060507148,0.0054388363,0.15492637,0.0007344291,0.00008870806,0.00019358296,0.0000962144,0.2498765],"genre_scores_gemma":[0.9424103,0.0019971773,0.0014678282,0.007090487,0.00006106992,0.00006224271,0.000060712613,0.000047910475,0.04680224],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940836,0.0026474607,0.00011042585,0.0006357642,0.001028426,0.0014943304],"domain_scores_gemma":[0.98986584,0.0021815544,0.00074931025,0.00036987342,0.0034858363,0.0033476234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006404616,0.0003990769,0.00041223617,0.0007862587,0.017764958,0.007956486,0.0017033297,0.0032939797,0.01334137],"category_scores_gemma":[0.01025194,0.00031370885,0.00034437812,0.00095313025,0.01624009,0.0061210836,0.007070501,0.005177028,0.0013274647],"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":[0.000042908825,0.000036456204,0.011996665,0.00014332928,0.00001608866,0.0014344612,0.91042674,0.00009152537,0.000797046,0.032060698,0.016001632,0.02695244],"study_design_scores_gemma":[0.0000061494648,0.000038800037,0.018467803,0.00041145209,0.000017563827,0.000632044,0.7966888,0.00012256342,0.00027816766,0.004638485,0.17864822,0.00004991473],"about_ca_topic_score_codex":0.6277271,"about_ca_topic_score_gemma":0.79686266,"teacher_disagreement_score":0.6277271,"about_ca_system_score_codex":0.02138461,"about_ca_system_score_gemma":0.037362166,"threshold_uncertainty_score":0.7489306},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875474,0.00038433127,0.00020141888,0.0044171214,0.00005035093,0.00008233862,0.0004066729,0.000012120706,0.0068982127],"genre_scores_gemma":[0.9943395,0.0004228395,0.00024787526,0.00054306973,0.000016243432,0.00005282357,0.00017262713,0.000011383572,0.0041936175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9920919,0.0015221323,0.0004412967,0.00042697033,0.002866069,0.0026517462],"domain_scores_gemma":[0.98021734,0.0019954375,0.0037274384,0.00083005417,0.0063508684,0.0068788882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004806693,0.0001360008,0.00036972106,0.002146129,0.0044061164,0.003294191,0.0019674702,0.0006783068,0.0048099784],"category_scores_gemma":[0.021839255,0.00027868064,0.00036775257,0.0034595435,0.0023590904,0.0010965592,0.0028125702,0.0009400979,0.00055788836],"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":[0.00027696762,0.00013836716,0.8919263,0.00011440659,0.00002839967,0.00016414202,0.025472444,0.00012717464,0.0006716601,0.0016093376,0.0049848277,0.07448581],"study_design_scores_gemma":[0.000019988858,0.00008380304,0.9642619,0.000108600085,0.000012708671,0.000044748136,0.02680433,0.00032070838,0.00024126148,0.0003050462,0.0077730687,0.000023815037],"about_ca_topic_score_codex":0.9485379,"about_ca_topic_score_gemma":0.97590023,"teacher_disagreement_score":0.9679315,"about_ca_system_score_codex":0.03206852,"about_ca_system_score_gemma":0.053262226,"threshold_uncertainty_score":0.23267448},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061850302,0.03806466,0.0076098526,0.44373354,0.00094462495,0.00013145887,0.00062493957,0.000113662325,0.44692695],"genre_scores_gemma":[0.93077594,0.011438309,0.004211129,0.014351932,0.00023232044,0.00006790686,0.000096229836,0.00004668234,0.03877956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9688975,0.010400036,0.00087568234,0.0017415852,0.010474311,0.007610836],"domain_scores_gemma":[0.9654168,0.016777234,0.0016419988,0.00089227833,0.011514429,0.0037572233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019238621,0.0007617743,0.00064034533,0.005695971,0.023749197,0.02182286,0.0024235628,0.007965035,0.010467832],"category_scores_gemma":[0.030840816,0.00064168207,0.0007791574,0.009229611,0.024752703,0.0068494105,0.004885466,0.006988362,0.0004203732],"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":[0.000072028444,0.000037546542,0.004171492,0.00038062932,0.00002097227,0.000616951,0.0403527,0.0009201203,0.00050238014,0.8712236,0.029630624,0.05207087],"study_design_scores_gemma":[0.00003226589,0.00007942455,0.04206192,0.0023784842,0.00007426085,0.0004972143,0.11643722,0.0012967074,0.0010479027,0.098767035,0.7369653,0.0003622994],"about_ca_topic_score_codex":0.98965734,"about_ca_topic_score_gemma":0.9925615,"teacher_disagreement_score":0.7565674,"about_ca_system_score_codex":0.24343258,"about_ca_system_score_gemma":0.22354533,"threshold_uncertainty_score":0.87751096},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7548704,0.033351034,0.048691332,0.028430553,0.00069798273,0.0013316027,0.0016453976,0.0005056944,0.130476],"genre_scores_gemma":[0.98336065,0.0023557972,0.012397497,0.0004926297,0.00006235889,0.00032307723,0.0002681336,0.000024575033,0.000715277],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.90782267,0.06626126,0.005242347,0.0016595358,0.01697535,0.0020389466],"domain_scores_gemma":[0.81958497,0.09504883,0.03883859,0.005231065,0.035681,0.0056155026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06997916,0.00046400022,0.0006811688,0.013392579,0.0025896835,0.004817309,0.0013310823,0.0008020034,0.0020664267],"category_scores_gemma":[0.14980273,0.00018012502,0.00038934583,0.01867814,0.0050649247,0.0041649626,0.004394011,0.0013531555,0.00017828541],"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":[0.0002832051,0.00046448444,0.29418135,0.0044840546,0.00013150154,0.00037485783,0.06484892,0.0018140748,0.0010439524,0.033839207,0.010758417,0.58777606],"study_design_scores_gemma":[0.000030393878,0.0011798358,0.7434429,0.008669193,0.00016204403,0.0009511734,0.12401213,0.0035401147,0.002241226,0.014910578,0.100581214,0.00027923554],"about_ca_topic_score_codex":0.029687062,"about_ca_topic_score_gemma":0.02892173,"teacher_disagreement_score":0.06997916,"about_ca_system_score_codex":0.013974057,"about_ca_system_score_gemma":0.015887542,"threshold_uncertainty_score":0.3700896},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030038372,0.15955356,0.21913402,0.13228212,0.007501622,0.0030972569,0.0020071524,0.00085623964,0.44552976],"genre_scores_gemma":[0.8246332,0.02847543,0.10479116,0.014819647,0.0037089752,0.0036121912,0.00076840026,0.0006580165,0.018533014],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6936247,0.25160554,0.009688916,0.0087862825,0.03285054,0.003444151],"domain_scores_gemma":[0.31967545,0.6074403,0.012972152,0.018199222,0.03712486,0.0045879856],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19789718,0.0025758762,0.00510643,0.017474378,0.0046725655,0.019830309,0.0049632974,0.0077440166,0.029312853],"category_scores_gemma":[0.5458512,0.0011675517,0.0028425572,0.009541236,0.02073945,0.03095697,0.012412416,0.00598691,0.002469103],"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":[0.0020002413,0.00021536287,0.010433132,0.0038575171,0.0008399385,0.0002496181,0.0015773883,0.0054334253,0.000103569415,0.5949234,0.026866078,0.35350034],"study_design_scores_gemma":[0.0005228265,0.0004464864,0.0038762195,0.0062154066,0.00054552115,0.00047792948,0.0016463889,0.01505232,0.00037156316,0.9149193,0.055763453,0.0001624537],"about_ca_topic_score_codex":0.007415744,"about_ca_topic_score_gemma":0.005354578,"teacher_disagreement_score":0.19789718,"about_ca_system_score_codex":0.018466331,"about_ca_system_score_gemma":0.01611341,"threshold_uncertainty_score":0.98913556},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050743427,0.024629746,0.8286372,0.015729615,0.0011378085,0.0003856325,0.00026752197,0.00069327187,0.12344494],"genre_scores_gemma":[0.13998294,0.042725187,0.66461504,0.0053095696,0.0018827647,0.0021826818,0.000866496,0.0011483927,0.14128686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9789347,0.01464933,0.00082466827,0.0009443847,0.0043995776,0.0002472182],"domain_scores_gemma":[0.8044195,0.18356422,0.0021058891,0.0050534518,0.0044920105,0.00036493066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.035102136,0.0013159077,0.0014192017,0.0028045026,0.0010061201,0.00850973,0.0019914745,0.0025310474,0.0076804413],"category_scores_gemma":[0.08415516,0.0008512983,0.0007800318,0.004066969,0.008874361,0.013385065,0.002428836,0.003825243,0.0036864986],"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":[0.000040696927,0.00005180761,0.0009265598,0.00073064654,0.000027192596,0.00006842388,0.0051919366,0.0020655238,0.00078758964,0.6951109,0.023295114,0.27170363],"study_design_scores_gemma":[0.0000057000643,0.000019756362,0.00077839574,0.0005213511,0.000014023622,0.000087622815,0.0011838421,0.0037655297,0.0009856223,0.9281589,0.064454496,0.000024710836],"about_ca_topic_score_codex":0.0019388489,"about_ca_topic_score_gemma":0.0022527913,"teacher_disagreement_score":0.9648979,"about_ca_system_score_codex":0.0028582881,"about_ca_system_score_gemma":0.0043032193,"threshold_uncertainty_score":0.1856401},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9581664,0.0006885841,0.0002278043,0.006541069,0.000037009147,0.00007720507,0.0024880557,0.000035059278,0.03173887],"genre_scores_gemma":[0.9955669,0.00032947568,0.00009224264,0.00009458993,0.000011838809,0.000015906098,0.00039027852,0.000005854708,0.0034927689],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99424225,0.0006407557,0.00020148471,0.00020425986,0.002777448,0.0019337035],"domain_scores_gemma":[0.99053967,0.0010249728,0.0022788297,0.00019955002,0.00233927,0.0036176995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019710117,0.00026058886,0.0004723769,0.0022801633,0.0031594923,0.004061283,0.0014775377,0.00084461295,0.006363025],"category_scores_gemma":[0.010740521,0.00043646665,0.0005850772,0.0037589995,0.0019276474,0.0010730855,0.0021015771,0.00094252743,0.00033483707],"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":[0.0004250269,0.00019578896,0.86423445,0.00027484907,0.00014666335,0.0011242025,0.00585466,0.012289034,0.00029627504,0.015980741,0.02820067,0.070977576],"study_design_scores_gemma":[0.00003552794,0.000121559504,0.9696203,0.00013679599,0.000045120556,0.00015077238,0.009086821,0.0043569286,0.00009619267,0.0019273756,0.014386307,0.000036344285],"about_ca_topic_score_codex":0.9508983,"about_ca_topic_score_gemma":0.96790177,"teacher_disagreement_score":0.90314984,"about_ca_system_score_codex":0.096850134,"about_ca_system_score_gemma":0.063313186,"threshold_uncertainty_score":0.7027002},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93275446,0.004048604,0.0014167699,0.002554878,0.00012891837,0.00048567244,0.0013929027,0.000058338665,0.057159573],"genre_scores_gemma":[0.9414811,0.002091731,0.0026148632,0.0003989636,0.000015756385,0.00030491126,0.0009854734,0.000016646074,0.052090622],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983979,0.00039034052,0.000052508753,0.00017807989,0.00066223036,0.00031901745],"domain_scores_gemma":[0.9938731,0.0005303138,0.00045714015,0.00010851838,0.0038021603,0.0012288919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003068598,0.00040944724,0.00029719103,0.0013635994,0.0029882353,0.0019461199,0.0006585446,0.0005593152,0.0044336496],"category_scores_gemma":[0.0043542814,0.00017426578,0.00024400075,0.001248214,0.0011509933,0.0008489091,0.0013757481,0.0007275753,0.000476976],"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":[0.00055925024,0.00053029304,0.47559267,0.0013559003,0.00017579121,0.00055835734,0.12742646,0.0010997934,0.011536339,0.0037966976,0.016780714,0.36058784],"study_design_scores_gemma":[0.0000065111735,0.0003224192,0.889494,0.0003386024,0.00005480373,0.000047989808,0.047303893,0.00038006844,0.0020242634,0.00018253578,0.0597956,0.000049322112],"about_ca_topic_score_codex":0.7563319,"about_ca_topic_score_gemma":0.9134257,"teacher_disagreement_score":0.24366808,"about_ca_system_score_codex":0.018320356,"about_ca_system_score_gemma":0.019576754,"threshold_uncertainty_score":0.49020612},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6455088,0.007516952,0.06623429,0.048496045,0.0009266016,0.0018834724,0.00073681667,0.00045204675,0.22824492],"genre_scores_gemma":[0.9075451,0.0024786952,0.02064133,0.002140086,0.000091499525,0.000790565,0.0002099811,0.0001845127,0.065918185],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9340957,0.029576575,0.0022109807,0.005440161,0.023067536,0.005608998],"domain_scores_gemma":[0.8622935,0.075779974,0.0087046195,0.0075955484,0.03793565,0.007690694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.061765198,0.0007396001,0.0011428419,0.004271695,0.017661646,0.01824481,0.0026946918,0.0030909127,0.009050088],"category_scores_gemma":[0.091740906,0.0008092291,0.0009078991,0.005561195,0.018570192,0.006339462,0.012411698,0.0059519103,0.0012865069],"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":[0.00028858523,0.00023038157,0.024243098,0.0010166506,0.0000877699,0.00076242175,0.72661465,0.0006208935,0.005585247,0.10892373,0.005640593,0.12598594],"study_design_scores_gemma":[0.000068542155,0.00044195747,0.08708729,0.0017876215,0.00014669997,0.00046238498,0.6435681,0.0009851154,0.010431013,0.028321767,0.2264402,0.00025938486],"about_ca_topic_score_codex":0.35803437,"about_ca_topic_score_gemma":0.54984087,"teacher_disagreement_score":0.35803437,"about_ca_system_score_codex":0.051259175,"about_ca_system_score_gemma":0.14742213,"threshold_uncertainty_score":0.7119008},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10494069,0.3174674,0.05968553,0.46126145,0.0039818203,0.00381738,0.006293357,0.0007278787,0.04182455],"genre_scores_gemma":[0.79085726,0.097928755,0.07403246,0.028411347,0.0012964788,0.004635852,0.0011953823,0.00028218934,0.0013602603],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.22585233,0.566015,0.11112303,0.012105282,0.08131899,0.003585455],"domain_scores_gemma":[0.034870684,0.82826024,0.046051912,0.028954107,0.058433343,0.0034297425],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.66019356,0.0007908579,0.002998483,0.033908036,0.0030310077,0.016715774,0.003838505,0.005200297,0.002985989],"category_scores_gemma":[0.9000523,0.0026338864,0.002973316,0.024814414,0.0067332275,0.013740654,0.010841559,0.006943375,0.00044876433],"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":[0.0020406086,0.00012846761,0.17945766,0.08070121,0.009879664,0.0006320426,0.11523175,0.0019141857,0.0029768024,0.03164812,0.054875392,0.5205141],"study_design_scores_gemma":[0.000683512,0.00052962784,0.1410075,0.3807563,0.011272831,0.0020435383,0.04632591,0.00797234,0.004808129,0.042082746,0.36124957,0.001268058],"about_ca_topic_score_codex":0.04840087,"about_ca_topic_score_gemma":0.06131239,"teacher_disagreement_score":0.97753215,"about_ca_system_score_codex":0.022467848,"about_ca_system_score_gemma":0.07476447,"threshold_uncertainty_score":0.41904187},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010647638,0.082510635,0.0042460426,0.48265725,0.11868664,0.0005446398,0.0019755885,0.00032430285,0.3079901],"genre_scores_gemma":[0.042158213,0.11575481,0.0063523566,0.10988939,0.04117719,0.00065856014,0.0043671145,0.00025677923,0.67938554],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931131,0.002684853,0.00052442466,0.0005977232,0.0023341784,0.00074574124],"domain_scores_gemma":[0.9825106,0.0041753785,0.0008049968,0.0011933467,0.006742207,0.004573484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017501183,0.0008754502,0.00076391373,0.0021993094,0.0012946423,0.0056540263,0.0010865419,0.005318664,0.11103424],"category_scores_gemma":[0.041673426,0.00050963747,0.0006740816,0.001195409,0.0017698413,0.002346769,0.004083467,0.0063871825,0.02728914],"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":[0.000053599542,0.000040067134,0.00016699528,0.0003290131,0.00001962377,0.0000359521,0.00006224704,0.00007934995,0.0001444459,0.0101940045,0.93103564,0.057839006],"study_design_scores_gemma":[0.000024841765,0.000034610566,0.00090031774,0.0018371579,0.000010549316,0.000025834404,0.00009943153,0.000089669105,0.00020059552,0.0072514866,0.98951566,0.000009903769],"about_ca_topic_score_codex":0.0033567187,"about_ca_topic_score_gemma":0.008225974,"teacher_disagreement_score":0.11103424,"about_ca_system_score_codex":0.004517965,"about_ca_system_score_gemma":0.01369738,"threshold_uncertainty_score":0.37144655},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038174592,0.0037159016,0.002216318,0.87280625,0.009297511,0.00010270173,0.000055617507,0.00003691037,0.073594175],"genre_scores_gemma":[0.6197119,0.011201355,0.003524253,0.276439,0.007914636,0.0003504099,0.00013235175,0.00026579387,0.08046027],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9577284,0.023793226,0.0008433355,0.0019724541,0.007076022,0.008586515],"domain_scores_gemma":[0.9519517,0.020861832,0.0019819466,0.00082878553,0.010169679,0.014206014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027312502,0.0010633594,0.00088975317,0.00226984,0.0311492,0.023894556,0.0074879136,0.02283337,0.008686425],"category_scores_gemma":[0.054412708,0.00090645126,0.0013884276,0.0025369509,0.021261245,0.011993923,0.013837004,0.042022884,0.0014083043],"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":[0.000121697856,0.0006959333,0.0033499533,0.0004250327,0.00002995495,0.010511437,0.24400884,0.0009560459,0.0004800813,0.14198342,0.56462747,0.032810163],"study_design_scores_gemma":[0.000019235496,0.000108461834,0.0013771495,0.0005797397,0.0000066057605,0.0018558445,0.38194317,0.00043915733,0.0002442857,0.008627862,0.6047079,0.000090648835],"about_ca_topic_score_codex":0.0659869,"about_ca_topic_score_gemma":0.14425272,"teacher_disagreement_score":0.9340131,"about_ca_system_score_codex":0.020693855,"about_ca_system_score_gemma":0.017379614,"threshold_uncertainty_score":0.15014511},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14927562,0.008114471,0.19229867,0.2587791,0.0010372424,0.0020492596,0.00005243883,0.00012485374,0.3882683],"genre_scores_gemma":[0.95935845,0.001565009,0.026144432,0.003998279,0.00014982326,0.00094932504,0.000009925684,0.000045038378,0.007779782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8094046,0.17177728,0.0021450305,0.0031265046,0.010080736,0.003465767],"domain_scores_gemma":[0.7116298,0.26289374,0.007330963,0.007811602,0.006709205,0.0036246849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14186181,0.0008078788,0.000598523,0.002478216,0.011407702,0.017512666,0.0029143794,0.004589947,0.003918427],"category_scores_gemma":[0.1118248,0.00044972467,0.0006511683,0.0020713047,0.06406427,0.013656779,0.012753939,0.005046647,0.00034565644],"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":[0.00008352543,0.00032726614,0.002018689,0.0005048222,0.000032946933,0.00035326966,0.1974958,0.001289475,0.0005490208,0.7199884,0.0034404928,0.07391621],"study_design_scores_gemma":[0.0001178458,0.00030157962,0.003044904,0.0014993683,0.000033932658,0.00023275107,0.15851104,0.0020595505,0.0014813809,0.7032749,0.12937137,0.0000713726],"about_ca_topic_score_codex":0.002268223,"about_ca_topic_score_gemma":0.003706617,"teacher_disagreement_score":0.14186181,"about_ca_system_score_codex":0.0107376445,"about_ca_system_score_gemma":0.015264125,"threshold_uncertainty_score":0.7502459},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020697946,0.004687773,0.9426202,0.015190818,0.0002648506,0.0009360016,0.00013214404,0.00018365707,0.03391475],"genre_scores_gemma":[0.123574525,0.0018856248,0.86783063,0.0011565567,0.0002137241,0.003257027,0.00013662371,0.000063807776,0.0018814206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.880291,0.100190945,0.0070444793,0.0033742422,0.0073582204,0.0017412173],"domain_scores_gemma":[0.91232336,0.06270637,0.004979268,0.005361799,0.012341178,0.0022880912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10764313,0.0021452112,0.002504278,0.015668215,0.0068697385,0.015325656,0.0042647985,0.007624788,0.0033454453],"category_scores_gemma":[0.07115547,0.0011121846,0.0025981006,0.01025344,0.058668625,0.015280645,0.00648941,0.007563903,0.0006738465],"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":[0.0000051043617,0.000014223868,0.00014530099,0.00010484628,0.000009061906,0.000031959113,0.0010833262,0.00096190383,0.000038073686,0.9905635,0.00070433505,0.0063383207],"study_design_scores_gemma":[0.000031357376,0.00003514976,0.0002789503,0.0007982287,0.000025718122,0.0001004931,0.0019269723,0.005234632,0.0001588226,0.9613761,0.030000018,0.000033579116],"about_ca_topic_score_codex":0.014331034,"about_ca_topic_score_gemma":0.011354427,"teacher_disagreement_score":0.8923569,"about_ca_system_score_codex":0.018263632,"about_ca_system_score_gemma":0.01962179,"threshold_uncertainty_score":0.56927806},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19051035,0.03602801,0.005261013,0.21323708,0.022356138,0.0024420924,0.028574731,0.0009504747,0.50064015],"genre_scores_gemma":[0.080911554,0.002680184,0.0016066388,0.0016388699,0.0005550021,0.00013886092,0.0022911627,0.00016356994,0.9100143],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9983595,0.0002597687,0.00006810251,0.00018233436,0.00060933543,0.0005209671],"domain_scores_gemma":[0.9961008,0.0002839757,0.000105953484,0.000071727416,0.0021632523,0.001274356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044049616,0.0008862692,0.00045979695,0.0014460704,0.006099513,0.003535574,0.0010476474,0.002784147,0.040420517],"category_scores_gemma":[0.003982639,0.0004973491,0.0003167493,0.0016907686,0.0008719213,0.0006757179,0.0017034765,0.0027192053,0.006499172],"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":[0.0008203398,0.00015011663,0.007765695,0.0003532946,0.000026632266,0.00060774165,0.0020183907,0.000835856,0.002957644,0.0016633741,0.9159398,0.066861205],"study_design_scores_gemma":[0.000064740794,0.000119204706,0.057301633,0.00028919423,0.00002296597,0.00005762676,0.003896917,0.00051869475,0.0010372872,0.00034531995,0.9363012,0.000045147463],"about_ca_topic_score_codex":0.7275263,"about_ca_topic_score_gemma":0.9245353,"teacher_disagreement_score":0.2724737,"about_ca_system_score_codex":0.017131504,"about_ca_system_score_gemma":0.038035423,"threshold_uncertainty_score":0.5481567},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034741744,0.019250177,0.009120228,0.412411,0.011070485,0.0010075792,0.0023562338,0.00089091196,0.5091517],"genre_scores_gemma":[0.33721367,0.012839277,0.014542756,0.019262407,0.0006132255,0.00023915214,0.0015784284,0.0003401638,0.61337095],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98924726,0.000726625,0.00016646321,0.0004526683,0.0071961842,0.0022107922],"domain_scores_gemma":[0.97195995,0.00070071925,0.00031996478,0.00048475922,0.01518507,0.0113496175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006985966,0.0007319936,0.00042320485,0.0015579491,0.012382197,0.008609718,0.0016406431,0.0023185406,0.02878656],"category_scores_gemma":[0.0070766434,0.00038306878,0.00039199376,0.002134638,0.0027727226,0.00264025,0.0049301563,0.0038767587,0.0030787399],"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":[0.0000930766,0.00020607687,0.0070988834,0.00036246068,0.000021585995,0.00018192152,0.0015901343,0.0008334453,0.001233701,0.05787244,0.689679,0.24082729],"study_design_scores_gemma":[0.0000343705,0.00005718202,0.020260673,0.00037713943,0.000027897595,0.000075000935,0.004447004,0.00074148545,0.0012989322,0.005492621,0.9671012,0.00008658164],"about_ca_topic_score_codex":0.9254911,"about_ca_topic_score_gemma":0.9828551,"teacher_disagreement_score":0.074508905,"about_ca_system_score_codex":0.0634825,"about_ca_system_score_gemma":0.35289145,"threshold_uncertainty_score":0.46059996},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052630972,0.006747151,0.035694093,0.13748524,0.018860992,0.0063902675,0.011833564,0.008694165,0.72166353],"genre_scores_gemma":[0.24125618,0.008069505,0.1378591,0.018053742,0.0073781614,0.006021943,0.0155493915,0.004865762,0.5609462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98828363,0.004360031,0.00066441105,0.0003855905,0.005001322,0.0013048284],"domain_scores_gemma":[0.93857646,0.013491417,0.0022238696,0.007952974,0.017924612,0.019830616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01585102,0.0008205057,0.000967574,0.004980355,0.009130226,0.007138952,0.00398539,0.003006765,0.10064169],"category_scores_gemma":[0.041685037,0.00087949104,0.0007359746,0.0034790556,0.0019389755,0.0041863928,0.013662186,0.0031317705,0.021947175],"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":[0.000042477343,0.00019700607,0.00072791206,0.00006433405,0.0000038727017,0.0010864959,0.0015587667,0.00016955893,0.00022044893,0.0029205435,0.9108979,0.08211073],"study_design_scores_gemma":[0.000034583925,0.000049376846,0.0013417577,0.00013184271,0.000002046865,0.00087364763,0.0041989717,0.00035172445,0.00011247032,0.0014059241,0.99145937,0.00003821646],"about_ca_topic_score_codex":0.052627213,"about_ca_topic_score_gemma":0.2721218,"teacher_disagreement_score":0.10064169,"about_ca_system_score_codex":0.0066975225,"about_ca_system_score_gemma":0.029909333,"threshold_uncertainty_score":0.33668},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020840212,0.008095893,0.91648644,0.025922006,0.0006914799,0.0031785422,0.00040170192,0.00048008285,0.04265981],"genre_scores_gemma":[0.08064108,0.0033717616,0.9045873,0.001701422,0.00048466164,0.006232387,0.0005014497,0.00008507345,0.002394854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73641074,0.20533115,0.013070523,0.0048197214,0.036959656,0.0034082548],"domain_scores_gemma":[0.86650175,0.07912498,0.008485863,0.004692676,0.037992515,0.003202142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20549226,0.0034854857,0.0026947535,0.015883045,0.004677771,0.01925333,0.007673924,0.0064596357,0.004546677],"category_scores_gemma":[0.12466125,0.001061851,0.002568332,0.01238267,0.012984783,0.013410503,0.006793248,0.006041234,0.0016065631],"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":[0.000024443101,0.00009067642,0.00067653606,0.0008150149,0.000057115103,0.00008189588,0.0013329537,0.007667236,0.00010716591,0.9321924,0.008979758,0.047974836],"study_design_scores_gemma":[0.00011659734,0.00037648928,0.0016955142,0.0048202253,0.000104012564,0.00023981194,0.002444756,0.027561964,0.0006845132,0.7977104,0.16409841,0.00014721614],"about_ca_topic_score_codex":0.017702064,"about_ca_topic_score_gemma":0.010347457,"teacher_disagreement_score":0.98229796,"about_ca_system_score_codex":0.03223038,"about_ca_system_score_gemma":0.044540234,"threshold_uncertainty_score":0.97976947},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9127801,0.0017413642,0.0013367218,0.04789867,0.00011062284,0.00074696064,0.00013738812,0.000018034176,0.03523012],"genre_scores_gemma":[0.99460137,0.0008566524,0.00076411775,0.00095463503,0.000032055315,0.00023470462,0.000025741478,0.000009301462,0.0025213952],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9707252,0.01806889,0.0006440834,0.0012130504,0.0044443416,0.004904438],"domain_scores_gemma":[0.92942274,0.04640998,0.006592913,0.0014815619,0.011421883,0.00467098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031110575,0.00034430035,0.0004516773,0.0025554833,0.032706562,0.009144961,0.0024432393,0.002536519,0.0014467686],"category_scores_gemma":[0.07609399,0.00066094997,0.00031167097,0.003946672,0.02060562,0.004622275,0.0037088154,0.003827753,0.000099829835],"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":[0.00035309955,0.00041538684,0.06274069,0.0006971809,0.00005630986,0.0011724511,0.78086567,0.0017775774,0.0014483321,0.0926467,0.014030463,0.043796156],"study_design_scores_gemma":[0.000069881666,0.0002465537,0.082997836,0.00046718874,0.000048322454,0.00008988023,0.8227371,0.0013559815,0.00063639606,0.007151165,0.08410042,0.000099266006],"about_ca_topic_score_codex":0.9333186,"about_ca_topic_score_gemma":0.9437829,"teacher_disagreement_score":0.28434923,"about_ca_system_score_codex":0.28434923,"about_ca_system_score_gemma":0.2626907,"threshold_uncertainty_score":0.83005345},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021484483,0.0023144977,0.7833662,0.02103388,0.00023787902,0.0067247506,0.0015431,0.0005046808,0.16279048],"genre_scores_gemma":[0.13187476,0.0010306698,0.8550566,0.0006750044,0.000033021308,0.0036775172,0.001407938,0.000084306856,0.0061602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97925586,0.011935171,0.002254736,0.0018067119,0.0033871813,0.0013603095],"domain_scores_gemma":[0.9776757,0.012306034,0.0011615052,0.00171157,0.005965574,0.0011795588],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03828987,0.0017117189,0.0010465203,0.014811311,0.0049088374,0.012771916,0.0034484332,0.0038730209,0.0072891186],"category_scores_gemma":[0.031589426,0.0009106437,0.0019627858,0.007496348,0.010839969,0.015281781,0.0079075275,0.0052257446,0.0019981423],"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":[0.000029447297,0.00011779615,0.0019207608,0.0008872488,0.00003078584,0.00022265485,0.015234016,0.003745061,0.0007324635,0.8717271,0.0044147302,0.10093786],"study_design_scores_gemma":[0.000055182332,0.0001110116,0.003605764,0.00474875,0.000067190944,0.00043952398,0.029757157,0.013666164,0.0019376846,0.6999706,0.24552725,0.00011376724],"about_ca_topic_score_codex":0.027474642,"about_ca_topic_score_gemma":0.024721492,"teacher_disagreement_score":0.96171016,"about_ca_system_score_codex":0.021697076,"about_ca_system_score_gemma":0.038339496,"threshold_uncertainty_score":0.20249861},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6219898,0.027189853,0.011814671,0.15402025,0.001948207,0.00078969606,0.0009262048,0.00016905046,0.18115224],"genre_scores_gemma":[0.9511026,0.0053457543,0.0040036663,0.00299383,0.00014659404,0.00021110832,0.0002278936,0.000043590513,0.035924915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9779139,0.0077838413,0.0008573485,0.0009214416,0.0092059225,0.00331762],"domain_scores_gemma":[0.92791545,0.014004524,0.0038483823,0.0014800474,0.043586202,0.0091654165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024632068,0.00049987255,0.000777446,0.002941221,0.008934504,0.008800708,0.0017293476,0.0016408078,0.0085893255],"category_scores_gemma":[0.062427353,0.00023353919,0.00041944295,0.0036839112,0.005542469,0.0031765548,0.0035941526,0.0027323232,0.0006774343],"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":[0.0005347136,0.0005612115,0.14349301,0.0020268632,0.00018603256,0.0010153872,0.103569746,0.0022478013,0.0020813441,0.07567662,0.066384785,0.6022225],"study_design_scores_gemma":[0.000086229884,0.0010043539,0.45450455,0.006385094,0.00019373823,0.00048482834,0.218252,0.0028970877,0.0022856973,0.007822826,0.30586338,0.0002200769],"about_ca_topic_score_codex":0.88896036,"about_ca_topic_score_gemma":0.94005364,"teacher_disagreement_score":0.11103964,"about_ca_system_score_codex":0.06822431,"about_ca_system_score_gemma":0.14175422,"threshold_uncertainty_score":0.49500436},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06293253,0.00025537785,0.8481491,0.025759468,0.00026415868,0.0033036247,0.00009324835,0.0015211717,0.057721365],"genre_scores_gemma":[0.61707294,0.00010164791,0.37344787,0.0015140636,0.0000851614,0.0025856532,0.00010090989,0.00029818527,0.004793501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8741333,0.097507164,0.006634554,0.0068861973,0.0114566665,0.0033821382],"domain_scores_gemma":[0.8473615,0.0735671,0.013373134,0.024537073,0.030194694,0.010966414],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13267203,0.0007655093,0.0007667793,0.0046872073,0.0066964054,0.015427276,0.0031717448,0.0030407577,0.007177154],"category_scores_gemma":[0.15927553,0.0009716215,0.0008459565,0.0028247463,0.011957318,0.020196581,0.01455798,0.005083101,0.0015465836],"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":[0.00039089553,0.0010642326,0.021441117,0.0005594489,0.00013292526,0.0005562635,0.049384806,0.009992202,0.0058960486,0.61730814,0.015295163,0.27797878],"study_design_scores_gemma":[0.000663511,0.0009916832,0.008820218,0.0017863734,0.00020611202,0.00051221007,0.025221841,0.104510784,0.008044275,0.70879346,0.14015746,0.0002920958],"about_ca_topic_score_codex":0.0023906776,"about_ca_topic_score_gemma":0.004155543,"teacher_disagreement_score":0.9976093,"about_ca_system_score_codex":0.009277616,"about_ca_system_score_gemma":0.016720023,"threshold_uncertainty_score":0.70164514},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056534335,0.002797513,0.92363876,0.0009156759,0.0003298112,0.0051631415,0.0010611623,0.0010883792,0.008471179],"genre_scores_gemma":[0.23618202,0.0013249927,0.73974764,0.00023185831,0.0001303217,0.0138115585,0.0009311985,0.00029342624,0.0073470124],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.91262054,0.062842935,0.0043991557,0.0075439,0.011634462,0.0009590402],"domain_scores_gemma":[0.82565236,0.14365552,0.0051907334,0.01002455,0.01352593,0.0019508663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059725106,0.0023483548,0.0026884456,0.004632457,0.0017695819,0.0064565027,0.0026573604,0.0030526053,0.01791529],"category_scores_gemma":[0.16363078,0.0015461626,0.0030879858,0.0038645214,0.0021306705,0.004253149,0.0055038664,0.003095793,0.0032102372],"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":[0.0056308177,0.0023555455,0.024279661,0.008184046,0.0024859596,0.0003196972,0.010778212,0.057745192,0.017097812,0.036081098,0.004874691,0.8301673],"study_design_scores_gemma":[0.0053549237,0.01575508,0.09134861,0.009828344,0.0044457004,0.0013115316,0.015774248,0.47822347,0.08369082,0.13358557,0.15952688,0.0011546978],"about_ca_topic_score_codex":0.008090059,"about_ca_topic_score_gemma":0.0071557797,"teacher_disagreement_score":0.059725106,"about_ca_system_score_codex":0.004489414,"about_ca_system_score_gemma":0.009771221,"threshold_uncertainty_score":0.31586033},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9663159,0.0013654458,0.004151386,0.0059552067,0.00021362443,0.00024056151,0.00028069425,0.000060058643,0.02141713],"genre_scores_gemma":[0.9825982,0.0010266338,0.0052871937,0.00065330067,0.000052456173,0.00030716835,0.00021774166,0.000033676326,0.009823488],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9934523,0.0029486571,0.0003220572,0.00042183537,0.0014802576,0.0013749476],"domain_scores_gemma":[0.98235714,0.009280864,0.0029164501,0.00088372803,0.0018854869,0.002676349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008673484,0.00026092972,0.00029617755,0.0008677329,0.0028441132,0.0015599583,0.0012716128,0.0012910075,0.0050013163],"category_scores_gemma":[0.033021476,0.00036295457,0.0005555056,0.00072790886,0.0021796394,0.0009936591,0.0025431097,0.002619711,0.0004401296],"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":[0.0015693443,0.0024216822,0.36594275,0.0009195272,0.00013622877,0.007029012,0.09031221,0.0028176575,0.0050647412,0.024626672,0.014123664,0.48503655],"study_design_scores_gemma":[0.00017133368,0.0041797278,0.76131546,0.0023368865,0.00013076363,0.005326442,0.047776915,0.002883069,0.00895839,0.0029202977,0.163789,0.00021173638],"about_ca_topic_score_codex":0.08734387,"about_ca_topic_score_gemma":0.13509259,"teacher_disagreement_score":0.08734387,"about_ca_system_score_codex":0.0069262553,"about_ca_system_score_gemma":0.012777261,"threshold_uncertainty_score":0.17367095},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5402719,0.0017852552,0.05659406,0.014531636,0.00021152374,0.0007627883,0.00023976986,0.00028367262,0.3853194],"genre_scores_gemma":[0.97739536,0.00029142003,0.0067623397,0.00030895372,0.000017282578,0.0001535932,0.00005776644,0.00006174515,0.014951564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.94756883,0.025877161,0.0023182447,0.0035741315,0.015063074,0.005598563],"domain_scores_gemma":[0.8637987,0.08106192,0.015952524,0.009134082,0.020850219,0.009202559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0303648,0.00063581567,0.0006713319,0.0039904206,0.0102274185,0.013245912,0.0019672932,0.0022183964,0.015808655],"category_scores_gemma":[0.11112166,0.0006280536,0.0006049987,0.0041944333,0.016340021,0.0066658678,0.01243828,0.004153044,0.0012414544],"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":[0.00024998435,0.0002339913,0.12133313,0.0006822923,0.00019727433,0.0018086921,0.24405481,0.002400096,0.0029261482,0.43914255,0.006285718,0.18068536],"study_design_scores_gemma":[0.00008266276,0.00045148502,0.2419877,0.002096316,0.00024770002,0.0010469138,0.28230056,0.005542924,0.0050334,0.12548235,0.33538744,0.00034055184],"about_ca_topic_score_codex":0.10289122,"about_ca_topic_score_gemma":0.11445597,"teacher_disagreement_score":0.97678536,"about_ca_system_score_codex":0.023214629,"about_ca_system_score_gemma":0.035377707,"threshold_uncertainty_score":0.2045846},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000069910224,0.9926644,0.000327161,0.005500074,0.0003299748,0.0000422776,0.000009264633,0.0000041762323,0.0010527617],"genre_scores_gemma":[0.0030241823,0.99284655,0.0012700406,0.0023227124,0.0002432496,0.000099715144,0.00001304255,0.000005320259,0.00017519006],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96552247,0.021332607,0.003930349,0.0012999594,0.0072095343,0.00070503005],"domain_scores_gemma":[0.877451,0.10643421,0.0037976396,0.0014307534,0.009925275,0.00096111355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043853123,0.001535507,0.0031133296,0.012716816,0.002206661,0.0075584566,0.0024974819,0.0054577626,0.003018499],"category_scores_gemma":[0.08928325,0.0009245961,0.0018817461,0.017816968,0.0061836736,0.0088835135,0.003915584,0.006029143,0.0006842979],"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":[0.00006315827,0.00008113659,0.00044254633,0.12419349,0.00036788126,0.00014041143,0.0029074426,0.00033280705,0.0001282367,0.04338833,0.03744002,0.7905145],"study_design_scores_gemma":[0.00003828741,0.000066638546,0.0014462237,0.43590182,0.00055884867,0.000485269,0.0032026612,0.00022301552,0.0001979262,0.016255625,0.54156,0.000063777035],"about_ca_topic_score_codex":0.011163689,"about_ca_topic_score_gemma":0.023219079,"teacher_disagreement_score":0.9561469,"about_ca_system_score_codex":0.00989441,"about_ca_system_score_gemma":0.032063365,"threshold_uncertainty_score":0.23192024},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011262391,0.059553295,0.0094980495,0.8871734,0.008651542,0.000060274604,0.00016674111,0.00012927328,0.03364118],"genre_scores_gemma":[0.18030445,0.1853505,0.039660502,0.4175987,0.008425522,0.00068081665,0.00037591744,0.00054553687,0.1670581],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965089,0.0015938566,0.00026018659,0.0002418637,0.0012375163,0.00015775427],"domain_scores_gemma":[0.9684521,0.019263972,0.0014878471,0.00066466915,0.007873782,0.002257517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011730905,0.00047248567,0.0003510132,0.0015007206,0.003676615,0.005411851,0.0012498159,0.0057780715,0.014654687],"category_scores_gemma":[0.03604434,0.00044057582,0.00037200944,0.0018780285,0.005930909,0.0073345522,0.0027605272,0.010804201,0.0049837874],"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":[0.000058612688,0.000033539334,0.0005659703,0.00050351117,0.0000120348195,0.00010272602,0.0032247002,0.00014222327,0.00022417492,0.09817217,0.7770477,0.11991267],"study_design_scores_gemma":[0.00004564937,0.00006138607,0.00327713,0.004383897,0.00003764143,0.00030287492,0.005422882,0.000530699,0.0011607339,0.18381095,0.8008935,0.00007266032],"about_ca_topic_score_codex":0.02007752,"about_ca_topic_score_gemma":0.049387038,"teacher_disagreement_score":0.02007752,"about_ca_system_score_codex":0.0034424376,"about_ca_system_score_gemma":0.013401617,"threshold_uncertainty_score":0.062039733},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8013944,0.0019335423,0.04293272,0.075502135,0.0004030395,0.0029945073,0.000091788956,0.00027922433,0.07446859],"genre_scores_gemma":[0.9731539,0.000524705,0.022003628,0.0016994525,0.000033677636,0.00062289106,0.000037285175,0.00006231082,0.0018621987],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86246324,0.118087135,0.0022365206,0.0022730299,0.008740755,0.006199294],"domain_scores_gemma":[0.84957576,0.0961994,0.0039734105,0.009047887,0.022384265,0.018819252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15069221,0.0005636522,0.0008027955,0.0015943728,0.016382596,0.016607143,0.003908941,0.00221214,0.003613662],"category_scores_gemma":[0.11044398,0.0005605368,0.0006025657,0.0011800206,0.016855435,0.009549435,0.018159274,0.0066053947,0.00028675236],"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":[0.00029667735,0.005965718,0.034857422,0.0011051858,0.00011920035,0.0012272296,0.5762296,0.0021117164,0.0016719085,0.03810634,0.014979701,0.32332936],"study_design_scores_gemma":[0.00020684897,0.0012379873,0.03553612,0.0033803515,0.00010424217,0.0008212931,0.8138289,0.005359578,0.005713329,0.032235533,0.10127492,0.0003009497],"about_ca_topic_score_codex":0.034626327,"about_ca_topic_score_gemma":0.08382906,"teacher_disagreement_score":0.15069221,"about_ca_system_score_codex":0.02493262,"about_ca_system_score_gemma":0.060506456,"threshold_uncertainty_score":0.7969461},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17562932,0.0013329053,0.004489108,0.3236297,0.0032066775,0.00034428193,0.00034050722,0.000105821666,0.4909217],"genre_scores_gemma":[0.82125247,0.0010398321,0.0015651581,0.031471208,0.0006525393,0.00021845847,0.00019483612,0.0000829829,0.14352252],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9846993,0.005698594,0.00043998484,0.00076200394,0.003796911,0.0046032444],"domain_scores_gemma":[0.97810614,0.005189203,0.00075840444,0.00046907642,0.008024673,0.0074525108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012637931,0.00053632417,0.00047922143,0.0014041949,0.020098705,0.020009682,0.0026774106,0.007473284,0.020211294],"category_scores_gemma":[0.0340636,0.00035802563,0.0006831751,0.001999026,0.009340479,0.0028637322,0.007820849,0.007717493,0.002525337],"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":[0.0001831244,0.00044055082,0.00990859,0.00015212111,0.00001940608,0.007207339,0.081014566,0.0018984065,0.0007509303,0.3922988,0.4656232,0.040502977],"study_design_scores_gemma":[0.000029737952,0.00009169033,0.0030945137,0.00015494562,0.0000049756723,0.00075247005,0.09732149,0.000900192,0.00042861572,0.012198214,0.8849569,0.00006624506],"about_ca_topic_score_codex":0.13965094,"about_ca_topic_score_gemma":0.20213518,"teacher_disagreement_score":0.13965094,"about_ca_system_score_codex":0.025415199,"about_ca_system_score_gemma":0.034797292,"threshold_uncertainty_score":0.27767617},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004599253,0.17716716,0.060225487,0.011578477,0.0031135362,0.00023215539,0.0005265742,0.0014166974,0.7411406],"genre_scores_gemma":[0.20297262,0.10018832,0.07399574,0.007723896,0.0033517142,0.00078723836,0.001411891,0.0016417952,0.60792685],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904227,0.0039878394,0.00044185898,0.0008232096,0.003936692,0.00038766107],"domain_scores_gemma":[0.99448305,0.0027627395,0.00023215175,0.00094597624,0.001415013,0.00016109263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006993443,0.0012386605,0.0012996064,0.0029553135,0.0012520219,0.009194767,0.0010903177,0.0024109075,0.025329227],"category_scores_gemma":[0.010122276,0.0005415492,0.00063258887,0.0028777665,0.0040466245,0.0063950038,0.0030178716,0.0030555136,0.011605602],"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":[0.000065420725,0.000065930864,0.00053847226,0.0008908005,0.000026925432,0.0000911857,0.0013144203,0.0007462167,0.00065999257,0.38442186,0.09699401,0.5141847],"study_design_scores_gemma":[0.000017871402,0.000047145222,0.0011997905,0.0009735172,0.000016764343,0.0003876337,0.00050818466,0.00079853716,0.0016271076,0.16175194,0.8326498,0.00002177871],"about_ca_topic_score_codex":0.00353354,"about_ca_topic_score_gemma":0.0032001203,"teacher_disagreement_score":0.025329227,"about_ca_system_score_codex":0.004279576,"about_ca_system_score_gemma":0.003458843,"threshold_uncertainty_score":0.08473474},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015237122,0.037031814,0.3758616,0.51050144,0.005972018,0.0025872726,0.00025102822,0.0005168415,0.052040793],"genre_scores_gemma":[0.41278255,0.021359216,0.5183361,0.031091778,0.0026216886,0.008417757,0.00018506074,0.00052708667,0.0046788184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43003294,0.52052486,0.012093807,0.008014379,0.026193976,0.003139997],"domain_scores_gemma":[0.1625745,0.70990825,0.013845983,0.037905917,0.06969826,0.006067165],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59534574,0.0016744982,0.003564248,0.009266533,0.010951931,0.028634137,0.007439304,0.006483531,0.009269423],"category_scores_gemma":[0.6288502,0.001242863,0.0020019182,0.010275704,0.03760518,0.03656106,0.016528914,0.013128783,0.0015009528],"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":[0.00021890114,0.00021287339,0.0058563193,0.005527712,0.0002001073,0.00013612663,0.03537477,0.0012836808,0.0002900131,0.55862004,0.027716227,0.3645631],"study_design_scores_gemma":[0.00014138593,0.00019167262,0.0022802763,0.0203041,0.00013911538,0.00017770422,0.041428875,0.0061270664,0.000726248,0.8185898,0.109732635,0.00016112477],"about_ca_topic_score_codex":0.007907366,"about_ca_topic_score_gemma":0.010991265,"teacher_disagreement_score":0.40465426,"about_ca_system_score_codex":0.016625047,"about_ca_system_score_gemma":0.058259945,"threshold_uncertainty_score":0.4990108},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004599253,0.17716716,0.060225487,0.011578477,0.0031135362,0.00023215539,0.0005265742,0.0014166974,0.7411406],"genre_scores_gemma":[0.20297262,0.10018832,0.07399574,0.007723896,0.0033517142,0.00078723836,0.001411891,0.0016417952,0.60792685],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904227,0.0039878394,0.00044185898,0.0008232096,0.003936692,0.00038766107],"domain_scores_gemma":[0.99448305,0.0027627395,0.00023215175,0.00094597624,0.001415013,0.00016109263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006993443,0.0012386605,0.0012996064,0.0029553135,0.0012520219,0.009194767,0.0010903177,0.0024109075,0.025329227],"category_scores_gemma":[0.010122276,0.0005415492,0.00063258887,0.0028777665,0.0040466245,0.0063950038,0.0030178716,0.0030555136,0.011605602],"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":[0.000065420725,0.000065930864,0.00053847226,0.0008908005,0.000026925432,0.0000911857,0.0013144203,0.0007462167,0.00065999257,0.38442186,0.09699401,0.5141847],"study_design_scores_gemma":[0.000017871402,0.000047145222,0.0011997905,0.0009735172,0.000016764343,0.0003876337,0.00050818466,0.00079853716,0.0016271076,0.16175194,0.8326498,0.00002177871],"about_ca_topic_score_codex":0.00353354,"about_ca_topic_score_gemma":0.0032001203,"teacher_disagreement_score":0.025329227,"about_ca_system_score_codex":0.004279576,"about_ca_system_score_gemma":0.003458843,"threshold_uncertainty_score":0.08473474},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029729247,0.01996103,0.35670224,0.5002475,0.013932642,0.0030855373,0.00018740198,0.00061502,0.07553946],"genre_scores_gemma":[0.5044464,0.025381977,0.29444188,0.1435975,0.006033676,0.0087305885,0.0001221739,0.000967975,0.016277803],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.33283368,0.6077165,0.010499336,0.008159855,0.037621826,0.0031688472],"domain_scores_gemma":[0.19187924,0.74116534,0.010304608,0.025961963,0.027001295,0.0036875012],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4684637,0.0018082261,0.0027480808,0.005477913,0.020080766,0.03852848,0.0073305364,0.011195917,0.004581095],"category_scores_gemma":[0.5389152,0.0018178221,0.0017376149,0.0043438813,0.14105776,0.03837541,0.029284297,0.027347038,0.0018088605],"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":[0.00014478837,0.00007059726,0.0006578021,0.0026174302,0.00009819254,0.0010722369,0.6321013,0.0005417552,0.0012817603,0.27751073,0.017111233,0.06679214],"study_design_scores_gemma":[0.00012986874,0.00028432647,0.0005232752,0.0159986,0.000087793,0.0019470152,0.23598659,0.0013615364,0.0023062632,0.47483748,0.26619238,0.0003449508],"about_ca_topic_score_codex":0.004419018,"about_ca_topic_score_gemma":0.0061195786,"teacher_disagreement_score":0.53153634,"about_ca_system_score_codex":0.012697804,"about_ca_system_score_gemma":0.02853106,"threshold_uncertainty_score":0.6554789},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018898902,0.24783209,0.17523275,0.5133523,0.03173677,0.0018597385,0.003049446,0.0011824724,0.023864646],"genre_scores_gemma":[0.059164964,0.25352427,0.4373685,0.17004445,0.010208834,0.012321306,0.002098703,0.0019819492,0.053287007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9618419,0.028492376,0.0018950192,0.0012514078,0.0061047724,0.0004145943],"domain_scores_gemma":[0.725594,0.21596408,0.009544439,0.006029243,0.039832313,0.0030360236],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.085257575,0.0016713995,0.0015240961,0.0042376937,0.0043092403,0.0048911623,0.0042795916,0.0063917567,0.0251887],"category_scores_gemma":[0.3234574,0.002416799,0.0014232744,0.0051295245,0.0033780346,0.0071539297,0.004634663,0.010858078,0.0093822675],"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":[0.00021264152,0.00003837366,0.0010265012,0.0024097785,0.00013113326,0.00010790678,0.0013038977,0.0003346351,0.00022977758,0.01405248,0.7900739,0.19007893],"study_design_scores_gemma":[0.00033003645,0.00019871208,0.006934741,0.017394869,0.0006524541,0.0004313723,0.0023652317,0.0021054426,0.0020298858,0.0770442,0.8902318,0.00028129356],"about_ca_topic_score_codex":0.042289022,"about_ca_topic_score_gemma":0.08722375,"teacher_disagreement_score":0.9147424,"about_ca_system_score_codex":0.0033245333,"about_ca_system_score_gemma":0.013553725,"threshold_uncertainty_score":0.45089054},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2773012,0.004267698,0.48841086,0.024569811,0.0007547644,0.003616709,0.000315224,0.0014272053,0.19933659],"genre_scores_gemma":[0.81703436,0.0011219356,0.17003883,0.0013084995,0.00007797637,0.0015840743,0.00019440745,0.00011468936,0.008525131],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9176633,0.06173225,0.005109314,0.0017111723,0.011258777,0.0025251315],"domain_scores_gemma":[0.8736761,0.06451932,0.008238139,0.008433678,0.034494862,0.010637859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08040453,0.00042630945,0.0005821008,0.0038490982,0.003010608,0.0066469195,0.00200669,0.0018122119,0.0055379923],"category_scores_gemma":[0.10600684,0.00050742517,0.00037408117,0.001865434,0.0046965578,0.0065813866,0.008502889,0.003306116,0.00094280776],"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":[0.00030206228,0.0013987047,0.07055115,0.0017356513,0.000047072695,0.00024679716,0.03212453,0.0050163567,0.0019193073,0.2650756,0.022594832,0.59898794],"study_design_scores_gemma":[0.00035051093,0.0026161484,0.16402066,0.010714681,0.00012153139,0.0018171518,0.06441143,0.04918636,0.021288665,0.36908376,0.31591895,0.00047021566],"about_ca_topic_score_codex":0.0031703704,"about_ca_topic_score_gemma":0.00543895,"teacher_disagreement_score":0.08040453,"about_ca_system_score_codex":0.007107804,"about_ca_system_score_gemma":0.028518802,"threshold_uncertainty_score":0.42522484},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47907358,0.008003992,0.0015838341,0.28262296,0.0005200561,0.000120876204,0.00059446617,0.000054624008,0.22742566],"genre_scores_gemma":[0.9698649,0.002309176,0.00065986376,0.0042852326,0.00008347459,0.000025940064,0.00015998085,0.000011867328,0.02259952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9932609,0.00071532844,0.00015948461,0.00054272625,0.0024328914,0.002888633],"domain_scores_gemma":[0.99359316,0.0006372749,0.00097431435,0.0002894827,0.0023841364,0.0021215365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004006252,0.00015631513,0.00027721017,0.0008146209,0.0073009706,0.0076747127,0.0010177555,0.0012019206,0.0039610923],"category_scores_gemma":[0.008768111,0.00020930036,0.00025228364,0.0027912676,0.008031387,0.002524291,0.0019070322,0.0018696088,0.0002055338],"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":[0.00026556716,0.00011074356,0.18301146,0.0005535287,0.00008150655,0.0011192774,0.075823255,0.0019666492,0.0017971889,0.5241963,0.07040983,0.14066467],"study_design_scores_gemma":[0.00006281308,0.00007532999,0.40318242,0.00047180263,0.00005845739,0.00014731984,0.057289157,0.00062340667,0.0007745983,0.013921431,0.5232962,0.00009699053],"about_ca_topic_score_codex":0.9841926,"about_ca_topic_score_gemma":0.99410313,"teacher_disagreement_score":0.21055366,"about_ca_system_score_codex":0.21055366,"about_ca_system_score_gemma":0.19599037,"threshold_uncertainty_score":0.91564584},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77882344,0.001676276,0.05996141,0.004343685,0.00022957832,0.007769938,0.0018726033,0.0002856625,0.1450375],"genre_scores_gemma":[0.96691716,0.00036815956,0.02792507,0.00012247759,0.00002396615,0.002266416,0.0005618463,0.000018976749,0.0017958782],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93327653,0.04882344,0.0024519677,0.0014341557,0.011982705,0.0020310928],"domain_scores_gemma":[0.78171605,0.12502284,0.016836816,0.0070064715,0.06264524,0.00677264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054581657,0.00088165863,0.000539735,0.005829599,0.0018734274,0.004663102,0.001581567,0.0008145762,0.006354492],"category_scores_gemma":[0.14020506,0.00023606107,0.00059424766,0.0045913677,0.002531421,0.0037526637,0.0053329337,0.0012454451,0.000542681],"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":[0.00092380453,0.003185679,0.15760006,0.0030760393,0.00058461126,0.00016579582,0.012007114,0.04551961,0.0013184712,0.07596114,0.015049439,0.68460816],"study_design_scores_gemma":[0.0014092864,0.019471861,0.3987267,0.0106355185,0.0015090891,0.00033548527,0.12429549,0.16909616,0.041702673,0.1071892,0.12502582,0.0006027015],"about_ca_topic_score_codex":0.009974676,"about_ca_topic_score_gemma":0.010502487,"teacher_disagreement_score":0.054581657,"about_ca_system_score_codex":0.011465749,"about_ca_system_score_gemma":0.016503291,"threshold_uncertainty_score":0.28865886},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8809752,0.0014588654,0.008172462,0.020571465,0.00035873422,0.00049528223,0.00010599067,0.000104706705,0.08775727],"genre_scores_gemma":[0.97349983,0.00059551734,0.00402781,0.0013749104,0.000043477266,0.00009505532,0.000053849348,0.00008171782,0.020227931],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97614086,0.013702959,0.00050864817,0.0016962588,0.0027535467,0.005197784],"domain_scores_gemma":[0.9529881,0.02195269,0.001511397,0.0029171149,0.009197814,0.011432922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014379395,0.000707343,0.0006322571,0.0019155991,0.053645004,0.010029612,0.003953711,0.0059230654,0.0043899477],"category_scores_gemma":[0.027605046,0.0005738173,0.00049741706,0.0036885133,0.013598797,0.004162497,0.012833097,0.005500631,0.00062998704],"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":[0.00011450535,0.000248665,0.00932637,0.00013119004,0.00003681746,0.010606197,0.92842895,0.0005137228,0.0011488177,0.014928006,0.004772663,0.029744096],"study_design_scores_gemma":[0.00002855935,0.00012975532,0.005241445,0.00022510013,0.000032355103,0.0019165459,0.8980445,0.0006195921,0.0005617283,0.0025369464,0.09060979,0.000053596552],"about_ca_topic_score_codex":0.6834108,"about_ca_topic_score_gemma":0.84438246,"teacher_disagreement_score":0.9856206,"about_ca_system_score_codex":0.035510976,"about_ca_system_score_gemma":0.08056407,"threshold_uncertainty_score":0.6369072},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71315414,0.009996364,0.050795987,0.097133495,0.0007682197,0.00073283707,0.000081865954,0.00014039736,0.1271968],"genre_scores_gemma":[0.98853683,0.0016845173,0.0056063626,0.0026700904,0.00008061679,0.0002650853,0.000034270695,0.00004101563,0.0010812278],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5484972,0.3848763,0.008063462,0.0050474247,0.045864023,0.0076515926],"domain_scores_gemma":[0.54199815,0.34346464,0.020541908,0.011453518,0.070470996,0.012070791],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25998196,0.00061923167,0.0012623703,0.0076077664,0.01011042,0.018524777,0.002723142,0.0053901994,0.0029037488],"category_scores_gemma":[0.41042277,0.0009224544,0.00083221425,0.004354594,0.017878938,0.016780525,0.015587884,0.005310623,0.00044065205],"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":[0.00032470882,0.00013777617,0.032456014,0.0007048024,0.000121129204,0.00091564143,0.8340864,0.00026116418,0.00073311833,0.038415235,0.0028486708,0.08899528],"study_design_scores_gemma":[0.00011380318,0.00030936295,0.023571456,0.002473112,0.00015968028,0.00082676363,0.9030727,0.00127684,0.0009352311,0.027224164,0.03992984,0.00010700774],"about_ca_topic_score_codex":0.005591585,"about_ca_topic_score_gemma":0.006643199,"teacher_disagreement_score":0.25998196,"about_ca_system_score_codex":0.01196244,"about_ca_system_score_gemma":0.018076405,"threshold_uncertainty_score":0.912574},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99636453,0.00005076551,0.0007026989,0.00068070705,0.0000059773593,0.0010328917,0.000027894563,0.000009673976,0.0011249837],"genre_scores_gemma":[0.9934182,0.00017071962,0.0032354505,0.00024703745,0.00001290191,0.0024237544,0.00004927287,0.00000608349,0.00043654698],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9780082,0.013602826,0.0015845544,0.00071515964,0.003513545,0.002575643],"domain_scores_gemma":[0.93030626,0.04304093,0.004303454,0.0017825944,0.013845719,0.00672107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044981744,0.0006595197,0.0009903107,0.005944534,0.0070505366,0.003462642,0.0019957628,0.003875275,0.0018322668],"category_scores_gemma":[0.06865742,0.0008676523,0.0007356878,0.0031337673,0.0028881375,0.0068630725,0.00643141,0.002951218,0.00038190398],"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":[0.0004929377,0.016305257,0.08076906,0.001529704,0.0000541343,0.0019084846,0.79522896,0.0007465494,0.0026833394,0.0022243839,0.0008026087,0.09725449],"study_design_scores_gemma":[0.00018551074,0.0048847096,0.060330275,0.0005256609,0.000056919176,0.00053667644,0.92313755,0.0030147238,0.0013362112,0.001862639,0.0040231217,0.00010612313],"about_ca_topic_score_codex":0.0031268366,"about_ca_topic_score_gemma":0.005163612,"teacher_disagreement_score":0.044981744,"about_ca_system_score_codex":0.006619556,"about_ca_system_score_gemma":0.011879443,"threshold_uncertainty_score":0.23788905},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038726134,0.04617639,0.0022452802,0.10590489,0.002926608,0.00013150778,0.00323673,0.00032142256,0.8351846],"genre_scores_gemma":[0.021612652,0.012345529,0.0015676917,0.0076886634,0.000245721,0.0000431379,0.00045253147,0.00015067423,0.9558934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99769586,0.00016281848,0.000052688905,0.00015108494,0.0012401601,0.00069739745],"domain_scores_gemma":[0.9978028,0.00041081145,0.00006116057,0.00007158344,0.0013319523,0.00032167957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013342993,0.0008409654,0.0005441139,0.0029417328,0.010713091,0.008914661,0.0011118567,0.0052299453,0.052802715],"category_scores_gemma":[0.004436673,0.0008052652,0.00052228855,0.0065463902,0.003031172,0.0022788392,0.001282662,0.0031139883,0.007366055],"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":[0.000018451883,0.000016508391,0.0008168448,0.00014384635,0.0000041090125,0.00011066105,0.0014867999,0.00039198136,0.000112505164,0.18269101,0.74268264,0.07152463],"study_design_scores_gemma":[0.0000036334989,0.0000026316168,0.0017756548,0.00013227442,0.000004928385,0.000020791782,0.00051626033,0.00018078029,0.00007486709,0.0055844826,0.9916899,0.0000136983945],"about_ca_topic_score_codex":0.9901661,"about_ca_topic_score_gemma":0.99728453,"teacher_disagreement_score":0.9108646,"about_ca_system_score_codex":0.08913542,"about_ca_system_score_gemma":0.194324,"threshold_uncertainty_score":0.6467258},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008312439,0.34467897,0.0025851557,0.60155135,0.04374437,0.00053561275,0.00026684906,0.000083730214,0.0057228087],"genre_scores_gemma":[0.019336758,0.56976575,0.022812648,0.3055323,0.068030976,0.0013356705,0.00045466874,0.0002272807,0.012504041],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8906,0.06278959,0.015661446,0.0024665915,0.027417447,0.0010648919],"domain_scores_gemma":[0.3340712,0.51567644,0.028971016,0.009268624,0.10150402,0.010508762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08472514,0.0011482205,0.0055938093,0.008986452,0.0025906146,0.016839119,0.0038213439,0.016925668,0.010065535],"category_scores_gemma":[0.45460096,0.0015287589,0.0018495076,0.0069845836,0.0064254873,0.00979953,0.0040147696,0.014148003,0.004100607],"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":[0.00009950213,0.0000808554,0.00079069927,0.020241551,0.00048628135,0.00026849261,0.00069038797,0.00015665367,0.00023313209,0.004163771,0.78867996,0.18410878],"study_design_scores_gemma":[0.00043330886,0.0002838061,0.003632337,0.13436188,0.0016542972,0.0015343333,0.0025470122,0.0006847921,0.00059078896,0.029817423,0.82417387,0.00028618073],"about_ca_topic_score_codex":0.007836939,"about_ca_topic_score_gemma":0.031634387,"teacher_disagreement_score":0.08472514,"about_ca_system_score_codex":0.0097312825,"about_ca_system_score_gemma":0.049377404,"threshold_uncertainty_score":0.44807476},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9179074,0.008301305,0.033579167,0.005332022,0.00016883075,0.0035375622,0.0010531022,0.00011546409,0.030005084],"genre_scores_gemma":[0.9662908,0.0037490334,0.011879996,0.0011602341,0.00004469184,0.003404056,0.00023203461,0.00004861873,0.013190483],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9732294,0.020242339,0.0010810966,0.0011438864,0.0024957962,0.0018075546],"domain_scores_gemma":[0.9617376,0.029448383,0.002615479,0.0012169959,0.004008292,0.00097329076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030756852,0.0006644894,0.0009951072,0.0035274003,0.008198899,0.0058338456,0.0016502818,0.0014945477,0.002379973],"category_scores_gemma":[0.027146794,0.0007056174,0.00055267406,0.0035078393,0.012696566,0.0031958716,0.0027363396,0.0019413456,0.0003015714],"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":[0.00007910188,0.00012509871,0.005432455,0.0006459837,0.00001314414,0.0010100593,0.95474815,0.00017899253,0.0013280651,0.007390837,0.00096119294,0.028086906],"study_design_scores_gemma":[0.000021835782,0.00013905457,0.010827965,0.0011634927,0.000020970348,0.0006076081,0.9100796,0.00028449763,0.0017531762,0.001626889,0.073425755,0.00004913098],"about_ca_topic_score_codex":0.13450523,"about_ca_topic_score_gemma":0.16915607,"teacher_disagreement_score":0.13450523,"about_ca_system_score_codex":0.01981945,"about_ca_system_score_gemma":0.015892135,"threshold_uncertainty_score":0.2674446},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99598557,0.00011760706,0.00021559332,0.0003657488,0.0000066125112,0.000021029211,0.000017807477,0.000005304027,0.0032646563],"genre_scores_gemma":[0.99924904,0.00006986786,0.00014052828,0.000046553843,0.0000019439547,0.000007732617,0.000011972651,0.0000018103223,0.00047065874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9903713,0.0052080625,0.00044849404,0.0005299364,0.0024437427,0.0009984899],"domain_scores_gemma":[0.9500488,0.02114171,0.0130588105,0.0013960704,0.008191357,0.0061632087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008842682,0.00016799312,0.00018836105,0.000694511,0.002090023,0.0035237083,0.00072448736,0.00038094475,0.0019742975],"category_scores_gemma":[0.02920527,0.00021309327,0.00014992444,0.0006885612,0.0025279124,0.00066969055,0.0012178783,0.000773832,0.00017192331],"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":[0.00018604092,0.00056330726,0.7521345,0.0001649335,0.00004360532,0.0004907091,0.20696893,0.00028765653,0.0018445138,0.0007191643,0.0010073029,0.035589255],"study_design_scores_gemma":[0.000020430212,0.00024019137,0.83821654,0.00015675453,0.000029971987,0.00010379741,0.15539671,0.0005780307,0.00054393837,0.00011548879,0.0045690667,0.000028987879],"about_ca_topic_score_codex":0.3876827,"about_ca_topic_score_gemma":0.4912769,"teacher_disagreement_score":0.3876827,"about_ca_system_score_codex":0.0073413635,"about_ca_system_score_gemma":0.010334524,"threshold_uncertainty_score":0.77085227},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056857128,0.016921949,0.23971282,0.111386865,0.0033631409,0.0003258569,0.0023474991,0.0022823731,0.5668024],"genre_scores_gemma":[0.46109352,0.016119614,0.13455503,0.0037021257,0.001443202,0.00059192075,0.0021527645,0.0027202023,0.3776215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98873144,0.006036159,0.0005549944,0.00080838695,0.0033245704,0.00054446125],"domain_scores_gemma":[0.983452,0.009621794,0.0008930829,0.0021140792,0.002846137,0.0010728575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014469045,0.00071361515,0.00083017955,0.0022939555,0.0026022545,0.023733564,0.0017067669,0.002575793,0.07024814],"category_scores_gemma":[0.03540195,0.0008812073,0.0003983361,0.0032536974,0.004628622,0.019546356,0.007062515,0.0038380162,0.011909084],"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":[0.00019620341,0.00018743012,0.002301319,0.000521059,0.000030148858,0.0003075474,0.010668268,0.001329064,0.0021000141,0.5363894,0.06956397,0.37640554],"study_design_scores_gemma":[0.000050144157,0.00006414551,0.001609183,0.0007916779,0.000027960046,0.00038517066,0.009098867,0.0045271525,0.0024351699,0.25837478,0.722572,0.000063696236],"about_ca_topic_score_codex":0.009119201,"about_ca_topic_score_gemma":0.010955422,"teacher_disagreement_score":0.07024814,"about_ca_system_score_codex":0.004691124,"about_ca_system_score_gemma":0.008398458,"threshold_uncertainty_score":0.23500347},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006606282,0.8463674,0.027104558,0.029427916,0.005093824,0.0004467413,0.000629177,0.0011153285,0.08915445],"genre_scores_gemma":[0.018565567,0.7484903,0.08787829,0.010673656,0.0033982443,0.002075405,0.0012120673,0.00121153,0.12649496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9880392,0.0046929438,0.0015384341,0.0006845435,0.0047048703,0.0003400009],"domain_scores_gemma":[0.9788168,0.013834136,0.00091307505,0.0013044797,0.004415455,0.0007161206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016683405,0.0020467318,0.0023014138,0.005395957,0.002189566,0.010188381,0.0023632937,0.0042346646,0.020108206],"category_scores_gemma":[0.021898685,0.0017500502,0.00082029664,0.007494568,0.0062112743,0.011280812,0.0035838715,0.0070207654,0.012879542],"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":[0.000030343552,0.000050527775,0.00024133909,0.0019465013,0.00001578508,0.00009059153,0.0024770636,0.00028116963,0.00029743847,0.024508154,0.47103834,0.49902272],"study_design_scores_gemma":[0.000009372636,0.00003340172,0.0006197437,0.0036633364,0.000009907638,0.00032804723,0.001248249,0.00012251725,0.00019389918,0.02149389,0.972252,0.000025593337],"about_ca_topic_score_codex":0.010102768,"about_ca_topic_score_gemma":0.016198296,"teacher_disagreement_score":0.020108206,"about_ca_system_score_codex":0.0051344424,"about_ca_system_score_gemma":0.012628283,"threshold_uncertainty_score":0.088231325},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29663935,0.0065713213,0.50799054,0.053937733,0.00023101422,0.0010970118,0.00022237595,0.0001967896,0.1331139],"genre_scores_gemma":[0.90479505,0.0022743484,0.088980965,0.0011143442,0.00012745666,0.0006684477,0.00009616329,0.00004107132,0.001902141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.924898,0.05407343,0.0035331943,0.0024783486,0.013377659,0.0016393214],"domain_scores_gemma":[0.5343642,0.4297297,0.010374832,0.011588253,0.011815233,0.0021277377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08989196,0.0008897629,0.0011781371,0.008584909,0.0030419074,0.012458914,0.003024174,0.0036277596,0.004342576],"category_scores_gemma":[0.2157173,0.0005111984,0.00087735034,0.004147746,0.02317979,0.01999827,0.008443667,0.0031930734,0.00043708849],"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":[0.000248199,0.00081325846,0.018765543,0.001497629,0.00012466917,0.00019475435,0.012775551,0.009285077,0.0009329787,0.70172256,0.0016815875,0.2519582],"study_design_scores_gemma":[0.00008360073,0.0004172839,0.008729389,0.002396692,0.00012395182,0.00014982389,0.010895171,0.028906157,0.0044649583,0.9305388,0.0131982155,0.00009587833],"about_ca_topic_score_codex":0.0047882656,"about_ca_topic_score_gemma":0.0073816082,"teacher_disagreement_score":0.08989196,"about_ca_system_score_codex":0.007388683,"about_ca_system_score_gemma":0.012941635,"threshold_uncertainty_score":0.4753998},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09370535,0.002929941,0.37233853,0.32056484,0.0033067649,0.0015588873,0.00010430487,0.0010250828,0.20446624],"genre_scores_gemma":[0.8655179,0.0007300435,0.09078588,0.023529435,0.0007301897,0.0010415816,0.0000923998,0.00063916214,0.016933406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7782135,0.16574287,0.00675806,0.011900001,0.030271469,0.0071140467],"domain_scores_gemma":[0.563286,0.18007354,0.022219302,0.039548174,0.11467776,0.08019531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1877207,0.0010330294,0.0015568555,0.00808846,0.024720808,0.04775627,0.0073176054,0.008609062,0.00564852],"category_scores_gemma":[0.23439042,0.001582944,0.0011442319,0.003778417,0.056575183,0.024131944,0.036339343,0.026327757,0.0016899969],"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":[0.00009160641,0.0013581716,0.01294739,0.00045843582,0.0003672234,0.00056873664,0.18066886,0.0031549134,0.0017946991,0.6398368,0.047299188,0.111454085],"study_design_scores_gemma":[0.00011395176,0.00028904222,0.00706121,0.002303526,0.00008541359,0.00047225255,0.09740111,0.0072067864,0.0018375034,0.5695055,0.31323713,0.00048652416],"about_ca_topic_score_codex":0.011128393,"about_ca_topic_score_gemma":0.012162154,"teacher_disagreement_score":0.1877207,"about_ca_system_score_codex":0.02048511,"about_ca_system_score_gemma":0.062249683,"threshold_uncertainty_score":0.99277383},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12008453,0.032853473,0.4367227,0.25248912,0.004822323,0.033962157,0.00069471955,0.00032086458,0.1180502],"genre_scores_gemma":[0.7240022,0.0062733716,0.21590734,0.008713137,0.0006509267,0.04029229,0.00009338267,0.00010920641,0.003958119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.3293348,0.63519126,0.011343086,0.0055762227,0.013172988,0.0053816494],"domain_scores_gemma":[0.3386228,0.5804783,0.012385827,0.033803277,0.030774258,0.0039354605],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5552001,0.0012115533,0.002839408,0.0037425857,0.013450522,0.018602561,0.0064789196,0.0050101774,0.0041125105],"category_scores_gemma":[0.4957375,0.0013761898,0.0014788391,0.008191721,0.04418193,0.018386599,0.014086615,0.0045517646,0.00042483237],"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":[0.00030564444,0.0006113684,0.008737368,0.013163611,0.00038309023,0.00046267442,0.33620864,0.0020523937,0.00047640555,0.50234556,0.0055735474,0.1296798],"study_design_scores_gemma":[0.000458687,0.00075257407,0.00629588,0.022661256,0.00037982847,0.00058086385,0.48728457,0.004936509,0.002187905,0.37314534,0.10109432,0.00022221578],"about_ca_topic_score_codex":0.029769016,"about_ca_topic_score_gemma":0.03171317,"teacher_disagreement_score":0.4447999,"about_ca_system_score_codex":0.018060442,"about_ca_system_score_gemma":0.061512534,"threshold_uncertainty_score":0.54851747},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24350335,0.008065783,0.28125435,0.06300704,0.000882531,0.00044764712,0.00027414208,0.00026258721,0.40230253],"genre_scores_gemma":[0.9172511,0.002219467,0.05902216,0.0020868063,0.00016001167,0.0006841989,0.00008566907,0.00011135409,0.018379355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9705992,0.018431474,0.0014039847,0.0016643405,0.0068143206,0.0010867503],"domain_scores_gemma":[0.9533459,0.02977632,0.0027643873,0.0034733184,0.009442719,0.0011973369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031032925,0.00071742065,0.0004128253,0.0031048642,0.004368836,0.009111588,0.0012610087,0.0025620537,0.00446912],"category_scores_gemma":[0.049889877,0.0005170043,0.0006837574,0.002123135,0.019486021,0.0068350746,0.0049037556,0.0046097273,0.00067348895],"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":[0.000042733558,0.00006943634,0.006536021,0.00013145663,0.000015009105,0.00005680583,0.03400036,0.0010576238,0.0004657481,0.9169079,0.0011869839,0.039529912],"study_design_scores_gemma":[0.0000713739,0.0002271219,0.02825306,0.0013796156,0.00006151407,0.00030895972,0.0419233,0.0057008094,0.0034020937,0.7529944,0.1655078,0.00017000185],"about_ca_topic_score_codex":0.011310235,"about_ca_topic_score_gemma":0.016525673,"teacher_disagreement_score":0.031032925,"about_ca_system_score_codex":0.010148943,"about_ca_system_score_gemma":0.0078237355,"threshold_uncertainty_score":0.16411972},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936219,0.000111121066,0.0004061807,0.00015900031,0.00002779455,0.00017492303,0.00018275395,0.000063940606,0.005252385],"genre_scores_gemma":[0.99464595,0.00008045145,0.0010579869,0.00006427737,0.000027716731,0.000110134424,0.000331547,0.00001719606,0.0036648407],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9845036,0.008046474,0.00080284616,0.00085943483,0.0046521598,0.0011354223],"domain_scores_gemma":[0.9569695,0.023217592,0.00474004,0.002105206,0.007825587,0.005142086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012932031,0.00038108788,0.00041652526,0.0011996517,0.0006148026,0.0014656954,0.0005389179,0.00044719735,0.0033793414],"category_scores_gemma":[0.037971906,0.00013845356,0.0005558999,0.0010002471,0.00047415547,0.0005967609,0.0011286433,0.000547716,0.0007429665],"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":[0.008990882,0.008351558,0.46052262,0.00030646566,0.00023145192,0.00020406305,0.0024446321,0.00084386964,0.007629113,0.00012136672,0.0035500226,0.506804],"study_design_scores_gemma":[0.00025442368,0.0058878004,0.98083663,0.000055599525,0.00013364917,0.00011809659,0.001083302,0.002090653,0.005261307,0.00006770498,0.0041612387,0.000049652313],"about_ca_topic_score_codex":0.023435049,"about_ca_topic_score_gemma":0.036329683,"teacher_disagreement_score":0.987068,"about_ca_system_score_codex":0.0014170429,"about_ca_system_score_gemma":0.0022886992,"threshold_uncertainty_score":0.06839192},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009527422,0.27043286,0.0060956622,0.70055586,0.0028416743,0.0019010516,0.0011233939,0.00025876204,0.007263358],"genre_scores_gemma":[0.33171785,0.41200766,0.11494849,0.12705757,0.0026420162,0.006242807,0.0020610439,0.0005151205,0.00280743],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.33793908,0.4007784,0.08534928,0.0154039245,0.13937844,0.021150809],"domain_scores_gemma":[0.07931654,0.53458405,0.052513912,0.027034668,0.27977395,0.02677687],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6175402,0.002604976,0.00909434,0.036072467,0.015765697,0.047177233,0.016485153,0.011262622,0.0045920038],"category_scores_gemma":[0.76478046,0.0040277485,0.0051727416,0.064007804,0.028409222,0.025539912,0.017006382,0.012483261,0.00073335896],"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":[0.0011237629,0.0002414461,0.03380904,0.20143344,0.0042119776,0.0008591725,0.07747925,0.0030393396,0.0015056407,0.049460966,0.13199829,0.4948376],"study_design_scores_gemma":[0.000529234,0.00036789445,0.053859282,0.42036816,0.0040161912,0.00066991313,0.07860061,0.0046706167,0.0012925541,0.025791885,0.4083233,0.0015104328],"about_ca_topic_score_codex":0.91915345,"about_ca_topic_score_gemma":0.9525644,"teacher_disagreement_score":0.6633531,"about_ca_system_score_codex":0.3366469,"about_ca_system_score_gemma":0.6735748,"threshold_uncertainty_score":0.7693956},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0152151575,0.026082449,0.410735,0.21022664,0.0026201701,0.0009932424,0.00031329555,0.00051875407,0.33329523],"genre_scores_gemma":[0.68042344,0.030617198,0.24744101,0.020940913,0.0039738053,0.0032994025,0.00035632288,0.00034789712,0.012600059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93629503,0.046208605,0.0036586053,0.0040879496,0.008025509,0.001724275],"domain_scores_gemma":[0.82993233,0.12874511,0.0071581653,0.015096333,0.014850399,0.004217632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.099250264,0.0016726316,0.0018358066,0.017198747,0.0034261458,0.020939797,0.0030618734,0.0068356413,0.00577251],"category_scores_gemma":[0.10966261,0.0009914573,0.0012856734,0.006471456,0.07797361,0.054525066,0.020765923,0.011866985,0.0014895437],"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":[0.0000107929045,0.000029292809,0.00060148747,0.0003956974,0.000015790278,0.000045697005,0.0033341548,0.0002964343,0.00014551327,0.9704607,0.0013296952,0.023334747],"study_design_scores_gemma":[0.000015884985,0.00007607122,0.00067899865,0.0014217033,0.00002966614,0.00017466165,0.0029904603,0.00079724507,0.00034587854,0.91920763,0.074218474,0.000043254553],"about_ca_topic_score_codex":0.0018080806,"about_ca_topic_score_gemma":0.0008573568,"teacher_disagreement_score":0.90074974,"about_ca_system_score_codex":0.0085074855,"about_ca_system_score_gemma":0.012177356,"threshold_uncertainty_score":0.52489185},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014682625,0.0013427068,0.00019067756,0.030031076,0.9662555,0.000015425694,0.000058866084,0.00008873015,0.0020023854],"genre_scores_gemma":[0.00038385257,0.0026055865,0.00028988867,0.032807723,0.92648435,0.000037980502,0.00010376763,0.00019358817,0.037093323],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99103665,0.0014314823,0.001081819,0.0007176799,0.005259045,0.0004733355],"domain_scores_gemma":[0.9631571,0.012452012,0.0021441295,0.0012343643,0.017091889,0.003920509],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007841541,0.0026888356,0.0034773864,0.004056067,0.0034456144,0.010644674,0.0029746848,0.013701755,0.04651884],"category_scores_gemma":[0.045791898,0.0011538145,0.0024117783,0.0017407376,0.002637,0.0039910893,0.0018243089,0.01807825,0.041682012],"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":[0.0000121449075,0.0000066888183,0.0000055939163,0.000049797774,0.00000470187,0.00004080451,0.0000035407663,0.000009265847,0.000026656557,0.00017330384,0.99745613,0.0022113863],"study_design_scores_gemma":[0.00004165902,0.000015515392,0.00007965186,0.00021160512,0.000017567148,0.00008695429,0.00002143948,0.000099388475,0.00009082502,0.0008394501,0.9984793,0.000016659182],"about_ca_topic_score_codex":0.002207704,"about_ca_topic_score_gemma":0.006507715,"teacher_disagreement_score":0.98629826,"about_ca_system_score_codex":0.0026679235,"about_ca_system_score_gemma":0.005289178,"threshold_uncertainty_score":0.15562099},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033825606,0.43953845,0.13001648,0.17776951,0.008579135,0.0008409731,0.0004308012,0.0008396773,0.23860252],"genre_scores_gemma":[0.066409536,0.45891714,0.27733928,0.034859132,0.006947009,0.001554409,0.00036589924,0.00058541563,0.1530222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996628,0.0015888247,0.00030253825,0.00016450383,0.0011604247,0.00015576514],"domain_scores_gemma":[0.9939553,0.0044778776,0.0002579156,0.00015069557,0.0008392021,0.00031893616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010359358,0.00095501874,0.0006304279,0.0030124034,0.0016748538,0.005608446,0.0011341663,0.0032685162,0.005446999],"category_scores_gemma":[0.011413975,0.0005988035,0.000670302,0.0035633368,0.0046326593,0.0069240914,0.0026712841,0.004559216,0.0029802008],"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":[0.00003365423,0.0001825106,0.0007820915,0.0010935446,0.000011651084,0.00030705333,0.0021528173,0.0019492776,0.0005264854,0.24339741,0.41400945,0.33555406],"study_design_scores_gemma":[0.000011231958,0.00007154567,0.0009929133,0.002134944,0.0000065075737,0.0004943563,0.0011734139,0.00070076797,0.00024930754,0.12228155,0.8718406,0.000042893666],"about_ca_topic_score_codex":0.008791694,"about_ca_topic_score_gemma":0.023218041,"teacher_disagreement_score":0.010359358,"about_ca_system_score_codex":0.005093372,"about_ca_system_score_gemma":0.006149354,"threshold_uncertainty_score":0.054786205},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06662581,0.03330371,0.02070856,0.71490526,0.004351955,0.00015170783,0.0005290243,0.00006545846,0.15935852],"genre_scores_gemma":[0.9395762,0.01039882,0.009097274,0.0360172,0.0021087092,0.000117714895,0.0002663827,0.000020671736,0.0023970674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96767634,0.018394396,0.003053967,0.0022224027,0.007548181,0.0011047957],"domain_scores_gemma":[0.73064786,0.1911738,0.024998222,0.014574494,0.030299015,0.008306596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046461307,0.00052140217,0.0009693118,0.0035204114,0.0011205284,0.010113881,0.0022566542,0.0064687277,0.011768012],"category_scores_gemma":[0.29366356,0.00051808514,0.00071887637,0.00197747,0.009426529,0.012478242,0.0030085165,0.0068038385,0.001359722],"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":[0.00072934636,0.0008600056,0.040643148,0.0031525632,0.001835937,0.00075601,0.011511264,0.0008848191,0.00056178274,0.4862827,0.036379874,0.41640252],"study_design_scores_gemma":[0.00044957316,0.0003753454,0.024594257,0.011794853,0.00072066666,0.0009796262,0.011979195,0.0018852093,0.0012377473,0.8605053,0.08532053,0.00015769947],"about_ca_topic_score_codex":0.0019818086,"about_ca_topic_score_gemma":0.0023984155,"teacher_disagreement_score":0.046461307,"about_ca_system_score_codex":0.0033994918,"about_ca_system_score_gemma":0.0056499424,"threshold_uncertainty_score":0.24571377},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026476366,0.002433195,0.7462005,0.02427543,0.0012543757,0.028510513,0.0029736427,0.015926493,0.15194947],"genre_scores_gemma":[0.07447267,0.0010159062,0.891631,0.0008628444,0.00010482799,0.01974771,0.0013109575,0.0010398781,0.00981412],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.78163576,0.18340966,0.0144791175,0.0025723376,0.014382617,0.003520431],"domain_scores_gemma":[0.61280036,0.26736608,0.015884677,0.03349643,0.05209991,0.018352555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21690279,0.0016033471,0.0017999883,0.010662153,0.0044606086,0.014209971,0.004864095,0.0035694065,0.025231557],"category_scores_gemma":[0.21776022,0.0014568008,0.0023058567,0.006833719,0.00519009,0.015249453,0.025696596,0.0046841563,0.008104555],"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":[0.0011803769,0.002864403,0.008035228,0.012724449,0.00039041508,0.0023720793,0.035601396,0.018006058,0.005890666,0.14635734,0.10197534,0.6646023],"study_design_scores_gemma":[0.0009851598,0.0013014694,0.009865401,0.0219499,0.00033866116,0.0012573828,0.02337877,0.033171088,0.006763329,0.27386427,0.62649435,0.0006302188],"about_ca_topic_score_codex":0.0032686281,"about_ca_topic_score_gemma":0.0061694505,"teacher_disagreement_score":0.21690279,"about_ca_system_score_codex":0.01070149,"about_ca_system_score_gemma":0.03966444,"threshold_uncertainty_score":0.9656983},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19084336,0.1023525,0.4931234,0.1273788,0.0027093464,0.017738707,0.0011226577,0.0004766706,0.064254574],"genre_scores_gemma":[0.6398478,0.047624394,0.28480428,0.012295478,0.00041866006,0.013306473,0.00068733643,0.000077885015,0.00093755545],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9068578,0.072011724,0.007339077,0.0032345646,0.009039607,0.0015172097],"domain_scores_gemma":[0.28306594,0.68403417,0.011949614,0.0062824483,0.012983574,0.0016842536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13944775,0.0017806446,0.0019693335,0.010658674,0.0032240485,0.011119957,0.005122725,0.004833147,0.004583794],"category_scores_gemma":[0.24949071,0.0015183714,0.0021390528,0.0062307273,0.017095491,0.0141332,0.0042164265,0.0058354223,0.00071780436],"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":[0.00047169405,0.0019982308,0.024402503,0.0579652,0.0005362977,0.0006808942,0.11687528,0.007839223,0.0011362276,0.3573181,0.0072154906,0.42356083],"study_design_scores_gemma":[0.0007108458,0.0014888463,0.014356639,0.19254151,0.00082011236,0.00052231026,0.18605214,0.027284442,0.004657586,0.5028117,0.06851524,0.00023869908],"about_ca_topic_score_codex":0.003697607,"about_ca_topic_score_gemma":0.0032498336,"teacher_disagreement_score":0.13944775,"about_ca_system_score_codex":0.017250415,"about_ca_system_score_gemma":0.03592153,"threshold_uncertainty_score":0.737479},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028344067,0.0073551103,0.008124991,0.067294076,0.0010737274,0.0004873277,0.010840824,0.0023996888,0.8740802],"genre_scores_gemma":[0.43146536,0.011718235,0.036953513,0.014720892,0.00054645014,0.00039427707,0.008795979,0.000543338,0.49486196],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930213,0.0006766964,0.0002748529,0.0007443242,0.00380354,0.0014792373],"domain_scores_gemma":[0.98735785,0.0007239964,0.0004713669,0.00074375415,0.007767011,0.0029359055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033279904,0.0007215257,0.00038058704,0.0043720338,0.012326785,0.009230726,0.0026115978,0.0021655909,0.033786736],"category_scores_gemma":[0.011902375,0.00046842135,0.0004653776,0.010147999,0.0033463626,0.0034465233,0.004541175,0.0017665498,0.0049685873],"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":[0.00013014874,0.000059129718,0.009161165,0.00043384978,0.000026524385,0.00035080875,0.0024222143,0.0011024585,0.00090981624,0.28729212,0.47950292,0.21860881],"study_design_scores_gemma":[0.000012182981,0.000017037986,0.012404684,0.00012921759,0.000011671472,0.00007671845,0.0008553845,0.0006161759,0.000300362,0.0034748712,0.9820502,0.000051521612],"about_ca_topic_score_codex":0.9823247,"about_ca_topic_score_gemma":0.9834764,"teacher_disagreement_score":0.99667203,"about_ca_system_score_codex":0.09355888,"about_ca_system_score_gemma":0.20270704,"threshold_uncertainty_score":0.6788204},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021124274,0.23330654,0.008497372,0.08138615,0.0012563939,0.000050813826,0.0004197618,0.00006895118,0.6538897],"genre_scores_gemma":[0.8250498,0.13364415,0.0065028477,0.007282715,0.00092905416,0.00016188572,0.00039758708,0.0001204239,0.025911639],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9858991,0.0063883783,0.00035122377,0.0005490003,0.0050796336,0.0017326553],"domain_scores_gemma":[0.9794581,0.0125588095,0.00097639934,0.00048146234,0.005683949,0.00084138144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014633192,0.0009109639,0.0008435589,0.009333338,0.0048823077,0.010439537,0.0015277984,0.0020745224,0.0077871797],"category_scores_gemma":[0.02384592,0.00024467052,0.0006143654,0.022128256,0.017084772,0.0068462025,0.0029044212,0.0031487679,0.00036119542],"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":[0.000019487647,0.000017933318,0.0005373901,0.00021563753,0.000013931523,0.0000163771,0.003394228,0.00031344718,0.00003203418,0.9417148,0.013553877,0.04017089],"study_design_scores_gemma":[0.00002256842,0.00013713063,0.030015234,0.004915225,0.00014278285,0.00012188011,0.034496393,0.0010053859,0.00067752966,0.37345892,0.5549236,0.000083350365],"about_ca_topic_score_codex":0.3310957,"about_ca_topic_score_gemma":0.36052352,"teacher_disagreement_score":0.6689043,"about_ca_system_score_codex":0.040778816,"about_ca_system_score_gemma":0.040898927,"threshold_uncertainty_score":0.658337},"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":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82342553,0.0020726926,0.04535044,0.03650125,0.001101547,0.06769474,0.0008435785,0.0002965024,0.02271386],"genre_scores_gemma":[0.879847,0.0015588393,0.06005433,0.002615389,0.00016646126,0.051181227,0.00024757377,0.00014781444,0.0041815005],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.44749027,0.49671087,0.014717138,0.005271938,0.02774137,0.008068438],"domain_scores_gemma":[0.29528072,0.56755686,0.020986794,0.015481304,0.08288383,0.017810564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4764518,0.0007828208,0.0014075716,0.006279705,0.016983025,0.012849405,0.005680615,0.0040132655,0.004381563],"category_scores_gemma":[0.535325,0.0013355401,0.0014161026,0.0051128343,0.017162256,0.009689296,0.019092761,0.0059720837,0.0008779395],"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":[0.0002912988,0.0008047944,0.0050270353,0.0027623826,0.000040331466,0.0005292674,0.89071125,0.000514923,0.001049408,0.010224625,0.0056469725,0.082397826],"study_design_scores_gemma":[0.0002852306,0.0014765675,0.007983823,0.0038865434,0.000068846064,0.0002479502,0.9206704,0.0010442559,0.0019655533,0.006132001,0.056037903,0.00020106102],"about_ca_topic_score_codex":0.006510315,"about_ca_topic_score_gemma":0.008372647,"teacher_disagreement_score":0.5235482,"about_ca_system_score_codex":0.035268232,"about_ca_system_score_gemma":0.07674821,"threshold_uncertainty_score":0.64562815},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29829943,0.001618166,0.38816234,0.023624973,0.00023109396,0.0010287071,0.00081905,0.00028502897,0.2859313],"genre_scores_gemma":[0.9218944,0.00060140796,0.050927643,0.00042376042,0.00010020284,0.0005418376,0.00016736402,0.000051089894,0.025292214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99455476,0.0036876814,0.00019834083,0.00052954175,0.00042173764,0.00060795294],"domain_scores_gemma":[0.9692665,0.025592519,0.0018433806,0.00069727964,0.0015005412,0.0010997213],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.010231894,0.00089686795,0.0007841087,0.0019567898,0.0027427217,0.0083638625,0.0027048036,0.0070709763,0.019150557],"category_scores_gemma":[0.025177062,0.00077838445,0.0012548927,0.002500557,0.0056032226,0.005725874,0.003871963,0.0035531002,0.001254368],"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":[0.00012141556,0.0001847826,0.0027845812,0.00007974376,0.000027353972,0.0004579596,0.0019967498,0.20351382,0.00035321125,0.7810174,0.0012033631,0.008259574],"study_design_scores_gemma":[0.00018822885,0.00009885561,0.001037266,0.00008567961,0.000050596555,0.00008404342,0.0016031328,0.64254856,0.00020997564,0.34494662,0.009096465,0.000050507268],"about_ca_topic_score_codex":0.039694358,"about_ca_topic_score_gemma":0.025553094,"teacher_disagreement_score":0.9972573,"about_ca_system_score_codex":0.008667632,"about_ca_system_score_gemma":0.007133648,"threshold_uncertainty_score":0.07892662},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032314856,0.000985766,0.01932128,0.94672954,0.0029485247,0.00037028853,0.00003481255,0.0001279301,0.026250344],"genre_scores_gemma":[0.38076484,0.005776064,0.22524348,0.30165038,0.006158647,0.004839519,0.00026453298,0.00028928323,0.07501321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9684275,0.017702859,0.00161602,0.0037017958,0.004665668,0.0038862901],"domain_scores_gemma":[0.9482213,0.018581225,0.002032648,0.0029591783,0.011282495,0.01692305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060780462,0.0011169178,0.0014136119,0.0042354874,0.021047935,0.034942035,0.011030703,0.042754445,0.01491799],"category_scores_gemma":[0.09617179,0.0010374419,0.0021661464,0.004712168,0.061629932,0.05045166,0.024795428,0.024937842,0.005030781],"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":[0.00003163771,0.000113217466,0.0007692608,0.00014399512,0.000007993897,0.0005067357,0.015871445,0.0002677286,0.000116735864,0.89683175,0.06498018,0.020359341],"study_design_scores_gemma":[0.000057078763,0.000073948504,0.00024889692,0.00038171074,0.000013067758,0.00033589566,0.061497744,0.0011092541,0.00013186241,0.76228845,0.17379291,0.00006911848],"about_ca_topic_score_codex":0.005149461,"about_ca_topic_score_gemma":0.009058987,"teacher_disagreement_score":0.060780462,"about_ca_system_score_codex":0.010104634,"about_ca_system_score_gemma":0.05524356,"threshold_uncertainty_score":0.32144165},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13245471,0.027066665,0.25322828,0.29553995,0.0024464915,0.0036068996,0.00015588771,0.00063041743,0.28487068],"genre_scores_gemma":[0.8551566,0.0060552238,0.111048825,0.010054252,0.0003314069,0.0027421734,0.000068555346,0.0002240729,0.014318923],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8348981,0.14735788,0.0018166235,0.0054502888,0.0057537267,0.0047234064],"domain_scores_gemma":[0.8773835,0.08109512,0.0054987436,0.012215224,0.010618323,0.013189158],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16183591,0.0010439228,0.0017105866,0.009894107,0.03905833,0.035605438,0.009026761,0.006915667,0.004953579],"category_scores_gemma":[0.08287982,0.0013935753,0.00096399686,0.0054099783,0.10718652,0.03023045,0.034844235,0.01184436,0.00094758434],"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":[0.00001585947,0.00007626659,0.001252351,0.00027341486,0.000018569632,0.0002801278,0.870815,0.000069258116,0.00016471649,0.10567203,0.0018672133,0.01949516],"study_design_scores_gemma":[0.00001778748,0.000063512394,0.0010476505,0.0009675273,0.000023998688,0.00028326447,0.7925141,0.0002615619,0.00018156506,0.10610166,0.09849796,0.000039381626],"about_ca_topic_score_codex":0.030863462,"about_ca_topic_score_gemma":0.07097226,"teacher_disagreement_score":0.96913654,"about_ca_system_score_codex":0.031692546,"about_ca_system_score_gemma":0.0702495,"threshold_uncertainty_score":0.8558803},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085308395,0.021403858,0.6212923,0.097011216,0.0051824916,0.020803796,0.0012583687,0.0015367849,0.14620283],"genre_scores_gemma":[0.5071461,0.0046648667,0.46036583,0.0075951754,0.0009272636,0.01641983,0.000315602,0.0005837391,0.0019814738],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.136986,0.73484606,0.03507402,0.011852112,0.07702082,0.0042210585],"domain_scores_gemma":[0.08529448,0.7579652,0.036483813,0.06495578,0.052030176,0.0032705797],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7326147,0.0042482587,0.0060574417,0.021734906,0.01092781,0.033564277,0.0050272713,0.009016406,0.0067849723],"category_scores_gemma":[0.8206303,0.00243081,0.0061071464,0.016668674,0.030416649,0.04658323,0.027518969,0.009403595,0.0012904654],"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":[0.0016560507,0.00082882994,0.03154932,0.01508532,0.003854085,0.00022969468,0.031945013,0.00842763,0.0014990992,0.36634275,0.012508004,0.5260741],"study_design_scores_gemma":[0.0016306195,0.004092477,0.03251217,0.026548287,0.0037045665,0.00040859779,0.023474295,0.023822771,0.010868169,0.7690744,0.10281872,0.0010449813],"about_ca_topic_score_codex":0.006882389,"about_ca_topic_score_gemma":0.004559941,"teacher_disagreement_score":0.2673853,"about_ca_system_score_codex":0.026594257,"about_ca_system_score_gemma":0.044687465,"threshold_uncertainty_score":0.32973373},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678669,0.00064356456,0.0033438215,0.013022493,0.00008357636,0.00043489024,0.000033488508,0.000023649973,0.014547668],"genre_scores_gemma":[0.9927263,0.0006168019,0.002843751,0.0014403989,0.000029437595,0.00017784846,0.000021735917,0.000019789304,0.0021237184],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96191645,0.029938854,0.0006030093,0.001022582,0.0021511554,0.00436786],"domain_scores_gemma":[0.9569426,0.026160965,0.0034858438,0.0012374192,0.0033967914,0.008776378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025808508,0.0006763458,0.0006726961,0.0022399323,0.024267538,0.007806676,0.003865111,0.005007568,0.0036531268],"category_scores_gemma":[0.03429561,0.000926519,0.0006098726,0.0018207576,0.014391233,0.005728484,0.009443374,0.007171604,0.00039100365],"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":[0.00004563675,0.00120582,0.01038759,0.00021130816,0.000012475667,0.011771326,0.95550114,0.00035411425,0.0003837892,0.0052490947,0.0023750302,0.012502561],"study_design_scores_gemma":[0.000010086643,0.00018021636,0.0030294769,0.00031283876,0.000005834673,0.0015109534,0.9814524,0.00042918057,0.00017873872,0.00075378036,0.0121181505,0.000018288812],"about_ca_topic_score_codex":0.02342782,"about_ca_topic_score_gemma":0.058110096,"teacher_disagreement_score":0.025808508,"about_ca_system_score_codex":0.018985145,"about_ca_system_score_gemma":0.019793142,"threshold_uncertainty_score":0.13774753},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03084341,0.015790485,0.03999778,0.20710349,0.004226344,0.0012744714,0.001088051,0.00079314533,0.6988829],"genre_scores_gemma":[0.75457865,0.0070308866,0.073995195,0.030893786,0.0009824234,0.0012472501,0.0008996595,0.00019624928,0.13017583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.90939707,0.025594797,0.0025265976,0.003444406,0.04700249,0.01203461],"domain_scores_gemma":[0.9220653,0.015982198,0.0026390464,0.0037159987,0.04661447,0.008983062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06623335,0.0006203254,0.0006785131,0.004709311,0.013964552,0.01530228,0.0048409393,0.004311293,0.00364317],"category_scores_gemma":[0.06629767,0.00074866513,0.0007636499,0.005122293,0.00992801,0.004642503,0.007887726,0.004704729,0.0005631539],"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":[0.00006545624,0.00008672435,0.0061282855,0.0004284106,0.00003269971,0.0005215858,0.010448627,0.0038461615,0.0006144704,0.7618416,0.090863585,0.12512238],"study_design_scores_gemma":[0.000057405327,0.00013814992,0.017102925,0.0010864022,0.000051399584,0.00025130014,0.0059165694,0.0024449541,0.0008860795,0.074472696,0.89740163,0.00019055782],"about_ca_topic_score_codex":0.86089385,"about_ca_topic_score_gemma":0.9045304,"teacher_disagreement_score":0.87262064,"about_ca_system_score_codex":0.12737934,"about_ca_system_score_gemma":0.38752177,"threshold_uncertainty_score":0.92420614},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99546814,0.00038446535,0.0003492334,0.00048592748,0.00005513636,0.0003518131,0.00006169152,0.000010472052,0.0028330223],"genre_scores_gemma":[0.99145764,0.0008318069,0.001882038,0.00026988596,0.00004477974,0.0007555526,0.0001299679,0.0000057992106,0.0046225535],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9923035,0.004254683,0.00055137236,0.0004558839,0.0015930086,0.0008415246],"domain_scores_gemma":[0.96138334,0.02393653,0.0042781965,0.0016093361,0.0035704477,0.0052221515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01038582,0.00050432415,0.00078285666,0.0005370675,0.0021066742,0.0018230486,0.0007440708,0.0012743208,0.007295422],"category_scores_gemma":[0.028037794,0.0004525233,0.0012187416,0.00041084955,0.0015713606,0.00088122656,0.0025052284,0.0021474601,0.00083089137],"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":[0.014570807,0.03219399,0.4466626,0.0035259791,0.0012222271,0.000778326,0.09361978,0.0010679655,0.010055628,0.0020601847,0.0030162549,0.3912263],"study_design_scores_gemma":[0.00095699704,0.047089595,0.86508507,0.0011379565,0.0008177764,0.00039037992,0.057844795,0.00088065775,0.007677173,0.0018682592,0.01610252,0.00014876122],"about_ca_topic_score_codex":0.0059651276,"about_ca_topic_score_gemma":0.011601764,"teacher_disagreement_score":0.01038582,"about_ca_system_score_codex":0.001482685,"about_ca_system_score_gemma":0.0049306056,"threshold_uncertainty_score":0.054926157},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75100124,0.004308074,0.14537244,0.0047609783,0.00047969,0.0011574749,0.0006671358,0.0011414747,0.0911116],"genre_scores_gemma":[0.9555649,0.0009703272,0.03181218,0.000104117644,0.00006956929,0.0003548233,0.0002830486,0.00023483553,0.010606184],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9462177,0.025749385,0.0029534493,0.0031336138,0.020288771,0.0016570209],"domain_scores_gemma":[0.85483825,0.08250697,0.009445246,0.009924139,0.040768612,0.0025168844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050899573,0.0009964653,0.0007680093,0.007871104,0.003476139,0.016111089,0.0020880934,0.0014308167,0.0053762845],"category_scores_gemma":[0.16102971,0.00081207446,0.0008007761,0.0061203437,0.0057664625,0.009061076,0.0038526393,0.0021577412,0.0009220532],"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":[0.00065532705,0.00026088595,0.15580301,0.0017350789,0.00016076105,0.0016653754,0.2706168,0.006249034,0.006250113,0.056295477,0.0056405263,0.49466756],"study_design_scores_gemma":[0.00014914465,0.0011310814,0.24660774,0.0042248582,0.00022607726,0.003516613,0.38096923,0.0218459,0.017973125,0.030843835,0.2920387,0.0004738297],"about_ca_topic_score_codex":0.02585918,"about_ca_topic_score_gemma":0.021109194,"teacher_disagreement_score":0.050899573,"about_ca_system_score_codex":0.009925522,"about_ca_system_score_gemma":0.008288568,"threshold_uncertainty_score":0.2691859},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0633897,0.006525162,0.6492327,0.099523954,0.001336842,0.0008573327,0.0013938237,0.0009137786,0.17682672],"genre_scores_gemma":[0.8014692,0.0042110016,0.17316331,0.0031110758,0.00036673478,0.0019846663,0.000691184,0.00027925504,0.014723601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9773018,0.016348768,0.00078977284,0.0013976421,0.0034184256,0.00074362406],"domain_scores_gemma":[0.9467524,0.04448442,0.0016438458,0.002670464,0.0039535253,0.0004952747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021021886,0.0016894613,0.001120183,0.0032081828,0.0022936773,0.010804745,0.0042810147,0.0056399857,0.011539718],"category_scores_gemma":[0.06443735,0.0009301268,0.0033177335,0.0045134397,0.008469728,0.01607895,0.0035717594,0.0061000623,0.0020101375],"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":[0.00009384881,0.00011933216,0.0022740772,0.0003432186,0.000067397734,0.00010613167,0.0019202261,0.019240823,0.00009863582,0.958873,0.002970945,0.013892428],"study_design_scores_gemma":[0.0001554965,0.00012901814,0.0016155398,0.0008747279,0.00013451351,0.00020892317,0.0027033112,0.14339894,0.00081408006,0.789646,0.060223296,0.00009616145],"about_ca_topic_score_codex":0.021913774,"about_ca_topic_score_gemma":0.017882172,"teacher_disagreement_score":0.021913774,"about_ca_system_score_codex":0.00909455,"about_ca_system_score_gemma":0.0062961043,"threshold_uncertainty_score":0.111175716},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4852779,0.0009471771,0.20345175,0.0044193603,0.0009786898,0.22093031,0.0057461224,0.0050078365,0.073240824],"genre_scores_gemma":[0.39354533,0.0007542982,0.49166965,0.0012363655,0.00014610846,0.086166404,0.005216519,0.0013479688,0.019917462],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9075254,0.06301938,0.005789492,0.00246958,0.018431755,0.002764232],"domain_scores_gemma":[0.7345852,0.07447094,0.0037769284,0.020447608,0.15901497,0.007704276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13006906,0.001216859,0.0012464207,0.0030580827,0.005096379,0.0026828158,0.004055235,0.0017463613,0.0072915005],"category_scores_gemma":[0.1566778,0.0011631919,0.001229064,0.003113368,0.002406629,0.0017250378,0.0039118812,0.003443125,0.0032101336],"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":[0.0048742266,0.03326654,0.01731692,0.0034341547,0.00016853152,0.0014292565,0.035385575,0.007374888,0.023478968,0.0069337506,0.09318785,0.7731494],"study_design_scores_gemma":[0.009778259,0.06273037,0.21698534,0.0040354254,0.000615876,0.0013225966,0.04846152,0.05575042,0.08119523,0.0072552706,0.5108091,0.0010604655],"about_ca_topic_score_codex":0.09864382,"about_ca_topic_score_gemma":0.11878434,"teacher_disagreement_score":0.13006906,"about_ca_system_score_codex":0.010778912,"about_ca_system_score_gemma":0.03339886,"threshold_uncertainty_score":0},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003385036,0.9481066,0.008771273,0.030188745,0.000653452,0.00019398596,0.00007360041,0.000014263493,0.008613011],"genre_scores_gemma":[0.15491511,0.8137237,0.01898636,0.008939554,0.0009169611,0.001124384,0.00013003066,0.00005548234,0.0012084555],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.88462514,0.08915382,0.005347548,0.0044034803,0.014659188,0.0018109243],"domain_scores_gemma":[0.6532491,0.32119632,0.008007821,0.0056646722,0.010717487,0.0011646316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1446991,0.0014121238,0.0061134966,0.006489622,0.0033362554,0.016704531,0.0051635997,0.0063461973,0.0041260957],"category_scores_gemma":[0.19088978,0.0007628814,0.0017154539,0.0129881445,0.023631172,0.025128482,0.01156586,0.0063278545,0.0003016617],"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":[0.00019069163,0.00012416815,0.0016403964,0.06513052,0.0006874604,0.00014052982,0.013872226,0.0005891606,0.00018737462,0.25658956,0.0054997103,0.65534824],"study_design_scores_gemma":[0.00012506136,0.00020782337,0.003607439,0.26330462,0.0013751221,0.0004394381,0.029107131,0.0007670569,0.001015292,0.4373557,0.26256272,0.00013256006],"about_ca_topic_score_codex":0.0063414783,"about_ca_topic_score_gemma":0.012108499,"teacher_disagreement_score":0.8553009,"about_ca_system_score_codex":0.0073861307,"about_ca_system_score_gemma":0.033236634,"threshold_uncertainty_score":0.7652511},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002668252,0.04800874,0.04662702,0.7037072,0.17129728,0.0002412134,0.000065654036,0.00036050857,0.027024152],"genre_scores_gemma":[0.09352757,0.057061546,0.12633905,0.23317137,0.46627566,0.0012514542,0.00015360901,0.0011721832,0.021047492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7782753,0.15091139,0.014709105,0.010522774,0.041767467,0.0038139962],"domain_scores_gemma":[0.47720563,0.3935658,0.021537282,0.02412197,0.064148374,0.01942087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17458306,0.0008377064,0.0013034448,0.0053782077,0.007831331,0.02773708,0.0033690725,0.012350907,0.0071040327],"category_scores_gemma":[0.33417,0.0011094396,0.0016117708,0.004013942,0.018764276,0.017395003,0.014070657,0.029144987,0.0028014053],"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":[0.0001335357,0.00012737144,0.0031792978,0.0024027408,0.00018249972,0.0006636752,0.02435007,0.00024673602,0.00078560936,0.41057375,0.33382732,0.2235274],"study_design_scores_gemma":[0.000029757974,0.000089836874,0.0012991274,0.0033619392,0.00008285266,0.00090443826,0.0062032924,0.0008588816,0.00060873374,0.121454574,0.8649596,0.00014701155],"about_ca_topic_score_codex":0.0011572961,"about_ca_topic_score_gemma":0.003312371,"teacher_disagreement_score":0.8254169,"about_ca_system_score_codex":0.00547602,"about_ca_system_score_gemma":0.015484439,"threshold_uncertainty_score":0.92329454},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1128118,0.033215497,0.06363075,0.46520746,0.004315183,0.00040204727,0.00010363053,0.00029659274,0.320017],"genre_scores_gemma":[0.9310343,0.008717489,0.01660006,0.020475829,0.0010620122,0.00049146794,0.000034090892,0.0002714265,0.021313373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.78921807,0.16098934,0.004591533,0.006059977,0.033766378,0.00537481],"domain_scores_gemma":[0.75162655,0.17384402,0.010764181,0.01569346,0.039113533,0.00895813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13469632,0.0010912773,0.0014027241,0.0041274284,0.012128514,0.029531356,0.002723515,0.005700956,0.006859791],"category_scores_gemma":[0.17312537,0.00072562677,0.0008778032,0.0029779773,0.056978755,0.019569974,0.016226923,0.009588808,0.0011993565],"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":[0.00021598945,0.00020871055,0.0084365625,0.0011336553,0.00015730428,0.000290476,0.18202576,0.00078290683,0.00095057435,0.57245195,0.020344974,0.21300107],"study_design_scores_gemma":[0.00009866736,0.0005696556,0.012846114,0.0077446033,0.00016299766,0.00042051225,0.19722417,0.0017284644,0.0025668985,0.35545686,0.42088446,0.00029656],"about_ca_topic_score_codex":0.021240616,"about_ca_topic_score_gemma":0.020168124,"teacher_disagreement_score":0.13469632,"about_ca_system_score_codex":0.021892037,"about_ca_system_score_gemma":0.04054378,"threshold_uncertainty_score":0.7123507},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47750488,0.010076225,0.10985906,0.045296572,0.0006949652,0.0016844362,0.0031250403,0.00030079784,0.35145792],"genre_scores_gemma":[0.9301098,0.0032741341,0.020358708,0.0013639844,0.000053165175,0.0009825457,0.0003911287,0.000085034226,0.043381624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902716,0.005540698,0.00027720616,0.0010460863,0.001933203,0.00093116995],"domain_scores_gemma":[0.9798117,0.012261997,0.0012071943,0.0011284635,0.0050110403,0.00057961745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009464165,0.00076388713,0.0007355276,0.004349525,0.009415391,0.010769017,0.0020467434,0.0015088501,0.012534038],"category_scores_gemma":[0.017723128,0.00046222648,0.0005095136,0.007416513,0.015847689,0.005776228,0.0038433853,0.0021793977,0.0004895418],"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":[0.000071712486,0.00010933826,0.035387613,0.0015151124,0.00011350497,0.00062388135,0.36319438,0.002471923,0.0012131676,0.4706812,0.010289979,0.11432819],"study_design_scores_gemma":[0.00004644989,0.00013816723,0.07565108,0.0034825362,0.0001852849,0.00028417964,0.47185475,0.005052878,0.0021513463,0.05389672,0.3870674,0.0001892904],"about_ca_topic_score_codex":0.94166553,"about_ca_topic_score_gemma":0.95329297,"teacher_disagreement_score":0.91036606,"about_ca_system_score_codex":0.08963393,"about_ca_system_score_gemma":0.08481746,"threshold_uncertainty_score":0.6503427},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95490974,0.0008400067,0.0052608205,0.011257901,0.0003119404,0.00023411277,0.000046061043,0.0001048902,0.027034601],"genre_scores_gemma":[0.9883387,0.0004378498,0.0013049933,0.0011181562,0.00006212305,0.0000856454,0.000024105473,0.00011090993,0.008517546],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.972985,0.016509414,0.00089079177,0.0015078388,0.0046841307,0.0034228284],"domain_scores_gemma":[0.9182844,0.05243654,0.0038876708,0.0035977166,0.013393546,0.00840014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017099593,0.0006773592,0.00084685086,0.0018704535,0.009940646,0.012533314,0.0024181618,0.0038825267,0.003077976],"category_scores_gemma":[0.08716098,0.00090282934,0.00059385586,0.00079793495,0.011751847,0.004517244,0.010042072,0.010263757,0.00088755705],"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":[0.00009088957,0.0006340194,0.009667485,0.00020929267,0.000013924975,0.0026573772,0.9477775,0.00017713619,0.0018717261,0.0021026325,0.0042595635,0.030538442],"study_design_scores_gemma":[0.000019967216,0.00039827332,0.00896498,0.00031302086,0.000015827545,0.001195289,0.9518654,0.00034236867,0.002328705,0.0012754534,0.0332205,0.000060141112],"about_ca_topic_score_codex":0.0057491804,"about_ca_topic_score_gemma":0.010071675,"teacher_disagreement_score":0.017099593,"about_ca_system_score_codex":0.0069615827,"about_ca_system_score_gemma":0.005480904,"threshold_uncertainty_score":0},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035259298,0.9864631,0.00092655694,0.00084737147,0.0004892769,0.0054691792,0.0006644999,0.000027389742,0.0015866654],"genre_scores_gemma":[0.06795192,0.9150133,0.0065713003,0.0009385004,0.00023658497,0.008426731,0.0004264054,0.000016334108,0.00041892935],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9147427,0.052235346,0.010935039,0.002427911,0.018569862,0.0010891233],"domain_scores_gemma":[0.8255639,0.12419954,0.019048799,0.0039516957,0.025996316,0.001239776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0737516,0.0014990988,0.008237099,0.0062250434,0.0017001939,0.0037872384,0.0030487985,0.0022822623,0.005598206],"category_scores_gemma":[0.21646662,0.0011760573,0.005907184,0.012488029,0.002079936,0.0016474231,0.001333161,0.0018815877,0.0003293448],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042405073,0.0005866008,0.0020326336,0.6944623,0.015478126,0.00008007195,0.00047850006,0.00084012654,0.00024668814,0.002503805,0.004070786,0.27497983],"study_design_scores_gemma":[0.0123405205,0.004179565,0.019525694,0.8112559,0.09884374,0.00016884414,0.0007737694,0.0008992641,0.0013213173,0.001834197,0.048704598,0.00015262804],"about_ca_topic_score_codex":0.20538707,"about_ca_topic_score_gemma":0.28645852,"teacher_disagreement_score":0.9704854,"about_ca_system_score_codex":0.029514626,"about_ca_system_score_gemma":0.079978,"threshold_uncertainty_score":0.40838313},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047408575,0.0038381468,0.86022705,0.04461905,0.0009540141,0.0011026566,0.000061178835,0.00060414115,0.083852924],"genre_scores_gemma":[0.14453173,0.0037499636,0.8292505,0.0051668896,0.0003050748,0.0026282405,0.0000966042,0.00047172228,0.013799246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93538684,0.05502274,0.0021625662,0.0016456229,0.0042838687,0.0014983823],"domain_scores_gemma":[0.9535828,0.033922292,0.0012432318,0.0028161814,0.0058632665,0.0025721784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06576261,0.0018314238,0.0012344604,0.0058655026,0.0074350233,0.016566502,0.005022863,0.005852554,0.005541181],"category_scores_gemma":[0.04693715,0.000981335,0.0015577616,0.0032168117,0.039131418,0.018200204,0.008325572,0.011588281,0.0018255493],"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":[0.000020125419,0.00008323985,0.00027912334,0.00029658794,0.0000066782386,0.00013764709,0.028774114,0.0008824204,0.00048936845,0.9210273,0.0069095287,0.04109386],"study_design_scores_gemma":[0.00003947031,0.00008144984,0.0002890127,0.0018456242,0.000016195725,0.0002526561,0.01817088,0.004533883,0.0009897132,0.7418768,0.231835,0.000069253525],"about_ca_topic_score_codex":0.017355632,"about_ca_topic_score_gemma":0.02342018,"teacher_disagreement_score":0.06576261,"about_ca_system_score_codex":0.022050101,"about_ca_system_score_gemma":0.023052542,"threshold_uncertainty_score":0.34779006},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060038073,0.0020201271,0.9592777,0.012189084,0.00036030193,0.0006774827,0.00023041165,0.0003110449,0.018930007],"genre_scores_gemma":[0.27028915,0.002102942,0.72070605,0.0015861505,0.0003486913,0.0034182034,0.0004119287,0.00017736915,0.00095951994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8728059,0.10354992,0.003953888,0.0062928824,0.012072734,0.0013246734],"domain_scores_gemma":[0.656586,0.2915028,0.010484801,0.023535667,0.016119046,0.0017716975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.108469434,0.0023460279,0.004492797,0.010102,0.0033527745,0.014689831,0.006293539,0.004998704,0.0072321747],"category_scores_gemma":[0.19732013,0.0014571485,0.0043413676,0.007173288,0.019791849,0.016342772,0.0071017086,0.0103381155,0.0010839036],"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":[0.000037763344,0.000104969535,0.0015209111,0.00073352247,0.0003193384,0.000052009596,0.0010963684,0.023259023,0.00008197864,0.94041175,0.002155964,0.030226458],"study_design_scores_gemma":[0.00003153388,0.000060491064,0.00043314518,0.00050090614,0.000054027896,0.000016895137,0.00042662333,0.036392603,0.00014352213,0.95750725,0.0044014887,0.000031484662],"about_ca_topic_score_codex":0.0037456783,"about_ca_topic_score_gemma":0.0032472704,"teacher_disagreement_score":0.108469434,"about_ca_system_score_codex":0.013409065,"about_ca_system_score_gemma":0.011785132,"threshold_uncertainty_score":0.5736481},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009828594,0.0017009721,0.00017923943,0.94566125,0.051615246,0.000014331764,0.00003882936,0.00001956808,0.0006721886],"genre_scores_gemma":[0.0021637592,0.0012056492,0.00030627934,0.9533126,0.04120224,0.00006601821,0.000015266867,0.000029493876,0.0016987314],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9806903,0.007501475,0.0021400729,0.0026771242,0.0056881052,0.0013028928],"domain_scores_gemma":[0.87430423,0.09345531,0.0045266515,0.0018786843,0.021290028,0.0045450786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017886735,0.0015408216,0.0020821374,0.0014780866,0.007769283,0.0059898756,0.009673016,0.061431687,0.0042425278],"category_scores_gemma":[0.109974526,0.0011830684,0.0021562346,0.002058921,0.014704579,0.0075313994,0.0044829953,0.08496114,0.0060545458],"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":[0.000041819007,0.0000073609594,0.000043894917,0.00021377695,0.000012477642,0.00026440131,0.0006851067,0.00004684851,0.00010460461,0.0032064174,0.9925383,0.0028350207],"study_design_scores_gemma":[0.00007571354,0.00006612221,0.0003799093,0.0018902003,0.000048725524,0.00087079365,0.0018476689,0.00032626733,0.00040807968,0.015285865,0.9787023,0.000098449105],"about_ca_topic_score_codex":0.02018398,"about_ca_topic_score_gemma":0.019699996,"teacher_disagreement_score":0.061431687,"about_ca_system_score_codex":0.009834159,"about_ca_system_score_gemma":0.017576257,"threshold_uncertainty_score":0.09459525},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03803951,0.008028104,0.023296496,0.7914035,0.0015236816,0.0013565137,0.00017818398,0.00012639692,0.1360476],"genre_scores_gemma":[0.8407347,0.0054831877,0.04540532,0.09400248,0.0010244655,0.0022635933,0.000116744915,0.0002004547,0.010768973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.42656484,0.48980516,0.0096102385,0.007238723,0.037230633,0.02955041],"domain_scores_gemma":[0.3955122,0.51167655,0.008112905,0.013055797,0.05911184,0.01253069],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4452792,0.00090456475,0.0018854953,0.004486668,0.030099627,0.043784875,0.0069954335,0.019436244,0.0049028276],"category_scores_gemma":[0.41576684,0.0013047882,0.0014183539,0.007196571,0.040046375,0.026990607,0.022074202,0.025319928,0.00053366565],"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":[0.00021509512,0.0002535269,0.0051739467,0.001316202,0.00017427158,0.0022562132,0.07501679,0.007820992,0.00054035085,0.7414671,0.06069359,0.10507193],"study_design_scores_gemma":[0.00048777155,0.00022341288,0.007902894,0.00538809,0.00019012808,0.0005321149,0.12842466,0.007699689,0.0020078148,0.4040523,0.44266164,0.00042951328],"about_ca_topic_score_codex":0.3859751,"about_ca_topic_score_gemma":0.4373461,"teacher_disagreement_score":0.8788888,"about_ca_system_score_codex":0.12111121,"about_ca_system_score_gemma":0.23163326,"threshold_uncertainty_score":0.87872744},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8832933,0.006557423,0.009729694,0.016078856,0.00020418013,0.00054897537,0.0008704248,0.000101601465,0.08261548],"genre_scores_gemma":[0.98809624,0.0015902617,0.00371904,0.00036184472,0.00001641073,0.00014633393,0.00021501922,0.000022718124,0.0058322055],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.97952133,0.008189453,0.0009563995,0.000841459,0.008013756,0.002477477],"domain_scores_gemma":[0.9611998,0.011720406,0.003870819,0.0011159935,0.016978476,0.0051144073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017444896,0.0005146185,0.0007385031,0.003299578,0.0041837655,0.0064534205,0.0011833305,0.00087177136,0.0063456767],"category_scores_gemma":[0.042089988,0.00039597167,0.00092230586,0.0042957333,0.0025573813,0.0024200308,0.0054937745,0.0016372178,0.00040420104],"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":[0.00030478186,0.00040953202,0.49430832,0.0018615837,0.00043282023,0.0006986307,0.15794092,0.0007527944,0.0017073202,0.015027112,0.0052296715,0.3213264],"study_design_scores_gemma":[0.000019746829,0.0003187197,0.8290545,0.0021681054,0.00029480676,0.0003327781,0.10765895,0.0009307717,0.0010384044,0.00279223,0.05529361,0.000097351476],"about_ca_topic_score_codex":0.50679696,"about_ca_topic_score_gemma":0.6402923,"teacher_disagreement_score":0.50679696,"about_ca_system_score_codex":0.031018928,"about_ca_system_score_gemma":0.050365265,"threshold_uncertainty_score":0.9922152},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043025997,0.0065423157,0.83807445,0.022653572,0.0014582769,0.031158037,0.0032965622,0.0003103859,0.05348041],"genre_scores_gemma":[0.27446985,0.004428928,0.6175686,0.007515794,0.00042076895,0.09042885,0.0012053859,0.00017254948,0.003789256],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6848048,0.29629132,0.007287449,0.0040942985,0.00611295,0.0014091746],"domain_scores_gemma":[0.6440445,0.29576805,0.014868091,0.025421355,0.017782748,0.0021152606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19977446,0.0012599779,0.0015210052,0.009765092,0.0059767086,0.007906278,0.0029867424,0.0034078087,0.007975497],"category_scores_gemma":[0.21477734,0.0009913071,0.0011263003,0.014273109,0.016697852,0.0094555905,0.008280172,0.0032853587,0.0015811484],"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":[0.00024452683,0.00036742567,0.0071583237,0.0077244607,0.00014302148,0.00055737625,0.24623954,0.0017110975,0.0018186505,0.582478,0.014961543,0.13659604],"study_design_scores_gemma":[0.00023384496,0.00059885404,0.005548156,0.012684791,0.0001220571,0.0008626171,0.2795371,0.0053928667,0.0028723003,0.43258792,0.2593176,0.0002418543],"about_ca_topic_score_codex":0.0042658094,"about_ca_topic_score_gemma":0.0047014635,"teacher_disagreement_score":0.19977446,"about_ca_system_score_codex":0.008075452,"about_ca_system_score_gemma":0.011487441,"threshold_uncertainty_score":0.9868206},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09758575,0.24709664,0.006075493,0.34014875,0.0018396752,0.00024001955,0.0070793256,0.0001119151,0.29982257],"genre_scores_gemma":[0.8847971,0.081233345,0.004060279,0.018820396,0.0008369786,0.0004177502,0.0025094587,0.000072704745,0.0072519723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9491858,0.03593053,0.0021837475,0.0013342858,0.009145037,0.0022206148],"domain_scores_gemma":[0.86957127,0.0873534,0.017508846,0.0064197974,0.01656734,0.0025794192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04823282,0.00044695995,0.00060160935,0.011574471,0.0016308296,0.009883083,0.0008927292,0.002315275,0.004663378],"category_scores_gemma":[0.10552824,0.00025639043,0.00034447748,0.034280267,0.006299533,0.008794059,0.004012671,0.002208374,0.00040181587],"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":[0.00022358005,0.00020021488,0.12580149,0.0016384413,0.00019491737,0.00016144062,0.006717718,0.0015035126,0.00006644233,0.5176539,0.11852643,0.22731198],"study_design_scores_gemma":[0.00006109959,0.00010030644,0.2556645,0.008539815,0.00018775702,0.00015487745,0.022621032,0.0011607377,0.00044404375,0.12687145,0.58410895,0.00008549256],"about_ca_topic_score_codex":0.03610371,"about_ca_topic_score_gemma":0.028200645,"teacher_disagreement_score":0.04823282,"about_ca_system_score_codex":0.010377301,"about_ca_system_score_gemma":0.015222258,"threshold_uncertainty_score":0.2550826},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22674401,0.008306019,0.5136428,0.007486301,0.0011557887,0.12749672,0.0024554795,0.0011430475,0.11156979],"genre_scores_gemma":[0.5681284,0.0009957007,0.3794292,0.0011997044,0.00011372176,0.04712068,0.0008355641,0.00010379299,0.0020732286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.42971656,0.51395565,0.020475272,0.005533007,0.027984755,0.0023348108],"domain_scores_gemma":[0.310218,0.42232713,0.03648316,0.062411506,0.16135977,0.0072004464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43155253,0.0015383806,0.003243291,0.010359598,0.004001325,0.00801127,0.003397316,0.0032013722,0.0076887314],"category_scores_gemma":[0.42602816,0.0010324232,0.0020024364,0.008021318,0.0030730169,0.008556809,0.009674949,0.0030637577,0.0011795267],"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":[0.009468226,0.00621701,0.044545323,0.021078425,0.0045265956,0.0003340229,0.0092521,0.014502405,0.003096665,0.050191354,0.015847994,0.8209398],"study_design_scores_gemma":[0.019926641,0.06824238,0.21688534,0.07670423,0.010562533,0.0015285306,0.030348804,0.15067105,0.05108293,0.19986582,0.17296755,0.0012142726],"about_ca_topic_score_codex":0.0055318032,"about_ca_topic_score_gemma":0.012031852,"teacher_disagreement_score":0.43155253,"about_ca_system_score_codex":0.011622785,"about_ca_system_score_gemma":0.026004309,"threshold_uncertainty_score":0.70099694},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06723404,0.014641592,0.0016430254,0.8085066,0.008257749,0.00030688074,0.0014677353,0.00026989286,0.09767245],"genre_scores_gemma":[0.70442915,0.02808337,0.0046896283,0.13775426,0.0051540225,0.00033363764,0.0014075512,0.00048057103,0.11766774],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9761035,0.0032483095,0.0011011332,0.0011073084,0.014615414,0.0038243644],"domain_scores_gemma":[0.85928804,0.04460553,0.006221139,0.0020200007,0.07404834,0.013817062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025522904,0.0008526118,0.00045893784,0.008190981,0.021815367,0.012542983,0.00263029,0.0077568027,0.008103356],"category_scores_gemma":[0.09873225,0.0007453557,0.00045404557,0.018868849,0.008164426,0.0026627749,0.0047570486,0.0075276042,0.000830735],"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":[0.000115754,0.000053557676,0.008817891,0.0005737131,0.000018119132,0.0008075739,0.08435386,0.0003440956,0.0012883284,0.023809034,0.8304351,0.04938296],"study_design_scores_gemma":[0.00003147615,0.000039232258,0.021475099,0.00039633815,0.000028388722,0.00013613299,0.09887452,0.00024280112,0.00062811794,0.0015915476,0.8764465,0.00010978035],"about_ca_topic_score_codex":0.9409069,"about_ca_topic_score_gemma":0.9751474,"teacher_disagreement_score":0.111191854,"about_ca_system_score_codex":0.111191854,"about_ca_system_score_gemma":0.17120746,"threshold_uncertainty_score":0.80675715},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007597561,0.28450564,0.11796324,0.22172756,0.051708017,0.0425915,0.02090377,0.0012663458,0.2517364],"genre_scores_gemma":[0.12523983,0.2931645,0.39327458,0.045765154,0.020595027,0.03990555,0.022837302,0.00083381316,0.058384232],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88950044,0.059670776,0.021551032,0.0026443051,0.02512255,0.001510936],"domain_scores_gemma":[0.5930676,0.24295567,0.020522993,0.030245807,0.1043303,0.0088775875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10356643,0.0020982297,0.0037949535,0.012906566,0.0026823464,0.007762854,0.0039575514,0.006398611,0.07635191],"category_scores_gemma":[0.41311446,0.0012270093,0.0045984164,0.0061582252,0.002055933,0.008994329,0.0063723205,0.0066754604,0.035908774],"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":[0.0017198513,0.00048823268,0.0019789063,0.08680986,0.0010573267,0.0003051767,0.000399706,0.0006758587,0.0015700456,0.01173911,0.124636725,0.7686193],"study_design_scores_gemma":[0.0011108165,0.0015466382,0.007086153,0.37602243,0.004137148,0.00059510214,0.0015007769,0.0011370372,0.007364106,0.050343353,0.5489049,0.00025158233],"about_ca_topic_score_codex":0.0016667584,"about_ca_topic_score_gemma":0.0034338294,"teacher_disagreement_score":0.10356643,"about_ca_system_score_codex":0.00485144,"about_ca_system_score_gemma":0.027251996,"threshold_uncertainty_score":0.54771817},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93726313,0.00012085853,0.028452381,0.0009987241,0.00012995777,0.0059508686,0.0010831122,0.00030129505,0.02569964],"genre_scores_gemma":[0.9723789,0.000051866726,0.017701672,0.00021973455,0.000028341101,0.006905088,0.00064297224,0.00006358372,0.0020079233],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93443584,0.04246715,0.0065845936,0.002924445,0.010170805,0.003417266],"domain_scores_gemma":[0.5267315,0.3632324,0.014432729,0.025899537,0.06348511,0.0062187095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08689402,0.00048392217,0.000667734,0.0030683677,0.0015337907,0.0024076276,0.0013687452,0.0011112833,0.006086902],"category_scores_gemma":[0.2114949,0.0005081357,0.0012822835,0.0015052009,0.0022539545,0.0030647889,0.0034841113,0.0019676697,0.0013587867],"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":[0.0025880388,0.0074380725,0.6496797,0.0013464177,0.00045947882,0.0003356231,0.046919398,0.008682658,0.011733925,0.017411957,0.011517236,0.24188744],"study_design_scores_gemma":[0.0006403994,0.0049388804,0.88012624,0.0008254063,0.0002785155,0.0002819128,0.023801923,0.02461899,0.01662226,0.0069889138,0.04059596,0.0002805969],"about_ca_topic_score_codex":0.0027146523,"about_ca_topic_score_gemma":0.0022955497,"teacher_disagreement_score":0.08689402,"about_ca_system_score_codex":0.0036873799,"about_ca_system_score_gemma":0.008783463,"threshold_uncertainty_score":0.45954502},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516063,0.0021680102,0.0008177164,0.035304196,0.0002758318,0.000122010824,0.0005254403,0.00003740861,0.009143049],"genre_scores_gemma":[0.97560227,0.0010965647,0.0011421221,0.0014268067,0.000070911265,0.00005239071,0.00012473643,0.000022773847,0.02046134],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99581236,0.0010484138,0.00012889544,0.0002714454,0.0010251207,0.0017137368],"domain_scores_gemma":[0.98905176,0.0022840966,0.0009713883,0.00023915233,0.0029633031,0.00449032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040602707,0.00034665014,0.00032040183,0.0010391467,0.0056657107,0.0033617618,0.002262584,0.0016060064,0.006542004],"category_scores_gemma":[0.013072545,0.00036596032,0.0005267441,0.0014706979,0.0030544924,0.0010196208,0.002723524,0.0024499623,0.0003151174],"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":[0.0007211733,0.0007325877,0.5982918,0.00044940485,0.00016126077,0.0069400105,0.13140853,0.0021192962,0.0070874942,0.01900445,0.022296622,0.21078731],"study_design_scores_gemma":[0.00007937853,0.0005154684,0.76260763,0.00036494105,0.0001033346,0.0006236148,0.10754352,0.0018442497,0.0015952204,0.0009478597,0.12365646,0.00011826724],"about_ca_topic_score_codex":0.97202355,"about_ca_topic_score_gemma":0.9856894,"teacher_disagreement_score":0.97202355,"about_ca_system_score_codex":0.06157446,"about_ca_system_score_gemma":0.12372572,"threshold_uncertainty_score":0.44675606},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99638957,0.00014565229,0.00064929883,0.00013462131,0.00000795693,0.000007243196,0.00004256332,0.000006342088,0.0026167494],"genre_scores_gemma":[0.99822146,0.000101760066,0.00082323654,0.00007774065,0.000005406496,0.000009726024,0.000071639355,0.000008522639,0.0006805395],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99928826,0.00032299646,0.000035642573,0.00015766818,0.00014004786,0.000055350905],"domain_scores_gemma":[0.9928894,0.0043175807,0.0013148246,0.0005365348,0.00017203722,0.000769634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017337269,0.00015788847,0.00038590372,0.00037191762,0.00033478884,0.0019986064,0.00036913875,0.00067305,0.005060793],"category_scores_gemma":[0.014453766,0.00020533203,0.00024813498,0.00030870692,0.0007979008,0.0015317977,0.001211543,0.00087236054,0.00039164338],"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":[0.0040957425,0.0017115664,0.8355391,0.00027186333,0.00038203466,0.00049747946,0.0061549232,0.002399045,0.023930073,0.0072861784,0.0020684807,0.11566351],"study_design_scores_gemma":[0.00006153811,0.0012594467,0.9636887,0.00008001237,0.00018793595,0.00036132976,0.0026619954,0.00653421,0.002192897,0.020789668,0.0021266008,0.00005578667],"about_ca_topic_score_codex":0.0012082977,"about_ca_topic_score_gemma":0.002476591,"teacher_disagreement_score":0.005060793,"about_ca_system_score_codex":0.00022756633,"about_ca_system_score_gemma":0.00020693465,"threshold_uncertainty_score":0.016930044},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013281982,0.21375518,0.019493362,0.47851443,0.0062682214,0.000112674425,0.000117075535,0.00004321409,0.26841378],"genre_scores_gemma":[0.7001718,0.17627509,0.014111296,0.071455136,0.0032661464,0.0003556854,0.000087064596,0.000100229074,0.034177564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9761213,0.015908811,0.0009752391,0.0012311111,0.0047699185,0.0009935388],"domain_scores_gemma":[0.9714415,0.021939611,0.0015508916,0.00092579005,0.0034530978,0.000689157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018780628,0.00032508234,0.0010772742,0.0025074696,0.0025280397,0.015549319,0.0008925476,0.004065239,0.0043359543],"category_scores_gemma":[0.03582826,0.0002273772,0.000346164,0.0036021823,0.022778567,0.020525094,0.0035465707,0.0051258295,0.00059857575],"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":[0.000025123456,0.000020061978,0.00046169796,0.00084726606,0.00001581467,0.00010902792,0.0066653444,0.0001521936,0.00007520907,0.9070096,0.011897075,0.072721645],"study_design_scores_gemma":[0.000015260823,0.00007850847,0.0012721308,0.00648586,0.000028813838,0.00018115585,0.028154323,0.00020294917,0.0003000805,0.3545559,0.6086938,0.000031207463],"about_ca_topic_score_codex":0.010751745,"about_ca_topic_score_gemma":0.011690723,"teacher_disagreement_score":0.018780628,"about_ca_system_score_codex":0.009354193,"about_ca_system_score_gemma":0.012616326,"threshold_uncertainty_score":0.09932268},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012941427,0.0006702872,0.83546424,0.0034128046,0.00020182466,0.00045436498,0.002281698,0.0018036778,0.14276975],"genre_scores_gemma":[0.2843797,0.0016807602,0.58837265,0.0005066331,0.00008851862,0.00115451,0.0037138194,0.0009004285,0.11920295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831676,0.00055489835,0.00009094822,0.0002237118,0.00067795336,0.00013577299],"domain_scores_gemma":[0.99825066,0.00077825057,0.00011716319,0.00022526213,0.00056106335,0.000067449866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018199421,0.0006819944,0.00039895458,0.001907367,0.0011494341,0.005883765,0.0011912833,0.0013180149,0.027300052],"category_scores_gemma":[0.0054140356,0.0005598742,0.0013575113,0.0017157512,0.0020304064,0.0047047245,0.0015225788,0.0015165999,0.004986621],"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":[0.00008569272,0.00005850795,0.001860177,0.0004630535,0.000027718552,0.00024419013,0.0021406699,0.0312828,0.0020150268,0.8631543,0.010565953,0.0881019],"study_design_scores_gemma":[0.000048437774,0.0001070867,0.003697269,0.00075942575,0.000058131543,0.000277786,0.0016846864,0.13329004,0.0060983333,0.42962065,0.4242338,0.00012425816],"about_ca_topic_score_codex":0.044953063,"about_ca_topic_score_gemma":0.030288186,"teacher_disagreement_score":0.044953063,"about_ca_system_score_codex":0.0044528586,"about_ca_system_score_gemma":0.0051447437,"threshold_uncertainty_score":0.09132779},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011444884,0.0063211694,0.03615046,0.6036859,0.010796624,0.000893136,0.00061771105,0.0007379206,0.3293523],"genre_scores_gemma":[0.46614608,0.011056565,0.09253913,0.21040525,0.005674617,0.0014159069,0.0013514991,0.0020826035,0.20932838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.86997944,0.057871018,0.008903546,0.007408461,0.04844833,0.0073891734],"domain_scores_gemma":[0.784923,0.0861202,0.012350837,0.037968438,0.06727886,0.011358609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07874735,0.00079216424,0.0010750409,0.0026105386,0.005712504,0.01784374,0.004846932,0.011781679,0.027501486],"category_scores_gemma":[0.3509742,0.00082395325,0.0012879511,0.0023270196,0.010217899,0.019399468,0.008264532,0.014044485,0.010631871],"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":[0.00009770744,0.00010764673,0.004588015,0.00068352616,0.00013021144,0.000897483,0.006691977,0.0009210051,0.00031948098,0.4246662,0.300347,0.26054978],"study_design_scores_gemma":[0.000040501018,0.00006117134,0.00087429275,0.0018227119,0.00004092114,0.00025074577,0.00466924,0.00058408605,0.00048850506,0.10458536,0.8865291,0.000053268057],"about_ca_topic_score_codex":0.012898574,"about_ca_topic_score_gemma":0.010684047,"teacher_disagreement_score":0.07874735,"about_ca_system_score_codex":0.009425563,"about_ca_system_score_gemma":0.038949557,"threshold_uncertainty_score":0.41646075},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80731046,0.0015948489,0.010256999,0.012996305,0.00023522283,0.0004268603,0.00028989176,0.00013928162,0.16675007],"genre_scores_gemma":[0.960304,0.000532942,0.0034818929,0.00050245493,0.000019133733,0.00014064342,0.00012312485,0.00003755923,0.03485835],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9840756,0.006173402,0.00046348467,0.0014003956,0.0054459902,0.0024410016],"domain_scores_gemma":[0.9708473,0.005918141,0.0021682412,0.0010495574,0.013932165,0.0060845385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016678289,0.00042151887,0.00035559246,0.002095178,0.0063439338,0.010205851,0.00208015,0.0012520344,0.008628737],"category_scores_gemma":[0.033051077,0.00042069468,0.00045275048,0.0022393207,0.0056806686,0.0035878532,0.005097475,0.0023711978,0.0009614121],"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":[0.00021605678,0.00035167224,0.14932154,0.00051965215,0.00007417358,0.00072375097,0.5052101,0.0010181802,0.004616228,0.07954933,0.012443839,0.24595551],"study_design_scores_gemma":[0.000028045104,0.00036832967,0.49769467,0.000955672,0.00006301291,0.000174188,0.29205397,0.0017482975,0.0032458948,0.0037253357,0.19975913,0.000183457],"about_ca_topic_score_codex":0.6936921,"about_ca_topic_score_gemma":0.7791205,"teacher_disagreement_score":0.6936921,"about_ca_system_score_codex":0.05794148,"about_ca_system_score_gemma":0.0978909,"threshold_uncertainty_score":0.61622363},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09433937,0.012105281,0.0015484085,0.5714756,0.0072424044,0.00016519311,0.0027482172,0.00092061737,0.3094549],"genre_scores_gemma":[0.44177446,0.011219549,0.002370444,0.30219743,0.0017561788,0.00013348053,0.0021550392,0.00037687187,0.23801658],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98211265,0.0014039282,0.00030906766,0.0007412158,0.010861777,0.0045712735],"domain_scores_gemma":[0.91442806,0.013322675,0.0028961562,0.0019975845,0.044416677,0.022938889],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01170247,0.00048191263,0.0007282027,0.004039654,0.013729873,0.011516202,0.0021788462,0.0051336484,0.032000232],"category_scores_gemma":[0.038192432,0.00039181477,0.0009725189,0.005319686,0.0058498746,0.0027614606,0.003216247,0.004407279,0.0054087234],"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":[0.00016367293,0.0000770623,0.02942733,0.00027420043,0.00008309552,0.00018877015,0.0037523822,0.00016862755,0.0012237354,0.012337956,0.8257415,0.12656161],"study_design_scores_gemma":[0.000051013703,0.000053061343,0.070959285,0.0004509988,0.000054738226,0.00009128542,0.021145869,0.00023325649,0.00078441715,0.0045477366,0.90150976,0.00011855895],"about_ca_topic_score_codex":0.9314832,"about_ca_topic_score_gemma":0.95639735,"teacher_disagreement_score":0.9882975,"about_ca_system_score_codex":0.046488646,"about_ca_system_score_gemma":0.16131458,"threshold_uncertainty_score":0.3373003},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03824799,0.05565294,0.12157626,0.4826188,0.0021102396,0.00036488022,0.0005108224,0.00038085898,0.29853728],"genre_scores_gemma":[0.868585,0.033086736,0.05110355,0.013052876,0.0020166112,0.000805866,0.00025535116,0.00022852233,0.030865533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8945079,0.07092842,0.0028527842,0.005491593,0.02068005,0.00553925],"domain_scores_gemma":[0.7850388,0.16463932,0.009292532,0.010543163,0.026468249,0.0040179202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10977215,0.001919264,0.00262138,0.011885227,0.0065743257,0.032779884,0.0033918975,0.011313493,0.0050080856],"category_scores_gemma":[0.14611949,0.0010614253,0.0014006349,0.0174807,0.03359224,0.02504292,0.0075802966,0.01681185,0.00061182026],"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":[0.000024684892,0.00005556962,0.0012721258,0.00019774515,0.000020884825,0.000028235267,0.0023988227,0.0018063497,0.0000807865,0.96071863,0.0030426448,0.03035345],"study_design_scores_gemma":[0.00007130346,0.00016996355,0.013871186,0.0032610085,0.00006346459,0.0001470811,0.008711707,0.0095289275,0.0012249448,0.7720354,0.19073553,0.00017942263],"about_ca_topic_score_codex":0.15503904,"about_ca_topic_score_gemma":0.06982148,"teacher_disagreement_score":0.93183625,"about_ca_system_score_codex":0.06816372,"about_ca_system_score_gemma":0.0818894,"threshold_uncertainty_score":0.58053756},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031432844,0.92997503,0.0005442053,0.04296084,0.02051201,0.000021327478,0.000051176798,0.000014552789,0.0056065647],"genre_scores_gemma":[0.0061620395,0.9694251,0.0007596114,0.009232555,0.011428338,0.000057799625,0.00014154773,0.000042155243,0.0027508824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9895985,0.004033101,0.0012565178,0.0006780572,0.00405732,0.00037646858],"domain_scores_gemma":[0.9537256,0.023941021,0.0029088452,0.0013524013,0.016385851,0.0016862566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015326988,0.00081165123,0.0018518621,0.009111892,0.0016888453,0.008333248,0.0014502516,0.0029499822,0.006904198],"category_scores_gemma":[0.04986389,0.00060542044,0.0011046533,0.01157218,0.0058700587,0.00705247,0.003510931,0.007301976,0.0023484118],"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":[0.000049700924,0.00004270349,0.00037612577,0.020546349,0.00013423474,0.00011231981,0.0032679,0.0001606054,0.00036054914,0.034467302,0.5659399,0.3745423],"study_design_scores_gemma":[0.0000052565347,0.000023994222,0.00071152597,0.01551769,0.000039325554,0.0001312379,0.0013728054,0.000034104032,0.000087942,0.002438784,0.9796205,0.000016900052],"about_ca_topic_score_codex":0.0039143697,"about_ca_topic_score_gemma":0.007071073,"teacher_disagreement_score":0.015326988,"about_ca_system_score_codex":0.0052345665,"about_ca_system_score_gemma":0.016004784,"threshold_uncertainty_score":0.08105785},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06547864,0.01848463,0.15129477,0.47478577,0.005717235,0.0014617004,0.00036760585,0.0006739849,0.28173575],"genre_scores_gemma":[0.67232496,0.007694644,0.10593203,0.03314786,0.0010205925,0.001315306,0.0002983695,0.0004691908,0.177797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8920942,0.07274437,0.003532184,0.006604724,0.019010443,0.006014157],"domain_scores_gemma":[0.8596211,0.04857205,0.008531733,0.018359063,0.04740216,0.017513884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13092762,0.00073256204,0.0010097187,0.0024300294,0.010344079,0.022417566,0.0039728167,0.0061159427,0.0055755745],"category_scores_gemma":[0.066476285,0.0006620078,0.0012920616,0.0028676768,0.018805403,0.007933467,0.01240256,0.009345488,0.001577383],"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":[0.00016707141,0.00020695575,0.006836624,0.0009857614,0.0001382136,0.0006877052,0.083219364,0.0016260053,0.004266546,0.7017096,0.07009235,0.1300638],"study_design_scores_gemma":[0.00004331071,0.00016615918,0.0069771837,0.0010804763,0.000050430386,0.00036960127,0.025561145,0.0013404862,0.002539335,0.028578155,0.93313867,0.00015508535],"about_ca_topic_score_codex":0.16089804,"about_ca_topic_score_gemma":0.19182858,"teacher_disagreement_score":0.9545679,"about_ca_system_score_codex":0.045432072,"about_ca_system_score_gemma":0.13466062,"threshold_uncertainty_score":0.69241977},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017533328,0.00025784073,0.95926595,0.0012000557,0.000067097695,0.00045647452,0.00021790902,0.0023748837,0.018626407],"genre_scores_gemma":[0.1719034,0.00052297977,0.8181643,0.0003474965,0.00003188334,0.0017012705,0.00035637908,0.0007823732,0.006189893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912861,0.006270105,0.00035410994,0.00086546957,0.0009778502,0.00024626407],"domain_scores_gemma":[0.96735686,0.026987191,0.0011234131,0.0028323818,0.0011873486,0.0005128414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011217174,0.002103378,0.0006483059,0.0031826575,0.0016920071,0.008893398,0.0035098754,0.0018778247,0.01446097],"category_scores_gemma":[0.02931217,0.0014076781,0.0019534298,0.0014376759,0.00795333,0.012541707,0.0056205723,0.0027435487,0.0015460949],"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":[0.00055652496,0.0006673213,0.0061335303,0.002225909,0.00021785437,0.0010064755,0.043147575,0.05683827,0.01663413,0.63217217,0.010493322,0.2299069],"study_design_scores_gemma":[0.00044546675,0.0008262383,0.0016135053,0.0012992759,0.0003080204,0.0008778188,0.0075499415,0.1920301,0.018906513,0.58206946,0.19381465,0.00025908696],"about_ca_topic_score_codex":0.0029828432,"about_ca_topic_score_gemma":0.0038959146,"teacher_disagreement_score":0.01446097,"about_ca_system_score_codex":0.003875034,"about_ca_system_score_gemma":0.0031041617,"threshold_uncertainty_score":0.059322834},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058946457,0.0005523171,0.8669188,0.009587152,0.00010425897,0.0051623895,0.00062035164,0.0006463085,0.057462],"genre_scores_gemma":[0.16404116,0.00035246476,0.8297036,0.00044460685,0.000020975707,0.002116109,0.0004652362,0.000058212652,0.002797616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.985876,0.009658807,0.0007203136,0.00065502507,0.0026515187,0.00043838957],"domain_scores_gemma":[0.9703781,0.021896293,0.000936548,0.0012419225,0.005080832,0.0004663877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018220933,0.00088747765,0.00068747596,0.0040684794,0.0024181963,0.0068777525,0.0029115805,0.001754429,0.005537845],"category_scores_gemma":[0.032779064,0.0010116965,0.0015672446,0.0019685556,0.004279401,0.008742929,0.0036606013,0.0043446566,0.0008485593],"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":[0.00026819398,0.0009476455,0.003793895,0.00074144866,0.00006180645,0.000643175,0.0075532254,0.07530845,0.0022684583,0.7251581,0.004179681,0.17907594],"study_design_scores_gemma":[0.0002576549,0.0007534394,0.0016614371,0.0016466035,0.00022106296,0.0003648473,0.010539537,0.4443939,0.0059723416,0.46007252,0.073936716,0.00018001247],"about_ca_topic_score_codex":0.019186798,"about_ca_topic_score_gemma":0.029746182,"teacher_disagreement_score":0.019186798,"about_ca_system_score_codex":0.012041055,"about_ca_system_score_gemma":0.0195734,"threshold_uncertainty_score":0.09636265},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010781893,0.024279263,0.06506575,0.6087296,0.005890106,0.000112687805,0.0002963497,0.00034510856,0.2844992],"genre_scores_gemma":[0.72650385,0.008506651,0.048968308,0.14250077,0.015637802,0.0012427367,0.0002228002,0.0014633132,0.05495379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9300809,0.038588468,0.002440563,0.00933867,0.01716774,0.002383641],"domain_scores_gemma":[0.701899,0.24102359,0.004638773,0.026602956,0.020528318,0.005307415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09663853,0.0011507011,0.002986433,0.004661984,0.011358474,0.017873356,0.0038796342,0.0122794155,0.015879543],"category_scores_gemma":[0.27169213,0.0013002544,0.001671694,0.0044305185,0.08379779,0.033737224,0.011254129,0.022453295,0.0038242457],"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":[0.000020631303,0.000008274559,0.0002123928,0.000026789308,0.000008420591,0.000009513313,0.00050988974,0.00009473824,0.000028984054,0.97492075,0.015190397,0.008969295],"study_design_scores_gemma":[0.000038920698,0.000012111385,0.00034621297,0.00016798956,0.000013084694,0.000039302533,0.000529777,0.00048548612,0.00007346588,0.9463791,0.051884435,0.000030146315],"about_ca_topic_score_codex":0.017567484,"about_ca_topic_score_gemma":0.012921227,"teacher_disagreement_score":0.09663853,"about_ca_system_score_codex":0.011920513,"about_ca_system_score_gemma":0.009144948,"threshold_uncertainty_score":0.51107955},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54670835,0.0106153665,0.009184369,0.04670935,0.00030877307,0.00010052694,0.00044586678,0.00004792683,0.3858795],"genre_scores_gemma":[0.9739977,0.0014031283,0.0008699515,0.00079906,0.000026404976,0.00003217188,0.00005756574,0.000019517624,0.022794547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9981504,0.0007401846,0.000034247016,0.00020913738,0.00041233172,0.00045363387],"domain_scores_gemma":[0.99713695,0.000928615,0.00032997574,0.00021000714,0.0009222082,0.0004722539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025450252,0.00028971166,0.00035036693,0.0020289728,0.010377991,0.007106969,0.00084371335,0.0010802591,0.008170507],"category_scores_gemma":[0.004239024,0.00015437811,0.00020802188,0.0040363804,0.0116907125,0.002490598,0.0026553303,0.0020299677,0.0002648727],"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":[0.00006727568,0.000032951368,0.03374563,0.00025267157,0.00004324804,0.00043373342,0.3259665,0.0009316337,0.00050270744,0.5830105,0.010231576,0.04478154],"study_design_scores_gemma":[0.000020764077,0.000051260402,0.12848535,0.00085861515,0.00008608178,0.00017549767,0.43204227,0.0018581903,0.0005143863,0.06236009,0.37348273,0.00006471079],"about_ca_topic_score_codex":0.9380427,"about_ca_topic_score_gemma":0.96569777,"teacher_disagreement_score":0.0619573,"about_ca_system_score_codex":0.049490433,"about_ca_system_score_gemma":0.041452713,"threshold_uncertainty_score":0.35907996},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012929484,0.014356254,0.00035834455,0.95090616,0.005276052,0.000028400926,0.00006100173,0.000014613466,0.016069686],"genre_scores_gemma":[0.47529462,0.027552178,0.0013297733,0.4371533,0.00638206,0.0002268759,0.00018436112,0.00022412154,0.05165264],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9576279,0.019731024,0.0027768116,0.0019484967,0.009709418,0.0082063805],"domain_scores_gemma":[0.92581636,0.020971313,0.0049275397,0.0011377453,0.022341415,0.02480568],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.06892526,0.00049828883,0.0006851289,0.0023116483,0.014522737,0.025754858,0.002624446,0.01813995,0.00649875],"category_scores_gemma":[0.09075246,0.00073807046,0.00088415004,0.0046863286,0.017558753,0.019726958,0.011911715,0.02744945,0.0014686546],"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":[0.00030744847,0.00028611117,0.0058033345,0.00066914817,0.000033539876,0.0011928747,0.1682687,0.00028317457,0.0005099238,0.18708432,0.57311535,0.062446047],"study_design_scores_gemma":[0.000029927623,0.00007360043,0.0071030357,0.0011306508,0.0000067420974,0.00023357844,0.11326988,0.000087839864,0.00016655047,0.00958557,0.8682546,0.000058048525],"about_ca_topic_score_codex":0.09766316,"about_ca_topic_score_gemma":0.14192814,"teacher_disagreement_score":0.98547727,"about_ca_system_score_codex":0.040565573,"about_ca_system_score_gemma":0.052879658,"threshold_uncertainty_score":0.36451596},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19387513,0.04901024,0.5729101,0.065813966,0.0077661965,0.009732107,0.0028316076,0.0016045399,0.09645606],"genre_scores_gemma":[0.77706826,0.0052846954,0.19040821,0.0055122827,0.001641373,0.014161676,0.0008053992,0.00052529963,0.004592833],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.378126,0.5147503,0.027776308,0.025906099,0.05058913,0.002852142],"domain_scores_gemma":[0.13267432,0.7552991,0.031098984,0.044375375,0.034981906,0.0015703076],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43395784,0.002764075,0.0039313086,0.007516804,0.004057942,0.013532634,0.004872381,0.0029155712,0.012972346],"category_scores_gemma":[0.6757822,0.0017582673,0.006623335,0.009534551,0.013283753,0.016047673,0.009927739,0.00749852,0.0016207874],"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":[0.0038045903,0.00048342196,0.123662524,0.021611372,0.022000497,0.00022867796,0.05453089,0.005076554,0.0016715208,0.23419271,0.011949587,0.5207877],"study_design_scores_gemma":[0.0026934454,0.0056836004,0.18207437,0.031714533,0.018269956,0.00053514953,0.031043105,0.028358875,0.01101172,0.54562205,0.14196028,0.0010328734],"about_ca_topic_score_codex":0.006891903,"about_ca_topic_score_gemma":0.0062118447,"teacher_disagreement_score":0.43395784,"about_ca_system_score_codex":0.008636879,"about_ca_system_score_gemma":0.014838994,"threshold_uncertainty_score":0.69803077},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86078197,0.0041765417,0.04322375,0.006166962,0.0001791346,0.0017298105,0.00093434623,0.00019266435,0.08261479],"genre_scores_gemma":[0.98247725,0.00041426794,0.015138105,0.00029993834,0.0000478727,0.00031853755,0.00012550312,0.0000735795,0.0011049142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.73306966,0.18761297,0.011721,0.0074155657,0.055699173,0.0044815405],"domain_scores_gemma":[0.05862703,0.8874244,0.014696992,0.009168209,0.0290675,0.001015908],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2515895,0.0010926286,0.0011844587,0.004498811,0.002012221,0.0067753,0.0023547781,0.0022432778,0.0042971596],"category_scores_gemma":[0.6554614,0.0006687673,0.001841431,0.0033560728,0.003954376,0.0046642637,0.002713998,0.003157767,0.00046836023],"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":[0.014701078,0.003515772,0.4318416,0.005378154,0.0032211458,0.0012993708,0.016969966,0.046412475,0.010606846,0.059777047,0.0076050335,0.3986715],"study_design_scores_gemma":[0.0017054231,0.009463877,0.65220225,0.003844893,0.010053461,0.000947512,0.025468966,0.14000991,0.057921853,0.056469988,0.04122982,0.0006820281],"about_ca_topic_score_codex":0.008886672,"about_ca_topic_score_gemma":0.00971665,"teacher_disagreement_score":0.74841046,"about_ca_system_score_codex":0.0063439123,"about_ca_system_score_gemma":0.0049091517,"threshold_uncertainty_score":0.9229234},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008710637,0.027281178,0.28585884,0.5124247,0.0055498704,0.0012911829,0.00036897033,0.0006470165,0.15786746],"genre_scores_gemma":[0.5397187,0.028200464,0.3498675,0.06254248,0.004609641,0.0040514274,0.0006593686,0.00083276996,0.009517668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.63194233,0.30198464,0.018748175,0.010536836,0.030589813,0.0061982335],"domain_scores_gemma":[0.33191445,0.59308404,0.008200551,0.039284736,0.02304043,0.0044757803],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38927352,0.0022361139,0.003193814,0.013909401,0.008073324,0.039009646,0.00801933,0.017147344,0.018733278],"category_scores_gemma":[0.45831475,0.0014104183,0.0032316595,0.012994364,0.060035735,0.068127416,0.03312132,0.021436842,0.0049545025],"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":[0.00009921159,0.00013005768,0.00045068187,0.0027161636,0.00009149462,0.00016514659,0.015116574,0.0022015953,0.00025361325,0.81910056,0.009176583,0.15049836],"study_design_scores_gemma":[0.000081052356,0.000056198765,0.00024452453,0.0051635406,0.000052446143,0.00006205746,0.005735246,0.0017432843,0.0004355697,0.9285852,0.057783958,0.00005686024],"about_ca_topic_score_codex":0.008157768,"about_ca_topic_score_gemma":0.005963411,"teacher_disagreement_score":0.38927352,"about_ca_system_score_codex":0.027975805,"about_ca_system_score_gemma":0.067444734,"threshold_uncertainty_score":0.7531345},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13101174,0.010532823,0.033806995,0.7161484,0.0012958942,0.007416077,0.00084887916,0.0010059106,0.09793328],"genre_scores_gemma":[0.88604426,0.0040304186,0.054064047,0.029394025,0.0004647877,0.0034627542,0.00055663893,0.00013532054,0.02184788],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9168986,0.047753286,0.0022999037,0.0027753564,0.010080353,0.020192448],"domain_scores_gemma":[0.6414361,0.1346667,0.012606716,0.0148363225,0.085908495,0.110545695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1284056,0.0013999855,0.0013234944,0.0035149637,0.017730644,0.026109396,0.009519392,0.00865595,0.0111115705],"category_scores_gemma":[0.13692965,0.0012620636,0.0015637341,0.003050953,0.01609162,0.013527186,0.02010613,0.009652615,0.0010162808],"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":[0.0013945501,0.0038510931,0.1381132,0.0064295507,0.0006336836,0.0010771625,0.039458178,0.019659642,0.0028060644,0.19102855,0.2060759,0.38947245],"study_design_scores_gemma":[0.0014104272,0.0019732094,0.20763399,0.012959921,0.0003366297,0.00027428078,0.11730376,0.02500291,0.00546717,0.1683038,0.45841476,0.000919184],"about_ca_topic_score_codex":0.6959859,"about_ca_topic_score_gemma":0.8351393,"teacher_disagreement_score":0.3040141,"about_ca_system_score_codex":0.094450936,"about_ca_system_score_gemma":0.5357704,"threshold_uncertainty_score":0.6852927},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3444614,0.014510002,0.011661447,0.16503821,0.00091335183,0.00014999753,0.000471778,0.00015172266,0.46264204],"genre_scores_gemma":[0.9776162,0.0033313867,0.0032114324,0.002663534,0.000054087617,0.00007770439,0.00007343096,0.00004695979,0.0129253045],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9905516,0.0043642637,0.00028265125,0.0005956007,0.0022440446,0.0019618277],"domain_scores_gemma":[0.9854248,0.006630137,0.0011919233,0.0003881756,0.0040756953,0.0022893024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010684867,0.0006163932,0.00050671515,0.0031837213,0.02631627,0.017694164,0.0024514054,0.0027207744,0.0068807593],"category_scores_gemma":[0.025224004,0.0004388014,0.00046993975,0.005919489,0.016721731,0.007003175,0.005640355,0.0037649986,0.0004484],"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":[0.000089183486,0.00003076836,0.018640313,0.00035250187,0.000021185762,0.000617897,0.7096171,0.0009283615,0.0003215798,0.1949824,0.027426915,0.04697182],"study_design_scores_gemma":[0.00001232824,0.000016480713,0.02612198,0.0010754035,0.000037529666,0.00023168695,0.7807517,0.0009689188,0.00021861935,0.033922583,0.15656035,0.00008239407],"about_ca_topic_score_codex":0.98500466,"about_ca_topic_score_gemma":0.9884558,"teacher_disagreement_score":0.16185911,"about_ca_system_score_codex":0.16185911,"about_ca_system_score_gemma":0.1638336,"threshold_uncertainty_score":0.97212464},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28560364,0.025168236,0.35036567,0.18389592,0.0060154465,0.007889979,0.00012859567,0.0009209761,0.14001161],"genre_scores_gemma":[0.81491715,0.0054189744,0.1513219,0.0061670113,0.0009143997,0.0027216177,0.00011995846,0.0005348081,0.017884096],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.67273575,0.26655093,0.010742444,0.010143006,0.03488705,0.004940787],"domain_scores_gemma":[0.58430856,0.29531297,0.015306091,0.02781819,0.05849494,0.018759267],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3487143,0.0009962375,0.0021851114,0.013213468,0.025080418,0.03856056,0.0057510673,0.005222922,0.0030389067],"category_scores_gemma":[0.33300582,0.0013461855,0.0011605136,0.006613804,0.04780551,0.025513787,0.048658486,0.012372347,0.00081842317],"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":[0.000049666367,0.00025869324,0.0039120787,0.00049154565,0.000041574374,0.0007020994,0.66260976,0.00024929797,0.0011608236,0.12733327,0.008399781,0.19479144],"study_design_scores_gemma":[0.00004669828,0.00029465512,0.0024237183,0.002674666,0.000050359762,0.0010125067,0.57521224,0.0015663087,0.0020518438,0.1178761,0.2966071,0.00018384332],"about_ca_topic_score_codex":0.0025260793,"about_ca_topic_score_gemma":0.0031600946,"teacher_disagreement_score":0.3487143,"about_ca_system_score_codex":0.017509056,"about_ca_system_score_gemma":0.050376374,"threshold_uncertainty_score":0.80315125},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2576288,0.017702136,0.0055596284,0.5499521,0.0017471081,0.0002981408,0.00022460251,0.0002519258,0.16663565],"genre_scores_gemma":[0.974649,0.0037316333,0.001747725,0.011455495,0.0004673302,0.00009647942,0.000054413074,0.00006856426,0.0077293846],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7573222,0.19030944,0.008486597,0.0031616038,0.026446804,0.01427335],"domain_scores_gemma":[0.57995826,0.2555805,0.04428513,0.010658003,0.07616129,0.03335677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13876566,0.000293124,0.00064433715,0.0043022754,0.010823257,0.015535755,0.00205882,0.004335232,0.005122074],"category_scores_gemma":[0.26215458,0.0008135934,0.0005586016,0.0039569535,0.0074231997,0.0054753083,0.0091454405,0.007345812,0.0003585944],"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":[0.00050810014,0.00090605876,0.07684978,0.0015116784,0.00027488166,0.0011964253,0.102775216,0.0018172947,0.0008606412,0.18365769,0.19365966,0.43598256],"study_design_scores_gemma":[0.00012849912,0.00095701905,0.20663102,0.004068031,0.00024613537,0.0010196333,0.073488116,0.0024414903,0.0027450987,0.021974346,0.68568444,0.00061610655],"about_ca_topic_score_codex":0.12553325,"about_ca_topic_score_gemma":0.16107024,"teacher_disagreement_score":0.96111447,"about_ca_system_score_codex":0.038885545,"about_ca_system_score_gemma":0.07990568,"threshold_uncertainty_score":0.7338717},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76779056,0.010632845,0.0048575597,0.040029276,0.00049272226,0.001240768,0.0009397432,0.00034200057,0.17367458],"genre_scores_gemma":[0.99169075,0.0014998312,0.0020415823,0.0009172028,0.00002232486,0.00010246369,0.00014842894,0.000020751271,0.0035566273],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9352121,0.02688237,0.0025609294,0.0024533977,0.024672732,0.008218473],"domain_scores_gemma":[0.8531897,0.036678974,0.0093180295,0.0046141976,0.08361454,0.012584613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048776716,0.00036856873,0.00046355708,0.009379648,0.013637003,0.011270786,0.0025306335,0.0010606757,0.0020824198],"category_scores_gemma":[0.067933306,0.0005467661,0.00034284472,0.010105548,0.005767411,0.0020672744,0.006199929,0.0018259188,0.00017929498],"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":[0.00047137792,0.00050089083,0.13059857,0.0024018628,0.00017000706,0.0018815079,0.164674,0.0028408782,0.00280298,0.05614063,0.052831903,0.5846854],"study_design_scores_gemma":[0.000059872826,0.00047710678,0.30346605,0.002454115,0.00013915394,0.00064968935,0.3021006,0.0034200703,0.0045603523,0.005527913,0.37675965,0.0003853936],"about_ca_topic_score_codex":0.90068674,"about_ca_topic_score_gemma":0.946577,"teacher_disagreement_score":0.83632994,"about_ca_system_score_codex":0.16367005,"about_ca_system_score_gemma":0.34934962,"threshold_uncertainty_score":0.9700242},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083164836,0.31680295,0.0072662276,0.26610053,0.33932438,0.000093261304,0.0004188592,0.00016150417,0.0690007],"genre_scores_gemma":[0.018908022,0.30776227,0.006402916,0.06641916,0.5357692,0.00028753994,0.00069472304,0.00037684364,0.06337926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.991723,0.0033071728,0.0010011257,0.00084202434,0.0026671782,0.00045944564],"domain_scores_gemma":[0.9313262,0.051340837,0.0021764713,0.0018222864,0.011195264,0.0021388917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011868261,0.0011466738,0.0015976827,0.007803238,0.0033269897,0.015663648,0.0018015021,0.005763847,0.023214165],"category_scores_gemma":[0.038570452,0.00053070224,0.0012547456,0.011310069,0.0055180485,0.011093242,0.0032487493,0.012088342,0.008368863],"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":[0.000021537957,0.000039170023,0.0003461689,0.0006859389,0.000010404968,0.000057886224,0.0004948666,0.00016727905,0.000054646862,0.04450514,0.8804067,0.07321035],"study_design_scores_gemma":[0.0000037596242,0.000018036595,0.00051291595,0.0011459024,0.00000657814,0.00012715303,0.00046752865,0.00010456751,0.000030254017,0.0145166125,0.983052,0.000014657818],"about_ca_topic_score_codex":0.0023268457,"about_ca_topic_score_gemma":0.0027665852,"teacher_disagreement_score":0.98813176,"about_ca_system_score_codex":0.005897814,"about_ca_system_score_gemma":0.0041225255,"threshold_uncertainty_score":0.07765913},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019041049,0.004440729,0.0007428978,0.8807361,0.10786509,0.00018579894,0.0005812386,0.000076020246,0.005181655],"genre_scores_gemma":[0.0024945461,0.0015032098,0.0014919904,0.96359795,0.025823945,0.00046778962,0.0001504271,0.000044100692,0.0044259666],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9474186,0.017016329,0.008585069,0.0048066545,0.019501658,0.0026716413],"domain_scores_gemma":[0.7229509,0.13500041,0.009398303,0.0066193803,0.121233016,0.0047980277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04827169,0.0016479329,0.002285021,0.002684904,0.00394059,0.004199455,0.009051038,0.052904665,0.014214305],"category_scores_gemma":[0.3075944,0.001413231,0.0049364013,0.00258162,0.0072239046,0.0065339203,0.0037057402,0.046617985,0.011075372],"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":[0.000095569085,0.000013006266,0.00010813379,0.00069423206,0.000045832647,0.00008072898,0.00015637653,0.00004929586,0.00016656992,0.0050789965,0.986153,0.0073581906],"study_design_scores_gemma":[0.00039745963,0.00007811829,0.0018169743,0.008552784,0.0003493698,0.00026948433,0.0006212102,0.0003316573,0.0011442396,0.023226067,0.96300817,0.00020455939],"about_ca_topic_score_codex":0.033768687,"about_ca_topic_score_gemma":0.046865474,"teacher_disagreement_score":0.052904665,"about_ca_system_score_codex":0.010731395,"about_ca_system_score_gemma":0.03304887,"threshold_uncertainty_score":0.25528812},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080076255,0.4611766,0.0013371126,0.39370614,0.0021963879,0.00019674265,0.00088039413,0.00009173322,0.060338527],"genre_scores_gemma":[0.8227635,0.12702064,0.0020258042,0.039215177,0.00081733544,0.00014549564,0.0003117849,0.000092690774,0.0076075504],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92019963,0.02668166,0.0032106678,0.0029341094,0.039196007,0.007777805],"domain_scores_gemma":[0.7761813,0.07984625,0.015660865,0.0042164135,0.10932203,0.014773167],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0592538,0.00035466297,0.0014136188,0.006551497,0.00834055,0.014885169,0.0024601172,0.0023590804,0.0018614818],"category_scores_gemma":[0.19050789,0.0005003776,0.00060277537,0.014996127,0.0136041315,0.0041527185,0.0033488318,0.0040930347,0.00013157493],"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":[0.0006243026,0.00015826944,0.057361223,0.008351365,0.0007619956,0.00047853205,0.027002586,0.0016682663,0.00052399293,0.21371724,0.2213931,0.46795923],"study_design_scores_gemma":[0.00016083913,0.00025482956,0.22502472,0.021368895,0.000827176,0.0002553548,0.0284342,0.0013144076,0.0016972672,0.02755176,0.6926743,0.00043638755],"about_ca_topic_score_codex":0.98062205,"about_ca_topic_score_gemma":0.9863383,"teacher_disagreement_score":0.9407462,"about_ca_system_score_codex":0.19843285,"about_ca_system_score_gemma":0.4723044,"threshold_uncertainty_score":0.9297043},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039243763,0.0059467866,0.2171626,0.009574087,0.0011155767,0.0020421164,0.0011857519,0.0012951855,0.7577535],"genre_scores_gemma":[0.20374164,0.009836013,0.21482521,0.0024069757,0.0007134949,0.0044896277,0.0030522917,0.0006237206,0.560311],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9640311,0.019794594,0.0014541857,0.0028741397,0.010853627,0.0009923544],"domain_scores_gemma":[0.9680669,0.01232121,0.0015113951,0.009316034,0.007849338,0.00093519106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029214336,0.000978784,0.0011595716,0.0045860927,0.003055589,0.010166687,0.0021896889,0.0024577582,0.035896517],"category_scores_gemma":[0.040087745,0.00070968625,0.00050454534,0.0048334934,0.0032889207,0.0078008682,0.0064859125,0.0020462673,0.011611751],"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":[0.0000649642,0.00012439267,0.0009735858,0.00060503517,0.000021684462,0.00005488558,0.002488685,0.0008076142,0.0007659865,0.3142375,0.12516676,0.55468893],"study_design_scores_gemma":[0.000020228283,0.000085243955,0.0017255056,0.0010527872,0.000021943524,0.0001220891,0.0013240167,0.0015014574,0.002088808,0.13135368,0.8606714,0.00003270268],"about_ca_topic_score_codex":0.004341448,"about_ca_topic_score_gemma":0.007008619,"teacher_disagreement_score":0.035896517,"about_ca_system_score_codex":0.003963618,"about_ca_system_score_gemma":0.013147496,"threshold_uncertainty_score":0.15450203},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99860054,0.000109738605,0.00012837135,0.00013095645,0.0000036121044,0.00016745273,0.000053698357,0.0000058844676,0.0007998995],"genre_scores_gemma":[0.9960445,0.00040445421,0.002110508,0.000073578725,0.000006234069,0.00040083588,0.00029520516,0.0000044563767,0.00066019734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.993622,0.0023752109,0.0004486528,0.00025456882,0.0023793473,0.0009201386],"domain_scores_gemma":[0.98760974,0.0022115184,0.0037806032,0.00044711935,0.0036616225,0.002289371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01104071,0.00040103655,0.00040690013,0.0019869704,0.002167166,0.0023812945,0.0015879777,0.00065198774,0.00053736655],"category_scores_gemma":[0.015338298,0.00053139747,0.00058618264,0.0019321531,0.0012462854,0.00081028574,0.0016980926,0.0012235909,0.000108975444],"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":[0.0001059564,0.0014904633,0.9410955,0.00010916271,0.00004852717,0.000099011755,0.022328964,0.00025376104,0.00021077474,0.00009401301,0.00041662122,0.033747204],"study_design_scores_gemma":[0.00001651775,0.00048358273,0.97440684,0.000066007335,0.000021000937,0.000024191693,0.02354305,0.00035467654,0.00017042221,0.000046378624,0.00085124234,0.000016054182],"about_ca_topic_score_codex":0.3878176,"about_ca_topic_score_gemma":0.60175204,"teacher_disagreement_score":0.3878176,"about_ca_system_score_codex":0.013442501,"about_ca_system_score_gemma":0.015344369,"threshold_uncertainty_score":0.7711205},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030617567,0.99808216,0.0003514532,0.00044320885,0.00008042469,0.000029375418,0.000027971926,0.0000045799334,0.0006745398],"genre_scores_gemma":[0.0044263056,0.9943032,0.00079477247,0.00021269103,0.00009499476,0.000057734942,0.000039358893,0.000005106753,0.00006590821],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9845803,0.006508444,0.0036805845,0.0011432739,0.0037441934,0.00034327715],"domain_scores_gemma":[0.857755,0.1262142,0.0053807213,0.0017152412,0.008211971,0.0007228453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02333668,0.0013906752,0.0041464544,0.016396664,0.0009389213,0.0045441594,0.0021740184,0.002329042,0.0034860673],"category_scores_gemma":[0.061837863,0.00093128585,0.0021228206,0.018113242,0.0029253254,0.0046537756,0.0024009289,0.0019898063,0.0005159995],"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":[0.000095595526,0.000086301945,0.0011251137,0.23998241,0.0005982105,0.00012456409,0.00087112345,0.00048424004,0.00029540056,0.007730629,0.0055162995,0.74309015],"study_design_scores_gemma":[0.00004616699,0.0002443557,0.006436808,0.55128974,0.0032488906,0.00084314856,0.0018599471,0.00050572807,0.0008477698,0.010302963,0.42425877,0.00011564042],"about_ca_topic_score_codex":0.00524851,"about_ca_topic_score_gemma":0.008880314,"teacher_disagreement_score":0.02333668,"about_ca_system_score_codex":0.004908866,"about_ca_system_score_gemma":0.01402998,"threshold_uncertainty_score":0.123417616},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15597679,0.029888991,0.16022487,0.040484436,0.0025994761,0.0040179677,0.0048787086,0.00049235177,0.60143644],"genre_scores_gemma":[0.95414966,0.0072129387,0.028365579,0.0015749361,0.00029592428,0.0030922804,0.00074148574,0.00011691944,0.004450218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.8732661,0.090497635,0.0067988364,0.004151207,0.022188473,0.0030977228],"domain_scores_gemma":[0.88338464,0.08496131,0.013026809,0.0049871164,0.011895183,0.0017450002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059530612,0.0015863775,0.0011873563,0.009203728,0.002047702,0.011257616,0.0015232221,0.0024513076,0.009539082],"category_scores_gemma":[0.16302256,0.00043745994,0.0018865723,0.0058415444,0.010876529,0.009573197,0.008454396,0.0034454488,0.0006577182],"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":[0.0005076659,0.00050790654,0.024702417,0.006027138,0.0007413821,0.0001765454,0.007871564,0.007817643,0.0005657935,0.7739328,0.0066354913,0.17051359],"study_design_scores_gemma":[0.0002985804,0.0016963194,0.07662067,0.012939941,0.0015294635,0.00038406564,0.015833171,0.007518196,0.0067863325,0.7692204,0.106936455,0.00023645234],"about_ca_topic_score_codex":0.002679595,"about_ca_topic_score_gemma":0.0020928164,"teacher_disagreement_score":0.059530612,"about_ca_system_score_codex":0.010371127,"about_ca_system_score_gemma":0.010213242,"threshold_uncertainty_score":0.31483173},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073137325,0.094137765,0.05299905,0.6956951,0.065389566,0.01948575,0.0018857103,0.0014046778,0.06168868],"genre_scores_gemma":[0.18258785,0.13275804,0.26924005,0.15217026,0.023470808,0.123624966,0.010243248,0.003625163,0.10227972],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6399045,0.27148607,0.028034976,0.011287721,0.0354285,0.0138581935],"domain_scores_gemma":[0.62814856,0.14503232,0.028372856,0.03479933,0.09882365,0.06482333],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.42989692,0.0022022675,0.0033432215,0.0044424813,0.009526768,0.021979045,0.00676627,0.014183076,0.05274394],"category_scores_gemma":[0.3726482,0.0023680034,0.0029354694,0.00405842,0.008469992,0.01379334,0.032938402,0.018780986,0.012018052],"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":[0.0006233185,0.0010111579,0.0031204857,0.008145189,0.00030858445,0.0001801635,0.012812222,0.0004894725,0.0009914022,0.035703424,0.5162924,0.42032227],"study_design_scores_gemma":[0.00025344657,0.00035759475,0.003498672,0.02462576,0.000096273914,0.00009932259,0.0061447658,0.00058652693,0.0005791447,0.019915896,0.94372404,0.000118471355],"about_ca_topic_score_codex":0.0029979597,"about_ca_topic_score_gemma":0.0057457993,"teacher_disagreement_score":0.42989692,"about_ca_system_score_codex":0.013516067,"about_ca_system_score_gemma":0.09551035,"threshold_uncertainty_score":0.7030386},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04346855,0.029804766,0.40552318,0.19181998,0.003457002,0.0004191272,0.000094826646,0.00023761608,0.3251749],"genre_scores_gemma":[0.9022131,0.0059331986,0.07659367,0.007487084,0.0010445318,0.00053527014,0.000053691714,0.00013703562,0.0060023703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.961203,0.02908615,0.0011095693,0.002073773,0.005136043,0.001391524],"domain_scores_gemma":[0.94309974,0.04292735,0.0026576547,0.0038671414,0.005511049,0.0019371447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056127205,0.0011681736,0.001061493,0.009611467,0.0063239634,0.018360147,0.0027672458,0.007123732,0.0033946033],"category_scores_gemma":[0.041600417,0.0007108085,0.0009811892,0.0037675805,0.08653028,0.024104992,0.00905633,0.009564678,0.00043205716],"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":[0.0000065720265,0.00000676817,0.00013742756,0.00003789789,0.000002742671,0.000020424774,0.003975489,0.000102174636,0.000024172583,0.9906763,0.00040815733,0.0046019647],"study_design_scores_gemma":[0.000011515715,0.000026118656,0.00022562324,0.00036612386,0.0000076182932,0.00005938372,0.003169345,0.0011135844,0.00014811472,0.97166145,0.023194278,0.000016864951],"about_ca_topic_score_codex":0.004042775,"about_ca_topic_score_gemma":0.0027846803,"teacher_disagreement_score":0.9438728,"about_ca_system_score_codex":0.019386759,"about_ca_system_score_gemma":0.009844198,"threshold_uncertainty_score":0.29683256},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6934147,0.075187266,0.0021915564,0.16574864,0.000424567,0.0002556035,0.0014347502,0.00019181373,0.0611511],"genre_scores_gemma":[0.9555649,0.021307563,0.0030987859,0.003235246,0.00008670076,0.000051779632,0.0002685056,0.000034816254,0.016351778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99313337,0.0014272975,0.00023709926,0.0004978416,0.0023679545,0.002336451],"domain_scores_gemma":[0.96673757,0.0060042264,0.0020538007,0.0005613866,0.013244139,0.011398927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074516446,0.00034848478,0.0006290528,0.0030530454,0.010397564,0.008481044,0.002622184,0.0017857595,0.007308854],"category_scores_gemma":[0.014707227,0.00038307207,0.00043768287,0.015391616,0.00753836,0.002414022,0.003428149,0.0021545107,0.00021985064],"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":[0.0007711094,0.0007628333,0.2304759,0.0022225452,0.00016127701,0.00070333754,0.038027328,0.0057538585,0.00071879174,0.07381275,0.04695458,0.59963566],"study_design_scores_gemma":[0.0002273265,0.00048119947,0.681414,0.0030407421,0.00019214653,0.00029712453,0.12625854,0.0053172447,0.0009045464,0.013335617,0.16820422,0.00032726835],"about_ca_topic_score_codex":0.9967836,"about_ca_topic_score_gemma":0.99841905,"teacher_disagreement_score":0.20890777,"about_ca_system_score_codex":0.20890777,"about_ca_system_score_gemma":0.42734438,"threshold_uncertainty_score":0.91755486},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022940034,0.0033066869,0.00015443531,0.98744875,0.008739854,0.000009480034,0.000012155204,0.000004317776,0.00030128908],"genre_scores_gemma":[0.0011703765,0.0016306981,0.0006129353,0.97279793,0.023436822,0.00008312721,0.000008928337,0.000015006864,0.00024419028],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7156383,0.15583698,0.03786365,0.015658442,0.06849518,0.0065075764],"domain_scores_gemma":[0.21451348,0.68718386,0.017895523,0.007893115,0.060633298,0.011880726],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20746717,0.0022059283,0.00744636,0.0077439058,0.013700904,0.02159744,0.015042326,0.15258375,0.005872497],"category_scores_gemma":[0.58931345,0.0030685544,0.0051102103,0.008555572,0.05039628,0.022745294,0.013946311,0.17447594,0.004396365],"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":[0.00008061361,0.000025758238,0.00018072898,0.0010719701,0.00014277929,0.0002225637,0.0008543716,0.00007564445,0.00004580946,0.024166862,0.9622055,0.010927278],"study_design_scores_gemma":[0.001008398,0.00011018612,0.0008084471,0.024706662,0.00062393025,0.00087409426,0.0029678037,0.0008746705,0.00035997192,0.1621382,0.80516636,0.00036128503],"about_ca_topic_score_codex":0.019497067,"about_ca_topic_score_gemma":0.043210898,"teacher_disagreement_score":0.7925328,"about_ca_system_score_codex":0.032406133,"about_ca_system_score_gemma":0.056710757,"threshold_uncertainty_score":0.9773341},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5218914,0.08301069,0.18631394,0.0140174925,0.0028952642,0.03659081,0.0018487133,0.00046335027,0.15296832],"genre_scores_gemma":[0.82247335,0.014654728,0.14931427,0.0010993073,0.00028769183,0.009540528,0.00044634158,0.000073397634,0.0021104433],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7264995,0.23779276,0.012876938,0.0032847452,0.018092956,0.0014531526],"domain_scores_gemma":[0.55418634,0.39119163,0.017371546,0.0072125755,0.027650539,0.0023873085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17137894,0.0016478365,0.0020297011,0.0067424276,0.0015791466,0.006889093,0.0017992423,0.0019223016,0.0069193286],"category_scores_gemma":[0.32965532,0.0004090881,0.0019170493,0.0045275334,0.0035894576,0.0054874527,0.0039524552,0.0012649894,0.00041919132],"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":[0.0015708002,0.0017373563,0.022199847,0.038472757,0.0037301008,0.00019385299,0.012938147,0.008654835,0.0015797538,0.07033233,0.0062949113,0.8322953],"study_design_scores_gemma":[0.004553753,0.047618188,0.08520885,0.15583383,0.018298315,0.0007481138,0.08245593,0.04097948,0.031188464,0.31658518,0.2156029,0.0009270485],"about_ca_topic_score_codex":0.001468389,"about_ca_topic_score_gemma":0.0033836174,"teacher_disagreement_score":0.17137894,"about_ca_system_score_codex":0.00747007,"about_ca_system_score_gemma":0.010281045,"threshold_uncertainty_score":0.9063493},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89063674,0.0017641794,0.0006142843,0.035648353,0.0001282749,0.00005543891,0.00033080368,0.000024283692,0.07079772],"genre_scores_gemma":[0.9923879,0.00050877983,0.00018659995,0.000908712,0.0000096626045,0.0000140335815,0.00006413902,0.0000122723095,0.005907981],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99383885,0.0012512176,0.00013634327,0.00045958225,0.0015283453,0.0027857216],"domain_scores_gemma":[0.9897412,0.0022102313,0.0007835755,0.00025922622,0.0040323786,0.0029733987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048204507,0.0002716235,0.0005136379,0.0027773224,0.021650312,0.010693142,0.0022171163,0.001986178,0.0062050135],"category_scores_gemma":[0.016125767,0.00035738113,0.00036688446,0.0063428967,0.010520147,0.004333102,0.004767655,0.0026193848,0.0002940199],"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":[0.00016986292,0.00023532672,0.25118262,0.00026456674,0.00007133769,0.0010066152,0.5087668,0.0013894762,0.0007105737,0.12179846,0.049933262,0.06447099],"study_design_scores_gemma":[0.00002592515,0.000027954085,0.19595948,0.0004132672,0.000049018297,0.00012218578,0.7164339,0.0009823064,0.0002588351,0.0062357704,0.07936566,0.00012579297],"about_ca_topic_score_codex":0.996732,"about_ca_topic_score_gemma":0.9989968,"teacher_disagreement_score":0.13366206,"about_ca_system_score_codex":0.13366206,"about_ca_system_score_gemma":0.16398185,"threshold_uncertainty_score":0.96979064},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0126497215,0.006272628,0.0015850047,0.6796927,0.15869196,0.00039076878,0.00095958705,0.00045263107,0.13930507],"genre_scores_gemma":[0.07027748,0.009697849,0.0033257352,0.134782,0.044308443,0.00048598542,0.00078352325,0.0003489674,0.73599],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924759,0.0011724121,0.00033085237,0.00050366635,0.0034972148,0.0020200543],"domain_scores_gemma":[0.8389705,0.0043441523,0.0031211271,0.0018778357,0.04660404,0.10508244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073429034,0.00047107754,0.0011298674,0.0026990473,0.00646247,0.008173648,0.0017048125,0.0044349357,0.2771303],"category_scores_gemma":[0.04255653,0.00042801705,0.0007844899,0.0017746058,0.0019914412,0.0043097516,0.0030095219,0.005282389,0.088385805],"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":[0.00007569912,0.00015734544,0.0039145583,0.00007823358,0.000016113878,0.0001382592,0.00016193793,0.000046829096,0.000110478526,0.00087282894,0.9388111,0.055616546],"study_design_scores_gemma":[0.0000444525,0.00010507481,0.0073265224,0.00028620972,0.000024166999,0.0003912643,0.0027094658,0.0002444757,0.00017691875,0.0015011,0.9871442,0.000046090787],"about_ca_topic_score_codex":0.01995928,"about_ca_topic_score_gemma":0.05049269,"teacher_disagreement_score":0.2771303,"about_ca_system_score_codex":0.0055481065,"about_ca_system_score_gemma":0.03605946,"threshold_uncertainty_score":0.9270932},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52533585,0.0754511,0.0006691544,0.31600863,0.0021481172,0.0012018606,0.0047437963,0.0001278317,0.07431375],"genre_scores_gemma":[0.9487757,0.027824832,0.0010184678,0.010897509,0.00027824778,0.00030764285,0.0011941944,0.00002624105,0.00967715],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9837847,0.004484819,0.0006796547,0.0007472157,0.006388605,0.0039150985],"domain_scores_gemma":[0.9225563,0.008592451,0.008826336,0.0012497382,0.03292492,0.025850276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013487886,0.00025706892,0.00060301844,0.0025712617,0.005438718,0.005502438,0.0026977244,0.0018022285,0.004619983],"category_scores_gemma":[0.050867554,0.00050686125,0.00045035442,0.0048270663,0.0023692811,0.0021004125,0.0018601613,0.0018465618,0.0005989576],"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":[0.00044047626,0.0006420632,0.5466424,0.002473465,0.00019011562,0.00017191393,0.01025169,0.0002761961,0.00042428478,0.0026829208,0.13504298,0.30076158],"study_design_scores_gemma":[0.00012009852,0.00022597791,0.91730314,0.0020381233,0.00015306158,0.00005413084,0.013332464,0.00015242923,0.0002668263,0.00032653887,0.06597256,0.00005453791],"about_ca_topic_score_codex":0.9195347,"about_ca_topic_score_gemma":0.98139924,"teacher_disagreement_score":0.08046532,"about_ca_system_score_codex":0.07896728,"about_ca_system_score_gemma":0.25233176,"threshold_uncertainty_score":0.57295036},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9541515,0.00045279245,0.00037644335,0.0062594498,0.00008083464,0.00039414543,0.0017702959,0.0000802632,0.03643423],"genre_scores_gemma":[0.963293,0.00034633378,0.0005349492,0.0006182422,0.000023823008,0.00022348133,0.00095458666,0.000023118098,0.0339825],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99685186,0.00033998245,0.0000663843,0.00015278958,0.0008426633,0.0017462912],"domain_scores_gemma":[0.99081516,0.0006729213,0.0006562094,0.00020466493,0.0024284858,0.0052226004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021300896,0.00018580718,0.000393898,0.0010965713,0.009024065,0.0029751826,0.0017283378,0.000980211,0.004001753],"category_scores_gemma":[0.006728851,0.0004933658,0.00026261862,0.0015204548,0.0015278705,0.0010834818,0.0031205409,0.0021613447,0.00059355795],"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":[0.0012907888,0.0021015725,0.4503247,0.0004040387,0.000046655136,0.001507392,0.22671627,0.0006505831,0.0036774168,0.0059180143,0.062051494,0.2453111],"study_design_scores_gemma":[0.000027163835,0.0003693355,0.8518199,0.0001274665,0.000011552273,0.000062118415,0.07708206,0.00022904071,0.00057077565,0.00028239493,0.069381945,0.00003624002],"about_ca_topic_score_codex":0.96869385,"about_ca_topic_score_gemma":0.9917354,"teacher_disagreement_score":0.064060375,"about_ca_system_score_codex":0.064060375,"about_ca_system_score_gemma":0.08111125,"threshold_uncertainty_score":0.46479273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.818704,0.0030586997,0.0058774995,0.061878767,0.00011258176,0.00085246324,0.00013187899,0.000060757295,0.10932331],"genre_scores_gemma":[0.991338,0.00067654025,0.0016663703,0.00071916997,0.00001083073,0.00007168141,0.00001854144,0.000011624344,0.0054871673],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96792746,0.018192258,0.001113361,0.0017109944,0.0047760946,0.006279923],"domain_scores_gemma":[0.9421425,0.037846256,0.003918141,0.0014726303,0.005881826,0.008738665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031192757,0.00037262455,0.00057562086,0.0025641248,0.026623415,0.013538949,0.0022905183,0.0028728435,0.003408628],"category_scores_gemma":[0.044618532,0.00066024734,0.0003263051,0.0040325257,0.018177794,0.0032061536,0.010650285,0.0027618979,0.0002208806],"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":[0.00032684626,0.0001859471,0.06994063,0.00068610447,0.00010637002,0.0043033357,0.748411,0.002353666,0.0029899601,0.075915195,0.007852709,0.08692822],"study_design_scores_gemma":[0.0000932313,0.00016998601,0.05438307,0.0009058985,0.00013699723,0.00033279712,0.6229046,0.004089001,0.0018396734,0.028551778,0.28639886,0.00019411532],"about_ca_topic_score_codex":0.86580974,"about_ca_topic_score_gemma":0.92327005,"teacher_disagreement_score":0.8632598,"about_ca_system_score_codex":0.1367402,"about_ca_system_score_gemma":0.19661908,"threshold_uncertainty_score":0.9921242},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77800936,0.0007470694,0.0047289245,0.015555529,0.00009634638,0.00016223054,0.00006805846,0.000048755013,0.2005837],"genre_scores_gemma":[0.99560416,0.00009952423,0.00072014815,0.00014888028,0.0000054060943,0.000009488742,0.000011689597,0.0000045169395,0.0033961313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.988009,0.006100044,0.00029018184,0.0008364954,0.0021195812,0.0026447687],"domain_scores_gemma":[0.986087,0.006837763,0.0014741936,0.00039529387,0.0019748406,0.0032308192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010122845,0.00031004392,0.00029719956,0.0016339833,0.012913809,0.011392576,0.0020722512,0.001448076,0.009120563],"category_scores_gemma":[0.013986636,0.00027628458,0.00035284186,0.0021683571,0.018390803,0.0022043956,0.0051559703,0.002743555,0.0003069791],"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":[0.0001989898,0.00044962048,0.09792596,0.0002985374,0.0000820304,0.004925715,0.25222015,0.007714691,0.0024452312,0.5169988,0.01302423,0.10371598],"study_design_scores_gemma":[0.00003635262,0.00015124984,0.0923168,0.00067410344,0.000031205203,0.0003047747,0.57873905,0.005307701,0.0011980118,0.1404528,0.18065205,0.00013596275],"about_ca_topic_score_codex":0.2160043,"about_ca_topic_score_gemma":0.29445097,"teacher_disagreement_score":0.2160043,"about_ca_system_score_codex":0.029378118,"about_ca_system_score_gemma":0.039490443,"threshold_uncertainty_score":0.42949408},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77534413,0.007968381,0.016990274,0.030715823,0.00071565935,0.00040002455,0.000860069,0.00017262052,0.16683294],"genre_scores_gemma":[0.97139263,0.0030387081,0.0040494786,0.0021467947,0.00008916846,0.00025207805,0.00022601646,0.00009938282,0.01870572],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98641336,0.006867943,0.00062255835,0.001444995,0.0027952718,0.0018559607],"domain_scores_gemma":[0.9562917,0.024846682,0.0054496527,0.0018795008,0.007396642,0.0041359486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016660899,0.0006033743,0.0005973968,0.0017666774,0.005085733,0.007391268,0.0011723695,0.0013066261,0.021458618],"category_scores_gemma":[0.03171562,0.0005746599,0.00074155396,0.0023787823,0.0059808204,0.0046634204,0.004171714,0.0029820479,0.0019309408],"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":[0.0004411003,0.00035183635,0.28766066,0.0030822973,0.00031972193,0.000660533,0.44723094,0.00070442405,0.0025829116,0.04458426,0.012449725,0.1999315],"study_design_scores_gemma":[0.000034345623,0.0003202099,0.58772993,0.00305286,0.00022164019,0.00022284543,0.28355542,0.00053664966,0.0013436172,0.006935758,0.115933195,0.00011358972],"about_ca_topic_score_codex":0.15679672,"about_ca_topic_score_gemma":0.35554346,"teacher_disagreement_score":0.15679672,"about_ca_system_score_codex":0.013277567,"about_ca_system_score_gemma":0.029573673,"threshold_uncertainty_score":0.3117681},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78951937,0.004573027,0.001989419,0.09865436,0.00045195295,0.000489733,0.0015470189,0.00018124796,0.10259387],"genre_scores_gemma":[0.98054814,0.0015848773,0.001968333,0.003098686,0.000058012054,0.00015599243,0.00059884385,0.000026043655,0.011961188],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9927127,0.0010102257,0.00013951029,0.00029835032,0.0014720132,0.0043671173],"domain_scores_gemma":[0.96424496,0.005677519,0.001604199,0.0005260006,0.00837274,0.019574612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074962815,0.00028985782,0.00043932936,0.0030304473,0.011025227,0.0050371718,0.0025472303,0.0014270241,0.010763335],"category_scores_gemma":[0.024018262,0.0003611114,0.00034080393,0.005360138,0.0036036032,0.0020842429,0.0056372853,0.0028543116,0.0006783521],"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":[0.00043137014,0.0010786718,0.22522908,0.001981417,0.00003335267,0.0009836078,0.12760127,0.0015546404,0.002557172,0.055119243,0.07550098,0.5079292],"study_design_scores_gemma":[0.000046163645,0.00029410032,0.5536153,0.0020714786,0.000026534035,0.00023747161,0.19726665,0.0016830887,0.001209738,0.008412374,0.23507148,0.000065648885],"about_ca_topic_score_codex":0.91509986,"about_ca_topic_score_gemma":0.96481055,"teacher_disagreement_score":0.08490014,"about_ca_system_score_codex":0.07807923,"about_ca_system_score_gemma":0.36567837,"threshold_uncertainty_score":0.5665071},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08905492,0.049969826,0.010211345,0.08370468,0.001142737,0.0001968598,0.0041129924,0.00027749134,0.7613292],"genre_scores_gemma":[0.7402375,0.04030591,0.011741277,0.0034099433,0.00040392525,0.00007750078,0.0019839308,0.00020129184,0.2016388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920908,0.0009315666,0.00016166571,0.00029469535,0.0055828844,0.0009383574],"domain_scores_gemma":[0.9936947,0.0013400671,0.00043309017,0.0001734426,0.0036239533,0.0007346979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051111514,0.0006917465,0.0005093747,0.0021549975,0.0027406265,0.0083704535,0.0019260233,0.0014076212,0.0037930862],"category_scores_gemma":[0.01124172,0.00028319348,0.00035905722,0.006115096,0.0038147348,0.0025431942,0.00088444917,0.0012593739,0.0008158778],"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":[0.000084123094,0.000097701544,0.04176781,0.00096178893,0.00006885329,0.00010092962,0.0052735265,0.00604625,0.00076463836,0.11138654,0.26704103,0.56640697],"study_design_scores_gemma":[0.000023814384,0.00016374074,0.3445357,0.0029254463,0.00014261102,0.00011896397,0.016290078,0.011810375,0.002665251,0.049486768,0.57160115,0.00023602392],"about_ca_topic_score_codex":0.9859309,"about_ca_topic_score_gemma":0.99412423,"teacher_disagreement_score":0.8705857,"about_ca_system_score_codex":0.12941433,"about_ca_system_score_gemma":0.17933409,"threshold_uncertainty_score":0.9389711},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022386951,0.03175883,0.11091693,0.021010637,0.00054103945,0.0005731241,0.00022129115,0.00008319012,0.812508],"genre_scores_gemma":[0.79469347,0.034588426,0.12563637,0.0028952612,0.00026033667,0.0027642602,0.00025361328,0.00012286473,0.038785398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9933206,0.005266482,0.00012639369,0.00029906872,0.0006021539,0.00038537662],"domain_scores_gemma":[0.99574775,0.00350859,0.0001330969,0.00016496688,0.00022657738,0.00021906583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008400782,0.00095330505,0.00057158124,0.003691374,0.004793611,0.00932016,0.0017563986,0.0020715443,0.005702235],"category_scores_gemma":[0.0036120554,0.0003383771,0.0006447438,0.0064025656,0.024323182,0.009713493,0.0061615705,0.0027441538,0.00035748642],"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":[0.000003437178,0.000012784802,0.00024797308,0.00019640638,0.0000057302937,0.000108083645,0.032451764,0.00037102148,0.00005490419,0.9481223,0.0021250097,0.016300593],"study_design_scores_gemma":[0.000007752748,0.000029573883,0.0010646066,0.0012075048,0.000007671331,0.0002502249,0.07312637,0.0008121309,0.00016725276,0.71625525,0.20704629,0.000025424695],"about_ca_topic_score_codex":0.009544837,"about_ca_topic_score_gemma":0.014489335,"teacher_disagreement_score":0.010073773,"about_ca_system_score_codex":0.010073773,"about_ca_system_score_gemma":0.008551407,"threshold_uncertainty_score":0.07309061},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11600976,0.017483542,0.1397346,0.3625353,0.0074124113,0.0007611119,0.0006322947,0.0008651729,0.35456586],"genre_scores_gemma":[0.8790617,0.0051652407,0.025782235,0.010493573,0.003373641,0.0006482105,0.000243978,0.00050255196,0.07472886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8654219,0.08092919,0.0036936563,0.009011139,0.036942042,0.004002099],"domain_scores_gemma":[0.684023,0.22842075,0.016907174,0.025944673,0.037035473,0.007668953],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.049791504,0.0011030104,0.0009891269,0.0051237973,0.016572788,0.026394606,0.0043798243,0.011700236,0.015213669],"category_scores_gemma":[0.18950728,0.00066586916,0.0011542459,0.0071611707,0.029394645,0.024212126,0.016261565,0.010774459,0.0030654985],"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":[0.00016800832,0.00021326797,0.0038885365,0.00088794477,0.0000882729,0.0013734513,0.26274973,0.00090569624,0.0012081703,0.6184627,0.044591524,0.06546266],"study_design_scores_gemma":[0.00006623641,0.000091847876,0.0036810613,0.00091198576,0.00003864564,0.00088513875,0.09490445,0.0011312284,0.0009958566,0.06780235,0.82942533,0.00006579816],"about_ca_topic_score_codex":0.024508793,"about_ca_topic_score_gemma":0.018897643,"teacher_disagreement_score":0.9502085,"about_ca_system_score_codex":0.018135432,"about_ca_system_score_gemma":0.019345593,"threshold_uncertainty_score":0.26332575},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011520536,0.64914644,0.028545616,0.22772178,0.019758668,0.00023047072,0.0027199383,0.0017000117,0.069025],"genre_scores_gemma":[0.027236512,0.66812795,0.052488115,0.03685171,0.0060548275,0.00053976814,0.0023211685,0.0014036256,0.20497636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956821,0.0011447738,0.00054065435,0.00030685897,0.0021139462,0.00021165103],"domain_scores_gemma":[0.9728717,0.010712412,0.0013176949,0.00072617125,0.012362441,0.0020096186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013154328,0.0012672528,0.00090752373,0.00452403,0.0019697056,0.0049699056,0.0020512412,0.0028658393,0.032774303],"category_scores_gemma":[0.039027292,0.0012600446,0.0005175977,0.0044668764,0.0020682733,0.0063346825,0.0023380893,0.0052202544,0.028641416],"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":[0.00003126838,0.000016601365,0.00033819585,0.00041228492,0.0000061360765,0.000040269115,0.0005470156,0.00008552169,0.00010911469,0.0017567016,0.7713256,0.22533138],"study_design_scores_gemma":[0.00001818821,0.000025407247,0.0027747229,0.0029585485,0.000026817084,0.00019394522,0.0010398615,0.00013012959,0.000462247,0.006458632,0.985852,0.00005958278],"about_ca_topic_score_codex":0.07289367,"about_ca_topic_score_gemma":0.21496566,"teacher_disagreement_score":0.07289367,"about_ca_system_score_codex":0.0036352768,"about_ca_system_score_gemma":0.017982438,"threshold_uncertainty_score":0.14493877},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8822368,0.0003487477,0.04394875,0.003445611,0.00003846385,0.00274883,0.0002198245,0.00009743747,0.06691554],"genre_scores_gemma":[0.9510813,0.00033030234,0.045368157,0.00016551295,0.0000054023135,0.0011038707,0.00007774366,0.000027602648,0.001840088],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97632295,0.020839883,0.00043523894,0.00038622582,0.0013056366,0.00070995337],"domain_scores_gemma":[0.96193886,0.032272056,0.001213134,0.0015389154,0.0023098136,0.0007271689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027844746,0.0005846195,0.00042610487,0.0020500058,0.004964511,0.003550044,0.0024054248,0.0020917512,0.0047271866],"category_scores_gemma":[0.031422447,0.0004282472,0.00057920086,0.0031812328,0.0040582195,0.0049137734,0.003516927,0.0029539468,0.0003068074],"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":[0.0015396802,0.016067805,0.061624248,0.001911658,0.0001258595,0.010299442,0.25355795,0.06347058,0.0028998428,0.22914338,0.008288638,0.35107085],"study_design_scores_gemma":[0.0011460172,0.008113258,0.034675814,0.0026241078,0.00032896284,0.0027052301,0.5698121,0.19174159,0.012806425,0.06954271,0.106161796,0.00034192012],"about_ca_topic_score_codex":0.030845435,"about_ca_topic_score_gemma":0.058396425,"teacher_disagreement_score":0.030845435,"about_ca_system_score_codex":0.014240426,"about_ca_system_score_gemma":0.009459924,"threshold_uncertainty_score":0},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02344108,0.037724316,0.0023072336,0.10600616,0.0006212652,0.00009141383,0.0007906354,0.0001658851,0.828852],"genre_scores_gemma":[0.842692,0.0569438,0.0060273656,0.011282569,0.00055981387,0.0002304443,0.0008893748,0.000167499,0.08120711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98531485,0.0034718702,0.00022772368,0.00044908494,0.005333059,0.0052033523],"domain_scores_gemma":[0.985967,0.0037048054,0.0004696339,0.0004928527,0.006032793,0.0033329355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007261131,0.00047575723,0.0007904416,0.0105819255,0.018913643,0.013529584,0.0027531048,0.0029669406,0.015239144],"category_scores_gemma":[0.016081184,0.00043610527,0.00044491192,0.027669238,0.010402063,0.004341067,0.004035545,0.0032492557,0.0005119006],"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":[0.000038758117,0.000081933715,0.0029207584,0.00047645636,0.000014209473,0.00014582227,0.007554836,0.0013753505,0.000089514375,0.8299914,0.05866822,0.09864273],"study_design_scores_gemma":[0.000017942146,0.00003338507,0.01639049,0.0012643015,0.000035031524,0.00007839759,0.021143299,0.0010362812,0.00022512143,0.028310059,0.93141115,0.0000545177],"about_ca_topic_score_codex":0.99039114,"about_ca_topic_score_gemma":0.9939926,"teacher_disagreement_score":0.7526443,"about_ca_system_score_codex":0.24735568,"about_ca_system_score_gemma":0.37675878,"threshold_uncertainty_score":0.87296075},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089242106,0.5374131,0.052849714,0.3135896,0.025307054,0.00060377957,0.0015463007,0.0015670276,0.0662309],"genre_scores_gemma":[0.033575352,0.58020514,0.13993038,0.080670536,0.013683866,0.0022517694,0.0014717946,0.0021860874,0.14602508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98788273,0.0046106125,0.0014540979,0.0006884871,0.0050887223,0.00027536316],"domain_scores_gemma":[0.8912484,0.058602925,0.0055622943,0.0033307518,0.03706487,0.004190827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0331716,0.0018836823,0.0013073045,0.0053381925,0.0022238777,0.006149715,0.0031539297,0.0054361317,0.021361375],"category_scores_gemma":[0.094535194,0.0015714121,0.0007171473,0.006109384,0.0056455475,0.006535431,0.003080223,0.008069312,0.016398972],"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":[0.000047616213,0.00001759582,0.0005014928,0.0010933289,0.000015257422,0.000057315843,0.000507915,0.00023370206,0.00018366503,0.007862395,0.73595864,0.25352108],"study_design_scores_gemma":[0.000029011031,0.000042716558,0.0024667645,0.008535783,0.000051788433,0.00023425803,0.0007247984,0.00043995806,0.00067140604,0.026165862,0.96054274,0.00009488287],"about_ca_topic_score_codex":0.07843633,"about_ca_topic_score_gemma":0.18023331,"teacher_disagreement_score":0.07843633,"about_ca_system_score_codex":0.007228211,"about_ca_system_score_gemma":0.02296058,"threshold_uncertainty_score":0.17543036},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28333142,0.014740713,0.19508094,0.33817166,0.0051439963,0.017979337,0.00030904886,0.0008169795,0.1444258],"genre_scores_gemma":[0.8363304,0.0035290075,0.12774415,0.015638055,0.0007229202,0.010518271,0.00007537909,0.00021500963,0.0052268077],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.4068881,0.48832107,0.030412488,0.0081513915,0.057227492,0.008999411],"domain_scores_gemma":[0.34667522,0.41796467,0.021191534,0.037192732,0.16483739,0.012138437],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5871889,0.0008533945,0.0018507456,0.004591893,0.015231018,0.018641217,0.007853328,0.00336508,0.0040527517],"category_scores_gemma":[0.56193495,0.0010666095,0.0011739263,0.0036179998,0.018389953,0.011212183,0.01625092,0.008165898,0.00060052006],"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":[0.0006706282,0.001965955,0.037973758,0.0065253573,0.00071409927,0.0008546591,0.33695805,0.00615229,0.0021423865,0.09436827,0.023091808,0.48858273],"study_design_scores_gemma":[0.0010137055,0.003058686,0.08268696,0.02514409,0.00055034325,0.000979626,0.47223204,0.014309101,0.0057634925,0.19815919,0.1952512,0.00085162814],"about_ca_topic_score_codex":0.081226304,"about_ca_topic_score_gemma":0.14845964,"teacher_disagreement_score":0.97126824,"about_ca_system_score_codex":0.028731737,"about_ca_system_score_gemma":0.11401515,"threshold_uncertainty_score":0.5090696},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2865761,0.03187551,0.0047138445,0.43624747,0.002336151,0.00034029994,0.02210722,0.0013240676,0.21447942],"genre_scores_gemma":[0.81987,0.021944968,0.008862607,0.03510492,0.00075013493,0.000109725246,0.006880019,0.00033825843,0.106139384],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9832303,0.0013288502,0.00078081904,0.0010321315,0.009931868,0.003696006],"domain_scores_gemma":[0.90455765,0.006170514,0.0036176536,0.00074232975,0.07082412,0.014087763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0115644755,0.00041114455,0.00055690494,0.0070853964,0.0067968816,0.0109763825,0.002935369,0.0027972015,0.011348932],"category_scores_gemma":[0.0294919,0.00056543923,0.0009845978,0.012790778,0.003005933,0.0025014826,0.0018446057,0.004392626,0.0010414489],"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":[0.0005299173,0.00047900478,0.22196925,0.0010990497,0.00020994323,0.00031225325,0.0031069587,0.007746831,0.0017956053,0.12781687,0.3688418,0.26609254],"study_design_scores_gemma":[0.00004432577,0.00009687826,0.37885085,0.00083926343,0.00010045683,0.00012704264,0.004998767,0.0064668315,0.0019238341,0.003835229,0.60256785,0.00014870719],"about_ca_topic_score_codex":0.9960872,"about_ca_topic_score_gemma":0.9977791,"teacher_disagreement_score":0.74008405,"about_ca_system_score_codex":0.25991595,"about_ca_system_score_gemma":0.47397614,"threshold_uncertainty_score":0.8583926},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012552812,0.005591004,0.0017033379,0.98132724,0.002464789,0.000024266626,0.000016714845,0.000015846457,0.0076015103],"genre_scores_gemma":[0.19773504,0.010745538,0.009010968,0.7674169,0.008777197,0.00044465024,0.000040527044,0.00022542817,0.005603733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7031562,0.21884526,0.008990664,0.01551701,0.038521085,0.014969783],"domain_scores_gemma":[0.6116119,0.3389685,0.0074475543,0.011605735,0.019264316,0.011102047],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26596406,0.0017690968,0.0022386878,0.0042389277,0.025079584,0.047223255,0.009240356,0.05518879,0.006214939],"category_scores_gemma":[0.22918287,0.0018250212,0.0034337477,0.0046733087,0.18418688,0.0675488,0.025456728,0.08914042,0.0015138952],"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":[0.0000845835,0.00007002002,0.00060272694,0.0004810719,0.00003189423,0.0004841348,0.047522426,0.00036862592,0.0002886694,0.8676601,0.07177733,0.010628334],"study_design_scores_gemma":[0.00010964572,0.00006588692,0.000721295,0.0019541339,0.00003062256,0.00039632732,0.05081776,0.0004353045,0.0004730294,0.53249097,0.41238657,0.000118445336],"about_ca_topic_score_codex":0.016750395,"about_ca_topic_score_gemma":0.018824453,"teacher_disagreement_score":0.73403597,"about_ca_system_score_codex":0.045280542,"about_ca_system_score_gemma":0.043600142,"threshold_uncertainty_score":0.905197},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49288988,0.0061982335,0.14417197,0.011743255,0.00054413447,0.0032625224,0.00018428145,0.00083794736,0.3401677],"genre_scores_gemma":[0.897687,0.0020164533,0.09461185,0.00033980337,0.00009136565,0.0013766751,0.000052800075,0.00004598546,0.0037779522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92377615,0.06873001,0.0016746824,0.0006608452,0.004118687,0.001039712],"domain_scores_gemma":[0.9269558,0.059953183,0.0027790589,0.0024235845,0.0066613755,0.0012270291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040325414,0.00054618926,0.0005086789,0.004256965,0.002406368,0.0070481533,0.0009197591,0.0008206497,0.006018867],"category_scores_gemma":[0.07569426,0.00027906563,0.00045435078,0.0024245924,0.0022405973,0.0044068336,0.0058155884,0.0010947979,0.0005666642],"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":[0.000656542,0.001328382,0.019646563,0.002564482,0.00014662153,0.00081589,0.079508565,0.002610979,0.004532249,0.05547404,0.009444523,0.8232713],"study_design_scores_gemma":[0.0010128289,0.007976346,0.07431842,0.017561372,0.00083627226,0.0021986535,0.19162624,0.018152883,0.03501315,0.1288803,0.52189326,0.0005301793],"about_ca_topic_score_codex":0.003059483,"about_ca_topic_score_gemma":0.0046995385,"teacher_disagreement_score":0.040325414,"about_ca_system_score_codex":0.0035810338,"about_ca_system_score_gemma":0.005718715,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6126487,0.009790704,0.21048838,0.010711033,0.0009717806,0.03501895,0.00043357056,0.00037719987,0.11955962],"genre_scores_gemma":[0.77704227,0.0031687808,0.20389077,0.0005461882,0.00013882718,0.011983378,0.00013287015,0.000035943824,0.003060865],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.90310895,0.083094686,0.003328466,0.0008851378,0.008391946,0.0011908032],"domain_scores_gemma":[0.9627739,0.02057349,0.0020051359,0.0010702609,0.01153127,0.0020459127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03848451,0.0007903862,0.0009482919,0.005627228,0.003828477,0.006440802,0.002181673,0.0013649357,0.0026569106],"category_scores_gemma":[0.052450668,0.0003608956,0.0011091776,0.0027416328,0.0032435006,0.0033261152,0.0052529676,0.0021982556,0.00033712262],"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":[0.00052037823,0.0040962747,0.0421467,0.0053872247,0.00046205957,0.00077620585,0.04216458,0.003940595,0.0020043897,0.02923772,0.0075933374,0.8616705],"study_design_scores_gemma":[0.0026673188,0.03263333,0.18805116,0.019391764,0.0027470586,0.0057828627,0.41422194,0.053485803,0.028538547,0.09493628,0.15674554,0.0007984168],"about_ca_topic_score_codex":0.0040392205,"about_ca_topic_score_gemma":0.009567687,"teacher_disagreement_score":0.03848451,"about_ca_system_score_codex":0.0056648534,"about_ca_system_score_gemma":0.01481225,"threshold_uncertainty_score":0.20352799},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003335113,0.002725084,0.6992628,0.008513038,0.0019770171,0.10232821,0.017019767,0.0055866055,0.15925243],"genre_scores_gemma":[0.005310185,0.0016121467,0.83113927,0.0017085025,0.000072933995,0.12131148,0.0025548376,0.00088468683,0.03540595],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9607294,0.032099083,0.0024927442,0.0012933852,0.0026822141,0.00070318655],"domain_scores_gemma":[0.9216004,0.05514126,0.0017828362,0.0084362235,0.011518059,0.0015211097],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05522916,0.0019279077,0.0012641901,0.0047256434,0.0051173256,0.00512895,0.004404142,0.0024047054,0.1272907],"category_scores_gemma":[0.06634557,0.002507311,0.0012036299,0.0064999573,0.0035797956,0.00333826,0.0063882875,0.006416859,0.038293637],"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":[0.00020636844,0.00047203124,0.000531311,0.004617838,0.000037677295,0.0006374121,0.053297408,0.0022965858,0.0034053277,0.12635937,0.4156596,0.39247903],"study_design_scores_gemma":[0.00012398938,0.00010120239,0.0004548506,0.0025253072,0.000010437771,0.00027045867,0.013053756,0.001336338,0.0007617307,0.04182259,0.9394507,0.000088659224],"about_ca_topic_score_codex":0.0094223535,"about_ca_topic_score_gemma":0.02984309,"teacher_disagreement_score":0.9447708,"about_ca_system_score_codex":0.0056292913,"about_ca_system_score_gemma":0.0224868,"threshold_uncertainty_score":0.42582983},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08530597,0.028941737,0.120711386,0.2728397,0.005542759,0.0009661134,0.0008663179,0.000780064,0.48404598],"genre_scores_gemma":[0.85232556,0.016309816,0.08448494,0.017915374,0.00072141504,0.0009320414,0.0006320832,0.00065073406,0.026027935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.94154876,0.03894329,0.0020755478,0.0068092896,0.0077096247,0.0029134774],"domain_scores_gemma":[0.94594496,0.030778393,0.004217942,0.009683486,0.0060533537,0.0033218234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057510164,0.001547578,0.0017986515,0.0056684082,0.009090774,0.029562797,0.0043784,0.0050587477,0.009715805],"category_scores_gemma":[0.05739331,0.0013202268,0.0013753395,0.0039468575,0.0591413,0.040278677,0.013590062,0.0062115355,0.0048461845],"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":[0.000073208466,0.00010608462,0.009470323,0.002131195,0.00036088983,0.0008733838,0.36867258,0.00059160497,0.0012414156,0.44831756,0.02992914,0.13823263],"study_design_scores_gemma":[0.000037663976,0.00007144423,0.002521079,0.003754506,0.00014759197,0.0005114827,0.25645766,0.0005770818,0.0007295961,0.43120283,0.30387363,0.00011536723],"about_ca_topic_score_codex":0.014708277,"about_ca_topic_score_gemma":0.0152194,"teacher_disagreement_score":0.057510164,"about_ca_system_score_codex":0.007923152,"about_ca_system_score_gemma":0.02602398,"threshold_uncertainty_score":0.30414647},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013238663,0.011889014,0.14948523,0.7838632,0.005095208,0.00035137238,0.00018357097,0.0015800899,0.034313682],"genre_scores_gemma":[0.48784274,0.0075579593,0.37744904,0.108410686,0.0074279374,0.0016226334,0.00037601616,0.00085082,0.008462204],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7712388,0.15541768,0.012336659,0.010106022,0.046593856,0.004306987],"domain_scores_gemma":[0.22800471,0.55875325,0.022660363,0.0393338,0.12648487,0.024762994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3016407,0.0020851912,0.0028328395,0.014607583,0.008830369,0.025082411,0.008349001,0.018122438,0.006904041],"category_scores_gemma":[0.5140064,0.002417527,0.001768144,0.005616866,0.023540622,0.056531806,0.018383043,0.03252623,0.0033408757],"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":[0.0006470824,0.0009874406,0.029844841,0.002298061,0.00028958378,0.00047853656,0.019673746,0.004037233,0.0028314064,0.36985832,0.13945071,0.42960307],"study_design_scores_gemma":[0.0002298537,0.00022400453,0.0067299423,0.0035160342,0.00013150575,0.00075899885,0.019200744,0.013417316,0.0017018913,0.72529286,0.22838755,0.0004093143],"about_ca_topic_score_codex":0.013192122,"about_ca_topic_score_gemma":0.01522988,"teacher_disagreement_score":0.3016407,"about_ca_system_score_codex":0.010137553,"about_ca_system_score_gemma":0.053497057,"threshold_uncertainty_score":0.86120135},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33781016,0.0027108402,0.293062,0.05286011,0.0006680273,0.0009353665,0.000107199696,0.00094618835,0.31090018],"genre_scores_gemma":[0.9586256,0.00040492162,0.03619913,0.00039539664,0.00005937896,0.00022487613,0.000027534157,0.0000692914,0.00399389],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.97861415,0.015354856,0.00069669145,0.0015218802,0.0025475873,0.001264846],"domain_scores_gemma":[0.9583796,0.024894474,0.003423658,0.006324415,0.0036708235,0.0033069735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018609101,0.0006270022,0.00041391485,0.001349034,0.00535308,0.010470405,0.0024374863,0.0027122472,0.00917422],"category_scores_gemma":[0.051447652,0.00044813275,0.00074243074,0.0005927907,0.022291781,0.019663515,0.018447634,0.0035564103,0.0010259433],"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":[0.00015040534,0.0003393677,0.010526781,0.00058991066,0.000055225122,0.0008411006,0.12398529,0.0033560738,0.004367659,0.64512163,0.0053874166,0.20527913],"study_design_scores_gemma":[0.00008943997,0.00038444548,0.0051140813,0.00082180195,0.00005288626,0.0006603855,0.10487921,0.004386424,0.006475233,0.62691265,0.25008702,0.00013638772],"about_ca_topic_score_codex":0.0010649068,"about_ca_topic_score_gemma":0.001601221,"teacher_disagreement_score":0.018609101,"about_ca_system_score_codex":0.0024015433,"about_ca_system_score_gemma":0.0070529343,"threshold_uncertainty_score":0.09841555},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8506183,0.00089208526,0.02146125,0.0006538064,0.00010581228,0.0016581038,0.0008402725,0.0006216013,0.123148814],"genre_scores_gemma":[0.98140633,0.00019014878,0.013626618,0.00007693645,0.000026749058,0.00045307324,0.00041304302,0.000058820468,0.0037481815],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98081553,0.006665598,0.001525175,0.0014683796,0.008446038,0.0010793615],"domain_scores_gemma":[0.8605171,0.08544034,0.008407427,0.0070742383,0.033102613,0.005458421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022921814,0.00081075844,0.00090884685,0.0048942966,0.0008730003,0.0030986744,0.0012946799,0.00070459093,0.006835839],"category_scores_gemma":[0.113461256,0.00021968466,0.00062628667,0.001735241,0.0014385799,0.0021658125,0.003970712,0.0005761503,0.0014188855],"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":[0.003869734,0.0017335841,0.25883606,0.0010935733,0.00030277195,0.0002385724,0.011301555,0.005311331,0.005152771,0.0103827985,0.008646225,0.69313097],"study_design_scores_gemma":[0.0006459432,0.019604035,0.767854,0.0013601737,0.00083668466,0.0011712823,0.020955373,0.07171711,0.035131745,0.020436753,0.06002241,0.0002645711],"about_ca_topic_score_codex":0.0022579827,"about_ca_topic_score_gemma":0.0031227593,"teacher_disagreement_score":0.022921814,"about_ca_system_score_codex":0.0017830959,"about_ca_system_score_gemma":0.0021350333,"threshold_uncertainty_score":0.12122357},"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":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010757239,0.059209097,0.0047577065,0.9203981,0.01210942,0.000058665406,0.00015144494,0.00006350094,0.00217631],"genre_scores_gemma":[0.10607276,0.16588151,0.03378443,0.65178084,0.036379494,0.0010225138,0.0007676371,0.0002533367,0.0040574097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91950107,0.04231098,0.010896531,0.007089514,0.015563848,0.0046380726],"domain_scores_gemma":[0.5769839,0.3339886,0.022661068,0.01203063,0.03610989,0.01822588],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12111605,0.0017988519,0.005236131,0.005994281,0.0053688316,0.019055668,0.0043607317,0.024940636,0.023224834],"category_scores_gemma":[0.3218565,0.0014281403,0.002695502,0.007843118,0.029616645,0.055718154,0.01451262,0.034077007,0.00488971],"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":[0.0009446143,0.00047247566,0.003988267,0.020873865,0.0009329065,0.00071755436,0.007550493,0.0013611874,0.0010148436,0.37851754,0.23103309,0.3525932],"study_design_scores_gemma":[0.0002497575,0.00016353923,0.001881659,0.023872746,0.00022834093,0.00041137994,0.024019163,0.00047907044,0.00025435523,0.6925817,0.25563198,0.0002262172],"about_ca_topic_score_codex":0.0027757357,"about_ca_topic_score_gemma":0.0027488046,"teacher_disagreement_score":0.87888396,"about_ca_system_score_codex":0.009426578,"about_ca_system_score_gemma":0.032035198,"threshold_uncertainty_score":0.6405306},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02803016,0.5097052,0.007521819,0.1907904,0.007260887,0.0009277906,0.003603751,0.00036568314,0.25179425],"genre_scores_gemma":[0.4973313,0.40392742,0.031665847,0.022966754,0.0014251624,0.00062387483,0.0031142202,0.00024131188,0.038704216],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97044665,0.0070657325,0.001224574,0.0013469852,0.014739999,0.0051759733],"domain_scores_gemma":[0.90740687,0.01938715,0.004906627,0.0022054282,0.050261855,0.015832135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033733305,0.0008668128,0.0012392635,0.0074912594,0.012308488,0.012897463,0.0031107336,0.0022209447,0.010271011],"category_scores_gemma":[0.050370835,0.0006210929,0.0008497309,0.017827118,0.00420536,0.0041969297,0.0057826093,0.004396488,0.0009111636],"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":[0.0004074991,0.00007513723,0.013398193,0.012429173,0.00036277503,0.00031501657,0.0070206802,0.0010103273,0.0008433389,0.2204864,0.20044619,0.54320526],"study_design_scores_gemma":[0.00005121511,0.00006208943,0.025398346,0.0066130455,0.00027854403,0.00009730977,0.008332087,0.00028282093,0.00064316083,0.0058423076,0.95230097,0.000098115925],"about_ca_topic_score_codex":0.9493561,"about_ca_topic_score_gemma":0.9830015,"teacher_disagreement_score":0.8583525,"about_ca_system_score_codex":0.14164753,"about_ca_system_score_gemma":0.398763,"threshold_uncertainty_score":0.9955672},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22308461,0.0014385374,0.57604676,0.09460577,0.0016576858,0.011559933,0.0001690014,0.0026533839,0.088784315],"genre_scores_gemma":[0.38351253,0.0005094256,0.601724,0.0025189721,0.00017529588,0.004145428,0.000089313195,0.00023257847,0.007092445],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88082916,0.09805995,0.0044689057,0.002762218,0.010728765,0.0031509888],"domain_scores_gemma":[0.8701426,0.06513018,0.009219975,0.0210321,0.017463703,0.017011397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14546391,0.00066945574,0.0007353878,0.003255204,0.010573013,0.0109345475,0.0031698686,0.0027647745,0.0069210394],"category_scores_gemma":[0.15671381,0.0008256394,0.000794716,0.0019788672,0.0088073,0.011618535,0.01732275,0.005984986,0.0018000545],"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":[0.00025470965,0.0016137741,0.01522057,0.0005921911,0.000024935604,0.0003346394,0.11509209,0.00072430115,0.0028653445,0.052557863,0.029075993,0.7816436],"study_design_scores_gemma":[0.00037541304,0.0025600577,0.027744316,0.0053538946,0.00007649928,0.0012736842,0.20393151,0.011741625,0.009182575,0.28043917,0.4568997,0.00042160726],"about_ca_topic_score_codex":0.001718172,"about_ca_topic_score_gemma":0.00508937,"teacher_disagreement_score":0.14546391,"about_ca_system_score_codex":0.007416067,"about_ca_system_score_gemma":0.033218347,"threshold_uncertainty_score":0.76929593},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074842654,0.0009016656,0.000027081767,0.9928952,0.0056916764,0.0000036453223,0.0000069011658,0.000003764109,0.0003952214],"genre_scores_gemma":[0.0016044683,0.0007257576,0.00008736423,0.98421484,0.012602489,0.000020384,0.0000047439053,0.00000985843,0.0007301744],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9716914,0.013383947,0.003118972,0.0029897077,0.006570743,0.0022452672],"domain_scores_gemma":[0.82177335,0.15139309,0.0033906328,0.0023176835,0.014358425,0.0067668175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032188687,0.0011074492,0.0024004425,0.0016136771,0.0106162885,0.009848443,0.008279711,0.103125595,0.0071863234],"category_scores_gemma":[0.17417388,0.0011334129,0.0023060278,0.001998828,0.021218665,0.016905788,0.0050657922,0.12366048,0.0039605824],"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":[0.00003442214,0.0000189823,0.00021771298,0.00012912838,0.000010226345,0.0005975006,0.0009571937,0.000042400443,0.00004188341,0.010002908,0.98236567,0.005581939],"study_design_scores_gemma":[0.00010892947,0.00005542813,0.00068691844,0.0017580283,0.00003650629,0.0013817187,0.003908623,0.0002863198,0.00020635984,0.030193051,0.96125996,0.00011808946],"about_ca_topic_score_codex":0.015518939,"about_ca_topic_score_gemma":0.023570046,"teacher_disagreement_score":0.103125595,"about_ca_system_score_codex":0.013422002,"about_ca_system_score_gemma":0.02482394,"threshold_uncertainty_score":0.17023206},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077648447,0.46350977,0.37720233,0.06994738,0.0074455435,0.0039541265,0.004298158,0.0021269526,0.063750945],"genre_scores_gemma":[0.06967883,0.33335307,0.5488117,0.008905412,0.0013036712,0.0067744926,0.001679353,0.0012611728,0.028232329],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9737579,0.016620139,0.0027551071,0.0012428329,0.005212853,0.00041122895],"domain_scores_gemma":[0.8352963,0.13124414,0.005065095,0.005331077,0.021021875,0.0020415166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.084911734,0.0020551288,0.0016679134,0.008874269,0.0061345473,0.0076785046,0.0030506544,0.0029936272,0.013799907],"category_scores_gemma":[0.083251104,0.0037761633,0.0011970989,0.009745634,0.012811693,0.010901355,0.0040640673,0.009464589,0.006974963],"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":[0.00018212451,0.00011094076,0.0022014065,0.011286485,0.00011560683,0.00046070138,0.04313848,0.0005767267,0.0029501186,0.055036187,0.22113025,0.6628109],"study_design_scores_gemma":[0.00010413851,0.00023384085,0.006452195,0.025173705,0.00022792279,0.0010820284,0.033887215,0.0005890145,0.0032198392,0.1164723,0.8122376,0.0003201801],"about_ca_topic_score_codex":0.028108057,"about_ca_topic_score_gemma":0.05569597,"teacher_disagreement_score":0.084911734,"about_ca_system_score_codex":0.0062593343,"about_ca_system_score_gemma":0.020119226,"threshold_uncertainty_score":0.4490615},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01586189,0.0014314163,0.026755927,0.8482597,0.002205355,0.001384951,0.00041686054,0.00049351936,0.10319031],"genre_scores_gemma":[0.49917352,0.004028406,0.15808009,0.21926253,0.001645128,0.0031830897,0.0020281419,0.00079603953,0.1118031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.88594264,0.059007782,0.0027627258,0.0058482634,0.02519384,0.02124468],"domain_scores_gemma":[0.7380201,0.05355936,0.0076518166,0.016151384,0.065962315,0.11865507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12542616,0.0009378198,0.00072482263,0.005809482,0.04899275,0.03666103,0.009598875,0.013941617,0.027827198],"category_scores_gemma":[0.1235833,0.0013093443,0.0015825944,0.0049827495,0.023778612,0.01880373,0.05352164,0.016101453,0.0045958026],"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":[0.00006508919,0.0005654634,0.01679129,0.00051058916,0.00009181821,0.0011845734,0.0773188,0.0017889697,0.0012972577,0.4163,0.3541724,0.12991382],"study_design_scores_gemma":[0.00003444797,0.00004583613,0.0029562158,0.00055249553,0.000029746401,0.0001284004,0.038859744,0.0012761762,0.0006110114,0.047488153,0.9079486,0.00006917129],"about_ca_topic_score_codex":0.50581163,"about_ca_topic_score_gemma":0.5997786,"teacher_disagreement_score":0.50581163,"about_ca_system_score_codex":0.09583433,"about_ca_system_score_gemma":0.43693224,"threshold_uncertainty_score":0.9941975},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0109973075,0.024781706,0.1455985,0.32486662,0.0022346533,0.00046377664,0.00052681385,0.0006168836,0.48991382],"genre_scores_gemma":[0.5470186,0.032795656,0.12550731,0.06043427,0.001365814,0.0009243147,0.0012814824,0.00041223073,0.23026031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952459,0.0014445023,0.000118333606,0.0006774642,0.0016547487,0.0008591516],"domain_scores_gemma":[0.9971234,0.00044825615,0.00022947781,0.000488589,0.0010781899,0.00063190504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007862738,0.0007132683,0.00055454863,0.0011217181,0.0029573052,0.007716091,0.0018453345,0.0039707287,0.011104814],"category_scores_gemma":[0.0063221417,0.00024223723,0.00053504313,0.0013559607,0.013107725,0.005390168,0.0075689014,0.0048210663,0.0023234542],"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":[0.000005842973,0.000022941687,0.0008923809,0.00025535803,0.000021364314,0.00008159483,0.0021278993,0.0022406229,0.0005621958,0.8811811,0.054996513,0.05761225],"study_design_scores_gemma":[0.000005903462,0.000014088093,0.0009823933,0.00048680135,0.000005255948,0.000040944513,0.0013579219,0.0009822978,0.00020807977,0.33062947,0.66527116,0.000015768348],"about_ca_topic_score_codex":0.15181556,"about_ca_topic_score_gemma":0.17450415,"teacher_disagreement_score":0.15181556,"about_ca_system_score_codex":0.018630182,"about_ca_system_score_gemma":0.04046869,"threshold_uncertainty_score":0.3018638},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013582646,0.009708515,0.005972616,0.92690307,0.035545837,0.00018850049,0.00046779535,0.00022797252,0.019627513],"genre_scores_gemma":[0.083640955,0.03611706,0.06893915,0.6063525,0.029541869,0.0017127201,0.0021735043,0.00056402734,0.17095818],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9884725,0.004566029,0.0011489736,0.0005006571,0.0034409233,0.001870868],"domain_scores_gemma":[0.9371277,0.019591372,0.0022647753,0.0032440792,0.02008581,0.017686285],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028274994,0.0006255147,0.00056281313,0.0014887345,0.003830014,0.011409881,0.0019141793,0.011214103,0.11389118],"category_scores_gemma":[0.05552669,0.00044982758,0.0012458747,0.001539839,0.0023915183,0.01379334,0.007968985,0.01256767,0.0262931],"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":[0.0005046593,0.00026111485,0.00093730696,0.0017057976,0.000034689172,0.00041016404,0.0007717816,0.00026838662,0.001008873,0.038745705,0.6928523,0.2624993],"study_design_scores_gemma":[0.00010222543,0.00033224773,0.0019973826,0.0035980707,0.000041559393,0.00025164185,0.0043860883,0.00021603263,0.00082337606,0.018880965,0.969304,0.00006645867],"about_ca_topic_score_codex":0.007073297,"about_ca_topic_score_gemma":0.014103738,"teacher_disagreement_score":0.971725,"about_ca_system_score_codex":0.0048205857,"about_ca_system_score_gemma":0.027468229,"threshold_uncertainty_score":0.38100398},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14530544,0.022566224,0.0063383183,0.54654425,0.001308289,0.00042844692,0.0020565158,0.00037178418,0.27508077],"genre_scores_gemma":[0.90829015,0.009976946,0.007400031,0.02703498,0.0003220742,0.00011143173,0.00056345644,0.00015765429,0.04614318],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.97216743,0.0034037873,0.00076889765,0.001756662,0.015854312,0.0060489182],"domain_scores_gemma":[0.86910224,0.026646238,0.00414524,0.0021149798,0.07055154,0.027439784],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02246012,0.0003545073,0.00060825446,0.0053264094,0.012648979,0.01817266,0.0032589824,0.0035332497,0.016377818],"category_scores_gemma":[0.044237826,0.0006729079,0.00064761087,0.0064986977,0.008398074,0.0035113366,0.0040617962,0.003842383,0.00077196385],"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":[0.00028210174,0.0002435487,0.033778116,0.00079296634,0.000049024617,0.0010522689,0.010211929,0.002144793,0.0016607583,0.49133778,0.2053912,0.25305548],"study_design_scores_gemma":[0.00008565362,0.00012522656,0.08197357,0.0016977098,0.000042292413,0.0002412947,0.022257095,0.0059798234,0.0010238646,0.026189474,0.8601332,0.00025094312],"about_ca_topic_score_codex":0.98623276,"about_ca_topic_score_gemma":0.9915679,"teacher_disagreement_score":0.9775399,"about_ca_system_score_codex":0.31247154,"about_ca_system_score_gemma":0.496807,"threshold_uncertainty_score":0.7974356},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2934028,0.057210673,0.06620674,0.42985225,0.015004113,0.00038420648,0.0046149027,0.0007655391,0.13255873],"genre_scores_gemma":[0.95664,0.007617137,0.013232682,0.014480568,0.0011594141,0.00034823842,0.0008728274,0.00034018286,0.0053088176],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92264307,0.041212097,0.0062445756,0.007041793,0.019322377,0.003536054],"domain_scores_gemma":[0.71899384,0.19725089,0.016532378,0.013322776,0.041781418,0.012118698],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08537719,0.0013153796,0.0017282746,0.0077670603,0.003242753,0.018666172,0.0047544143,0.0022671376,0.0043844674],"category_scores_gemma":[0.2305644,0.0006934627,0.0011051717,0.0070637655,0.017778583,0.01892796,0.00651502,0.008992382,0.0018640326],"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":[0.00025239837,0.00045155367,0.4318032,0.00162299,0.0011756609,0.00012568399,0.037712652,0.0013118241,0.00041347896,0.115820125,0.06692682,0.34238362],"study_design_scores_gemma":[0.00007970635,0.0009980117,0.47320348,0.0071152695,0.00062188896,0.00022591703,0.07812214,0.0041064974,0.0013641937,0.25125617,0.18223524,0.0006714595],"about_ca_topic_score_codex":0.10266971,"about_ca_topic_score_gemma":0.17619175,"teacher_disagreement_score":0.9146228,"about_ca_system_score_codex":0.009766964,"about_ca_system_score_gemma":0.011691512,"threshold_uncertainty_score":0.45152313},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77479124,0.0020402547,0.078533895,0.006651314,0.0010816759,0.014730285,0.002360261,0.0006496038,0.11916154],"genre_scores_gemma":[0.8669548,0.00071116275,0.08483831,0.0009115736,0.00008654875,0.019034777,0.0017388241,0.0001990831,0.02552492],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9084063,0.044424653,0.0062293955,0.006737192,0.031523176,0.0026793575],"domain_scores_gemma":[0.7765786,0.07366626,0.009856103,0.017880104,0.1162581,0.0057608685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11449049,0.0012956552,0.0015845046,0.0084369425,0.006570272,0.012501944,0.0037169734,0.0019501017,0.009061988],"category_scores_gemma":[0.17827249,0.0010351232,0.0024324546,0.004881879,0.0070400694,0.0066049444,0.008543717,0.0044454327,0.0019631388],"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":[0.0012703417,0.0022257227,0.20260876,0.0027584578,0.00051762315,0.00046903462,0.28221083,0.0030456495,0.008171607,0.053719044,0.019072406,0.42393056],"study_design_scores_gemma":[0.0004873654,0.0031672413,0.58236384,0.005760271,0.0005414833,0.0002698267,0.17147638,0.011628916,0.013374935,0.01607543,0.19432834,0.0005259209],"about_ca_topic_score_codex":0.10225149,"about_ca_topic_score_gemma":0.1335654,"teacher_disagreement_score":0.11449049,"about_ca_system_score_codex":0.024027105,"about_ca_system_score_gemma":0.039429013,"threshold_uncertainty_score":0.6054908},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16511421,0.038354035,0.3114067,0.030826394,0.00091227156,0.0009559922,0.00019062794,0.00030759655,0.45193213],"genre_scores_gemma":[0.96410674,0.004821611,0.02364879,0.00096391764,0.0002403753,0.001069644,0.000041516036,0.000071260896,0.0050362754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8151757,0.14399429,0.0060637724,0.010769101,0.019976676,0.004020467],"domain_scores_gemma":[0.75516474,0.20548436,0.011858955,0.01396777,0.011016645,0.0025075658],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12301218,0.0009397196,0.0015991863,0.007119008,0.00450021,0.022467388,0.0029970363,0.002475711,0.0077408543],"category_scores_gemma":[0.11731192,0.000981509,0.0007972919,0.006857897,0.044062886,0.020168453,0.025906602,0.004357743,0.00063605054],"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":[0.00008055879,0.00013796851,0.007653143,0.0012965603,0.00013747388,0.0003265313,0.10371627,0.0006282298,0.00049279415,0.7990804,0.00073357206,0.08571658],"study_design_scores_gemma":[0.000098980345,0.00032268185,0.019597135,0.003706659,0.00008479749,0.0006542857,0.08505245,0.0018657823,0.00091699616,0.79122925,0.0963705,0.000100374564],"about_ca_topic_score_codex":0.0032630635,"about_ca_topic_score_gemma":0.0036602553,"teacher_disagreement_score":0.8769878,"about_ca_system_score_codex":0.009667239,"about_ca_system_score_gemma":0.011760135,"threshold_uncertainty_score":0.65055835},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95190126,0.0010351094,0.0003407936,0.0008910521,0.000079498364,0.00004372479,0.012958113,0.0000357111,0.03271474],"genre_scores_gemma":[0.950861,0.0020653252,0.0008635212,0.0004984982,0.000044606808,0.00013510746,0.015882738,0.000086345324,0.029562842],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995491,0.000034734752,0.00003427179,0.000110670575,0.0001759643,0.000095140334],"domain_scores_gemma":[0.9987452,0.00030268723,0.00031998145,0.000086200555,0.0003878398,0.00015799826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002944702,0.00021451333,0.00034537684,0.0018418175,0.002740813,0.0019054643,0.00039511276,0.00031860493,0.013744492],"category_scores_gemma":[0.0017868477,0.00018953028,0.00012962057,0.0047001163,0.0009934277,0.0017729341,0.0014810615,0.00048147736,0.0013527555],"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":[0.000401838,0.00018865461,0.500988,0.0010497933,0.00013360454,0.0021918626,0.23273791,0.000226538,0.012135739,0.015642352,0.10836937,0.12593426],"study_design_scores_gemma":[0.000010006852,0.000011478855,0.85357785,0.0000702732,0.000023346109,0.0002284179,0.035700053,0.00013543834,0.00079348474,0.0002215706,0.10917475,0.00005334578],"about_ca_topic_score_codex":0.8086562,"about_ca_topic_score_gemma":0.9474982,"teacher_disagreement_score":0.8086562,"about_ca_system_score_codex":0.0052252887,"about_ca_system_score_gemma":0.0025923783,"threshold_uncertainty_score":0.38494128},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001002135,0.0094671985,0.0017839713,0.011785811,0.0013067082,0.00006688399,0.000117678734,0.000044445962,0.9744252],"genre_scores_gemma":[0.07261378,0.0096060615,0.0017067551,0.013914197,0.0018681736,0.00041313324,0.00028554775,0.00016509206,0.89942735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992131,0.00021049097,0.00002410272,0.00019397218,0.00021662287,0.00014163766],"domain_scores_gemma":[0.99951565,0.0002362596,0.000031299864,0.00006199472,0.000104022205,0.0000507583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082406274,0.0004838359,0.00030170023,0.00063294865,0.003968072,0.0040483447,0.001126245,0.0025460604,0.046449833],"category_scores_gemma":[0.002204794,0.00023837462,0.00027243394,0.000656651,0.004483255,0.0028213423,0.0021668556,0.005726689,0.009658593],"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":[0.000009001378,0.000029429219,0.00006209831,0.000065476524,0.00000141217,0.00006392262,0.0015269797,0.00007580849,0.000053902168,0.8835283,0.09606119,0.018522602],"study_design_scores_gemma":[0.000003327991,0.000007893134,0.00014995025,0.0003019612,0.0000011457887,0.00005110902,0.0004195666,0.000044500815,0.00008608077,0.058320906,0.9406102,0.000003313812],"about_ca_topic_score_codex":0.005928562,"about_ca_topic_score_gemma":0.008521506,"teacher_disagreement_score":0.046449833,"about_ca_system_score_codex":0.0050352816,"about_ca_system_score_gemma":0.0033382268,"threshold_uncertainty_score":0.1553902},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14724977,0.008429239,0.122932926,0.6259275,0.0018908754,0.0035875684,0.00026434963,0.00067900505,0.08903879],"genre_scores_gemma":[0.92236954,0.0031684837,0.036457445,0.02878113,0.00064517127,0.002909872,0.00013320033,0.00017513747,0.0053600064],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.40101,0.44669625,0.05091659,0.013799153,0.068471916,0.01910605],"domain_scores_gemma":[0.09573043,0.7610738,0.030925024,0.051659394,0.048348732,0.012262678],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49347672,0.000870168,0.0018247205,0.010532575,0.011443945,0.03265345,0.009610514,0.0107435575,0.011296384],"category_scores_gemma":[0.7154202,0.0015984526,0.0018327249,0.009662297,0.025541507,0.027844263,0.035698876,0.014725409,0.0021617098],"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":[0.00038796713,0.0009339487,0.023817249,0.0058900514,0.0002858478,0.0021652654,0.132854,0.0033230968,0.0022211075,0.33535606,0.031043882,0.46172157],"study_design_scores_gemma":[0.0004089365,0.0008626054,0.015627608,0.020274825,0.00023057817,0.0013614605,0.1814977,0.0076726656,0.0046538087,0.554915,0.21214668,0.00034819866],"about_ca_topic_score_codex":0.0069727204,"about_ca_topic_score_gemma":0.0037676913,"teacher_disagreement_score":0.50652325,"about_ca_system_score_codex":0.024389572,"about_ca_system_score_gemma":0.09617166,"threshold_uncertainty_score":0.6246334},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38425693,0.050641075,0.032661203,0.10759285,0.0050276113,0.0017152207,0.0020908432,0.00053102936,0.4154833],"genre_scores_gemma":[0.9199965,0.012048884,0.021398494,0.0061071254,0.0004349966,0.0008512783,0.00065154285,0.00023574285,0.038275436],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9514985,0.024433272,0.002000886,0.002306114,0.016658533,0.0031026914],"domain_scores_gemma":[0.914257,0.015267463,0.004596672,0.0026583667,0.052524943,0.010695506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03345655,0.0007798686,0.0011746779,0.0033290852,0.007236935,0.01517427,0.0020099317,0.0020460677,0.014359027],"category_scores_gemma":[0.07443499,0.00029507358,0.0008497949,0.004517823,0.0067653027,0.0093428,0.0076620453,0.0038770072,0.0030538044],"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":[0.0005176724,0.0004781883,0.055612244,0.004958005,0.00031831829,0.00032672132,0.14213137,0.0012949355,0.0019501823,0.092416026,0.06321665,0.63677967],"study_design_scores_gemma":[0.00008152017,0.0011696066,0.11855707,0.008573231,0.00029289845,0.00031984615,0.24549642,0.0015850681,0.002690897,0.030500976,0.5904517,0.0002807638],"about_ca_topic_score_codex":0.12770954,"about_ca_topic_score_gemma":0.17524351,"teacher_disagreement_score":0.8722905,"about_ca_system_score_codex":0.027273221,"about_ca_system_score_gemma":0.03905364,"threshold_uncertainty_score":0.25393236},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50704265,0.003918906,0.0016095702,0.21691725,0.00040381358,0.00022782353,0.00029415797,0.0000713889,0.26951435],"genre_scores_gemma":[0.97561604,0.0011031175,0.00061081507,0.001806038,0.000058002395,0.000040205487,0.00003025016,0.000017894616,0.020717647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9829405,0.0049054185,0.0006826316,0.0008945592,0.00527311,0.0053037135],"domain_scores_gemma":[0.96781397,0.011400948,0.0040121824,0.0010414956,0.008988997,0.006742352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011987889,0.00017687124,0.00037042084,0.0014742089,0.021185923,0.009513692,0.0013757934,0.0023364916,0.003592631],"category_scores_gemma":[0.03817362,0.00043299975,0.00020241739,0.003690573,0.013024137,0.003094872,0.003781649,0.0035056716,0.00027105745],"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":[0.0005220801,0.00021719198,0.12667106,0.0007086806,0.000058957427,0.002110171,0.24595498,0.0036516911,0.001979548,0.43201864,0.053951938,0.13215505],"study_design_scores_gemma":[0.00011217961,0.00014882759,0.31016952,0.00075799203,0.000045384873,0.00016313509,0.15392855,0.0026320538,0.0012698584,0.04173185,0.48881346,0.00022715777],"about_ca_topic_score_codex":0.98282063,"about_ca_topic_score_gemma":0.99209386,"teacher_disagreement_score":0.98282063,"about_ca_system_score_codex":0.24336506,"about_ca_system_score_gemma":0.31555685,"threshold_uncertainty_score":0.8775893},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5440579,0.0034417384,0.27704456,0.009697029,0.00068264385,0.031534128,0.0024353976,0.00025308374,0.13085352],"genre_scores_gemma":[0.78194183,0.0009930116,0.14837518,0.0013177673,0.00011818243,0.05970327,0.00069548824,0.0001269977,0.0067282384],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8772202,0.11246415,0.0027441129,0.0026584514,0.0038164142,0.0010966166],"domain_scores_gemma":[0.9042284,0.060257602,0.008371769,0.012001743,0.011641605,0.003498934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0729803,0.0009289782,0.0007014651,0.0056962087,0.004515259,0.0058208234,0.002716025,0.0013084679,0.009001489],"category_scores_gemma":[0.095426,0.0008088898,0.0006129029,0.0038206577,0.008705724,0.007340001,0.010354905,0.0024328236,0.0008987842],"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":[0.0013693484,0.001826032,0.045136698,0.0029452946,0.00023407805,0.00093764096,0.43849337,0.0014206492,0.0030670618,0.083992094,0.009277587,0.41130018],"study_design_scores_gemma":[0.0008560201,0.0036975043,0.044974,0.0053405394,0.00037705118,0.0009408385,0.56413776,0.00567217,0.009462442,0.12552768,0.23866166,0.0003523042],"about_ca_topic_score_codex":0.0016361729,"about_ca_topic_score_gemma":0.004881443,"teacher_disagreement_score":0.9270197,"about_ca_system_score_codex":0.0056477003,"about_ca_system_score_gemma":0.0051672137,"threshold_uncertainty_score":0.38596135},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03419506,0.033159886,0.1828912,0.71033096,0.0035115636,0.0020326532,0.00035408404,0.0009729741,0.032551672],"genre_scores_gemma":[0.36315095,0.027105007,0.5807827,0.016532928,0.0021406803,0.0045474516,0.00037675988,0.0004696479,0.004893736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.642046,0.32332388,0.0068590944,0.0035345526,0.02012777,0.0041086897],"domain_scores_gemma":[0.33959466,0.5284733,0.009920499,0.022695702,0.08661703,0.01269885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32830358,0.0021117276,0.0027007114,0.007068804,0.006935097,0.024180828,0.006287604,0.0065625114,0.0071336236],"category_scores_gemma":[0.30453,0.00126742,0.0020609128,0.0111484025,0.01390234,0.0325239,0.009706244,0.009068931,0.0013452345],"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":[0.0004341115,0.0010882528,0.028637504,0.005954436,0.00033376538,0.00080033165,0.033690147,0.009126783,0.0012775605,0.112581894,0.06662758,0.7394476],"study_design_scores_gemma":[0.00026489203,0.0008031442,0.015680663,0.023511063,0.00023878452,0.0009620319,0.17453009,0.04929458,0.002611805,0.45652527,0.2749177,0.00065999787],"about_ca_topic_score_codex":0.023302302,"about_ca_topic_score_gemma":0.039322153,"teacher_disagreement_score":0.6716964,"about_ca_system_score_codex":0.012052916,"about_ca_system_score_gemma":0.03632509,"threshold_uncertainty_score":0.8283213},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14963132,0.012750437,0.2521066,0.29399556,0.025818404,0.008869952,0.000797325,0.0069809,0.24904963],"genre_scores_gemma":[0.58227044,0.0030383249,0.31170896,0.030961521,0.0062259375,0.0057680043,0.00069694984,0.0016692263,0.05766077],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9435165,0.043333583,0.0010351738,0.0026385756,0.0036949513,0.005781163],"domain_scores_gemma":[0.94070435,0.013041453,0.0021023804,0.0048091053,0.006228625,0.033113986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069758385,0.001047006,0.00082282064,0.0015587838,0.0075484267,0.005935488,0.0039722812,0.002562969,0.015770545],"category_scores_gemma":[0.021712875,0.0010846484,0.0009713938,0.0016807024,0.008670578,0.004741342,0.015057919,0.011170697,0.0040264023],"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":[0.001214738,0.0077953595,0.011986937,0.0009360566,0.00005690819,0.0008263129,0.030327743,0.0015731666,0.0035603035,0.057471182,0.29488543,0.58936596],"study_design_scores_gemma":[0.0013131652,0.004322549,0.029100716,0.0016895653,0.00007731901,0.0012453803,0.036556415,0.002349459,0.0037731542,0.038851164,0.8804572,0.00026395242],"about_ca_topic_score_codex":0.0035981094,"about_ca_topic_score_gemma":0.019285891,"teacher_disagreement_score":0.069758385,"about_ca_system_score_codex":0.009513944,"about_ca_system_score_gemma":0.04295551,"threshold_uncertainty_score":0.368922},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28119078,0.002772564,0.25294548,0.28097582,0.004759406,0.0062592486,0.0002699032,0.005695674,0.16513115],"genre_scores_gemma":[0.86727697,0.0006795645,0.10163619,0.018241879,0.00035167145,0.0034122146,0.00014700193,0.00043079918,0.0078237355],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.79297346,0.17858988,0.008227567,0.0027240685,0.011345156,0.0061397958],"domain_scores_gemma":[0.6240653,0.26134962,0.014998865,0.013023591,0.06035835,0.026204392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1649315,0.001055832,0.0009501486,0.0030172693,0.011266977,0.0124350935,0.0024049685,0.009933919,0.008116563],"category_scores_gemma":[0.36309755,0.0009310188,0.00094233576,0.0018745414,0.011704041,0.016989976,0.018226884,0.0153020425,0.0023105117],"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":[0.00095479295,0.0013516066,0.025103942,0.0017530005,0.000043869903,0.0035288334,0.52143633,0.0016828533,0.005258711,0.16679266,0.08840189,0.18369144],"study_design_scores_gemma":[0.0003149032,0.0013362081,0.013796201,0.004036708,0.00008327497,0.0018999898,0.42703,0.007702124,0.0062918747,0.1735394,0.36327884,0.0006905071],"about_ca_topic_score_codex":0.0016016383,"about_ca_topic_score_gemma":0.002142404,"teacher_disagreement_score":0.1649315,"about_ca_system_score_codex":0.0122146085,"about_ca_system_score_gemma":0.021282177,"threshold_uncertainty_score":0.87225163},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33177635,0.02412717,0.18354708,0.14068434,0.0022182849,0.0010860696,0.0006049432,0.0002739834,0.31568173],"genre_scores_gemma":[0.9725859,0.0030917395,0.013937647,0.0019448356,0.00022482297,0.00058015186,0.00011226359,0.00012535704,0.0073973243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8325301,0.11305567,0.009672762,0.0073776008,0.031257685,0.0061062477],"domain_scores_gemma":[0.5106432,0.3896826,0.02064653,0.013194928,0.058295134,0.0075375913],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20484284,0.0007150546,0.00096568186,0.0076300977,0.010933052,0.033325385,0.0032424848,0.0056519406,0.007947959],"category_scores_gemma":[0.3634502,0.0008388578,0.0015332849,0.00866243,0.018380284,0.031051757,0.012389175,0.0092360005,0.00089214626],"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":[0.00038268277,0.0001762195,0.044513483,0.0016813844,0.00034815632,0.00075419125,0.22263491,0.0021825226,0.00083343347,0.52217877,0.009088322,0.1952259],"study_design_scores_gemma":[0.00010436179,0.0003755484,0.07787251,0.008363702,0.0004256676,0.0007738942,0.20358461,0.004144473,0.004771488,0.427565,0.27164695,0.00037184294],"about_ca_topic_score_codex":0.019049931,"about_ca_topic_score_gemma":0.01944912,"teacher_disagreement_score":0.20484284,"about_ca_system_score_codex":0.018338157,"about_ca_system_score_gemma":0.016918434,"threshold_uncertainty_score":0.9805703},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13391997,0.007825759,0.06459125,0.27060518,0.004467782,0.0004081761,0.00020359884,0.00020493421,0.5177734],"genre_scores_gemma":[0.9090142,0.0028612046,0.020545712,0.018223379,0.00061440485,0.00033337524,0.00009502159,0.00021920372,0.04809344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9414558,0.041888054,0.001255183,0.0026269942,0.009513358,0.0032607233],"domain_scores_gemma":[0.960334,0.021580307,0.0030259453,0.0018590965,0.010470176,0.0027304075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04064946,0.0006277146,0.0006938137,0.0013737346,0.007134611,0.014932328,0.0020851644,0.006351167,0.022254955],"category_scores_gemma":[0.086718775,0.0002957805,0.0010413671,0.0014990031,0.008793848,0.011100448,0.0056850393,0.0072339005,0.0023657964],"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":[0.00047820297,0.00042831904,0.0178649,0.00065985904,0.00018860404,0.00313708,0.06531733,0.0009767029,0.0024775,0.6916462,0.029432336,0.18739292],"study_design_scores_gemma":[0.00008389881,0.00021620409,0.009292684,0.0028839272,0.00013920752,0.0014274105,0.11108734,0.0016657567,0.0058997204,0.19967441,0.66749465,0.00013489355],"about_ca_topic_score_codex":0.016705353,"about_ca_topic_score_gemma":0.017575327,"teacher_disagreement_score":0.99099696,"about_ca_system_score_codex":0.009003051,"about_ca_system_score_gemma":0.012231356,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034396796,0.37215203,0.030252475,0.48479474,0.021912247,0.0004776458,0.0009850587,0.0007877456,0.08829409],"genre_scores_gemma":[0.02105717,0.54597706,0.06821413,0.15897787,0.016509175,0.0011851736,0.0010335513,0.001304655,0.18574132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867792,0.004945581,0.0010589415,0.0004994269,0.0062860115,0.00043087336],"domain_scores_gemma":[0.9406622,0.028909253,0.002795728,0.0010353768,0.022927985,0.0036694398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032061145,0.0012343174,0.00093538896,0.0063640866,0.002699344,0.007079639,0.0023462311,0.005091418,0.03497472],"category_scores_gemma":[0.055113737,0.00095248804,0.0007024201,0.0052357884,0.004845375,0.008894722,0.003210529,0.008274137,0.0201984],"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":[0.000020157942,0.00001880196,0.0002892344,0.0005658017,0.000008385053,0.000026256961,0.00035466344,0.00010693135,0.00006680287,0.011149906,0.8849498,0.10244325],"study_design_scores_gemma":[0.00001711495,0.00002287023,0.0008996061,0.0033294414,0.000013740397,0.00013113298,0.0006196012,0.00011158338,0.00015141873,0.023100136,0.9715646,0.00003872046],"about_ca_topic_score_codex":0.05282899,"about_ca_topic_score_gemma":0.119167484,"teacher_disagreement_score":0.05282899,"about_ca_system_score_codex":0.008738364,"about_ca_system_score_gemma":0.02100258,"threshold_uncertainty_score":0.16955757},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047833573,0.030848922,0.0069972547,0.055882208,0.0007919488,0.00033870552,0.0013860556,0.00041866253,0.8555027],"genre_scores_gemma":[0.49405375,0.048565805,0.02421921,0.0053541074,0.00016159416,0.00016246786,0.0014691984,0.0001847055,0.42582914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975623,0.00015240134,0.00005629586,0.00012640131,0.0013062432,0.0007964732],"domain_scores_gemma":[0.997926,0.00016911463,0.00007995711,0.000059233957,0.0012781542,0.00048755782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00174559,0.00038573178,0.00024658433,0.001401152,0.0069168657,0.0060093836,0.0011817793,0.0009940502,0.00606512],"category_scores_gemma":[0.0024305312,0.00031179757,0.0003416393,0.0035498315,0.0033040284,0.0012302503,0.0018036497,0.0013440747,0.0006086705],"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":[0.00003274068,0.00008193624,0.0053248457,0.0006790276,0.000020986412,0.00049223367,0.008734062,0.0036968049,0.0009031852,0.51921225,0.20593914,0.2548828],"study_design_scores_gemma":[0.000014453915,0.000017828605,0.010862019,0.00041137144,0.000013409489,0.00007130048,0.0032256416,0.0010953952,0.00043939543,0.008904481,0.9749136,0.000031032698],"about_ca_topic_score_codex":0.9957163,"about_ca_topic_score_gemma":0.99837637,"teacher_disagreement_score":0.22733946,"about_ca_system_score_codex":0.22733946,"about_ca_system_score_gemma":0.42462027,"threshold_uncertainty_score":0.8961767},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005159905,0.9733907,0.00039201308,0.00921908,0.014473328,0.00007179008,0.00016851722,0.00004030951,0.0021926032],"genre_scores_gemma":[0.00067231467,0.97417235,0.0008856321,0.005022611,0.008098812,0.00016327231,0.00035502602,0.000038374194,0.010591576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658316,0.001080209,0.00039783676,0.0002805278,0.001497348,0.0001609234],"domain_scores_gemma":[0.98022354,0.012023706,0.0015261577,0.00029932396,0.005143625,0.00078361237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034326809,0.0021567785,0.0034491546,0.0077368636,0.0007664819,0.003472893,0.0030243895,0.0036854935,0.020956686],"category_scores_gemma":[0.014146361,0.0009751725,0.0014128314,0.011653735,0.001677657,0.0031064423,0.0012344015,0.0042431485,0.015117161],"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":[0.000037955408,0.00002899084,0.000091310736,0.008679944,0.000053309912,0.000050217386,0.00006833518,0.000112306516,0.00008582882,0.0007873516,0.8628005,0.12720391],"study_design_scores_gemma":[0.00003956098,0.000058609254,0.00086413784,0.013820985,0.000074132506,0.0005137644,0.000103468,0.00009525313,0.0000881229,0.001351732,0.9829574,0.00003273774],"about_ca_topic_score_codex":0.012861677,"about_ca_topic_score_gemma":0.042672917,"teacher_disagreement_score":0.020956686,"about_ca_system_score_codex":0.0037962408,"about_ca_system_score_gemma":0.007209129,"threshold_uncertainty_score":0.0701071},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8231791,0.005768344,0.074986234,0.0030737314,0.00028560506,0.00056432624,0.0031437238,0.0010292024,0.08796981],"genre_scores_gemma":[0.9425052,0.0018775733,0.033000905,0.00039196285,0.000052658394,0.00059411617,0.0014669081,0.0004761043,0.01963452],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9338512,0.025221096,0.0047997558,0.006167518,0.028088143,0.0018723853],"domain_scores_gemma":[0.7083757,0.18525428,0.013100987,0.014853621,0.075705945,0.0027095817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058171365,0.0010254526,0.00087054656,0.0059490954,0.0031163918,0.008490533,0.0018537403,0.0014049213,0.007474901],"category_scores_gemma":[0.16441053,0.00071012066,0.0010666893,0.0048881257,0.004613424,0.004871664,0.0038616813,0.0019162656,0.0021377078],"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":[0.0012985626,0.0002554459,0.21526542,0.0044294395,0.00044060586,0.0009058986,0.22827876,0.002467217,0.01419695,0.0168457,0.0075364867,0.5080795],"study_design_scores_gemma":[0.00007145971,0.0011771935,0.580138,0.0052288477,0.0007000385,0.001328939,0.1448213,0.0052635297,0.03863698,0.010472506,0.21166937,0.0004918552],"about_ca_topic_score_codex":0.06333591,"about_ca_topic_score_gemma":0.086469345,"teacher_disagreement_score":0.06333591,"about_ca_system_score_codex":0.00818367,"about_ca_system_score_gemma":0.008387406,"threshold_uncertainty_score":0.30764323},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66886675,0.016453922,0.009242423,0.20909578,0.00040347342,0.0014847488,0.00032959413,0.000059262256,0.09406398],"genre_scores_gemma":[0.9909734,0.0020892709,0.001782859,0.0022891797,0.00006961186,0.0006578369,0.000023478267,0.0000118150865,0.002102525],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.83986074,0.14713462,0.0016662783,0.0020549113,0.004386763,0.004896776],"domain_scores_gemma":[0.90525943,0.07855759,0.008973404,0.001641615,0.0025465775,0.003021489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08558172,0.00026784188,0.0005074382,0.0010824219,0.007142485,0.010468681,0.0013014068,0.0023721117,0.0035156438],"category_scores_gemma":[0.06512967,0.0005170795,0.00033556586,0.0020555328,0.019690607,0.007101883,0.008732472,0.0030913432,0.0001391443],"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":[0.00034142451,0.00024958674,0.06099602,0.0016480213,0.0000622847,0.0014844949,0.6040758,0.0005478752,0.00083279924,0.1562286,0.010144565,0.16338858],"study_design_scores_gemma":[0.00013496992,0.0006183261,0.06730167,0.0058083623,0.000059866674,0.00050674,0.73561543,0.0007871844,0.0012502698,0.052394122,0.13544154,0.000081597296],"about_ca_topic_score_codex":0.015574307,"about_ca_topic_score_gemma":0.01969555,"teacher_disagreement_score":0.08558172,"about_ca_system_score_codex":0.011482418,"about_ca_system_score_gemma":0.022424437,"threshold_uncertainty_score":0.45260483},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11633927,0.041459426,0.013608857,0.14597756,0.0021549868,0.0017985097,0.0047049737,0.0003497602,0.67360663],"genre_scores_gemma":[0.6184672,0.04596868,0.08108986,0.025505688,0.00037707924,0.0009926116,0.0041465648,0.0008913042,0.22256097],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97204065,0.0070446352,0.00086247997,0.0007402055,0.016644947,0.0026670576],"domain_scores_gemma":[0.9596829,0.013705821,0.0005736186,0.00087606435,0.023296362,0.0018652478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026125956,0.00066518737,0.0009993602,0.0034725366,0.014686133,0.008510804,0.0026039232,0.0017414967,0.0038809723],"category_scores_gemma":[0.029798657,0.00037471202,0.00052537647,0.013536152,0.004028686,0.0033656512,0.0029405106,0.0033161999,0.000653756],"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":[0.00018215594,0.00033916614,0.016678533,0.0013561962,0.00007787968,0.001373518,0.063340984,0.0018367998,0.0011147736,0.16715936,0.3260492,0.42049143],"study_design_scores_gemma":[0.00006143224,0.00015465301,0.038938157,0.001849474,0.00006853615,0.0002545752,0.059446402,0.0016041484,0.0017085274,0.013974235,0.88172203,0.00021789344],"about_ca_topic_score_codex":0.97785723,"about_ca_topic_score_gemma":0.99201113,"teacher_disagreement_score":0.11130324,"about_ca_system_score_codex":0.11130324,"about_ca_system_score_gemma":0.1860145,"threshold_uncertainty_score":0.80756533},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20950317,0.0015836296,0.41641283,0.07861678,0.0011657954,0.0054493295,0.00015265119,0.00045829418,0.28665757],"genre_scores_gemma":[0.80660385,0.00069195585,0.17475218,0.0012103032,0.00010969955,0.0027796782,0.000100359604,0.0001055084,0.013646482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9106541,0.07313357,0.0021709679,0.0033175189,0.007336043,0.003387773],"domain_scores_gemma":[0.8924832,0.06570368,0.005832839,0.006971171,0.018187877,0.010821314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11443396,0.0005323138,0.00054689124,0.003279301,0.009263548,0.014036881,0.0030626594,0.0029615571,0.005315356],"category_scores_gemma":[0.10934793,0.00047333652,0.00042014066,0.0017717023,0.014547339,0.016679978,0.019340536,0.0042482447,0.0009668427],"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":[0.00010879408,0.0008444895,0.011235588,0.00068187667,0.000036469122,0.0006586818,0.1583849,0.006017079,0.0013567955,0.53405565,0.015284203,0.2713355],"study_design_scores_gemma":[0.0000887698,0.0007363238,0.008861965,0.0025159684,0.00004413803,0.0005537974,0.20764737,0.015145694,0.004991697,0.3284539,0.43077236,0.00018789807],"about_ca_topic_score_codex":0.0034499546,"about_ca_topic_score_gemma":0.0053789807,"teacher_disagreement_score":0.11443396,"about_ca_system_score_codex":0.016410565,"about_ca_system_score_gemma":0.035463106,"threshold_uncertainty_score":0.6051918},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890938,0.0003384634,0.00008575146,0.0013004136,0.000032709388,0.00016449002,0.0008072854,0.00003611347,0.008141096],"genre_scores_gemma":[0.98775417,0.00021422606,0.0002498678,0.00014402551,0.000008822455,0.0000805243,0.00063949317,0.000010577844,0.010898348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960257,0.00037037412,0.0001051096,0.00019574366,0.0011538236,0.0021492792],"domain_scores_gemma":[0.98418,0.00080582494,0.001019947,0.0002323546,0.005861436,0.00790046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024792429,0.0002957842,0.00060887594,0.0010387558,0.0060608243,0.0025213137,0.0020237716,0.0009758087,0.003211339],"category_scores_gemma":[0.007865335,0.0004937163,0.00041268245,0.0016127487,0.0013367682,0.0011753533,0.002850639,0.0014815073,0.00072879985],"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":[0.0022288654,0.0025015944,0.83403116,0.00024619428,0.000046282454,0.0006607702,0.027164806,0.0007711772,0.0013916501,0.0010777996,0.018252295,0.11162742],"study_design_scores_gemma":[0.000034545687,0.00034325838,0.9743285,0.00007796678,0.000013821893,0.000027486596,0.017515562,0.00028717835,0.00048039877,0.000089559246,0.006780332,0.00002138214],"about_ca_topic_score_codex":0.9829783,"about_ca_topic_score_gemma":0.9953577,"teacher_disagreement_score":0.9171583,"about_ca_system_score_codex":0.08284171,"about_ca_system_score_gemma":0.11884028,"threshold_uncertainty_score":0.60106146},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7311859,0.0031907428,0.027975757,0.08717054,0.0007121017,0.0046343133,0.00017213578,0.0003988419,0.14455956],"genre_scores_gemma":[0.95100904,0.0016599039,0.037198912,0.0035123162,0.000064562635,0.0014239057,0.00006518322,0.000056337885,0.005009919],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95373404,0.038788084,0.0010741177,0.00085155276,0.0030186495,0.0025335767],"domain_scores_gemma":[0.9705095,0.014396343,0.002045609,0.002249256,0.0050228196,0.0057764435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056862958,0.0005671984,0.00037341967,0.0010637824,0.011772599,0.0052815042,0.0022204183,0.0014251011,0.0035442528],"category_scores_gemma":[0.053061936,0.00035940998,0.00064168515,0.0006404714,0.008476962,0.00372733,0.016823558,0.0031523216,0.00034336644],"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":[0.00019179366,0.0013452373,0.014040808,0.0017317489,0.00005439006,0.00212728,0.5871722,0.0005907694,0.0019732995,0.016350105,0.014935484,0.3594869],"study_design_scores_gemma":[0.00015529066,0.0009447729,0.021385835,0.0043139732,0.00012599806,0.0011729664,0.78132445,0.0009000293,0.004782165,0.016039228,0.16872993,0.00012536606],"about_ca_topic_score_codex":0.0295283,"about_ca_topic_score_gemma":0.09016111,"teacher_disagreement_score":0.056862958,"about_ca_system_score_codex":0.01448798,"about_ca_system_score_gemma":0.071313016,"threshold_uncertainty_score":0.30072367},"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":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027722096,0.036690705,0.007226912,0.016128074,0.0007888678,0.00023738225,0.0004961783,0.00039001417,0.9103199],"genre_scores_gemma":[0.41398892,0.04975731,0.016776688,0.0031720127,0.0001923049,0.00012393104,0.0005754676,0.00025801727,0.51515543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99411994,0.0005048578,0.00016269243,0.00033596193,0.003664155,0.00121235],"domain_scores_gemma":[0.9954146,0.0005617024,0.00013722538,0.00013915726,0.0033052084,0.00044210252],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030553467,0.00038383954,0.0003821875,0.0038802573,0.008900609,0.00876548,0.0014130097,0.0011125263,0.005132258],"category_scores_gemma":[0.0056641554,0.0004834747,0.00032245403,0.008882854,0.003906597,0.0017047605,0.0018161563,0.001681413,0.0009268602],"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":[0.00003595599,0.0000416271,0.0036173998,0.0004022393,0.000010979164,0.00029986465,0.0064717946,0.003401136,0.00078392215,0.47402388,0.14558859,0.3653226],"study_design_scores_gemma":[0.0000050467083,0.000013643238,0.009363346,0.00045227577,0.000009041836,0.00011264478,0.0024140717,0.0015819598,0.00071578915,0.010502673,0.97477585,0.000053666758],"about_ca_topic_score_codex":0.9859656,"about_ca_topic_score_gemma":0.99200636,"teacher_disagreement_score":0.99694467,"about_ca_system_score_codex":0.16896181,"about_ca_system_score_gemma":0.23750652,"threshold_uncertainty_score":0.9638865},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99097484,0.000107963926,0.0010944159,0.0001296331,0.000018679017,0.0033843513,0.00017658487,0.000116457966,0.003997006],"genre_scores_gemma":[0.97761506,0.0003978227,0.015504336,0.00011608987,0.000033699223,0.0036114121,0.00046714692,0.00002391215,0.0022306065],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947068,0.002967927,0.00028193637,0.00040628854,0.0011508022,0.00048626369],"domain_scores_gemma":[0.9824286,0.0070909103,0.0020419436,0.00069882395,0.0044388277,0.0033008629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009425188,0.0005567441,0.00047284883,0.0010855007,0.0010090893,0.0009639059,0.0015551856,0.00039592246,0.002285434],"category_scores_gemma":[0.01837519,0.00024200961,0.00039929055,0.00066928926,0.00050097844,0.0005473919,0.000771994,0.0006704246,0.00060198683],"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":[0.010452145,0.08383094,0.2632343,0.001467021,0.0004931505,0.00026385166,0.008969143,0.003755892,0.013784392,0.00046692262,0.0039917906,0.6092905],"study_design_scores_gemma":[0.0035384686,0.21470392,0.7378455,0.0004061241,0.0008590902,0.00013493028,0.011567331,0.0074545224,0.015879475,0.00015725066,0.007339343,0.00011405205],"about_ca_topic_score_codex":0.016627355,"about_ca_topic_score_gemma":0.045426298,"teacher_disagreement_score":0.016627355,"about_ca_system_score_codex":0.00277039,"about_ca_system_score_gemma":0.007219529,"threshold_uncertainty_score":0.049845755},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018010048,0.0069101593,0.029295726,0.6024801,0.2872885,0.008632581,0.0014680012,0.00069040427,0.045224503],"genre_scores_gemma":[0.14498344,0.01170332,0.07257496,0.18334292,0.15756473,0.028187739,0.006723966,0.002764632,0.39215428],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.97414714,0.012002227,0.0014499772,0.0022508414,0.00537101,0.0047788476],"domain_scores_gemma":[0.8847706,0.01709002,0.0035704314,0.004155515,0.028342763,0.062070627],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08225887,0.0030475045,0.0019986054,0.0019277637,0.014512224,0.018428082,0.0062858406,0.027909292,0.028789192],"category_scores_gemma":[0.06300625,0.0014057825,0.0029611024,0.001322062,0.0069298544,0.011235001,0.026264532,0.02921481,0.01495465],"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":[0.00041864018,0.0004814279,0.0009708218,0.0010193607,0.000059331374,0.0004740491,0.027573027,0.0005115959,0.0030567471,0.016606841,0.90921396,0.039614215],"study_design_scores_gemma":[0.00012086805,0.00032056533,0.0011920293,0.0011663967,0.000022023423,0.00021251333,0.020509265,0.00026973977,0.00081882847,0.012267262,0.96297,0.00013049933],"about_ca_topic_score_codex":0.0047064936,"about_ca_topic_score_gemma":0.0064262054,"teacher_disagreement_score":0.9177411,"about_ca_system_score_codex":0.008958202,"about_ca_system_score_gemma":0.043377515,"threshold_uncertainty_score":0.4350317},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3689816,0.021419516,0.008966116,0.466176,0.0012698331,0.0021557834,0.00036396156,0.0002534481,0.13041371],"genre_scores_gemma":[0.90570754,0.013919582,0.022650115,0.02867581,0.00013748455,0.0007844772,0.00023715041,0.000063619846,0.027824331],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98930675,0.0050664116,0.00017215303,0.0002257688,0.0011134307,0.0041154646],"domain_scores_gemma":[0.9834235,0.0061792973,0.0007082052,0.0005060564,0.0033145922,0.005868417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017144933,0.0008623362,0.0004849251,0.001502272,0.011560776,0.01011825,0.003292202,0.0034429238,0.0048819156],"category_scores_gemma":[0.012906663,0.00038077068,0.00055448915,0.0024387862,0.007257196,0.0024040753,0.009446828,0.005532344,0.0003541003],"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":[0.00061337405,0.005476365,0.08763893,0.0030840915,0.00035127904,0.006608863,0.05524766,0.014049622,0.0039643915,0.359934,0.07683706,0.3861943],"study_design_scores_gemma":[0.0006809441,0.0017539796,0.09639132,0.0076158126,0.00028231094,0.0007592686,0.29870108,0.00929346,0.0041762684,0.073694475,0.5063059,0.00034525327],"about_ca_topic_score_codex":0.6696023,"about_ca_topic_score_gemma":0.8877638,"teacher_disagreement_score":0.33039773,"about_ca_system_score_codex":0.055151183,"about_ca_system_score_gemma":0.25555992,"threshold_uncertainty_score":0.664687},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011939651,0.17061768,0.0013813644,0.4843059,0.019889522,0.00012487093,0.0017568184,0.00018535981,0.3097989],"genre_scores_gemma":[0.35984218,0.35485044,0.008216549,0.107109934,0.007542201,0.0002399762,0.0021326712,0.0005837801,0.15948227],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98122483,0.0029267052,0.00085109257,0.0014519183,0.008919845,0.0046255537],"domain_scores_gemma":[0.9542229,0.012126961,0.0014528355,0.0013702563,0.02252188,0.008305098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013453553,0.0007017322,0.001206226,0.009757228,0.03645304,0.02864509,0.003172096,0.0051397937,0.021285158],"category_scores_gemma":[0.029900312,0.0007853127,0.0006782279,0.024635047,0.017986905,0.00834109,0.0069791125,0.005629555,0.0016993702],"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":[0.0000364405,0.000043296994,0.0036342724,0.0016101758,0.000034205797,0.0006014086,0.043431465,0.00025520346,0.00032258418,0.3176359,0.5361887,0.096206404],"study_design_scores_gemma":[0.0000044511453,0.000006755505,0.003078864,0.0010411721,0.000010961702,0.000083186234,0.017861966,0.00006044428,0.00007426512,0.005428056,0.97230744,0.000042265296],"about_ca_topic_score_codex":0.9897048,"about_ca_topic_score_gemma":0.99501085,"teacher_disagreement_score":0.74281317,"about_ca_system_score_codex":0.25718683,"about_ca_system_score_gemma":0.47552866,"threshold_uncertainty_score":0.86155796},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6742236,0.008080326,0.12288592,0.050433844,0.0015007977,0.0009558237,0.00011399966,0.00048886094,0.14131677],"genre_scores_gemma":[0.97427034,0.0007570565,0.020526119,0.0006296936,0.000099580706,0.00016583738,0.000023804014,0.000045156445,0.0034823588],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9008527,0.08359285,0.0020660176,0.0015713784,0.010059718,0.0018573288],"domain_scores_gemma":[0.82207584,0.13523749,0.010414666,0.0038957554,0.018271891,0.010104387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.077650934,0.0008668706,0.00090737286,0.0027078448,0.00450049,0.015005717,0.00165362,0.0031194212,0.0029891077],"category_scores_gemma":[0.16481082,0.00025449076,0.00044101998,0.0024653184,0.010531028,0.011472879,0.0044582835,0.0035684844,0.00067097624],"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":[0.0009951718,0.0015506393,0.055485718,0.0009005972,0.00017084848,0.00016289219,0.037067655,0.008179728,0.0015379126,0.19655138,0.010312215,0.6870853],"study_design_scores_gemma":[0.0002051854,0.0023963624,0.049697828,0.0023438362,0.00025823968,0.00019886172,0.0876453,0.06158623,0.010996649,0.72610193,0.05813549,0.0004341352],"about_ca_topic_score_codex":0.0038647712,"about_ca_topic_score_gemma":0.0039826445,"teacher_disagreement_score":0.077650934,"about_ca_system_score_codex":0.004625176,"about_ca_system_score_gemma":0.012994449,"threshold_uncertainty_score":0.4106623},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9185853,0.0008849551,0.05880079,0.0037989893,0.000048462985,0.00066200853,0.0018963317,0.00028862103,0.015034518],"genre_scores_gemma":[0.9768325,0.00012383141,0.021481011,0.000070900816,0.000023569355,0.00022728412,0.0007707809,0.00003127442,0.00043882604],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97633535,0.019013228,0.0013237274,0.00076437736,0.002112226,0.0004511756],"domain_scores_gemma":[0.8229765,0.15126517,0.00908312,0.003994525,0.011811471,0.0008692218],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022033785,0.00048286814,0.0005962981,0.0069777346,0.00082470605,0.004298218,0.0008499399,0.0006279459,0.0018165403],"category_scores_gemma":[0.106103174,0.00018307604,0.00065236806,0.0064876396,0.0013795188,0.00505839,0.0025839466,0.0014282893,0.00022411188],"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":[0.0006427816,0.00076875224,0.2679621,0.0016563461,0.0006687848,0.00046248137,0.031859234,0.03934302,0.0015462419,0.026015053,0.006473978,0.6226013],"study_design_scores_gemma":[0.00021442636,0.0009781319,0.27304044,0.0019504201,0.000672844,0.0001777228,0.07413198,0.49635765,0.009904895,0.12267816,0.019607672,0.0002856523],"about_ca_topic_score_codex":0.0069511747,"about_ca_topic_score_gemma":0.011938746,"teacher_disagreement_score":0.9779662,"about_ca_system_score_codex":0.0036609804,"about_ca_system_score_gemma":0.002150115,"threshold_uncertainty_score":0.11652714},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032263994,0.073189326,0.022790503,0.114519656,0.0038287954,0.00045553638,0.0006826347,0.00030657116,0.7810006],"genre_scores_gemma":[0.3303794,0.13172543,0.06498126,0.030137066,0.003563305,0.0009843344,0.0010910208,0.000825118,0.43631306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9523497,0.016203033,0.0016282155,0.0023140947,0.022296095,0.0052088164],"domain_scores_gemma":[0.9455807,0.032064132,0.0013685246,0.0025835775,0.015548947,0.002854038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032296624,0.00079662516,0.0013605608,0.006353662,0.015584737,0.030607844,0.0029052787,0.005480083,0.009905379],"category_scores_gemma":[0.064155586,0.00082793675,0.00053427764,0.014496466,0.03519248,0.0078845285,0.005606141,0.008074975,0.0019653833],"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":[0.0000054338147,0.0000066959556,0.00022822354,0.00019687538,0.000005643439,0.000045841454,0.004778703,0.00042875207,0.000031146523,0.9054555,0.060824618,0.02799248],"study_design_scores_gemma":[0.00000513024,0.000003340935,0.0007068559,0.00088143727,0.000006564506,0.000027788143,0.0049596997,0.00033131219,0.00007454641,0.13008489,0.86288536,0.000033100976],"about_ca_topic_score_codex":0.8530069,"about_ca_topic_score_gemma":0.88451177,"teacher_disagreement_score":0.8530069,"about_ca_system_score_codex":0.15452519,"about_ca_system_score_gemma":0.27379465,"threshold_uncertainty_score":0.98063093},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85702807,0.0046882587,0.00037352633,0.08683081,0.00019342988,0.000073807605,0.0011532626,0.000047892183,0.04961093],"genre_scores_gemma":[0.9766698,0.002242422,0.00030076166,0.003118413,0.000038909893,0.00002239164,0.00023008113,0.000023029,0.017354315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945462,0.0008243405,0.00014730066,0.00022472025,0.0013595854,0.0028979108],"domain_scores_gemma":[0.97217166,0.0030446665,0.0022434467,0.00022973417,0.008132242,0.014178182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037835392,0.00022580138,0.00040746256,0.003189016,0.015803952,0.012816947,0.002331005,0.0024607973,0.0072911964],"category_scores_gemma":[0.012535071,0.0002989726,0.00031589586,0.007869276,0.006490655,0.0027707836,0.003484166,0.0027908736,0.0003590697],"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":[0.00050161436,0.0005416577,0.5834886,0.00041837967,0.00013600815,0.0014848614,0.07738558,0.0025417486,0.00093489746,0.1330243,0.07691012,0.122632176],"study_design_scores_gemma":[0.00006383922,0.00006736063,0.59248203,0.0006698977,0.00007763068,0.0001424221,0.22821938,0.0018033466,0.0004578603,0.007294456,0.16856271,0.00015913566],"about_ca_topic_score_codex":0.9976927,"about_ca_topic_score_gemma":0.9990477,"teacher_disagreement_score":0.77103686,"about_ca_system_score_codex":0.22896317,"about_ca_system_score_gemma":0.37700415,"threshold_uncertainty_score":0.8942934},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75868964,0.05403216,0.019718021,0.044996783,0.00092869607,0.0251573,0.0036730224,0.0019181889,0.09088625],"genre_scores_gemma":[0.8414156,0.02773134,0.10609704,0.0034395223,0.00011966785,0.0061604492,0.002275459,0.00018947326,0.012571516],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9864232,0.0044197156,0.0008055193,0.000680177,0.0059339926,0.0017374486],"domain_scores_gemma":[0.9708185,0.005326753,0.002044836,0.0012482894,0.014527923,0.0060337055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023724865,0.00059805886,0.0006221309,0.004639238,0.004380435,0.0051938132,0.00246429,0.00093769736,0.0026171769],"category_scores_gemma":[0.02520445,0.00048404673,0.00057266664,0.0072536175,0.0019756623,0.0018767652,0.003661993,0.0020240007,0.00028335257],"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":[0.0005909246,0.0039089792,0.017820252,0.0036946558,0.00013911701,0.00017878553,0.011813302,0.0014987399,0.0017929659,0.008513903,0.024558514,0.9254898],"study_design_scores_gemma":[0.0032788566,0.0069769146,0.30440482,0.011069729,0.0014439798,0.00041172866,0.039185297,0.007597922,0.0149263935,0.003955976,0.60621786,0.0005305717],"about_ca_topic_score_codex":0.8532706,"about_ca_topic_score_gemma":0.9145686,"teacher_disagreement_score":0.9135164,"about_ca_system_score_codex":0.086483605,"about_ca_system_score_gemma":0.27930996,"threshold_uncertainty_score":0.6274854},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048198767,0.73969585,0.07458205,0.083292015,0.0017248464,0.0038744106,0.0013251357,0.00017814658,0.047128875],"genre_scores_gemma":[0.5018679,0.36793703,0.11185008,0.009592909,0.0004810798,0.005275796,0.0007307431,0.00014255535,0.002121969],"study_design_codex":"qualitative","study_design_gemma":"systematic_review","domain_scores_codex":[0.8905732,0.06810565,0.014455629,0.0061152065,0.016965711,0.0037846249],"domain_scores_gemma":[0.7004648,0.24339437,0.011718897,0.006875928,0.034650527,0.00289548],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15885517,0.0014473399,0.0030875732,0.037376232,0.012936885,0.03775045,0.0038309728,0.0046245945,0.0034428993],"category_scores_gemma":[0.20468359,0.0013114936,0.0021501982,0.046244785,0.014419113,0.023288205,0.014209642,0.004365587,0.00036774515],"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":[0.00021512965,0.000116766365,0.0066606607,0.079142235,0.00069452485,0.0010978556,0.42656314,0.0011144874,0.0013307442,0.16775937,0.01005743,0.30524772],"study_design_scores_gemma":[0.000100944664,0.00016400914,0.011167239,0.1434906,0.0016759847,0.0008308698,0.45675585,0.0013718285,0.0012081085,0.09656108,0.28648648,0.00018694456],"about_ca_topic_score_codex":0.136516,"about_ca_topic_score_gemma":0.24531451,"teacher_disagreement_score":0.8411448,"about_ca_system_score_codex":0.0546553,"about_ca_system_score_gemma":0.16432701,"threshold_uncertainty_score":0.8401165},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36580926,0.002209097,0.53365564,0.010464409,0.00048442822,0.006524444,0.0019856046,0.00058408186,0.07828297],"genre_scores_gemma":[0.78231734,0.00041488567,0.21155648,0.0007338268,0.00005139621,0.0032672724,0.0005929978,0.000108981076,0.0009568186],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.8267537,0.12213585,0.010042201,0.007208976,0.030736296,0.0031230063],"domain_scores_gemma":[0.59458596,0.28700095,0.020389799,0.034865644,0.06140463,0.001752984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1772847,0.0012406252,0.0014237948,0.008705346,0.003125612,0.007677546,0.0031601393,0.0021139132,0.0043034256],"category_scores_gemma":[0.5195755,0.0012180343,0.0022796916,0.01034605,0.0059824167,0.0065543656,0.010378558,0.0036675048,0.0006307717],"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":[0.00053746015,0.0004899507,0.3660946,0.0035356903,0.0013767275,0.00040880678,0.024669234,0.05986282,0.0014290398,0.17599152,0.006681395,0.35892278],"study_design_scores_gemma":[0.00046745467,0.0021563414,0.3850152,0.008525155,0.0019068249,0.00044226414,0.037521757,0.14757316,0.012152896,0.29147097,0.112196885,0.0005710821],"about_ca_topic_score_codex":0.09259604,"about_ca_topic_score_gemma":0.098916985,"teacher_disagreement_score":0.1772847,"about_ca_system_score_codex":0.018069915,"about_ca_system_score_gemma":0.026284656,"threshold_uncertainty_score":0.9375823},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014432336,0.09929142,0.001991047,0.14498861,0.002578804,0.00004952373,0.000080332065,0.00010450034,0.7494725],"genre_scores_gemma":[0.22508378,0.18579008,0.0061587514,0.041715264,0.007269285,0.0002469607,0.00021021518,0.00027987835,0.53324574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9857853,0.006503645,0.00037825023,0.00084624067,0.0045648804,0.0019216443],"domain_scores_gemma":[0.9872658,0.0072369524,0.0006857578,0.0007487717,0.0025735581,0.0014891686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011023568,0.00091648527,0.0009368441,0.003177793,0.0126874475,0.027342254,0.001956544,0.0067998017,0.018367575],"category_scores_gemma":[0.017082138,0.00048148696,0.00042191803,0.009317229,0.032112524,0.010860341,0.005088791,0.008977285,0.004654973],"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":[0.00000603297,0.000017196235,0.000107596665,0.00014405276,0.0000039233555,0.00002133064,0.0024191514,0.00017837067,0.00002185538,0.90433794,0.063675344,0.029067222],"study_design_scores_gemma":[0.0000051541488,0.0000062147724,0.00022867974,0.00056166603,0.000003817606,0.000020035432,0.0018727378,0.000105473286,0.0000511569,0.19519246,0.80194426,0.000008392892],"about_ca_topic_score_codex":0.08636126,"about_ca_topic_score_gemma":0.09346242,"teacher_disagreement_score":0.08636126,"about_ca_system_score_codex":0.04978015,"about_ca_system_score_gemma":0.07226411,"threshold_uncertainty_score":0.3611819},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005464619,0.004128284,0.0041269925,0.79235053,0.018312305,0.0001387492,0.00056474376,0.000924182,0.17398961],"genre_scores_gemma":[0.07096743,0.0031468,0.005265561,0.2938289,0.008827831,0.00043596403,0.00038186775,0.0021492778,0.6149965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99541265,0.0023366064,0.00011470814,0.0006267005,0.00102377,0.00048547308],"domain_scores_gemma":[0.990515,0.003215878,0.00037413737,0.0007430789,0.0018249265,0.0033269692],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.0068635144,0.0006890331,0.00043780933,0.000612233,0.009461488,0.0066503203,0.0009478606,0.005298554,0.09136891],"category_scores_gemma":[0.028139617,0.0005591593,0.00043237957,0.0006202358,0.0031516922,0.007602667,0.0056075496,0.009826227,0.047251448],"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":[0.000011684848,0.000019304818,0.00027382225,0.000018505129,0.0000023388716,0.00008042241,0.006215484,0.0000081899525,0.000086118125,0.0042835413,0.9769135,0.012087119],"study_design_scores_gemma":[0.000004259887,0.000008656785,0.00034710925,0.00005084504,0.0000019784377,0.00006990174,0.004049159,0.000016103071,0.000060898892,0.0013032279,0.99407476,0.00001307107],"about_ca_topic_score_codex":0.01924894,"about_ca_topic_score_gemma":0.05005998,"teacher_disagreement_score":0.99938774,"about_ca_system_score_codex":0.0028487758,"about_ca_system_score_gemma":0.0028179167,"threshold_uncertainty_score":0.30565947},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8970105,0.00390001,0.0014975393,0.007299127,0.000035971567,0.00047068045,0.036392555,0.000056285822,0.053337503],"genre_scores_gemma":[0.9828147,0.0018693823,0.0016668917,0.0004391147,0.000009640326,0.00020544085,0.005569622,0.000025983545,0.007399172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99470735,0.0005211346,0.00028747364,0.0004106927,0.00300037,0.0010729486],"domain_scores_gemma":[0.9756393,0.0063789254,0.0038084527,0.001190297,0.011280979,0.0017020196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043516527,0.0001673611,0.00032975292,0.0053978353,0.005457388,0.0025030107,0.0009149231,0.00041463558,0.003089607],"category_scores_gemma":[0.02131058,0.00033852895,0.0002948348,0.020659452,0.001705018,0.0011541542,0.0025905394,0.00055343023,0.00017380429],"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":[0.00016300319,0.00004227862,0.7931365,0.0011498798,0.000098123055,0.00040240234,0.069957,0.00071455934,0.00113791,0.008625702,0.017884392,0.10668834],"study_design_scores_gemma":[0.00000711522,0.000020692009,0.90196633,0.0003017852,0.00004359336,0.000042977143,0.03427761,0.0002742314,0.0004001319,0.0006891367,0.0619545,0.000021846865],"about_ca_topic_score_codex":0.99332327,"about_ca_topic_score_gemma":0.9974141,"teacher_disagreement_score":0.080792286,"about_ca_system_score_codex":0.080792286,"about_ca_system_score_gemma":0.16747221,"threshold_uncertainty_score":0.5861918},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018185655,0.015196907,0.8745622,0.041174226,0.0034682946,0.0029894763,0.00040459054,0.0007268426,0.043291755],"genre_scores_gemma":[0.23526318,0.009094978,0.72378707,0.013484768,0.0015248916,0.008446133,0.00049054506,0.00058321457,0.007325178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4570781,0.44416085,0.021809446,0.022898465,0.051110227,0.002942838],"domain_scores_gemma":[0.37807763,0.43757853,0.021151802,0.09710554,0.064103186,0.001983374],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4118213,0.0029090452,0.0038509162,0.008015592,0.005922588,0.01856373,0.0053515495,0.0060583316,0.005133573],"category_scores_gemma":[0.5309756,0.0018548585,0.0037977684,0.007416267,0.028653745,0.022703672,0.008086073,0.01048075,0.0031417725],"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":[0.00043272212,0.0003872963,0.013403183,0.006986352,0.0016701662,0.0003280894,0.0345528,0.0020309277,0.002918381,0.5072932,0.011447345,0.41854957],"study_design_scores_gemma":[0.0004681406,0.0016121551,0.0177621,0.019413298,0.0011658316,0.0012084258,0.023817863,0.008735086,0.010353287,0.6685408,0.24628794,0.0006350921],"about_ca_topic_score_codex":0.0084545445,"about_ca_topic_score_gemma":0.007007272,"teacher_disagreement_score":0.5881787,"about_ca_system_score_codex":0.008061038,"about_ca_system_score_gemma":0.026859919,"threshold_uncertainty_score":0.72532904},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031952336,0.010321078,0.8115804,0.0169335,0.00050529104,0.0029231508,0.0012098942,0.0012033087,0.12337096],"genre_scores_gemma":[0.31061685,0.00514884,0.6652822,0.0014197184,0.0003432948,0.00501861,0.000605202,0.00060900126,0.010956322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.769573,0.14493804,0.01101428,0.0074311164,0.06481395,0.0022296878],"domain_scores_gemma":[0.53693044,0.37403783,0.012468005,0.025629835,0.049737163,0.0011967324],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.118975766,0.0020564299,0.00292278,0.02583858,0.0032385774,0.03168595,0.004094876,0.004550924,0.018185034],"category_scores_gemma":[0.26805058,0.0018146021,0.0030490102,0.020246081,0.013098082,0.017919365,0.005851766,0.005280252,0.0032471593],"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":[0.00029636017,0.0003497799,0.0096517205,0.0056264848,0.0006168436,0.00012164894,0.010467152,0.008722289,0.0021255668,0.60626745,0.0059587867,0.34979594],"study_design_scores_gemma":[0.00063039194,0.0010353478,0.026076477,0.012278062,0.0011040946,0.0007570073,0.019155193,0.079122536,0.019730326,0.6344157,0.20512737,0.0005674948],"about_ca_topic_score_codex":0.013601956,"about_ca_topic_score_gemma":0.0076952614,"teacher_disagreement_score":0.96831405,"about_ca_system_score_codex":0.016585305,"about_ca_system_score_gemma":0.017287364,"threshold_uncertainty_score":0.62921154},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63375473,0.002936241,0.008770725,0.0404055,0.00056909985,0.0017039902,0.00043985312,0.00015301646,0.31126675],"genre_scores_gemma":[0.97921926,0.001210931,0.0067440034,0.0017595395,0.000026908603,0.00038151053,0.00009655862,0.000062076724,0.010499133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9750093,0.019076908,0.0006220211,0.0005635007,0.0030772886,0.0016508834],"domain_scores_gemma":[0.9747166,0.01281292,0.0015976294,0.001975292,0.005366831,0.0035306874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03898979,0.0005934358,0.0004162589,0.0014957777,0.0041495585,0.0078082127,0.00095113774,0.0012134117,0.005338823],"category_scores_gemma":[0.041613907,0.0003109945,0.00036774727,0.0015647396,0.00491082,0.0038280697,0.008593741,0.00292616,0.0004977052],"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":[0.0005505218,0.0007828498,0.08732533,0.0021214623,0.00013738839,0.002637105,0.29664174,0.002339215,0.0041211625,0.09038303,0.020364402,0.4925958],"study_design_scores_gemma":[0.000089629226,0.0021121658,0.07117392,0.0040533007,0.00030430328,0.0013148434,0.43536615,0.0041870363,0.01652188,0.029953273,0.43469355,0.00022991626],"about_ca_topic_score_codex":0.01638146,"about_ca_topic_score_gemma":0.015640235,"teacher_disagreement_score":0.03898979,"about_ca_system_score_codex":0.009327987,"about_ca_system_score_gemma":0.017157827,"threshold_uncertainty_score":0.20620024},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83032256,0.00036288513,0.0032595282,0.025280863,0.00021315893,0.00042052794,0.00013426442,0.000060343613,0.13994572],"genre_scores_gemma":[0.98819506,0.0003431687,0.0018837668,0.0008331536,0.000040368595,0.00019817302,0.000037219877,0.000024875066,0.0084441565],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9837736,0.010380299,0.00019290061,0.00046919665,0.0025536725,0.0026303579],"domain_scores_gemma":[0.9865546,0.0052721743,0.0015206548,0.00057688594,0.002793676,0.0032820278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006410117,0.00033583373,0.00027045648,0.0019251003,0.0072352495,0.0066375243,0.0013617435,0.0011662635,0.007900725],"category_scores_gemma":[0.031935055,0.0002618216,0.00020196472,0.0017277901,0.0042120228,0.003908384,0.0053104116,0.0024732323,0.00059146027],"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":[0.00032271675,0.0010475806,0.10427602,0.0007672136,0.000121963756,0.0023634853,0.23118894,0.0019554235,0.0022130727,0.13149175,0.07050887,0.4537431],"study_design_scores_gemma":[0.000040726107,0.0011459349,0.0938033,0.0013689968,0.00010408627,0.0008515228,0.6768065,0.0021367925,0.0025966535,0.012010875,0.20900601,0.00012864148],"about_ca_topic_score_codex":0.016570738,"about_ca_topic_score_gemma":0.04966354,"teacher_disagreement_score":0.016570738,"about_ca_system_score_codex":0.012149172,"about_ca_system_score_gemma":0.013651204,"threshold_uncertainty_score":0.08814883},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001020686,0.0014793172,0.0001778691,0.3595703,0.6342458,0.000040514024,0.00013811013,0.00006487429,0.004181208],"genre_scores_gemma":[0.0017493305,0.0018545586,0.0007523719,0.60105073,0.3483057,0.00016656394,0.00008123362,0.00009235787,0.045947064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9848316,0.0017452309,0.002198349,0.0023345018,0.007494464,0.0013959457],"domain_scores_gemma":[0.9267165,0.019949324,0.0036952794,0.0030560386,0.040386185,0.006196702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021694392,0.0018067395,0.0020381205,0.0029731097,0.005175034,0.009633575,0.005126462,0.030518448,0.019403867],"category_scores_gemma":[0.14048252,0.001104353,0.0030400758,0.0022537562,0.0030331076,0.0052986243,0.0023387412,0.03223159,0.015677955],"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":[0.000012328802,0.00000817717,0.000051353894,0.00003905398,0.000007433712,0.00007644297,0.000021943846,0.000019732997,0.000021326448,0.00057594513,0.9971263,0.0020398903],"study_design_scores_gemma":[0.000033187163,0.000012002023,0.0003415615,0.00018685493,0.000022193562,0.000106301166,0.000083066596,0.00008468361,0.00010868243,0.0008956088,0.9981007,0.000025169355],"about_ca_topic_score_codex":0.011308815,"about_ca_topic_score_gemma":0.017211067,"teacher_disagreement_score":0.030518448,"about_ca_system_score_codex":0.0061352686,"about_ca_system_score_gemma":0.012259628,"threshold_uncertainty_score":0.114732265},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032788962,0.010332228,0.6042263,0.20116481,0.0022070785,0.0011791938,0.00025835435,0.0008998008,0.14694324],"genre_scores_gemma":[0.6451907,0.0050973254,0.32587737,0.009620631,0.00038593882,0.0018717084,0.00016685281,0.00049136556,0.011298089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93930966,0.05177737,0.0010910515,0.0014639925,0.0053456123,0.0010122064],"domain_scores_gemma":[0.9001199,0.07495884,0.003877532,0.0077315695,0.010841531,0.0024706183],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.067496195,0.0007901227,0.00087769446,0.005335294,0.0053236866,0.015564443,0.0020409285,0.0039817896,0.009498235],"category_scores_gemma":[0.11738776,0.0007205025,0.00087650097,0.0057086023,0.022385575,0.030806186,0.006730113,0.0067701326,0.00136972],"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":[0.00009111823,0.0001075812,0.0019839716,0.0004078444,0.000028803528,0.000073733936,0.010300893,0.0014528859,0.00014952847,0.868245,0.013974773,0.103183925],"study_design_scores_gemma":[0.000088180735,0.00017136573,0.0019034892,0.0028442,0.000046160483,0.00007816673,0.017641194,0.008030143,0.00062067364,0.8633543,0.10513743,0.00008473274],"about_ca_topic_score_codex":0.019215463,"about_ca_topic_score_gemma":0.0291831,"teacher_disagreement_score":0.9325038,"about_ca_system_score_codex":0.017735776,"about_ca_system_score_gemma":0.023695024,"threshold_uncertainty_score":0.35695827},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079575986,0.008430371,0.09880889,0.52289516,0.00326143,0.0011505601,0.0005724943,0.0008340358,0.28447115],"genre_scores_gemma":[0.92806524,0.004341299,0.039374545,0.019838521,0.0004013434,0.0007723531,0.00024104153,0.00026204865,0.0067035463],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9411583,0.039547667,0.002155327,0.0017459939,0.011804256,0.0035884487],"domain_scores_gemma":[0.91655666,0.040504463,0.0062168376,0.008026938,0.024984317,0.0037108026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052674655,0.00050884066,0.0010275934,0.0023495103,0.0029666994,0.011977762,0.0025452913,0.004892344,0.012409237],"category_scores_gemma":[0.15196842,0.00041356045,0.001175649,0.0032764003,0.0077640843,0.012620206,0.0032606295,0.005025745,0.0032481565],"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":[0.00027314248,0.0010163971,0.045180283,0.004012634,0.00026664344,0.00030168562,0.014163745,0.0032356947,0.0006583977,0.41671523,0.05547487,0.45870128],"study_design_scores_gemma":[0.0002723147,0.0021559263,0.050963785,0.014090123,0.00064243266,0.0010232528,0.0826837,0.022041334,0.006206555,0.40520296,0.4143643,0.00035326922],"about_ca_topic_score_codex":0.00985094,"about_ca_topic_score_gemma":0.008735023,"teacher_disagreement_score":0.052674655,"about_ca_system_score_codex":0.009108699,"about_ca_system_score_gemma":0.018237408,"threshold_uncertainty_score":0.2785735},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024834111,0.0008145169,0.9341268,0.0046148743,0.00024198709,0.004779272,0.00025385362,0.00035602142,0.029978499],"genre_scores_gemma":[0.40091026,0.00046712902,0.58923715,0.00058232364,0.000043913504,0.007612561,0.00016124776,0.000100120815,0.0008852998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6669112,0.3042743,0.005982872,0.007918364,0.0132142,0.0016991568],"domain_scores_gemma":[0.5476487,0.38129118,0.01871288,0.029542523,0.020195827,0.0026088273],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23320101,0.0018886692,0.0022146495,0.0058490457,0.00359972,0.010902235,0.0039631603,0.0029366617,0.008679924],"category_scores_gemma":[0.33769426,0.0011286819,0.0023637929,0.003538313,0.015416517,0.012871948,0.01007703,0.0058678496,0.00088778377],"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":[0.0004883928,0.00089775474,0.01957136,0.0041077994,0.0012350158,0.00018295787,0.014480846,0.11677562,0.0010555477,0.6436063,0.0038882645,0.19371015],"study_design_scores_gemma":[0.0004825768,0.0011895966,0.006556317,0.004536991,0.00042795998,0.00009241816,0.009385366,0.21670869,0.0028985695,0.7329442,0.02458816,0.0001891511],"about_ca_topic_score_codex":0.007963577,"about_ca_topic_score_gemma":0.010459181,"teacher_disagreement_score":0.766799,"about_ca_system_score_codex":0.015015022,"about_ca_system_score_gemma":0.021931145,"threshold_uncertainty_score":0.9455997},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9794994,0.00044792274,0.00043138224,0.005413414,0.00002352996,0.000072539195,0.00017493764,0.00000976949,0.013927069],"genre_scores_gemma":[0.99852425,0.00020698326,0.00021646486,0.00011273067,0.0000069693556,0.000016987045,0.000056323555,0.0000023197456,0.00085696176],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951858,0.0015282829,0.00013538022,0.0002788356,0.0013612581,0.0015105195],"domain_scores_gemma":[0.9882804,0.0031902276,0.0034606447,0.00024376521,0.0021814068,0.0026435356],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054774196,0.0002025332,0.00026582828,0.0009550947,0.001790005,0.0037621043,0.0009507793,0.00056512107,0.0023514056],"category_scores_gemma":[0.016686816,0.00016013684,0.00039987528,0.0013609495,0.0019402889,0.0013264018,0.0019971414,0.0011513815,0.0001565199],"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":[0.00015880728,0.0006671377,0.9093812,0.00017485885,0.00010464865,0.000110425535,0.017245056,0.00073542504,0.00046566591,0.0041275844,0.0020736535,0.064755574],"study_design_scores_gemma":[0.000010219275,0.00015700955,0.9834699,0.00010835089,0.00004795851,0.000009700352,0.011672912,0.00049393735,0.00020139421,0.00073835923,0.003078114,0.000012155185],"about_ca_topic_score_codex":0.66919327,"about_ca_topic_score_gemma":0.79349065,"teacher_disagreement_score":0.9945226,"about_ca_system_score_codex":0.023114156,"about_ca_system_score_gemma":0.036365595,"threshold_uncertainty_score":0.6655098},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009891292,0.0034796018,0.16957635,0.69302,0.0040450604,0.0002558897,0.00029272362,0.0005490835,0.11889],"genre_scores_gemma":[0.7560239,0.005851338,0.17060058,0.03278971,0.0020035214,0.001112479,0.00042669722,0.001214824,0.029977012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95879775,0.033016115,0.0010859607,0.0014494009,0.0044530947,0.001197651],"domain_scores_gemma":[0.8779532,0.09158253,0.0027389082,0.013858003,0.009770689,0.00409676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08827783,0.0009073569,0.0006804931,0.0021635033,0.009002012,0.020243093,0.0023937866,0.004444743,0.0072014956],"category_scores_gemma":[0.07406461,0.00049058284,0.00071006315,0.002413021,0.04817071,0.023532193,0.008193519,0.014830931,0.000951202],"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":[0.000013930316,0.00002247175,0.00016007778,0.000057298093,0.0000036512329,0.000039177972,0.010716639,0.000273775,0.00013540559,0.9667585,0.013241318,0.0085776625],"study_design_scores_gemma":[0.00002437628,0.00002836676,0.00014729491,0.00056144904,0.000010820922,0.000048883587,0.010905231,0.001975135,0.00051929854,0.7482776,0.23746534,0.00003618192],"about_ca_topic_score_codex":0.010042888,"about_ca_topic_score_gemma":0.011500406,"teacher_disagreement_score":0.9117222,"about_ca_system_score_codex":0.015447314,"about_ca_system_score_gemma":0.028865853,"threshold_uncertainty_score":0.4668634},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084518903,0.13398059,0.0035329892,0.7361677,0.09811451,0.000021431259,0.00011864538,0.0001469756,0.027071893],"genre_scores_gemma":[0.09848252,0.23278546,0.014275464,0.1463703,0.46714568,0.00019164495,0.00026442084,0.00055588904,0.03992855],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926804,0.0029410038,0.00035989867,0.0011896783,0.002353408,0.00047565607],"domain_scores_gemma":[0.84567773,0.114828244,0.00272907,0.0032859598,0.025964169,0.007514747],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023479758,0.000665072,0.0013319731,0.005195245,0.0035175069,0.01702265,0.003028834,0.004980341,0.018771427],"category_scores_gemma":[0.07753252,0.00052606576,0.0005066958,0.0033564873,0.01628658,0.011602894,0.0037779252,0.012911208,0.0021940898],"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":[0.00005198082,0.00003568837,0.00042105326,0.00068073935,0.0000113085225,0.000075163545,0.0018424679,0.00026703096,0.00009797445,0.30901107,0.5914697,0.09603583],"study_design_scores_gemma":[0.00001598033,0.000017855624,0.0003374434,0.0019529662,0.000010244884,0.00008917533,0.0021368784,0.000609417,0.00008701418,0.13509598,0.8596118,0.000035212208],"about_ca_topic_score_codex":0.012930534,"about_ca_topic_score_gemma":0.015940158,"teacher_disagreement_score":0.97652024,"about_ca_system_score_codex":0.009768033,"about_ca_system_score_gemma":0.013954241,"threshold_uncertainty_score":0.1241743},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9086662,0.0013413016,0.0039146664,0.0039479425,0.0004293428,0.0010511182,0.0041888426,0.00013674806,0.07632382],"genre_scores_gemma":[0.98559433,0.0004584715,0.0038455776,0.00039478525,0.000028908265,0.00047800623,0.003078653,0.000065570435,0.006055631],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.97627693,0.005585606,0.0013847856,0.0015022678,0.011672992,0.0035773115],"domain_scores_gemma":[0.9103972,0.021648314,0.0022070261,0.0036670878,0.057663675,0.0044168043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044667725,0.00068589457,0.00085546327,0.005680935,0.0030976566,0.006058553,0.0023965097,0.0008665918,0.0038521674],"category_scores_gemma":[0.07381044,0.0002928902,0.00093485706,0.0054802545,0.0022690205,0.0020260457,0.004515501,0.0015511845,0.0007051455],"study_design_candidate":"bench_or_experimental","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":[0.0033196528,0.0021937245,0.54057056,0.00076339126,0.00084843935,0.00052716385,0.029370982,0.00713219,0.002373327,0.015210619,0.035160474,0.36252952],"study_design_scores_gemma":[0.00037809566,0.00071895984,0.87203854,0.0015839646,0.0004991227,0.00021428188,0.03343988,0.010509221,0.0061576823,0.002579194,0.07168474,0.0001963406],"about_ca_topic_score_codex":0.85801786,"about_ca_topic_score_gemma":0.8404303,"teacher_disagreement_score":0.94949764,"about_ca_system_score_codex":0.050502382,"about_ca_system_score_gemma":0.1176493,"threshold_uncertainty_score":0.36642212},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1744933,0.03136776,0.009911945,0.2470013,0.0030250598,0.000675219,0.0015836898,0.00021128643,0.5317304],"genre_scores_gemma":[0.7278617,0.011358221,0.0046086204,0.010153494,0.00029809124,0.0003139596,0.0005032615,0.0002396702,0.24466307],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98023903,0.0070244176,0.0004054498,0.0010339813,0.007906695,0.0033904866],"domain_scores_gemma":[0.95186055,0.017563164,0.0019118297,0.0014343791,0.018303793,0.008926232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023277316,0.0004393495,0.0005947137,0.0025074566,0.028750798,0.010406974,0.0034371305,0.0032336307,0.012164737],"category_scores_gemma":[0.046805553,0.0005116889,0.00038632093,0.0070409286,0.020449126,0.0034916091,0.007081091,0.004964887,0.0010325271],"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":true,"study_design_scores_codex":[0.000141163,0.00013228308,0.0055293827,0.0005453122,0.000015041251,0.00054188597,0.40135574,0.0005645486,0.0005266368,0.23970902,0.19112335,0.15981565],"study_design_scores_gemma":[0.000011497164,0.000021388812,0.011934946,0.000796989,0.000007158877,0.00015576855,0.1503542,0.00016156037,0.00037901677,0.00784402,0.8282825,0.000050928014],"about_ca_topic_score_codex":0.98260325,"about_ca_topic_score_gemma":0.99178106,"teacher_disagreement_score":0.72531676,"about_ca_system_score_codex":0.2746832,"about_ca_system_score_gemma":0.42492244,"threshold_uncertainty_score":0.84126467},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7719297,0.0063395454,0.042890143,0.04306656,0.0007892558,0.0030975644,0.00009475229,0.00017951819,0.13161287],"genre_scores_gemma":[0.9529728,0.0017326709,0.027454711,0.0039645648,0.00006209207,0.0010831492,0.000039436738,0.0000650687,0.012625354],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9406085,0.04604421,0.002205574,0.0017084095,0.0032307736,0.0062025087],"domain_scores_gemma":[0.9472362,0.03151507,0.0027336832,0.0036793693,0.0044685416,0.010367197],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045084737,0.00039645348,0.0008038282,0.00225304,0.013665992,0.008829222,0.0028449206,0.004980086,0.0033722825],"category_scores_gemma":[0.043953005,0.0011017396,0.00094976585,0.002135957,0.010280725,0.0050162873,0.01915777,0.005701486,0.0006954598],"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":[0.00038066978,0.0010559881,0.032449864,0.002450375,0.000112320195,0.08914016,0.56990534,0.0032274046,0.005415685,0.17147028,0.014793393,0.10959848],"study_design_scores_gemma":[0.00011898325,0.0013129206,0.015620281,0.002272617,0.000103657665,0.029328842,0.6057346,0.0025657231,0.0023921113,0.015422328,0.32483387,0.00029400398],"about_ca_topic_score_codex":0.022821648,"about_ca_topic_score_gemma":0.045955837,"teacher_disagreement_score":0.9549153,"about_ca_system_score_codex":0.009698328,"about_ca_system_score_gemma":0.03003196,"threshold_uncertainty_score":0.23843372},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86946446,0.00026892818,0.06616499,0.0042615174,0.00041899586,0.017112324,0.001283959,0.00095157296,0.040073235],"genre_scores_gemma":[0.88340014,0.00041115092,0.09864073,0.00072541623,0.000056924266,0.0070349225,0.00044311638,0.00016594518,0.009121634],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9697212,0.013972355,0.0041423696,0.0012728607,0.009181397,0.0017098067],"domain_scores_gemma":[0.8742912,0.038629316,0.0039598877,0.0076342407,0.0702594,0.0052259504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054122895,0.000648864,0.00048053742,0.0032157796,0.0042666644,0.0030879725,0.0015207712,0.0006794665,0.003606318],"category_scores_gemma":[0.10228829,0.0006390532,0.00050929264,0.0021825586,0.002924768,0.0014156712,0.0026357812,0.0021171132,0.00084039796],"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":[0.000616315,0.0018127551,0.13638929,0.0016353305,0.00008155979,0.0013157321,0.38249144,0.0026058655,0.03402123,0.0048669307,0.026638826,0.40752473],"study_design_scores_gemma":[0.0004970353,0.0029401993,0.42559385,0.0010260938,0.00013616856,0.0006122881,0.2584639,0.013954097,0.027109573,0.003400606,0.26528016,0.0009860407],"about_ca_topic_score_codex":0.5130775,"about_ca_topic_score_gemma":0.68002224,"teacher_disagreement_score":0.98018533,"about_ca_system_score_codex":0.01981468,"about_ca_system_score_gemma":0.05351921,"threshold_uncertainty_score":0.97958016},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9613406,0.0003258798,0.005720242,0.0013959049,0.0002652372,0.012072506,0.0004690338,0.0005518374,0.017858835],"genre_scores_gemma":[0.9192221,0.0005720737,0.050857432,0.0007303304,0.00020176043,0.015283583,0.00096730277,0.00009585361,0.012069545],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9697659,0.021745766,0.0012773366,0.00080532115,0.0049348655,0.0014708204],"domain_scores_gemma":[0.952078,0.020934217,0.0030322412,0.0024937496,0.011690343,0.009771397],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037004273,0.00048473195,0.000478119,0.001347296,0.00109193,0.0012088013,0.0013061751,0.00079494365,0.0041815112],"category_scores_gemma":[0.040296312,0.00024758835,0.0006654315,0.00075872027,0.0008127642,0.0006827941,0.003110389,0.00083937513,0.0006548598],"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":[0.01237331,0.0552964,0.029568013,0.0015967907,0.00020527488,0.00029102745,0.009583943,0.0041646133,0.0033423407,0.0018642735,0.013354843,0.8683593],"study_design_scores_gemma":[0.02561547,0.38706547,0.38562143,0.0035955529,0.0010981176,0.0008554264,0.022967886,0.016246941,0.031716984,0.0024318267,0.12245461,0.000330344],"about_ca_topic_score_codex":0.0022264854,"about_ca_topic_score_gemma":0.006219562,"teacher_disagreement_score":0.9629957,"about_ca_system_score_codex":0.0029868574,"about_ca_system_score_gemma":0.013739543,"threshold_uncertainty_score":0.19569963},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36142534,0.0012111845,0.550996,0.004279358,0.0012942806,0.031039238,0.0062945755,0.0051057953,0.038354173],"genre_scores_gemma":[0.32887068,0.00058864616,0.6436798,0.00050627877,0.00015606021,0.019808657,0.0034460232,0.00027175044,0.0026720103],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.8855933,0.04244329,0.026093619,0.003197715,0.040806506,0.0018655378],"domain_scores_gemma":[0.6279126,0.17854726,0.03063251,0.018051812,0.14184369,0.0030121764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14083514,0.0009909123,0.0014711252,0.01070416,0.0011953686,0.004350089,0.0027354471,0.0010651981,0.0025359578],"category_scores_gemma":[0.24099085,0.0008748181,0.0026088979,0.006861562,0.0010829944,0.0043420233,0.003129284,0.0021565107,0.0012525903],"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":[0.0005277101,0.0014821457,0.23052107,0.0014027101,0.00039415457,0.00015472891,0.005654799,0.0019422964,0.0038918566,0.0065770037,0.014232006,0.73321956],"study_design_scores_gemma":[0.00077356386,0.009278345,0.7139939,0.0045834826,0.00083071255,0.0015475873,0.01489895,0.07046923,0.032414377,0.015808903,0.13449776,0.0009032103],"about_ca_topic_score_codex":0.0025629424,"about_ca_topic_score_gemma":0.0036864253,"teacher_disagreement_score":0.85916483,"about_ca_system_score_codex":0.003032061,"about_ca_system_score_gemma":0.007739463,"threshold_uncertainty_score":0.7448163},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014807631,0.12700562,0.02373364,0.47651613,0.086622514,0.0014203285,0.0016406404,0.0010166727,0.28056374],"genre_scores_gemma":[0.00685531,0.07096934,0.018190246,0.09691774,0.014554405,0.0007739581,0.0009007302,0.00048307958,0.79035527],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806195,0.00064658833,0.00010861686,0.00009401816,0.0010255701,0.000063252846],"domain_scores_gemma":[0.9906929,0.005725177,0.00025515858,0.00014691577,0.002853059,0.00032676762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023225427,0.00075793004,0.0010183714,0.0023374788,0.0014474805,0.0026423302,0.0019075957,0.0039096335,0.04034255],"category_scores_gemma":[0.01085067,0.00048696366,0.000712934,0.0025030905,0.0014449174,0.0025948812,0.001076092,0.0036275508,0.020615462],"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":[0.000004709379,0.000018086603,0.000023364679,0.00015994674,0.0000020537097,0.00007732195,0.000053650347,0.000088738285,0.000048590682,0.0016537643,0.9716123,0.0262575],"study_design_scores_gemma":[0.00000771781,0.000020383755,0.00021674186,0.00044168453,0.0000048273705,0.0002817798,0.00011968276,0.00017667617,0.00008121126,0.002279397,0.99635834,0.000011556914],"about_ca_topic_score_codex":0.014240113,"about_ca_topic_score_gemma":0.06131649,"teacher_disagreement_score":0.04034255,"about_ca_system_score_codex":0.0034739394,"about_ca_system_score_gemma":0.0063083204,"threshold_uncertainty_score":0.13495922},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99694175,0.000055003962,0.00022881608,0.00025804056,0.0000026637156,0.00014493315,0.000054063537,0.0000049341998,0.0023098632],"genre_scores_gemma":[0.99885476,0.000048318772,0.0005878384,0.00005062301,9.632648e-7,0.0000758651,0.000048067184,0.0000025399377,0.00033118442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9844356,0.0044440585,0.00075592124,0.001012629,0.0057032323,0.0036485093],"domain_scores_gemma":[0.92838424,0.023063151,0.009132685,0.002951202,0.029939318,0.0065293666],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02320449,0.0004499706,0.0005361484,0.0067533776,0.016768469,0.00489308,0.0028780415,0.00096840714,0.0013812733],"category_scores_gemma":[0.04739523,0.00071596657,0.0004174451,0.00865444,0.007865978,0.0019238007,0.004692736,0.0018222894,0.00012284819],"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":[0.00018022006,0.000519723,0.62767476,0.0001840612,0.000045759723,0.00029989923,0.32099757,0.0005923452,0.0009191569,0.0049387035,0.0017798942,0.041867867],"study_design_scores_gemma":[0.000013178027,0.00012089489,0.5619986,0.000121608704,0.000017678285,0.000044939214,0.42916307,0.0018086229,0.00055282534,0.00049048354,0.0055967406,0.00007137303],"about_ca_topic_score_codex":0.94562435,"about_ca_topic_score_gemma":0.97145736,"teacher_disagreement_score":0.9767955,"about_ca_system_score_codex":0.099586904,"about_ca_system_score_gemma":0.12665504,"threshold_uncertainty_score":0.72255695},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021889121,0.015239017,0.020616865,0.0068641338,0.0009143755,0.00012887709,0.00013448327,0.00023209717,0.95368123],"genre_scores_gemma":[0.06414402,0.02887063,0.032689445,0.0022819021,0.00078633666,0.00021437141,0.00038192226,0.00022636044,0.8704051],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984464,0.00060178875,0.00004749474,0.000077675395,0.0007561444,0.000070557515],"domain_scores_gemma":[0.9974815,0.0018925016,0.00006935296,0.000090788104,0.00040067598,0.000065119144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021838269,0.00056950934,0.0005467753,0.0012861467,0.00078540127,0.0052562896,0.00084346975,0.0013638312,0.021913039],"category_scores_gemma":[0.0055856328,0.0001855556,0.0001901925,0.0019729834,0.001332376,0.003260377,0.0011105171,0.0014088833,0.0047571566],"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":[0.000010825194,0.00006965387,0.0003770897,0.00026388292,0.000008536803,0.000034669578,0.00060988497,0.0022885741,0.00021760784,0.26933566,0.18442316,0.5423605],"study_design_scores_gemma":[0.000005583753,0.000040382707,0.0017406673,0.0008929158,0.0000091099555,0.00006332561,0.0012247323,0.0048292167,0.00083448505,0.39663318,0.59370404,0.000022342512],"about_ca_topic_score_codex":0.0073185717,"about_ca_topic_score_gemma":0.019825792,"teacher_disagreement_score":0.021913039,"about_ca_system_score_codex":0.0041779447,"about_ca_system_score_gemma":0.0035009277,"threshold_uncertainty_score":0.07330644},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4955188,0.08695801,0.08807176,0.12568198,0.005163042,0.02735337,0.0024873298,0.0007470562,0.16801861],"genre_scores_gemma":[0.85192204,0.02075472,0.07320711,0.0070601883,0.00035334288,0.023679351,0.00078830065,0.00008852117,0.022146445],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.94732445,0.044051103,0.0011907388,0.0020250215,0.0035686188,0.0018401885],"domain_scores_gemma":[0.92530227,0.052550964,0.0040306393,0.0042275414,0.0072040856,0.006684536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056143764,0.0011104102,0.0014443169,0.002336098,0.0051140375,0.0045648566,0.0036169926,0.0023540626,0.020979064],"category_scores_gemma":[0.09457014,0.0006544493,0.0015909917,0.002433531,0.0054818452,0.0044817207,0.012565475,0.003622272,0.0019117447],"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":[0.0018569517,0.0030138155,0.026719859,0.015962489,0.0009275201,0.00045387325,0.047740977,0.0018099586,0.0006499847,0.042809665,0.01873257,0.8393223],"study_design_scores_gemma":[0.005967386,0.017491596,0.10305359,0.069005005,0.0032238823,0.0014169527,0.19032936,0.005152963,0.006284809,0.09261067,0.5050107,0.00045309396],"about_ca_topic_score_codex":0.021305237,"about_ca_topic_score_gemma":0.034826253,"teacher_disagreement_score":0.056143764,"about_ca_system_score_codex":0.010386315,"about_ca_system_score_gemma":0.04254748,"threshold_uncertainty_score":0.29692012},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99668026,0.000038336893,0.0021295603,0.00003661605,0.0000017011935,0.00006750103,0.0001497196,0.00001061229,0.00088574603],"genre_scores_gemma":[0.9989135,0.000018581308,0.0006737189,0.0000048963047,0.0000010855041,0.000060804454,0.00017233292,0.000003571604,0.00015149571],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9911317,0.005049553,0.0009823794,0.00057908066,0.0017322201,0.0005250038],"domain_scores_gemma":[0.92065054,0.043002076,0.017018238,0.0065960367,0.010780835,0.0019521187],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011930924,0.00023847554,0.00035477203,0.0030129906,0.00074777997,0.0020071666,0.00051322486,0.00057975453,0.0013489209],"category_scores_gemma":[0.05521978,0.00024172297,0.00042245555,0.001521003,0.0010365992,0.0013194574,0.0015133222,0.00069640053,0.00034083446],"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":[0.00024730875,0.00017038391,0.9533986,0.000066949266,0.000056446057,0.00004890728,0.025192138,0.00040504575,0.0010734901,0.00047680692,0.00019861244,0.018665291],"study_design_scores_gemma":[0.00002334351,0.00032679256,0.9523359,0.000103860555,0.000027585498,0.00019171996,0.037328377,0.0056794942,0.0013719252,0.0010391466,0.0015085653,0.000063318104],"about_ca_topic_score_codex":0.0017476919,"about_ca_topic_score_gemma":0.001974979,"teacher_disagreement_score":0.98806906,"about_ca_system_score_codex":0.0011201794,"about_ca_system_score_gemma":0.0009922397,"threshold_uncertainty_score":0.06309754},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16425644,0.038367122,0.25917482,0.44482502,0.0028259996,0.00767938,0.0007879907,0.0012262973,0.08085687],"genre_scores_gemma":[0.7101815,0.008661559,0.25541076,0.013794213,0.00079048984,0.0048792176,0.00032535655,0.00034942033,0.0056075538],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.79048187,0.1609143,0.008124706,0.0031159292,0.034774814,0.0025882747],"domain_scores_gemma":[0.52405924,0.3531492,0.03679468,0.019146806,0.053969424,0.012880651],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2127866,0.00056207256,0.001475938,0.0056278817,0.0034448921,0.016849637,0.002524818,0.0019395365,0.00410327],"category_scores_gemma":[0.33537918,0.00042596378,0.0012764795,0.0058690403,0.006750106,0.012507385,0.0068891975,0.0039995485,0.0004980431],"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":[0.00023185312,0.00057002826,0.029309995,0.0049351156,0.0003095703,0.00009355383,0.0070973383,0.0041759843,0.00092189055,0.044586908,0.01946462,0.8883031],"study_design_scores_gemma":[0.0009274501,0.0050666356,0.21202485,0.034537736,0.001114874,0.0007958381,0.041003503,0.046241093,0.0126402825,0.29747245,0.34709918,0.0010760862],"about_ca_topic_score_codex":0.008834148,"about_ca_topic_score_gemma":0.019630715,"teacher_disagreement_score":0.7872134,"about_ca_system_score_codex":0.016666453,"about_ca_system_score_gemma":0.062314928,"threshold_uncertainty_score":0.9707743},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92359096,0.0018976235,0.00030651863,0.027339472,0.0001101525,0.0010313044,0.014373811,0.00001101474,0.031339124],"genre_scores_gemma":[0.97343,0.002250256,0.0008041763,0.0036376724,0.000034983866,0.0006722151,0.0042950986,0.000013254567,0.014862381],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943362,0.0018527802,0.00040487837,0.0003113513,0.0013502587,0.0017444743],"domain_scores_gemma":[0.97670263,0.008301823,0.0014064803,0.00069825276,0.010988223,0.001902467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010845287,0.00046515986,0.000707618,0.0014056688,0.00570157,0.0030255096,0.0022295518,0.0017195548,0.0057959286],"category_scores_gemma":[0.046308503,0.0004624087,0.00039262543,0.0070017595,0.0017093022,0.00083845865,0.001644109,0.0019907353,0.00047451537],"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":[0.0018906709,0.0005841024,0.76253766,0.001444341,0.00030341267,0.0018622811,0.07582572,0.0017625552,0.00077153085,0.005225547,0.09631296,0.05147931],"study_design_scores_gemma":[0.00025160995,0.00014728431,0.74358296,0.0005518847,0.00038052216,0.0000906052,0.21771894,0.0005769682,0.0008039871,0.0011779133,0.034631286,0.00008606796],"about_ca_topic_score_codex":0.9957195,"about_ca_topic_score_gemma":0.99864453,"teacher_disagreement_score":0.04352774,"about_ca_system_score_codex":0.04352774,"about_ca_system_score_gemma":0.11183148,"threshold_uncertainty_score":0.3158173},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011218026,0.15441547,0.09351037,0.14277746,0.018568717,0.013157244,0.0027169068,0.0015013488,0.5621344],"genre_scores_gemma":[0.44744694,0.097168654,0.23285818,0.08202945,0.006738403,0.047473293,0.005283606,0.0010881107,0.07991343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7861394,0.1382128,0.023858758,0.007330578,0.0348783,0.009580088],"domain_scores_gemma":[0.8124045,0.112817466,0.024292005,0.01195301,0.032430574,0.006102439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17575301,0.0018380763,0.0012731337,0.0138273,0.006291124,0.020721551,0.007290113,0.008741714,0.021762237],"category_scores_gemma":[0.23251595,0.0012583156,0.004048633,0.011561882,0.009345192,0.018781872,0.018110774,0.010439158,0.003277391],"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":[0.000086879525,0.00023422288,0.0011761792,0.02152738,0.00020490825,0.00023347043,0.012069279,0.0019410142,0.0004041158,0.7114841,0.06340588,0.18723251],"study_design_scores_gemma":[0.00012519225,0.00017568003,0.0034120053,0.035310075,0.0002267544,0.0001583084,0.011191867,0.0005248797,0.000523962,0.09429442,0.8539082,0.00014867487],"about_ca_topic_score_codex":0.008833571,"about_ca_topic_score_gemma":0.010021718,"teacher_disagreement_score":0.17575301,"about_ca_system_score_codex":0.023066893,"about_ca_system_score_gemma":0.06478168,"threshold_uncertainty_score":0.92948186},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010228457,0.1093766,0.063272186,0.014130038,0.004027243,0.00021149091,0.00018089845,0.00044616626,0.79812694],"genre_scores_gemma":[0.06609533,0.15326788,0.08285606,0.006622735,0.002818652,0.00021575617,0.00035273007,0.0004154496,0.6873554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994873,0.00009996367,0.000019618365,0.000062858744,0.0003034751,0.000026705642],"domain_scores_gemma":[0.9993356,0.00044696557,0.000019791756,0.000035863646,0.0001078619,0.000053952943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072351657,0.00030445796,0.00016329008,0.0012165688,0.0005189751,0.0036023327,0.0006285267,0.00085326034,0.00937571],"category_scores_gemma":[0.0015148254,0.00017329346,0.00021582963,0.0012799199,0.0017173404,0.0027871365,0.0012585362,0.0024139648,0.0026045488],"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":[0.000008504061,0.00006359182,0.00019919453,0.00060853275,0.00000435312,0.000051523573,0.0015843755,0.0007878165,0.0008848149,0.38742852,0.052248448,0.5561303],"study_design_scores_gemma":[0.0000021621825,0.000017904358,0.00041528005,0.0005008875,0.0000017620279,0.000109320456,0.0002568422,0.0005105779,0.00039774412,0.028852655,0.9689276,0.0000073628744],"about_ca_topic_score_codex":0.0020987971,"about_ca_topic_score_gemma":0.004467292,"teacher_disagreement_score":0.00937571,"about_ca_system_score_codex":0.0014503552,"about_ca_system_score_gemma":0.0015771969,"threshold_uncertainty_score":0.031364918},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16966662,0.009152648,0.62493193,0.039152686,0.00065865,0.00272399,0.00091757154,0.0003524441,0.15244353],"genre_scores_gemma":[0.833593,0.00284905,0.15136634,0.0019020792,0.00012209338,0.0029777298,0.00042477186,0.00019564052,0.0065693306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91797,0.05564527,0.0036671115,0.0058548152,0.01591513,0.0009476573],"domain_scores_gemma":[0.69679075,0.25059474,0.012808,0.0137739815,0.024531325,0.0015012482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.088970006,0.001425693,0.0015001956,0.008791608,0.0023203967,0.014680234,0.0035146817,0.0023422106,0.008367513],"category_scores_gemma":[0.21866252,0.0011549306,0.0018478006,0.005964062,0.013165178,0.01728913,0.005816016,0.003956277,0.0010345865],"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":[0.0003536921,0.00029806406,0.033618424,0.0036876868,0.00064200786,0.0003715415,0.08193868,0.007948099,0.00089779,0.6829184,0.004652085,0.18267348],"study_design_scores_gemma":[0.00029923575,0.000787291,0.048866797,0.009594233,0.0006957519,0.0007215974,0.063316144,0.061279535,0.0027323905,0.7121376,0.09915017,0.0004192871],"about_ca_topic_score_codex":0.014009994,"about_ca_topic_score_gemma":0.010160402,"teacher_disagreement_score":0.088970006,"about_ca_system_score_codex":0.013589966,"about_ca_system_score_gemma":0.011995313,"threshold_uncertainty_score":0.470524},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98071516,0.0012570145,0.00022436546,0.0012742861,0.00005622767,0.00019267906,0.0004387382,0.000013245422,0.015828248],"genre_scores_gemma":[0.99356973,0.00071358413,0.0004900404,0.00038326657,0.000008088867,0.0001244072,0.00015827036,0.000007917775,0.0045446567],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.986534,0.0054007093,0.0010086405,0.00078070385,0.004360623,0.0019152465],"domain_scores_gemma":[0.9357979,0.02109228,0.01077203,0.0042795353,0.019822197,0.008235928],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0126681095,0.0003114764,0.00053581677,0.0025636957,0.0055474807,0.005446495,0.001010981,0.0006171989,0.006187076],"category_scores_gemma":[0.042985674,0.0006721049,0.0004079677,0.003919432,0.0017308984,0.0011640121,0.0025073516,0.0013722086,0.000526306],"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":[0.00035686442,0.00048463835,0.79424584,0.00026910656,0.00008338234,0.0005021025,0.11959158,0.00006013789,0.0004499723,0.0008123362,0.010491295,0.07265275],"study_design_scores_gemma":[0.00005596656,0.00024242837,0.83222556,0.0004012453,0.00007915639,0.00023311886,0.13813865,0.00026139413,0.0003310773,0.00020220195,0.027738823,0.000090370464],"about_ca_topic_score_codex":0.8743627,"about_ca_topic_score_gemma":0.9383094,"teacher_disagreement_score":0.98733187,"about_ca_system_score_codex":0.02696464,"about_ca_system_score_gemma":0.03312951,"threshold_uncertainty_score":0.25275433},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7271717,0.004828616,0.0019332938,0.15944436,0.000267815,0.0003505328,0.0011933241,0.00006695071,0.10474343],"genre_scores_gemma":[0.9867372,0.0010077977,0.0004643342,0.0009643446,0.000028399114,0.00005524556,0.00008083676,0.000017332437,0.010644475],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9844127,0.0043680193,0.00063149206,0.00066891604,0.003786312,0.0061325002],"domain_scores_gemma":[0.93462855,0.023350915,0.008090972,0.0021203686,0.01472024,0.017089022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01016059,0.00023661653,0.00069880515,0.0017713711,0.01680761,0.008437685,0.0019655367,0.0028713236,0.0062190583],"category_scores_gemma":[0.058621008,0.0005590674,0.00052652776,0.0041787503,0.008355348,0.0042224033,0.005146535,0.0035688488,0.00023344347],"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":[0.00093964377,0.00046031547,0.43008074,0.0011853473,0.00041520532,0.0021494038,0.10281159,0.010290528,0.00064071285,0.2631725,0.06467255,0.12318151],"study_design_scores_gemma":[0.0002770233,0.00022021378,0.59663844,0.0013804509,0.00028613413,0.0002056804,0.11176635,0.0074558957,0.0008535844,0.054129604,0.22646712,0.00031950415],"about_ca_topic_score_codex":0.9940416,"about_ca_topic_score_gemma":0.99793696,"teacher_disagreement_score":0.24974027,"about_ca_system_score_codex":0.24974027,"about_ca_system_score_gemma":0.46735212,"threshold_uncertainty_score":0.8701949},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13341962,0.0045574773,0.04218168,0.43505302,0.0022184146,0.0025412766,0.00014550681,0.00031375862,0.3795692],"genre_scores_gemma":[0.88229346,0.0016875919,0.04657254,0.03941999,0.0005531794,0.001754048,0.00009866084,0.00032119118,0.027299339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7689577,0.18023278,0.0042297686,0.004366523,0.019718042,0.022495188],"domain_scores_gemma":[0.68974894,0.19782206,0.0059462613,0.014187146,0.042115238,0.05018038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1675794,0.0006482744,0.0010340505,0.004228611,0.036722377,0.02528243,0.004228065,0.011663907,0.011200665],"category_scores_gemma":[0.17462401,0.0011786406,0.001908375,0.0034920604,0.019722719,0.012094937,0.020434428,0.017250787,0.0011058168],"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":[0.00042521828,0.0021284884,0.029705131,0.0017852515,0.0002888844,0.016233696,0.13320337,0.0056443834,0.001561578,0.48504025,0.13448218,0.1895016],"study_design_scores_gemma":[0.00046022906,0.000790952,0.020454314,0.0044331043,0.00025154316,0.004260202,0.128277,0.009939133,0.0019122357,0.15491316,0.6737827,0.00052546954],"about_ca_topic_score_codex":0.100673094,"about_ca_topic_score_gemma":0.20358865,"teacher_disagreement_score":0.1675794,"about_ca_system_score_codex":0.04582985,"about_ca_system_score_gemma":0.12501983,"threshold_uncertainty_score":0.88625515},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016206877,0.5292511,0.12787044,0.16350539,0.0068069,0.00048059336,0.0002149449,0.00013223421,0.15553159],"genre_scores_gemma":[0.8071557,0.11870686,0.035053603,0.024377463,0.006906625,0.0014961152,0.00015305089,0.0002910164,0.005859506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6462646,0.2908277,0.01422319,0.010703774,0.0314569,0.0065239067],"domain_scores_gemma":[0.4606217,0.47414884,0.018275023,0.02509928,0.019326745,0.0025284074],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2395361,0.0014567288,0.0033115332,0.015892515,0.0068569686,0.026556866,0.0037242095,0.0069358097,0.0057292795],"category_scores_gemma":[0.25960594,0.000888019,0.0013881737,0.017250221,0.057921913,0.031517264,0.027219886,0.008310259,0.00063741265],"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":[0.00006253911,0.000046664896,0.001392104,0.0046104547,0.00010339552,0.000068230336,0.021772398,0.00047574507,0.00012308735,0.8688198,0.0035558129,0.09896968],"study_design_scores_gemma":[0.00004185599,0.00015280164,0.0032757865,0.030447401,0.00018739278,0.00038274383,0.03117812,0.0009470679,0.0011447491,0.73343366,0.19872686,0.00008142437],"about_ca_topic_score_codex":0.0035799984,"about_ca_topic_score_gemma":0.0031590986,"teacher_disagreement_score":0.7604639,"about_ca_system_score_codex":0.02100345,"about_ca_system_score_gemma":0.023447761,"threshold_uncertainty_score":0.93778735},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85409623,0.041571904,0.01603848,0.008102383,0.0012236199,0.033887733,0.0023473469,0.00039776432,0.042334422],"genre_scores_gemma":[0.91623914,0.018517315,0.03640237,0.0009143714,0.00034918013,0.018763196,0.0008324604,0.00004253493,0.007939448],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9599931,0.029956654,0.0018316284,0.0012937004,0.0053710397,0.0015539195],"domain_scores_gemma":[0.9532523,0.03204334,0.00378865,0.0019940578,0.0062643876,0.002657175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0265898,0.0016754494,0.0020880378,0.0025216604,0.0018772582,0.001975711,0.0020190927,0.0011476605,0.011103437],"category_scores_gemma":[0.048259772,0.00042973514,0.002419523,0.0017508868,0.0013391637,0.00103525,0.002470964,0.0015176046,0.00076970324],"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":[0.0108787315,0.013221612,0.017376553,0.018741569,0.0024846382,0.0001965727,0.007556113,0.0040610284,0.0018182612,0.0029847748,0.0034415459,0.91723865],"study_design_scores_gemma":[0.027721679,0.23393954,0.4577436,0.05560531,0.01862241,0.00052829325,0.024906293,0.01134756,0.01879795,0.00892398,0.14132535,0.0005380305],"about_ca_topic_score_codex":0.048597593,"about_ca_topic_score_gemma":0.085377805,"teacher_disagreement_score":0.048597593,"about_ca_system_score_codex":0.008051055,"about_ca_system_score_gemma":0.0253528,"threshold_uncertainty_score":0.14062196},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010685009,0.03869881,0.00442166,0.84609354,0.033991672,0.00046847344,0.0007110163,0.0012616899,0.06366814],"genre_scores_gemma":[0.22441085,0.13805941,0.09258132,0.37721628,0.063395984,0.0025463952,0.0015914282,0.0009581608,0.09924025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99536234,0.00112882,0.0004089661,0.00039983125,0.001985368,0.0007146494],"domain_scores_gemma":[0.96532816,0.006457689,0.0023515727,0.0020250957,0.0062044235,0.017633088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006319378,0.0011548003,0.0015679409,0.0020300315,0.0044993623,0.005394915,0.0016223962,0.009131335,0.052482754],"category_scores_gemma":[0.046866294,0.00052278885,0.0015968218,0.0008535189,0.0014767317,0.0063692806,0.0027381824,0.0062304763,0.021379132],"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":[0.00034917003,0.0018884399,0.016116995,0.0022294433,0.00017990463,0.00066103763,0.0007450545,0.00025648536,0.00074623595,0.0023802759,0.4707909,0.5036561],"study_design_scores_gemma":[0.00087908225,0.0023420106,0.06800472,0.025798196,0.0005542753,0.0035665873,0.0067019504,0.0006628814,0.0015622227,0.03180029,0.8576979,0.00042976884],"about_ca_topic_score_codex":0.006706001,"about_ca_topic_score_gemma":0.013902302,"teacher_disagreement_score":0.052482754,"about_ca_system_score_codex":0.001630513,"about_ca_system_score_gemma":0.01122664,"threshold_uncertainty_score":0.17557228},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42508256,0.00030733124,0.51289123,0.0064718793,0.00027010625,0.0014555585,0.00039948954,0.01576538,0.037356533],"genre_scores_gemma":[0.53332675,0.00024626483,0.4575683,0.0004406853,0.000077533325,0.00067873875,0.00043126952,0.00028531364,0.006945206],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9919858,0.004712021,0.000466457,0.0007144837,0.0017800358,0.00034104564],"domain_scores_gemma":[0.9841547,0.0070889643,0.0023838717,0.0026501655,0.0021334447,0.0015889086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00906886,0.0008051037,0.00046475566,0.0017358029,0.0010868319,0.0040559075,0.0012962297,0.0008737273,0.00732455],"category_scores_gemma":[0.02071467,0.00030419568,0.00070175435,0.0009823901,0.00078758824,0.003535965,0.004725363,0.0013055272,0.00165979],"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":[0.0008201405,0.005051952,0.025058597,0.0004764628,0.00012517205,0.00020582703,0.0036242853,0.014692517,0.012849214,0.014128853,0.010544793,0.9124223],"study_design_scores_gemma":[0.0019915064,0.018135369,0.0969625,0.002125588,0.0011481546,0.001883125,0.008778092,0.38266426,0.1298466,0.10713003,0.24815899,0.0011757916],"about_ca_topic_score_codex":0.00093473546,"about_ca_topic_score_gemma":0.001355643,"teacher_disagreement_score":0.00906886,"about_ca_system_score_codex":0.0010784524,"about_ca_system_score_gemma":0.0035987797,"threshold_uncertainty_score":0.047961295},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28764635,0.0022002005,0.0010473167,0.6471612,0.015025787,0.0003337227,0.000212597,0.00009994847,0.04627285],"genre_scores_gemma":[0.80420166,0.002517001,0.0014084104,0.12044277,0.0047223126,0.00042360643,0.00026050812,0.00021829818,0.06580559],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95008916,0.023887068,0.0013075279,0.0016076511,0.010634355,0.012474198],"domain_scores_gemma":[0.89949685,0.016240302,0.003898836,0.0019069213,0.025092307,0.053364735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05172373,0.00092211994,0.0009309195,0.0016017052,0.031678982,0.020171653,0.0060895565,0.013103987,0.009550915],"category_scores_gemma":[0.08409288,0.0007901223,0.0015367182,0.0016199526,0.009261522,0.0054961094,0.014701403,0.027310126,0.0023483783],"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":[0.0002647069,0.0030920513,0.01595653,0.0002414663,0.00006917189,0.01480394,0.33797973,0.0004148877,0.0010557683,0.016973693,0.5439876,0.06516051],"study_design_scores_gemma":[0.000043440108,0.0004335897,0.010891521,0.0003903072,0.000015392714,0.0021145053,0.5166534,0.00034670637,0.0004510318,0.0019986005,0.466498,0.00016356615],"about_ca_topic_score_codex":0.072613016,"about_ca_topic_score_gemma":0.21915932,"teacher_disagreement_score":0.072613016,"about_ca_system_score_codex":0.02697572,"about_ca_system_score_gemma":0.030060848,"threshold_uncertainty_score":0.2735445},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014224928,0.025748936,0.027811993,0.90348566,0.0026022007,0.0017208118,0.00008473404,0.00024772823,0.024072982],"genre_scores_gemma":[0.60466754,0.037167404,0.14743057,0.19579662,0.0025061679,0.0057424675,0.00011893834,0.0008047161,0.005765525],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.38533494,0.50029576,0.01932883,0.0094676055,0.07129613,0.014276737],"domain_scores_gemma":[0.1761922,0.7108731,0.007321544,0.012186246,0.08047525,0.0129516525],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5902271,0.0018812286,0.002268019,0.006046728,0.017172983,0.029200492,0.0112418365,0.015507813,0.00514044],"category_scores_gemma":[0.4671737,0.0015724069,0.0032363278,0.0052109817,0.048177816,0.032223396,0.017927164,0.039517146,0.0006682153],"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":[0.0005501951,0.0017934532,0.008088786,0.009184608,0.00035912363,0.0009242231,0.18575078,0.003582717,0.00095186976,0.22291835,0.115411095,0.45048478],"study_design_scores_gemma":[0.0008213797,0.0018969525,0.011188155,0.028716726,0.0003457844,0.0009952495,0.23393843,0.005335251,0.0039596637,0.15331453,0.5588617,0.0006261546],"about_ca_topic_score_codex":0.11558251,"about_ca_topic_score_gemma":0.1014183,"teacher_disagreement_score":0.40977287,"about_ca_system_score_codex":0.09023738,"about_ca_system_score_gemma":0.21917458,"threshold_uncertainty_score":0.6547211},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012656188,0.01342854,0.015927218,0.36178896,0.0054260767,0.0005190801,0.00031093773,0.000514689,0.5894283],"genre_scores_gemma":[0.7758658,0.017976098,0.017630825,0.08554293,0.003979149,0.002364982,0.00041014652,0.0005782531,0.09565179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93638545,0.051095523,0.0013792255,0.0029706147,0.0059159785,0.0022532155],"domain_scores_gemma":[0.94128346,0.0337722,0.004337899,0.006996271,0.0059072967,0.0077028377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026314685,0.00092882325,0.0006804558,0.0022153754,0.00891525,0.014934412,0.0019711796,0.00605679,0.05367302],"category_scores_gemma":[0.05754159,0.0003533756,0.00095563225,0.0020269926,0.021354882,0.0129556265,0.0147495875,0.00877472,0.010896966],"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":[0.000072022696,0.00018512023,0.0016689573,0.0018210782,0.000065265835,0.00031764634,0.081609786,0.00031105336,0.00046239272,0.4496145,0.19419242,0.2696797],"study_design_scores_gemma":[0.000027590662,0.0001331677,0.0010079177,0.002239166,0.000022774031,0.00030610658,0.015827931,0.00014767802,0.0002845184,0.097290285,0.8826858,0.000026983671],"about_ca_topic_score_codex":0.001255338,"about_ca_topic_score_gemma":0.0011345289,"teacher_disagreement_score":0.05367302,"about_ca_system_score_codex":0.007058396,"about_ca_system_score_gemma":0.016673332,"threshold_uncertainty_score":0.17955416},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20391122,0.03773283,0.12477252,0.41892058,0.003375614,0.0027739133,0.000083764484,0.00082325184,0.20760636],"genre_scores_gemma":[0.9016031,0.008976458,0.07668684,0.0061745257,0.0006705843,0.0012314281,0.000043964006,0.00013753521,0.0044756276],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.88773954,0.09827054,0.0011742396,0.0014586928,0.009645156,0.0017117697],"domain_scores_gemma":[0.7829431,0.18010417,0.0026876437,0.009791773,0.014202308,0.010270952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09959565,0.00066157413,0.0009825245,0.0029024526,0.0047726575,0.00818784,0.0030230912,0.0032035552,0.0055973222],"category_scores_gemma":[0.16033217,0.00041654095,0.0008206481,0.0021560725,0.011893686,0.008030934,0.010810292,0.0042805737,0.0006221502],"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":[0.00017944879,0.0015292764,0.007807644,0.0013042346,0.00006990579,0.00040178697,0.026517019,0.0011458149,0.00014499425,0.05539845,0.013975933,0.8915255],"study_design_scores_gemma":[0.00090048247,0.00409523,0.03742019,0.018874407,0.00031049876,0.0025940286,0.15482906,0.018835122,0.0018576578,0.57429993,0.18562041,0.00036308292],"about_ca_topic_score_codex":0.006385156,"about_ca_topic_score_gemma":0.0142347915,"teacher_disagreement_score":0.09959565,"about_ca_system_score_codex":0.005417524,"about_ca_system_score_gemma":0.017151916,"threshold_uncertainty_score":0.52671844},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8731806,0.0024935268,0.0042937007,0.06157008,0.00031329432,0.00022061054,0.00004007143,0.00004679373,0.057841316],"genre_scores_gemma":[0.99110305,0.00069627963,0.0007002539,0.003930991,0.000049323426,0.00006912853,0.00001129291,0.000030488474,0.003409307],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8732608,0.10601166,0.0025403993,0.0021000232,0.007519554,0.008567649],"domain_scores_gemma":[0.7886861,0.15597129,0.011939421,0.0043831957,0.022163698,0.016856302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085609645,0.00067610055,0.0009881698,0.003409746,0.023136677,0.024292976,0.0021810285,0.0046033734,0.0043237275],"category_scores_gemma":[0.10456429,0.00087338267,0.00077805074,0.001990687,0.038327415,0.008457511,0.015645683,0.011221596,0.00043072354],"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":[0.000024038118,0.0000619148,0.0053544557,0.00010081758,0.00000770707,0.00041281804,0.98199123,0.00003737804,0.00020201752,0.0055354494,0.0014916515,0.0047804187],"study_design_scores_gemma":[0.000005598311,0.00004606976,0.0022733829,0.00043516344,0.000008591164,0.00023160526,0.976384,0.00014192135,0.00025420467,0.0015030437,0.018689362,0.000026949527],"about_ca_topic_score_codex":0.023986755,"about_ca_topic_score_gemma":0.025126193,"teacher_disagreement_score":0.085609645,"about_ca_system_score_codex":0.022662245,"about_ca_system_score_gemma":0.024823125,"threshold_uncertainty_score":0.45275247},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048895256,0.35597038,0.009698357,0.52718353,0.06470337,0.00032159008,0.0008712932,0.00024640057,0.04051606],"genre_scores_gemma":[0.023139387,0.58618355,0.028481608,0.15825067,0.024370693,0.00088233734,0.0013488539,0.0006856294,0.17665724],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99040496,0.0036835603,0.00093338126,0.0006766281,0.0040360754,0.0002653222],"domain_scores_gemma":[0.9238383,0.022819908,0.005056628,0.0015219514,0.04392774,0.002835466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019829271,0.0010445676,0.0007429233,0.004055114,0.0022212965,0.0049854596,0.0017921159,0.0034257127,0.015997997],"category_scores_gemma":[0.08063032,0.0007560433,0.00054921396,0.004216078,0.0032463847,0.007454283,0.0031451986,0.008038273,0.012017632],"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":[0.000023578614,0.0000076535425,0.00026649173,0.00091449346,0.00000799,0.000033487562,0.00057319016,0.00006169905,0.00010740718,0.0053102104,0.9274439,0.06524991],"study_design_scores_gemma":[0.0000071784552,0.000010461009,0.00085652416,0.00410346,0.000014044482,0.0000931672,0.0007604336,0.00005248458,0.00022202895,0.003958704,0.9899003,0.000021301577],"about_ca_topic_score_codex":0.02536543,"about_ca_topic_score_gemma":0.05004096,"teacher_disagreement_score":0.02536543,"about_ca_system_score_codex":0.003079375,"about_ca_system_score_gemma":0.015964964,"threshold_uncertainty_score":0.10486847},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47916886,0.01602205,0.0061150594,0.14072107,0.0004656077,0.00084008527,0.0024250809,0.00047806028,0.35376418],"genre_scores_gemma":[0.8428958,0.0027976697,0.00826433,0.009937916,0.000076581724,0.00024432037,0.0009574501,0.00013762682,0.1346884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.981545,0.0035762948,0.0005983689,0.0010491941,0.0048982394,0.008332885],"domain_scores_gemma":[0.9544455,0.014109454,0.0012120556,0.0011377145,0.013500589,0.015594762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015607087,0.00043336724,0.00059045205,0.004125069,0.018001148,0.015653249,0.0049793012,0.004856885,0.010426452],"category_scores_gemma":[0.033298776,0.0012710522,0.00047596046,0.007160425,0.006632624,0.0036980042,0.004952547,0.0039881356,0.0006764392],"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":[0.0006010432,0.00047127856,0.0896782,0.00066208956,0.000079876954,0.001099493,0.024638377,0.015683575,0.0025714722,0.43411297,0.18508466,0.24531709],"study_design_scores_gemma":[0.00027808885,0.0002773018,0.4515557,0.0022579257,0.00015656168,0.0004282349,0.08097268,0.014689145,0.0025098652,0.053753126,0.39262792,0.0004935106],"about_ca_topic_score_codex":0.9890104,"about_ca_topic_score_gemma":0.9973157,"teacher_disagreement_score":0.69920754,"about_ca_system_score_codex":0.30079246,"about_ca_system_score_gemma":0.50728637,"threshold_uncertainty_score":0.81098163},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063845348,0.71411175,0.15795742,0.054193337,0.002644047,0.020060003,0.0012414341,0.00029475795,0.043112714],"genre_scores_gemma":[0.068215355,0.53037995,0.36284748,0.0052546207,0.00049841206,0.029348748,0.0008140798,0.00014089113,0.0025004332],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.7905819,0.13501422,0.036793318,0.004119088,0.030826064,0.0026655062],"domain_scores_gemma":[0.68164134,0.2392655,0.013810537,0.010195534,0.05333888,0.0017482621],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26068592,0.0022200996,0.004923676,0.04545834,0.007002658,0.01881349,0.004943403,0.004821462,0.0031686784],"category_scores_gemma":[0.28841582,0.0018521282,0.004334516,0.04250257,0.012428167,0.014980837,0.010655743,0.0061247516,0.0009553327],"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":[0.00011408783,0.00017800777,0.0028249053,0.18906717,0.0007278605,0.0004904763,0.0463493,0.0023473632,0.0008235762,0.1312186,0.017208504,0.6086502],"study_design_scores_gemma":[0.000068339396,0.000121252546,0.0028027825,0.6729056,0.0009757883,0.00034402378,0.034183882,0.0014920379,0.00082641054,0.09093033,0.19518703,0.00016255616],"about_ca_topic_score_codex":0.03219179,"about_ca_topic_score_gemma":0.04793666,"teacher_disagreement_score":0.7393141,"about_ca_system_score_codex":0.028591413,"about_ca_system_score_gemma":0.13214305,"threshold_uncertainty_score":0.91170585},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005471,0.58640325,0.005203366,0.32286713,0.05224663,0.00027334213,0.00054746657,0.000113319904,0.03179841],"genre_scores_gemma":[0.019949844,0.78294766,0.00985908,0.082330875,0.01158178,0.0006707269,0.0008338487,0.00032186846,0.091504335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99151224,0.003450223,0.00044205028,0.0007709376,0.0036131984,0.00021135359],"domain_scores_gemma":[0.9460218,0.019708809,0.001984491,0.0008393881,0.02969873,0.001746791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017486202,0.00088079466,0.00086039095,0.003981625,0.0028397092,0.0045284145,0.0021481437,0.0036563794,0.015618931],"category_scores_gemma":[0.06724502,0.00047555822,0.0005301996,0.0031476829,0.0034817196,0.0053868974,0.002461434,0.006054408,0.008849743],"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":[0.000047549358,0.000010209494,0.0002740387,0.00252034,0.00001737167,0.000039380575,0.00085864484,0.000060683302,0.000117147625,0.00670375,0.9084,0.08095084],"study_design_scores_gemma":[0.000016907015,0.000016587977,0.0007349398,0.0070862053,0.0000290008,0.00010575839,0.0008486425,0.000047344784,0.00020568813,0.0033309343,0.9875486,0.000029364095],"about_ca_topic_score_codex":0.028990982,"about_ca_topic_score_gemma":0.07946575,"teacher_disagreement_score":0.028990982,"about_ca_system_score_codex":0.0039933287,"about_ca_system_score_gemma":0.014454072,"threshold_uncertainty_score":0.092476964},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57320285,0.004609883,0.25321892,0.016759666,0.00011573504,0.0014503011,0.0001774664,0.00015412625,0.15031104],"genre_scores_gemma":[0.9556742,0.0010610238,0.041209985,0.0002912553,0.000007506535,0.0003381457,0.000029625451,0.000044502132,0.001343729],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.92609394,0.0655516,0.0013144426,0.0015827444,0.004129543,0.0013277015],"domain_scores_gemma":[0.7502189,0.22243536,0.005124141,0.0068390784,0.0131356465,0.0022468294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06944663,0.0005449841,0.000673782,0.0075350753,0.007040592,0.010467653,0.0030014736,0.0015240156,0.0036727027],"category_scores_gemma":[0.1643035,0.0005590445,0.0004313831,0.008283466,0.010519528,0.011755741,0.007791164,0.002786103,0.00031664726],"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":[0.00015537383,0.0005705095,0.026035896,0.0008596189,0.00004120653,0.00062784454,0.42430288,0.0028096477,0.00050874567,0.23530626,0.0020633382,0.30671865],"study_design_scores_gemma":[0.00008523456,0.00040204465,0.024302123,0.002222187,0.00007670193,0.0011294746,0.6617105,0.011594909,0.0026213804,0.22746001,0.068280295,0.000115112714],"about_ca_topic_score_codex":0.011065088,"about_ca_topic_score_gemma":0.011079843,"teacher_disagreement_score":0.9305534,"about_ca_system_score_codex":0.009628354,"about_ca_system_score_gemma":0.020719023,"threshold_uncertainty_score":0.36727327},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966133,0.00029111293,0.00041660274,0.0007293927,0.000056380053,0.00068922003,0.0000848356,0.000025893343,0.001093119],"genre_scores_gemma":[0.9917887,0.00038035927,0.004028125,0.0008813064,0.00006609634,0.0014274578,0.00015978521,0.00001332629,0.0012548446],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9836574,0.006383805,0.0014623409,0.0020678588,0.0034114204,0.0030170323],"domain_scores_gemma":[0.87812114,0.06506303,0.015337702,0.008022123,0.012968409,0.020487502],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03715367,0.0007608544,0.0013154467,0.0020375843,0.0022753433,0.0036973415,0.0020235453,0.0023336802,0.0027781916],"category_scores_gemma":[0.083802864,0.00089132506,0.0018818276,0.0014616756,0.002627422,0.003246528,0.0052977046,0.0029652428,0.00067107065],"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":[0.0069668614,0.066331856,0.43459156,0.0024588562,0.0006962302,0.0010569087,0.05583141,0.0018803263,0.012249405,0.0014916583,0.0053758062,0.41106924],"study_design_scores_gemma":[0.0011896146,0.031170195,0.925668,0.0009806588,0.0003704317,0.00027376067,0.015062093,0.0012898173,0.0111978855,0.001416625,0.011210189,0.0001707826],"about_ca_topic_score_codex":0.005017342,"about_ca_topic_score_gemma":0.008358778,"teacher_disagreement_score":0.96284634,"about_ca_system_score_codex":0.005290576,"about_ca_system_score_gemma":0.014142997,"threshold_uncertainty_score":0.19648975},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008103226,0.001575071,0.977978,0.0010116829,0.00046010857,0.0003916527,0.0008892865,0.0029613825,0.013922429],"genre_scores_gemma":[0.012349516,0.0023676169,0.9635124,0.0006621444,0.0002132805,0.001103726,0.0019939586,0.001773708,0.016023552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9504564,0.020578614,0.0053353403,0.00719302,0.015364511,0.0010721555],"domain_scores_gemma":[0.95996904,0.01957038,0.0011343275,0.009476067,0.009172339,0.0006778694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021484235,0.0028326227,0.0021872814,0.007107854,0.0028928402,0.0213148,0.0051247645,0.0030515115,0.038199678],"category_scores_gemma":[0.06801461,0.0024201563,0.0067560454,0.0060380106,0.0046598343,0.010997612,0.008314701,0.0089218,0.023195608],"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":[0.0002126312,0.00016138669,0.0011514593,0.0031499746,0.00032898842,0.00031909224,0.0042944797,0.006468795,0.004899135,0.51609653,0.028111849,0.43480566],"study_design_scores_gemma":[0.00011218739,0.000103830505,0.0007142257,0.0018005095,0.00018974577,0.00070611073,0.0019067544,0.027496276,0.011027279,0.21683154,0.73893404,0.00017756406],"about_ca_topic_score_codex":0.012495158,"about_ca_topic_score_gemma":0.008129033,"teacher_disagreement_score":0.038199678,"about_ca_system_score_codex":0.004460282,"about_ca_system_score_gemma":0.0099746715,"threshold_uncertainty_score":0.12779069},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99214137,0.0000774801,0.0007326954,0.0018066822,0.000015479949,0.00020381619,0.000016075797,0.000006614321,0.0049997303],"genre_scores_gemma":[0.9981622,0.00009228778,0.0006891996,0.0002072983,0.00000445021,0.000193484,0.000009330456,0.000005024023,0.00063683],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9720668,0.021247374,0.0011221747,0.0007582367,0.002698768,0.0021067113],"domain_scores_gemma":[0.8528661,0.10905779,0.009137664,0.0024512825,0.016491093,0.009995982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044877857,0.00032216302,0.00040858964,0.0014359936,0.009643238,0.006556412,0.00096549693,0.00096706237,0.004825209],"category_scores_gemma":[0.08410046,0.00035106455,0.00022536905,0.0011482512,0.0065574185,0.0023153708,0.0049427464,0.0020680644,0.0003256531],"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":[0.00053821324,0.001747385,0.15103683,0.0005009145,0.000032911095,0.0012522935,0.79727894,0.00028827993,0.0021110591,0.0036148925,0.0015207737,0.040077504],"study_design_scores_gemma":[0.00006059145,0.0005566683,0.064241484,0.00050334627,0.00002347248,0.00016570129,0.92233276,0.0006928137,0.0011208436,0.0019909989,0.008255693,0.00005560497],"about_ca_topic_score_codex":0.013332467,"about_ca_topic_score_gemma":0.02551812,"teacher_disagreement_score":0.044877857,"about_ca_system_score_codex":0.008220175,"about_ca_system_score_gemma":0.018367846,"threshold_uncertainty_score":0.23733962},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049217895,0.27350608,0.036732055,0.3327884,0.01190168,0.010009537,0.005232007,0.0005371183,0.28007525],"genre_scores_gemma":[0.5118827,0.23252213,0.112710804,0.0783512,0.002882626,0.011454422,0.0036343655,0.0005088331,0.0460529],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.71823543,0.16382849,0.013622419,0.0056839744,0.09101453,0.007615111],"domain_scores_gemma":[0.60327,0.19269337,0.017840791,0.011404523,0.16623089,0.008560472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19453351,0.0014975879,0.002560665,0.006219706,0.0076830876,0.016314793,0.005245971,0.00439706,0.008042179],"category_scores_gemma":[0.28419587,0.0010108742,0.0031037263,0.007581528,0.0071575586,0.005599948,0.0048035528,0.0076045813,0.001032144],"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":[0.0012009497,0.00061182905,0.017305844,0.040281054,0.0017024222,0.00035389423,0.027416587,0.002714246,0.0021868781,0.086505026,0.11410286,0.7056184],"study_design_scores_gemma":[0.00054646085,0.001151495,0.042481296,0.10912207,0.0026875082,0.00020492109,0.015482336,0.0013275006,0.0039466517,0.013783077,0.80891085,0.00035568624],"about_ca_topic_score_codex":0.65322506,"about_ca_topic_score_gemma":0.798317,"teacher_disagreement_score":0.91565454,"about_ca_system_score_codex":0.084345445,"about_ca_system_score_gemma":0.3105434,"threshold_uncertainty_score":0.99328357},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17606977,0.002229724,0.42160657,0.10428055,0.0008857844,0.012288578,0.00034555097,0.0013612389,0.28093225],"genre_scores_gemma":[0.51302326,0.0016162415,0.45178324,0.0037531857,0.000091179674,0.0044388254,0.00020800495,0.00021674356,0.024869313],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9629216,0.030593008,0.00077942427,0.00091456465,0.0028711755,0.0019202437],"domain_scores_gemma":[0.9603016,0.026837261,0.0011251933,0.0037181578,0.0036332773,0.0043845214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054800805,0.0010297387,0.00066239404,0.0024398768,0.009336164,0.012102535,0.0042477464,0.0065399962,0.0108964415],"category_scores_gemma":[0.037670314,0.0005542601,0.0008851447,0.0019283886,0.007461868,0.009809613,0.006704295,0.004579065,0.0025981932],"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":[0.00032428294,0.009126447,0.010442158,0.0021519952,0.000060340037,0.006277909,0.12364476,0.008497648,0.0037105638,0.31707752,0.04388124,0.47480524],"study_design_scores_gemma":[0.000556411,0.002218988,0.007971055,0.005743297,0.00013717574,0.0052661295,0.26161122,0.026620552,0.0093437405,0.2414704,0.43878144,0.00027960882],"about_ca_topic_score_codex":0.0036052093,"about_ca_topic_score_gemma":0.008220948,"teacher_disagreement_score":0.054800805,"about_ca_system_score_codex":0.006952998,"about_ca_system_score_gemma":0.017629337,"threshold_uncertainty_score":0.2898178},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09523573,0.0039529717,0.06429152,0.40870544,0.004091275,0.0022873364,0.00034138482,0.0011672259,0.41992718],"genre_scores_gemma":[0.86683226,0.002630764,0.058834333,0.032852475,0.0008239303,0.001204379,0.00032780482,0.00023539377,0.03625865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9803705,0.011687875,0.0005190038,0.0018689331,0.0020070144,0.0035467064],"domain_scores_gemma":[0.98076034,0.0058012246,0.0012070502,0.002210878,0.0027543388,0.0072661755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025486255,0.0007823443,0.00054495555,0.0022920347,0.009280175,0.012665736,0.003194558,0.0049664164,0.025687894],"category_scores_gemma":[0.027848206,0.00032276343,0.0010151375,0.0016333845,0.010381939,0.010122787,0.020632725,0.0052107493,0.0027562],"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":[0.000078934514,0.001069775,0.014989994,0.0012254262,0.00013492073,0.0005919343,0.07157619,0.0021865875,0.0015713421,0.47466862,0.084899694,0.34700647],"study_design_scores_gemma":[0.000085662236,0.000566208,0.010433896,0.0013339558,0.00006453188,0.0001991065,0.051820803,0.0012780915,0.0007896066,0.20456198,0.7288103,0.00005582527],"about_ca_topic_score_codex":0.0080882,"about_ca_topic_score_gemma":0.0113324,"teacher_disagreement_score":0.025687894,"about_ca_system_score_codex":0.010946668,"about_ca_system_score_gemma":0.047639072,"threshold_uncertainty_score":0.13478583},"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":"commentary","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074307417,0.0061361436,0.025009945,0.952478,0.0042465706,0.00071558193,0.00005346606,0.0003053509,0.01031191],"genre_scores_gemma":[0.10202846,0.01735385,0.3152071,0.5364714,0.0093511725,0.0067846053,0.00037464328,0.0007095642,0.011719214],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.34747028,0.5337562,0.030758398,0.0074777557,0.07155301,0.008984444],"domain_scores_gemma":[0.1656388,0.65873706,0.015116846,0.031805005,0.10008847,0.0286138],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6195292,0.0027388756,0.005974706,0.007788901,0.013698829,0.042186633,0.010294567,0.040152308,0.014299209],"category_scores_gemma":[0.5939354,0.0022020356,0.0047506997,0.005039988,0.047435973,0.049383674,0.027848464,0.051552653,0.0032484483],"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":[0.00025059725,0.00079140055,0.0017168622,0.0048817866,0.00016175247,0.00040109214,0.008684715,0.0018675674,0.00055653823,0.23350492,0.4462766,0.30090612],"study_design_scores_gemma":[0.00028565014,0.00039423478,0.0021266236,0.024456872,0.00012665636,0.00041485322,0.016720148,0.0024031536,0.0007515468,0.4055137,0.54631406,0.0004924672],"about_ca_topic_score_codex":0.009849535,"about_ca_topic_score_gemma":0.010955283,"teacher_disagreement_score":0.6195292,"about_ca_system_score_codex":0.029997118,"about_ca_system_score_gemma":0.17745037,"threshold_uncertainty_score":0.46918827},"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":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082001364,0.0009955957,0.0007578088,0.27568698,0.7032332,0.00009467115,0.009472647,0.00062110694,0.008317978],"genre_scores_gemma":[0.06663078,0.006803061,0.007812422,0.27468577,0.1315498,0.0006775191,0.009839895,0.0034429396,0.4985578],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9868896,0.0014731424,0.0017591569,0.0013436814,0.006274059,0.0022603096],"domain_scores_gemma":[0.8388195,0.022587184,0.0037238041,0.0063397773,0.12177647,0.006753222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007802577,0.0017752057,0.0022950778,0.005067982,0.0083163725,0.008233501,0.0050001726,0.0096165575,0.07093395],"category_scores_gemma":[0.16082677,0.0012087782,0.0017115624,0.009004833,0.0043332116,0.002533255,0.0032463216,0.012632768,0.021090757],"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":[0.000013842213,0.000001989686,0.000099552126,0.00004358311,0.000005536207,0.0000394691,0.00008001099,0.0000377956,0.000009982474,0.0004762774,0.9977151,0.0014767577],"study_design_scores_gemma":[0.00004744207,0.000010094547,0.0024504992,0.00038110215,0.00003021399,0.00010426994,0.0007829861,0.00030779705,0.00015315949,0.00086406345,0.9947896,0.00007876587],"about_ca_topic_score_codex":0.7056898,"about_ca_topic_score_gemma":0.68053687,"teacher_disagreement_score":0.9921974,"about_ca_system_score_codex":0.031217929,"about_ca_system_score_gemma":0.07879319,"threshold_uncertainty_score":0.5920869},"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":"protocol","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08651213,0.0167211,0.29523024,0.014701399,0.00609558,0.536755,0.0037241818,0.0011009936,0.039159305],"genre_scores_gemma":[0.15431352,0.0026466728,0.14883623,0.0030607877,0.00028761433,0.6867858,0.0007375661,0.00019656043,0.0031352972],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.27628964,0.62473136,0.054215074,0.008493594,0.033197224,0.003073185],"domain_scores_gemma":[0.46224818,0.35919276,0.033236902,0.051558234,0.08849409,0.0052698664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4892293,0.0025685008,0.005306091,0.005047516,0.0063408916,0.009062836,0.0040060654,0.0055299858,0.009777281],"category_scores_gemma":[0.50735044,0.0028647603,0.0054229964,0.0046909926,0.007795987,0.006957645,0.007846132,0.008204702,0.00237677],"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":[0.027876629,0.0055298796,0.025275426,0.07956912,0.0056586773,0.00042810972,0.09246496,0.0048640114,0.0053831534,0.08549427,0.02745383,0.64000195],"study_design_scores_gemma":[0.043845568,0.032389496,0.13374309,0.14950497,0.009361735,0.0008132677,0.03259158,0.016761871,0.025693081,0.09668083,0.45660195,0.0020125257],"about_ca_topic_score_codex":0.010979308,"about_ca_topic_score_gemma":0.011342111,"teacher_disagreement_score":0.4892293,"about_ca_system_score_codex":0.017378613,"about_ca_system_score_gemma":0.05888967,"threshold_uncertainty_score":0.62987125},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9572129,0.0012775587,0.0006490877,0.012110191,0.00018347478,0.00029568336,0.0005355129,0.00004265011,0.02769293],"genre_scores_gemma":[0.96631837,0.0008845562,0.0015461392,0.0015252674,0.000020903299,0.0002172446,0.00044154355,0.00002761502,0.029018452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99803835,0.00038553594,0.000108454784,0.0001605748,0.0004387069,0.000868402],"domain_scores_gemma":[0.9964928,0.00065157295,0.00032336035,0.00015048283,0.0010079304,0.0013738698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021895638,0.0002567106,0.00027078105,0.00088412437,0.005016754,0.004271044,0.0017822736,0.00089586363,0.0037486283],"category_scores_gemma":[0.0038279765,0.000320598,0.00021205835,0.0022742546,0.0018933655,0.0013380182,0.0034773252,0.0019066192,0.00032333352],"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":[0.0015003887,0.0013451976,0.49563104,0.0005936566,0.0001334556,0.0034662841,0.08396596,0.002695407,0.0064917007,0.02320798,0.031969655,0.3489992],"study_design_scores_gemma":[0.000121151614,0.0003034923,0.80748576,0.00031392885,0.000054296874,0.00017487291,0.12166494,0.0012914928,0.0012349064,0.0010479524,0.06620693,0.000100187564],"about_ca_topic_score_codex":0.9296098,"about_ca_topic_score_gemma":0.9862909,"teacher_disagreement_score":0.070390224,"about_ca_system_score_codex":0.05259949,"about_ca_system_score_gemma":0.111719765,"threshold_uncertainty_score":0.3816378},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7420208,0.0053384844,0.06216232,0.017071232,0.00036180927,0.0018247422,0.00008487495,0.00013145777,0.1710043],"genre_scores_gemma":[0.9734317,0.0011035912,0.020895723,0.00037933036,0.000033739016,0.000725323,0.000028643326,0.000025956897,0.0033759922],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9057069,0.08191437,0.0014572574,0.0025576444,0.0037289462,0.0046349503],"domain_scores_gemma":[0.96269053,0.029104361,0.0013544582,0.0019916368,0.0017588992,0.0031000588],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.080315225,0.00077961414,0.0008099469,0.0040734136,0.02250244,0.018205902,0.0028107625,0.0029393644,0.0021929771],"category_scores_gemma":[0.03506547,0.00059907034,0.0004880732,0.0041016527,0.029763535,0.012240249,0.023865923,0.0032143001,0.00027592474],"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":[0.000025434156,0.0001507859,0.0038785713,0.00018442584,0.000027811044,0.0004715503,0.90827,0.00042564695,0.00034156872,0.06027078,0.00085625827,0.025097221],"study_design_scores_gemma":[0.000013606277,0.000055129498,0.001053084,0.00023721025,0.0000146305465,0.00012387199,0.9436042,0.00043286232,0.00022127618,0.026211703,0.028017005,0.000015446425],"about_ca_topic_score_codex":0.00960125,"about_ca_topic_score_gemma":0.017861774,"teacher_disagreement_score":0.9774976,"about_ca_system_score_codex":0.009495889,"about_ca_system_score_gemma":0.020772025,"threshold_uncertainty_score":0.4247526},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70277184,0.0091562085,0.06455613,0.17118771,0.0006597898,0.0003274611,0.00017483906,0.00009128047,0.05107467],"genre_scores_gemma":[0.9956638,0.00041164926,0.0028451323,0.0008410665,0.000036892678,0.000057287547,0.000010676325,0.000009491356,0.00012391328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9466292,0.04316966,0.0012921226,0.0029464692,0.0033984073,0.0025641494],"domain_scores_gemma":[0.841455,0.13221377,0.008806333,0.008707945,0.0044677784,0.0043491833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0813982,0.0009523927,0.0018366737,0.0039800047,0.0048754197,0.010122143,0.0031857602,0.0036979567,0.0027664406],"category_scores_gemma":[0.12274949,0.00056195044,0.0012751403,0.0030843914,0.06956541,0.02012935,0.009497867,0.005578653,0.00013196722],"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":[0.0003420033,0.0006169972,0.05631137,0.0013215662,0.00070892106,0.0002653553,0.0643238,0.005298082,0.00019094914,0.76104796,0.0026690233,0.10690387],"study_design_scores_gemma":[0.00006601758,0.00014423442,0.008805518,0.00071598176,0.00013192659,0.000057097826,0.02697427,0.004718037,0.00022768126,0.9562855,0.0018203136,0.000053417916],"about_ca_topic_score_codex":0.006295893,"about_ca_topic_score_gemma":0.006804431,"teacher_disagreement_score":0.0813982,"about_ca_system_score_codex":0.0079522235,"about_ca_system_score_gemma":0.012695682,"threshold_uncertainty_score":0.43047994},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7270857,0.0014914126,0.12974758,0.010273685,0.0002469844,0.0009731535,0.00047752654,0.00014702526,0.12955686],"genre_scores_gemma":[0.9674466,0.00056442415,0.018314183,0.00040564965,0.000042804917,0.0006664188,0.0001274287,0.00007011264,0.012362317],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96978116,0.020578902,0.0008605211,0.0027320387,0.0046816273,0.0013657238],"domain_scores_gemma":[0.9418986,0.039675433,0.005226924,0.0058106324,0.0060738996,0.001314514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021527572,0.00061215454,0.00074965035,0.002343458,0.005848269,0.0090357615,0.0015726014,0.0014293159,0.00947123],"category_scores_gemma":[0.060651086,0.00045672845,0.00079669885,0.0031146263,0.010437208,0.009340236,0.0072196955,0.0027744714,0.00087121624],"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":[0.00025563725,0.00028992014,0.071473055,0.0012662495,0.00012690845,0.0004439658,0.50752085,0.0015546264,0.0022956682,0.257782,0.0027069477,0.15428422],"study_design_scores_gemma":[0.000060126193,0.0004908042,0.085032836,0.0018867402,0.00021364524,0.0005207269,0.60438025,0.008042203,0.006059734,0.1556936,0.1374484,0.00017096501],"about_ca_topic_score_codex":0.017723178,"about_ca_topic_score_gemma":0.026627747,"teacher_disagreement_score":0.021527572,"about_ca_system_score_codex":0.008316274,"about_ca_system_score_gemma":0.00864748,"threshold_uncertainty_score":0.11385006},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011734486,0.0431785,0.00095063925,0.9387827,0.0022298126,0.000037597576,0.000035812925,0.00001699023,0.013594429],"genre_scores_gemma":[0.3349514,0.20645021,0.015468612,0.40487644,0.00946915,0.0005428791,0.00014097162,0.0002062003,0.027894126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8600927,0.106679335,0.0034669829,0.0038655696,0.015771165,0.010124272],"domain_scores_gemma":[0.70858514,0.25757724,0.0035442784,0.0033799943,0.019511305,0.0074020447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15511355,0.0014002508,0.0023197688,0.0043736384,0.025224091,0.06319047,0.0077280058,0.03343309,0.004700685],"category_scores_gemma":[0.11840639,0.001349663,0.0014154224,0.00961603,0.124592416,0.034625173,0.011190012,0.038217094,0.0010035092],"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":[0.000049265436,0.00005589388,0.0003101074,0.0011484161,0.000015629736,0.000359486,0.07265129,0.0005550481,0.00018532603,0.813983,0.092116944,0.018569514],"study_design_scores_gemma":[0.000025718493,0.000041088435,0.0007453947,0.0061965534,0.000018975188,0.0001677098,0.10669307,0.00037747846,0.00032301765,0.26261833,0.62267953,0.00011311012],"about_ca_topic_score_codex":0.28001484,"about_ca_topic_score_gemma":0.26598924,"teacher_disagreement_score":0.8448864,"about_ca_system_score_codex":0.12313835,"about_ca_system_score_gemma":0.1330671,"threshold_uncertainty_score":0.8934355},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40424842,0.00074611255,0.5366763,0.0034203697,0.00016433053,0.0056395642,0.00022810444,0.0007758976,0.048100937],"genre_scores_gemma":[0.5634431,0.0003927617,0.42828006,0.00026157557,0.000017260545,0.0039618565,0.00010682302,0.00006386138,0.0034727403],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96402323,0.0318717,0.000559077,0.001103467,0.0014480716,0.0009944579],"domain_scores_gemma":[0.96647257,0.02493447,0.0017714995,0.0027250198,0.002004491,0.0020919177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0308003,0.0008035157,0.0006860799,0.0031742891,0.0029423425,0.0049818135,0.0020028425,0.0010886297,0.00428717],"category_scores_gemma":[0.040777136,0.0004729879,0.0006680198,0.001849835,0.0029680748,0.0040400554,0.011494104,0.001763207,0.00055890327],"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":[0.0005363511,0.0025782322,0.028822063,0.001049688,0.00013806384,0.00052720704,0.23784256,0.003846579,0.00627,0.044620387,0.0063342964,0.66743463],"study_design_scores_gemma":[0.00074093067,0.0042423476,0.03536004,0.0028946416,0.00040102281,0.0017045159,0.49405703,0.027126936,0.02152351,0.22080009,0.19086716,0.00028179915],"about_ca_topic_score_codex":0.0031868236,"about_ca_topic_score_gemma":0.0061424365,"teacher_disagreement_score":0.0308003,"about_ca_system_score_codex":0.0031210214,"about_ca_system_score_gemma":0.008030338,"threshold_uncertainty_score":0.16288948},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084797084,0.013623512,0.027095113,0.57398367,0.0020286732,0.00033511213,0.00008991616,0.00019819304,0.29784873],"genre_scores_gemma":[0.94270295,0.0054219035,0.009647496,0.025454305,0.00072978646,0.00020309183,0.00005128916,0.0001020724,0.015687235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.90443045,0.06845542,0.0017266639,0.0050186575,0.010820278,0.009548535],"domain_scores_gemma":[0.9040936,0.044572502,0.005282979,0.008269231,0.009692516,0.028089162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08426565,0.0005254328,0.0012512917,0.0031107247,0.019521141,0.035194017,0.0026433836,0.009182568,0.009500254],"category_scores_gemma":[0.080426455,0.00045417325,0.0007049668,0.0030026054,0.040745758,0.022829337,0.021959824,0.008047324,0.001915003],"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":[0.00017204392,0.00039940004,0.0077031287,0.00051341334,0.000095054726,0.00037082614,0.08958918,0.0007909946,0.00028510712,0.6917828,0.0417591,0.16653898],"study_design_scores_gemma":[0.00012190568,0.00020894493,0.0050060153,0.0014283602,0.000050725703,0.00015812142,0.07884613,0.0008376334,0.00032408355,0.51813084,0.3948096,0.000077672266],"about_ca_topic_score_codex":0.03358513,"about_ca_topic_score_gemma":0.043616112,"teacher_disagreement_score":0.08426565,"about_ca_system_score_codex":0.020857949,"about_ca_system_score_gemma":0.081486575,"threshold_uncertainty_score":0.44564468},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6269426,0.0076275943,0.013053254,0.039128557,0.00051069027,0.00039039814,0.006472393,0.0004595945,0.30541486],"genre_scores_gemma":[0.9165641,0.0025531973,0.003928772,0.0013974526,0.000064175554,0.00013781618,0.0010409158,0.00012405096,0.07418955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9851482,0.0028462606,0.00044018266,0.0012509883,0.0077330056,0.0025814178],"domain_scores_gemma":[0.9568001,0.01113028,0.0035290027,0.0018579643,0.021402923,0.005279745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009428043,0.00037066138,0.00053861673,0.0043082642,0.0074705547,0.011984625,0.0012309584,0.0010728713,0.013676479],"category_scores_gemma":[0.039312806,0.0004465243,0.0005746276,0.010180814,0.003887029,0.0029880393,0.0043282313,0.001973796,0.0017794323],"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":[0.0005294355,0.00015822818,0.34624928,0.0010733423,0.00031428246,0.0006606817,0.106699675,0.004007046,0.003672891,0.1911396,0.042745605,0.30275],"study_design_scores_gemma":[0.000057306206,0.00013662755,0.58634657,0.0010701702,0.00022982567,0.0001940884,0.06381287,0.0023720516,0.0029689695,0.010048685,0.33256847,0.0001944104],"about_ca_topic_score_codex":0.9491792,"about_ca_topic_score_gemma":0.96574503,"teacher_disagreement_score":0.990572,"about_ca_system_score_codex":0.07443114,"about_ca_system_score_gemma":0.16167401,"threshold_uncertainty_score":0.5400383},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21289955,0.16987905,0.05510821,0.27252552,0.005902534,0.014206272,0.0036274355,0.00090490514,0.26494658],"genre_scores_gemma":[0.8522779,0.03786676,0.07020642,0.014017019,0.0005521488,0.006321024,0.0029242507,0.00040705598,0.0154273175],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7039132,0.2413447,0.012897495,0.003994267,0.02767122,0.010179015],"domain_scores_gemma":[0.6418645,0.13791099,0.022098253,0.015507516,0.16849032,0.014128429],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.33664796,0.0012422216,0.0018228535,0.004010301,0.0040236055,0.013020803,0.0030689104,0.0026943483,0.008404044],"category_scores_gemma":[0.31600788,0.0006444671,0.0015020825,0.0053708255,0.00479534,0.012280105,0.006787196,0.0034893139,0.0013627704],"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":[0.0014108609,0.0009910017,0.027570732,0.022794416,0.00055530923,0.00038488006,0.018316338,0.0041431184,0.001207023,0.054869477,0.07175566,0.79600126],"study_design_scores_gemma":[0.00080669555,0.004472093,0.11213852,0.12286502,0.00072382024,0.00097424997,0.05796925,0.0068177325,0.00779403,0.028705236,0.6562603,0.00047310296],"about_ca_topic_score_codex":0.032044847,"about_ca_topic_score_gemma":0.027279938,"teacher_disagreement_score":0.33664796,"about_ca_system_score_codex":0.036578123,"about_ca_system_score_gemma":0.100982666,"threshold_uncertainty_score":0.8180312},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088529006,0.07003363,0.24726313,0.51009583,0.018065082,0.025911063,0.0005529754,0.001823364,0.037725847],"genre_scores_gemma":[0.28617984,0.025976658,0.61728805,0.04458561,0.0025109658,0.019568797,0.00028300675,0.0006487267,0.002958271],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.12282914,0.78127915,0.04285199,0.008744287,0.040517133,0.0037783177],"domain_scores_gemma":[0.06851787,0.79055864,0.03245716,0.036545996,0.06739932,0.0045210985],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73574877,0.0021829314,0.003738694,0.01561495,0.008799182,0.03396354,0.0095051415,0.009370499,0.003251261],"category_scores_gemma":[0.85011894,0.0034183494,0.0035282297,0.00986323,0.013821845,0.027821923,0.019758774,0.011860791,0.0017237057],"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":[0.0004653931,0.00028446128,0.0147821065,0.039002255,0.0020899274,0.0008936987,0.2829017,0.00091405236,0.0031330264,0.018601634,0.053484004,0.58344775],"study_design_scores_gemma":[0.0010744577,0.0022854183,0.01319907,0.13318747,0.0036800914,0.0012667753,0.27134883,0.0032710612,0.008461046,0.06615564,0.4951007,0.00096948893],"about_ca_topic_score_codex":0.00574074,"about_ca_topic_score_gemma":0.016831446,"teacher_disagreement_score":0.9834456,"about_ca_system_score_codex":0.016554412,"about_ca_system_score_gemma":0.059783198,"threshold_uncertainty_score":0.32586884},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009877836,0.010019003,0.0013029142,0.8392235,0.011351286,0.000020290641,0.00035274375,0.00018683924,0.12766546],"genre_scores_gemma":[0.5498262,0.011906029,0.0029975888,0.2555369,0.005031234,0.00010883754,0.00037822506,0.0009651898,0.17324966],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96856064,0.009703764,0.0015042826,0.003928332,0.010135438,0.006167537],"domain_scores_gemma":[0.9084269,0.03058355,0.0052284603,0.008018643,0.032540035,0.015202385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025651067,0.0004068309,0.0008678921,0.0014390867,0.006354002,0.023257399,0.0020529062,0.005081835,0.03630698],"category_scores_gemma":[0.11379799,0.0006482077,0.00037961046,0.0019642024,0.016578658,0.019344177,0.0055180043,0.010739498,0.00861881],"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":[0.00010815551,0.000036599125,0.003992449,0.00051445543,0.000049624414,0.00021590058,0.011913775,0.00010792573,0.000359807,0.22794929,0.6521092,0.10264277],"study_design_scores_gemma":[0.000028748185,0.000038905753,0.009599629,0.001779831,0.000043352076,0.00015998342,0.018804787,0.00012872818,0.0005569531,0.07298729,0.8957465,0.00012518764],"about_ca_topic_score_codex":0.18957247,"about_ca_topic_score_gemma":0.25868198,"teacher_disagreement_score":0.18957247,"about_ca_system_score_codex":0.026421392,"about_ca_system_score_gemma":0.040565174,"threshold_uncertainty_score":0.37693805},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006808948,0.0076894686,0.013781247,0.9081184,0.026552042,0.0002119407,0.00007823997,0.0008864867,0.0420012],"genre_scores_gemma":[0.06897282,0.014758123,0.099103704,0.6449706,0.08025492,0.0014503915,0.00039522458,0.0026690194,0.08742521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7218497,0.15028925,0.026944958,0.019014621,0.06925973,0.012641723],"domain_scores_gemma":[0.41499674,0.3184541,0.027081411,0.06514468,0.12270315,0.051619958],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2810387,0.0028294686,0.0025327792,0.01503054,0.018348962,0.100432515,0.009295303,0.048876707,0.03432662],"category_scores_gemma":[0.51951027,0.002775101,0.002726188,0.008708864,0.04748396,0.1181151,0.040946536,0.04476303,0.028697846],"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":[0.00004374571,0.0001677245,0.0013506218,0.0006510478,0.00006782903,0.00045967713,0.010861684,0.0007376863,0.0003202466,0.4600963,0.41871572,0.106527716],"study_design_scores_gemma":[0.00003544928,0.000040408595,0.00024221838,0.0005848967,0.000030878513,0.0001223687,0.0030939162,0.0002404703,0.00020109376,0.15827654,0.8370502,0.00008160783],"about_ca_topic_score_codex":0.0053300946,"about_ca_topic_score_gemma":0.0075773457,"teacher_disagreement_score":0.7189613,"about_ca_system_score_codex":0.01796684,"about_ca_system_score_gemma":0.062486727,"threshold_uncertainty_score":0.8866073},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009330179,0.79500234,0.008523974,0.08483292,0.008814612,0.00014764795,0.0011481384,0.0003777416,0.10021966],"genre_scores_gemma":[0.017435469,0.7890297,0.016749738,0.012649794,0.0035209463,0.0003341288,0.0010586972,0.00058195513,0.15863958],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774384,0.00066503783,0.0001706402,0.0002603163,0.0010299118,0.00013025643],"domain_scores_gemma":[0.9920879,0.0051280227,0.0005748228,0.00028750626,0.0014497694,0.0004719585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039024092,0.0009550597,0.0009148285,0.0028011852,0.0026043109,0.008839785,0.0019167765,0.002745898,0.032363858],"category_scores_gemma":[0.011484096,0.0012565522,0.0005158001,0.0044206316,0.004161432,0.010865168,0.0018061332,0.00507817,0.01933228],"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":[0.000012162413,0.000014501218,0.00026691685,0.0010088594,0.0000065831173,0.000030012601,0.0021119947,0.00006482858,0.00011583149,0.01674069,0.8166072,0.16302054],"study_design_scores_gemma":[0.0000033175531,0.000010492848,0.0008604779,0.0018394478,0.000007547711,0.00007694803,0.0014013926,0.000037034926,0.00010747136,0.010604994,0.9850322,0.000018726692],"about_ca_topic_score_codex":0.039070737,"about_ca_topic_score_gemma":0.103921786,"teacher_disagreement_score":0.039070737,"about_ca_system_score_codex":0.0048030037,"about_ca_system_score_gemma":0.011834849,"threshold_uncertainty_score":0.1082679},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21828444,0.100457646,0.007946042,0.43530762,0.0021551505,0.0013431242,0.00017395777,0.000104857354,0.23422715],"genre_scores_gemma":[0.935555,0.028485572,0.0058097425,0.021150038,0.00053012744,0.00051256525,0.000055583772,0.000060906394,0.00784058],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.93437046,0.053449597,0.0014258748,0.0010644874,0.004086589,0.0056029162],"domain_scores_gemma":[0.80560845,0.13135086,0.005061563,0.004038375,0.03522698,0.018713819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.067844056,0.0004699727,0.0009769626,0.0026311884,0.0125036575,0.017225163,0.0024467222,0.0036359348,0.004706574],"category_scores_gemma":[0.092838146,0.0002976203,0.00051642285,0.0034454833,0.011936446,0.0069676386,0.006848414,0.0053801006,0.00037348914],"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":[0.00059638225,0.0022056794,0.024729865,0.005378432,0.00016036218,0.003991125,0.21462974,0.0022062093,0.00080004876,0.116395034,0.071286514,0.5576207],"study_design_scores_gemma":[0.00018911298,0.0007021939,0.03285742,0.018635416,0.00008382687,0.0006789462,0.5820024,0.0009592334,0.0009963022,0.044823892,0.3178438,0.00022738532],"about_ca_topic_score_codex":0.14071572,"about_ca_topic_score_gemma":0.20684077,"teacher_disagreement_score":0.14071572,"about_ca_system_score_codex":0.027530316,"about_ca_system_score_gemma":0.08780412,"threshold_uncertainty_score":0.35879797},"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":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030417155,0.5683186,0.0017420499,0.2451848,0.16583782,0.00030689317,0.00038080485,0.00036975884,0.017554995],"genre_scores_gemma":[0.0051341597,0.5417045,0.0059791924,0.17561106,0.16938622,0.0007615968,0.000723989,0.000742813,0.09995647],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9738144,0.008061544,0.0021638758,0.0009268115,0.014466818,0.00056649745],"domain_scores_gemma":[0.81571704,0.0714352,0.011610232,0.004699065,0.08921545,0.0073231],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014675413,0.0010284504,0.0052341474,0.0072124614,0.0016666229,0.010646568,0.0024761753,0.0070946277,0.019007217],"category_scores_gemma":[0.11213553,0.0011608602,0.0011427351,0.008353902,0.0033629441,0.0062170126,0.0022991563,0.008624794,0.01777358],"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":[0.000009082402,0.000014695423,0.00007822575,0.000935469,0.000024145385,0.000023548166,0.000032150234,0.00002876094,0.000050618117,0.00042249545,0.95211154,0.046269327],"study_design_scores_gemma":[0.000023330931,0.000029356679,0.0005790075,0.005554953,0.00006223747,0.00022377314,0.00010724554,0.00008596573,0.000082914434,0.0017972259,0.99141484,0.00003913375],"about_ca_topic_score_codex":0.0048110536,"about_ca_topic_score_gemma":0.012412756,"teacher_disagreement_score":0.98532456,"about_ca_system_score_codex":0.0051382706,"about_ca_system_score_gemma":0.011436072,"threshold_uncertainty_score":0.07761192},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01301791,0.004758947,0.21186943,0.011908615,0.0069468906,0.07462343,0.047750358,0.011937294,0.6171871],"genre_scores_gemma":[0.16660388,0.010524195,0.47018757,0.006306546,0.0019692343,0.13051403,0.03862126,0.0062144827,0.1690588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8959323,0.054467294,0.009642656,0.0037670026,0.03342541,0.002765273],"domain_scores_gemma":[0.6747469,0.101797,0.011734463,0.02834832,0.1780872,0.0052861297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.119456105,0.0026444283,0.0022175277,0.010986332,0.0028248604,0.008377989,0.004698825,0.0027120446,0.19045697],"category_scores_gemma":[0.25054088,0.001076949,0.0031853346,0.0073625175,0.0017676203,0.007551064,0.008252852,0.0034523685,0.030281542],"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":[0.0016050546,0.0004897519,0.0028195754,0.008061211,0.00027316427,0.00023141954,0.001492261,0.0032433092,0.0009008144,0.041433435,0.34979934,0.5896505],"study_design_scores_gemma":[0.0005530839,0.00093560293,0.003669679,0.0064430484,0.00032555393,0.00017352098,0.0013325611,0.003134979,0.002793478,0.025079252,0.9553778,0.00018151179],"about_ca_topic_score_codex":0.003510656,"about_ca_topic_score_gemma":0.0043269764,"teacher_disagreement_score":0.19045697,"about_ca_system_score_codex":0.005884175,"about_ca_system_score_gemma":0.026714193,"threshold_uncertainty_score":0.63714206},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5227099,0.00944907,0.0063274433,0.12888879,0.0004308377,0.0012972668,0.00877386,0.00014333132,0.32197958],"genre_scores_gemma":[0.98064303,0.0020925098,0.0024816904,0.0025041152,0.000031630472,0.0001866361,0.0007755948,0.000033971395,0.011250773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98688436,0.0025972817,0.00034971634,0.0005573229,0.0049527627,0.0046585286],"domain_scores_gemma":[0.9598963,0.015933208,0.0016726675,0.0009993723,0.017730353,0.0037680413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012927802,0.0003933554,0.0007447898,0.0066768113,0.0082257595,0.00969655,0.002349621,0.001877099,0.011528378],"category_scores_gemma":[0.059210766,0.00030875343,0.000519784,0.016050821,0.0040487484,0.003582096,0.0032883456,0.0024226592,0.0002701202],"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":[0.00047509663,0.00038614825,0.099052265,0.0014205526,0.0003063553,0.00040733433,0.024276761,0.012954243,0.0010910842,0.5964176,0.09609706,0.16711546],"study_design_scores_gemma":[0.00010285901,0.00013421744,0.4368779,0.0029805952,0.00034433583,0.00009051671,0.1599856,0.012264122,0.0020293752,0.09820422,0.28677797,0.00020825624],"about_ca_topic_score_codex":0.98840964,"about_ca_topic_score_gemma":0.9922092,"teacher_disagreement_score":0.7625617,"about_ca_system_score_codex":0.2374383,"about_ca_system_score_gemma":0.4143232,"threshold_uncertainty_score":0.8844635},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017779041,0.0057083494,0.0016736669,0.93166536,0.0015857343,0.00009360094,0.00013558984,0.00007603602,0.04128253],"genre_scores_gemma":[0.7624139,0.015697787,0.018493734,0.13296899,0.0009127113,0.00017675266,0.00036012693,0.00020146478,0.06877449],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9680664,0.006380067,0.00071744417,0.0010621856,0.013489238,0.010284591],"domain_scores_gemma":[0.9428996,0.0032461341,0.0011630169,0.00079571526,0.017061755,0.034833807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016973905,0.00051688385,0.0005535967,0.0019854656,0.030289987,0.017337417,0.0021554213,0.005036331,0.007552932],"category_scores_gemma":[0.035548173,0.00044137114,0.0005570801,0.0026942769,0.013132989,0.004840193,0.010157857,0.01142172,0.00080258056],"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":[0.00022518764,0.000459483,0.03255049,0.00059317215,0.000056043475,0.0009395972,0.02172704,0.0013460199,0.00055299164,0.24935059,0.4423404,0.24985899],"study_design_scores_gemma":[0.00012290386,0.0002692595,0.051723763,0.0018583158,0.000055390978,0.00050703,0.07748531,0.0026663912,0.00065720326,0.074346565,0.78999186,0.00031601836],"about_ca_topic_score_codex":0.97432476,"about_ca_topic_score_gemma":0.99309087,"teacher_disagreement_score":0.85870594,"about_ca_system_score_codex":0.14129405,"about_ca_system_score_gemma":0.58798635,"threshold_uncertainty_score":0.99597716},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960969,0.000023075952,0.00026909824,0.00010132691,0.000056651184,0.0028004108,0.00004690953,0.000015775035,0.0005898659],"genre_scores_gemma":[0.98687774,0.00008814119,0.004146579,0.00014557701,0.0001302871,0.0071371263,0.00010534853,0.000007760165,0.0013615332],"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.9907991,0.0050398996,0.00053014606,0.0009182905,0.0015414122,0.0011711717],"domain_scores_gemma":[0.96000254,0.026627736,0.0039794995,0.002971879,0.0021265936,0.0042917854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017640645,0.00090406375,0.0012822339,0.0010183583,0.0011757212,0.0010238469,0.0014108919,0.002289639,0.0043626516],"category_scores_gemma":[0.035932105,0.0009782433,0.0009503848,0.0007410997,0.00169627,0.0011660185,0.0014287443,0.0024352737,0.0006306556],"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":[0.1725833,0.69342667,0.018446777,0.00056404865,0.00026355157,0.00014641279,0.0027029987,0.0016609209,0.009816331,0.000639345,0.0006562858,0.09909335],"study_design_scores_gemma":[0.033262327,0.91422904,0.043940958,0.000036856265,0.00019040868,0.000019282714,0.00043964185,0.0010604017,0.0055824597,0.00019868031,0.0010059314,0.00003396097],"about_ca_topic_score_codex":0.0024490885,"about_ca_topic_score_gemma":0.0036995048,"teacher_disagreement_score":0.98235935,"about_ca_system_score_codex":0.0017229534,"about_ca_system_score_gemma":0.0057766004,"threshold_uncertainty_score":0.093293786},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020354932,0.008705017,0.4291885,0.009759328,0.0006546778,0.4976076,0.003075352,0.0004279515,0.030226639],"genre_scores_gemma":[0.030701384,0.0032406768,0.7339194,0.0005913559,0.000039536848,0.22940376,0.0011780919,0.000048705646,0.00087715866],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55220705,0.31561837,0.071192026,0.010754524,0.04604359,0.0041844114],"domain_scores_gemma":[0.3925951,0.4304723,0.020952424,0.026510397,0.12638867,0.0030810134],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5108261,0.004101857,0.0059766066,0.03492105,0.00998333,0.014679778,0.009574111,0.008635948,0.007040926],"category_scores_gemma":[0.5123567,0.0033141894,0.011182111,0.020332938,0.013544096,0.016093403,0.018454472,0.0076524173,0.0019709507],"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":[0.00061629876,0.0008626416,0.009469691,0.10096512,0.0012114788,0.00092730817,0.13401017,0.012989817,0.0023139555,0.1695073,0.012260821,0.5548653],"study_design_scores_gemma":[0.0014544374,0.0019234839,0.0142698,0.4287883,0.0034123084,0.00098054,0.11157935,0.026455749,0.007208672,0.18346936,0.21970771,0.00075024256],"about_ca_topic_score_codex":0.012123075,"about_ca_topic_score_gemma":0.017624052,"teacher_disagreement_score":0.4891739,"about_ca_system_score_codex":0.035944834,"about_ca_system_score_gemma":0.15963668,"threshold_uncertainty_score":0.6032385},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07256103,0.042419694,0.3927259,0.27398467,0.0024015368,0.010907905,0.0027138675,0.0014259301,0.20085946],"genre_scores_gemma":[0.5956465,0.009102884,0.38142255,0.006935294,0.0005453397,0.0035329203,0.0005050884,0.0001097114,0.002199734],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7942593,0.16616072,0.0072365515,0.0037744096,0.025782049,0.0027869528],"domain_scores_gemma":[0.8290816,0.11536596,0.014406321,0.009871865,0.025788793,0.0054854415],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20956796,0.0023388457,0.0018768858,0.013644034,0.0029857615,0.01227172,0.00316718,0.002680189,0.0042366255],"category_scores_gemma":[0.19399005,0.0005156049,0.0022292635,0.009692018,0.009387019,0.013939828,0.011782706,0.004710516,0.00060998386],"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":[0.00024137973,0.0010161807,0.043632522,0.004132397,0.0009845321,0.00013930463,0.005860233,0.007583138,0.00039113685,0.2863261,0.024149628,0.62554336],"study_design_scores_gemma":[0.00033784195,0.0014795229,0.03225929,0.014255761,0.00048602105,0.0001828552,0.011990354,0.018325422,0.0022296794,0.84545726,0.07268956,0.00030655254],"about_ca_topic_score_codex":0.008647779,"about_ca_topic_score_gemma":0.01083082,"teacher_disagreement_score":0.20956796,"about_ca_system_score_codex":0.012956536,"about_ca_system_score_gemma":0.019709567,"threshold_uncertainty_score":0.9747434},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026861465,0.00062127743,0.00048678758,0.96087295,0.03730986,0.000029385228,0.000027634815,0.000027806307,0.00035572372],"genre_scores_gemma":[0.002474734,0.00033090013,0.000910037,0.98102957,0.013953296,0.00010912677,0.000010225182,0.00006197071,0.0011200673],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.85917926,0.065486245,0.017381072,0.015591374,0.0336704,0.008691734],"domain_scores_gemma":[0.46219948,0.42096725,0.022057835,0.0077833687,0.07836683,0.008625279],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09138436,0.0021859466,0.0023210216,0.0027393508,0.018194001,0.014853069,0.010463901,0.070952274,0.005001928],"category_scores_gemma":[0.42855304,0.002273785,0.004680369,0.0030987451,0.029095445,0.014054321,0.011886756,0.14079183,0.0049228985],"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":[0.00006228599,0.000035946585,0.00028383592,0.0005387778,0.000070966154,0.0007362643,0.015503822,0.000099257566,0.0007471366,0.005549572,0.9698714,0.0065006334],"study_design_scores_gemma":[0.00014986002,0.0000753854,0.0011617756,0.0054908004,0.0002648401,0.0014372861,0.026099289,0.00075379474,0.0029365676,0.02040751,0.9408406,0.00038246973],"about_ca_topic_score_codex":0.03376222,"about_ca_topic_score_gemma":0.04059702,"teacher_disagreement_score":0.90861565,"about_ca_system_score_codex":0.024654405,"about_ca_system_score_gemma":0.040809788,"threshold_uncertainty_score":0.48329246},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15293527,0.0046476945,0.014562248,0.25965217,0.0014578818,0.0073258923,0.0012088391,0.00025089618,0.5579591],"genre_scores_gemma":[0.8778387,0.005059082,0.045423362,0.014214536,0.00019844504,0.0035354772,0.00092025724,0.00007236337,0.052737754],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96129113,0.022727791,0.0012402118,0.0012415069,0.00727814,0.006221172],"domain_scores_gemma":[0.9632167,0.010872173,0.0016431896,0.0011657422,0.012803858,0.010298413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04278584,0.00046502418,0.00046878317,0.0037816472,0.012576276,0.014060858,0.002595755,0.0027140444,0.0082634855],"category_scores_gemma":[0.06425706,0.00037050227,0.0005572169,0.0032261729,0.004592233,0.0048912093,0.0075712404,0.0041925716,0.0006114734],"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":[0.00020667915,0.001560068,0.03458751,0.0019669014,0.00014268752,0.0010320096,0.052449577,0.008755884,0.0006576502,0.3892952,0.11815305,0.3911927],"study_design_scores_gemma":[0.00009377574,0.00043947384,0.05171149,0.00452048,0.00009117828,0.00021394542,0.124530464,0.0054703453,0.0015288584,0.061623033,0.7495703,0.00020652486],"about_ca_topic_score_codex":0.52190095,"about_ca_topic_score_gemma":0.65239537,"teacher_disagreement_score":0.52190095,"about_ca_system_score_codex":0.08529735,"about_ca_system_score_gemma":0.35227057,"threshold_uncertainty_score":0.96182936},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10374579,0.016135622,0.0066709053,0.6201789,0.0018246826,0.00034804855,0.0015181823,0.0002880285,0.2492898],"genre_scores_gemma":[0.91838986,0.011584317,0.015164627,0.024035992,0.0004222111,0.00019117151,0.00054313784,0.00015534666,0.029513484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9508531,0.013556977,0.0016313067,0.0012451666,0.02436406,0.008349416],"domain_scores_gemma":[0.8736863,0.032166686,0.0030782463,0.0027000182,0.06647296,0.021895869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044755932,0.00057477166,0.001009272,0.0063248863,0.015614613,0.021165935,0.002910069,0.0048649115,0.004948312],"category_scores_gemma":[0.11731678,0.00065178087,0.00075257535,0.0080091255,0.008903794,0.0076868907,0.0073018726,0.0056605632,0.00029660875],"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":[0.00031482877,0.00026361633,0.04643394,0.0005320245,0.00015274115,0.00029915848,0.006573693,0.008728662,0.0002450227,0.44409838,0.22194247,0.2704155],"study_design_scores_gemma":[0.00029639283,0.0001576365,0.19351485,0.0032141735,0.0005164814,0.00018306727,0.027064709,0.024697188,0.0015864114,0.20001398,0.54802626,0.0007289003],"about_ca_topic_score_codex":0.9937484,"about_ca_topic_score_gemma":0.99592006,"teacher_disagreement_score":0.23123963,"about_ca_system_score_codex":0.23123963,"about_ca_system_score_gemma":0.5882203,"threshold_uncertainty_score":0.89165306},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1764221,0.02139076,0.10396141,0.18908545,0.003774356,0.0010219609,0.00050840323,0.0003711073,0.5034645],"genre_scores_gemma":[0.92808455,0.004953665,0.027066343,0.006833802,0.00053848576,0.00043195367,0.00020291224,0.00008868081,0.031799674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.965158,0.022125855,0.0018339746,0.002020028,0.0075505967,0.0013114378],"domain_scores_gemma":[0.952852,0.018154271,0.0053461185,0.002804563,0.018882282,0.001960718],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.030564891,0.00027709073,0.00034939146,0.0015246527,0.0023409752,0.008012373,0.00073139113,0.0012429233,0.0044743232],"category_scores_gemma":[0.046887152,0.00016849748,0.00030421308,0.0020069394,0.0059885755,0.0042282837,0.0016390653,0.0017657191,0.0022642068],"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":[0.00018224915,0.00020200084,0.027614798,0.0019335176,0.00007727147,0.00030722196,0.019704483,0.0011623964,0.0026477724,0.45733142,0.06339295,0.42544392],"study_design_scores_gemma":[0.000058531175,0.00033695408,0.053477522,0.0035183688,0.000100430414,0.00096362724,0.0361181,0.0040676626,0.007463518,0.20483018,0.6888804,0.00018481513],"about_ca_topic_score_codex":0.005791512,"about_ca_topic_score_gemma":0.0055103586,"teacher_disagreement_score":0.99875706,"about_ca_system_score_codex":0.006562278,"about_ca_system_score_gemma":0.01215654,"threshold_uncertainty_score":0.16164452},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2875154,0.018088898,0.05168841,0.14829847,0.0005709008,0.00029871415,0.0009751763,0.00018778678,0.49237624],"genre_scores_gemma":[0.97233677,0.003588281,0.0040475116,0.0019127929,0.000083798914,0.00013918756,0.00011550957,0.00006452004,0.017711593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883172,0.005515032,0.0003004108,0.0010324614,0.0034593216,0.0013755338],"domain_scores_gemma":[0.9735701,0.013899539,0.0024932933,0.0018700655,0.0071419105,0.0010250906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010177269,0.00045024283,0.00056701433,0.0060504065,0.00802331,0.010672002,0.0013008298,0.0018430171,0.008661685],"category_scores_gemma":[0.02232515,0.00037110815,0.0006126971,0.008008367,0.026632203,0.0068643405,0.0038034045,0.0033297595,0.00047719502],"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":[0.000044044522,0.000033636396,0.022255998,0.0005609184,0.00004272787,0.0002657621,0.09682005,0.001264932,0.0004383423,0.83075625,0.007022519,0.040494695],"study_design_scores_gemma":[0.000039951166,0.00009744294,0.16563185,0.0031397126,0.00011411937,0.00031155316,0.15362652,0.0050028916,0.0013089848,0.20854637,0.4619877,0.00019289674],"about_ca_topic_score_codex":0.7879386,"about_ca_topic_score_gemma":0.7699469,"teacher_disagreement_score":0.7879386,"about_ca_system_score_codex":0.06781791,"about_ca_system_score_gemma":0.057684347,"threshold_uncertainty_score":0.4920557},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025171977,0.0028065369,0.01981993,0.029950486,0.008976714,0.014228207,0.19030966,0.0100985095,0.6986381],"genre_scores_gemma":[0.06959013,0.0088896565,0.059814043,0.01939542,0.0011379676,0.009368147,0.18562885,0.0039898907,0.64218587],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9816828,0.0017263837,0.0012719901,0.001533896,0.010379478,0.0034055577],"domain_scores_gemma":[0.9400843,0.001960411,0.0010633167,0.0035539102,0.047064293,0.0062738475],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011244805,0.0009408009,0.0010795745,0.006655422,0.0050894064,0.005697873,0.0017564219,0.0016319925,0.121493205],"category_scores_gemma":[0.03771716,0.0010858963,0.0014464065,0.008230153,0.0010364703,0.0033737654,0.0037136867,0.0034849604,0.0919965],"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":[0.00004548491,0.0001494521,0.015342253,0.00054291484,0.000020625597,0.000106864325,0.0015699054,0.00013013855,0.0011036902,0.0017772984,0.7931826,0.18602875],"study_design_scores_gemma":[0.000017918346,0.00006987919,0.053410865,0.00063991605,0.000023823814,0.000060910137,0.0036094245,0.00006249216,0.00074593764,0.00036714078,0.94094825,0.000043529144],"about_ca_topic_score_codex":0.5903776,"about_ca_topic_score_gemma":0.63375634,"teacher_disagreement_score":0.98875517,"about_ca_system_score_codex":0.014113938,"about_ca_system_score_gemma":0.069370024,"threshold_uncertainty_score":0.82406944},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48079196,0.00052483415,0.0062118424,0.007838431,0.000236171,0.009303774,0.2561793,0.0006885827,0.23822507],"genre_scores_gemma":[0.7335776,0.0022099677,0.01405575,0.0053136987,0.00024988857,0.029521631,0.1512954,0.0002225329,0.063553505],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9800299,0.0071897814,0.002622492,0.000960929,0.0072718337,0.0019250541],"domain_scores_gemma":[0.9446855,0.017137669,0.00857951,0.0034094956,0.023579428,0.0026084878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023137769,0.00033601708,0.000417847,0.005457931,0.0009360005,0.002231251,0.0007602865,0.0006737512,0.015437224],"category_scores_gemma":[0.048787437,0.0002208686,0.00047744182,0.0081862565,0.00042065504,0.0018965219,0.0020154612,0.0009298003,0.0077093104],"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":[0.00029327345,0.0017919063,0.56855834,0.0010585525,0.00011525866,0.00014903111,0.00647244,0.0008327831,0.0008631204,0.0057355464,0.2661171,0.14801262],"study_design_scores_gemma":[0.000051623905,0.00053514884,0.7507154,0.0003804044,0.00004224002,0.00015760545,0.016692603,0.0005926414,0.0012256141,0.00084527384,0.22871354,0.000047885118],"about_ca_topic_score_codex":0.009394343,"about_ca_topic_score_gemma":0.011746976,"teacher_disagreement_score":0.97686225,"about_ca_system_score_codex":0.002814803,"about_ca_system_score_gemma":0.00662663,"threshold_uncertainty_score":0.12236565},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013751073,0.04638799,0.012386705,0.65687,0.0041890573,0.00012210666,0.000045577126,0.00013845209,0.26610908],"genre_scores_gemma":[0.7812164,0.025154324,0.011145843,0.14207363,0.00464029,0.0007876306,0.000060018916,0.00028145613,0.034640435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7714618,0.20149288,0.0029444834,0.0068934443,0.0115926135,0.0056147836],"domain_scores_gemma":[0.8256501,0.13548277,0.008090722,0.010751646,0.005786906,0.014237911],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.13043332,0.0010630115,0.0016561908,0.0041801436,0.023972547,0.043148562,0.0029021574,0.014765618,0.0066294777],"category_scores_gemma":[0.07056895,0.0007716616,0.0006661977,0.0061077974,0.21177687,0.036564924,0.015761776,0.017973691,0.0016817732],"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":[0.000023568742,0.000037211463,0.0004990928,0.00017267278,0.000009902519,0.000070444505,0.03225793,0.00007894724,0.000039627645,0.9432688,0.011550645,0.011991166],"study_design_scores_gemma":[0.000027172526,0.0000465937,0.0004731364,0.0011439313,0.00000663775,0.00012317495,0.037432168,0.00013024244,0.00009421706,0.787045,0.17344142,0.000036280013],"about_ca_topic_score_codex":0.007534851,"about_ca_topic_score_gemma":0.0054612737,"teacher_disagreement_score":0.9760274,"about_ca_system_score_codex":0.016404279,"about_ca_system_score_gemma":0.031120917,"threshold_uncertainty_score":0.68980557},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18055429,0.010074172,0.3728181,0.023419444,0.0016935196,0.018241985,0.003314083,0.0021135288,0.38777092],"genre_scores_gemma":[0.80648255,0.002371418,0.17767031,0.0014997531,0.0001853089,0.0055723414,0.0012240565,0.0002856266,0.0047087623],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.859254,0.10833242,0.0064089634,0.0061794133,0.016754646,0.0030704974],"domain_scores_gemma":[0.7783446,0.15488315,0.013938774,0.018090606,0.030329686,0.0044132248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08404168,0.001974538,0.0014864979,0.004999613,0.0031011542,0.0140633695,0.002822096,0.0020270438,0.022309482],"category_scores_gemma":[0.21207406,0.00046619013,0.0018984807,0.0056578987,0.00805901,0.0143960435,0.011077982,0.0029206173,0.0020513516],"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":[0.0014346256,0.0010322327,0.01899654,0.0064554187,0.00079110137,0.00031816313,0.008276662,0.036394265,0.0010195576,0.3006378,0.016473912,0.60816973],"study_design_scores_gemma":[0.0010796984,0.0057309084,0.02048362,0.013513141,0.0011934788,0.000458201,0.035135042,0.086536795,0.0094514415,0.6198591,0.20617995,0.00037858295],"about_ca_topic_score_codex":0.006112642,"about_ca_topic_score_gemma":0.006018602,"teacher_disagreement_score":0.08404168,"about_ca_system_score_codex":0.016475521,"about_ca_system_score_gemma":0.020221267,"threshold_uncertainty_score":0.4444602},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070014433,0.5477571,0.10548467,0.23556471,0.005357752,0.0025719476,0.0010067556,0.0009925165,0.09426312],"genre_scores_gemma":[0.15482187,0.5739484,0.22051556,0.018815093,0.0052327956,0.0047937385,0.002648767,0.0007647959,0.018459069],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.87090105,0.07034669,0.013988438,0.0053761494,0.032692112,0.006695552],"domain_scores_gemma":[0.70043516,0.14102808,0.018860128,0.0126480255,0.11346213,0.013566581],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27128124,0.0035831172,0.0036216802,0.018189097,0.0038392618,0.023724686,0.0066857156,0.00825225,0.008106653],"category_scores_gemma":[0.19011343,0.0014563292,0.0023111436,0.01512903,0.0069345287,0.023283834,0.011988104,0.0085175345,0.0038081084],"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":[0.0002649074,0.000580618,0.0033525953,0.010172759,0.00025565655,0.00007356142,0.0016524581,0.0034202065,0.00035868603,0.0936682,0.05561256,0.83058774],"study_design_scores_gemma":[0.00025015115,0.0014328995,0.008642573,0.06514671,0.0007766548,0.00046240597,0.005606431,0.0059922384,0.004577483,0.17405929,0.73276806,0.0002851236],"about_ca_topic_score_codex":0.008771435,"about_ca_topic_score_gemma":0.009135607,"teacher_disagreement_score":0.27128124,"about_ca_system_score_codex":0.017301701,"about_ca_system_score_gemma":0.06941464,"threshold_uncertainty_score":0.89864},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006323441,0.99481237,0.0007687639,0.0017046512,0.0004805698,0.0004786999,0.00037391315,0.000017679922,0.0007310155],"genre_scores_gemma":[0.0072694332,0.9859045,0.0035241398,0.0014933976,0.00021513009,0.000976972,0.0003813939,0.00001865504,0.000216332],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.92314553,0.027902037,0.029313637,0.003950466,0.014540205,0.0011479481],"domain_scores_gemma":[0.7300088,0.19398808,0.031445578,0.0067951977,0.03584599,0.0019164239],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0852981,0.0023574873,0.007952844,0.04485676,0.002566199,0.0091929855,0.0035093299,0.0044765053,0.004627622],"category_scores_gemma":[0.28433204,0.0019218654,0.007136647,0.036418907,0.0035142796,0.00786314,0.006203902,0.0035958176,0.0007215349],"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":[0.00027591258,0.00007248709,0.0010105219,0.7481106,0.0042972355,0.00012702204,0.0014251376,0.00022524869,0.00050457765,0.0022826833,0.0076036854,0.23406486],"study_design_scores_gemma":[0.000050754057,0.00006831014,0.0015573531,0.95255953,0.007568531,0.00012996595,0.0005358269,0.000053948843,0.00018102018,0.0010104435,0.036254838,0.00002947218],"about_ca_topic_score_codex":0.014073212,"about_ca_topic_score_gemma":0.05025904,"teacher_disagreement_score":0.9147019,"about_ca_system_score_codex":0.013624924,"about_ca_system_score_gemma":0.06417594,"threshold_uncertainty_score":0.45110488},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16769728,0.0072951014,0.4107548,0.12817743,0.0084851235,0.014314153,0.00036109085,0.0011022867,0.26181278],"genre_scores_gemma":[0.82200515,0.0011895661,0.14398235,0.0073456587,0.00058607414,0.007090804,0.00013794129,0.00043057662,0.017231802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.577626,0.3384596,0.01367816,0.014797877,0.04942566,0.006012692],"domain_scores_gemma":[0.63487446,0.22522774,0.011678897,0.04887906,0.07047224,0.008867653],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26274893,0.0016265475,0.0015625748,0.006507071,0.007872117,0.020401357,0.003871696,0.005204618,0.0058556204],"category_scores_gemma":[0.35850295,0.0010027284,0.0015165616,0.0029924207,0.029245526,0.020459484,0.017500585,0.0126823485,0.0009685631],"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":[0.000490891,0.0008069652,0.0029728606,0.0024009065,0.00014110668,0.0004641081,0.0632751,0.003056082,0.0019295119,0.6919272,0.014375563,0.2181597],"study_design_scores_gemma":[0.0008158493,0.0032160447,0.006472943,0.00911882,0.00025259578,0.00095852884,0.06540868,0.014576975,0.010076734,0.31529328,0.5733026,0.00050693407],"about_ca_topic_score_codex":0.0033947485,"about_ca_topic_score_gemma":0.0045217625,"teacher_disagreement_score":0.26274893,"about_ca_system_score_codex":0.025722448,"about_ca_system_score_gemma":0.03553602,"threshold_uncertainty_score":0.9091618},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043170396,0.37281993,0.2335161,0.031218825,0.0022459836,0.0004617819,0.0005177066,0.00028529193,0.35461736],"genre_scores_gemma":[0.23944773,0.46073827,0.2291071,0.0072895163,0.0032568043,0.0014658702,0.00052442116,0.00027631255,0.05789405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.988313,0.0060183126,0.0006519864,0.000540198,0.0041200267,0.00035643773],"domain_scores_gemma":[0.9853098,0.012511124,0.00049083424,0.0002885287,0.0012333008,0.00016642813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014213498,0.001933857,0.0019442878,0.0077401623,0.0008829121,0.015560651,0.0028095949,0.002939204,0.0035807702],"category_scores_gemma":[0.01310257,0.0005560059,0.0009386444,0.008792318,0.011487333,0.010473681,0.0029857943,0.004630373,0.0009052999],"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":[0.000024622492,0.000056902496,0.00037072727,0.001146476,0.000034142002,0.000034063916,0.00061883405,0.003218085,0.00021347973,0.83529276,0.008737998,0.15025194],"study_design_scores_gemma":[0.0000072760454,0.00010487548,0.0012436457,0.0025022626,0.000036821602,0.00013371833,0.0014132883,0.005197442,0.0007268909,0.85316455,0.13541953,0.00004971957],"about_ca_topic_score_codex":0.0038368024,"about_ca_topic_score_gemma":0.0042914343,"teacher_disagreement_score":0.015560651,"about_ca_system_score_codex":0.007383942,"about_ca_system_score_gemma":0.0049604815,"threshold_uncertainty_score":0.07516909},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99345934,0.00023126874,0.00009910764,0.0013972752,0.000006122272,0.000013403374,0.000040075272,0.000004386128,0.0047490182],"genre_scores_gemma":[0.99938023,0.000047695557,0.000035200344,0.0000518987,0.0000012419242,0.0000027814883,0.000011053792,0.000001003057,0.00046889007],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99590236,0.0016764613,0.00015463865,0.00025622256,0.0012316629,0.0007786911],"domain_scores_gemma":[0.9719135,0.0082554305,0.0066658305,0.00052270707,0.008585272,0.00405716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057784435,0.00013291031,0.00021778038,0.00091366656,0.0038617195,0.0038401443,0.0006573679,0.0005609553,0.0025642102],"category_scores_gemma":[0.014131505,0.00021105545,0.00016153857,0.0013419917,0.0028043133,0.0007934761,0.0009374933,0.0013608937,0.00012048478],"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":[0.00021448488,0.00017684892,0.8835716,0.000069412396,0.00004621702,0.00037803635,0.08672394,0.00030456437,0.0008159968,0.0017362378,0.0015902534,0.0243724],"study_design_scores_gemma":[0.000010119555,0.000062795436,0.9340714,0.000064661865,0.000013718315,0.000038545102,0.06110989,0.0003989711,0.00017067713,0.000108427135,0.00392572,0.0000249742],"about_ca_topic_score_codex":0.9557198,"about_ca_topic_score_gemma":0.97274417,"teacher_disagreement_score":0.04428017,"about_ca_system_score_codex":0.042078357,"about_ca_system_score_gemma":0.027611196,"threshold_uncertainty_score":0.3053013},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998544,0.00006478418,0.000092384915,0.00025561452,0.000002736619,0.000030226209,0.000007654593,0.000001282762,0.0010014807],"genre_scores_gemma":[0.9996724,0.000043395565,0.000102454964,0.000030342666,0.0000012913681,0.000011851419,0.000003449683,7.3386303e-7,0.00013407617],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99039406,0.0062655765,0.00035663752,0.00032547058,0.0006189156,0.0020393387],"domain_scores_gemma":[0.9625375,0.022382312,0.0073734173,0.0004917972,0.0034819061,0.00373304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009882057,0.00029290974,0.0002831133,0.0013594669,0.005602046,0.005575263,0.00072683865,0.0010182739,0.0014169336],"category_scores_gemma":[0.030933825,0.00021904132,0.00014892992,0.0014016037,0.003483075,0.0014440425,0.0024737995,0.0011543917,0.000113070375],"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":[0.0004970159,0.0014239518,0.78541833,0.00022907632,0.00007815508,0.0019021411,0.16016734,0.00075055455,0.0026527783,0.0025877235,0.00050522515,0.043787733],"study_design_scores_gemma":[0.000021333632,0.00067884475,0.55053943,0.00025488128,0.000048219063,0.0002587683,0.44286978,0.0007459208,0.00091457384,0.00068925496,0.0029395563,0.000039478702],"about_ca_topic_score_codex":0.08328322,"about_ca_topic_score_gemma":0.16188142,"teacher_disagreement_score":0.08328322,"about_ca_system_score_codex":0.009312027,"about_ca_system_score_gemma":0.013593412,"threshold_uncertainty_score":0.1655969},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74476576,0.0011650833,0.0063146194,0.19198191,0.0009624591,0.0017425732,0.00049423263,0.00014689723,0.05242645],"genre_scores_gemma":[0.95702124,0.0009154481,0.01416467,0.011723688,0.00008988434,0.0003519178,0.0002245139,0.0001492395,0.01535935],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99353117,0.0021907934,0.00017326794,0.00044688198,0.0013369606,0.002320923],"domain_scores_gemma":[0.98919,0.0011544392,0.0004869046,0.0004154111,0.002003995,0.0067493757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008440386,0.00047258768,0.00037524037,0.0008470616,0.01186609,0.008958713,0.0025182504,0.0023511136,0.0022082375],"category_scores_gemma":[0.01293493,0.00055477093,0.000359797,0.0013462175,0.004446216,0.0021300563,0.007452978,0.0035240264,0.00025309337],"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":[0.0009192804,0.0013850109,0.17794038,0.0015453905,0.00044095842,0.010332447,0.19116187,0.013011415,0.01784614,0.1460954,0.106148206,0.3331734],"study_design_scores_gemma":[0.0002719752,0.00081351114,0.19204363,0.0007586946,0.00015428978,0.000961239,0.22983554,0.0039401194,0.003417401,0.011122693,0.5564146,0.00026627467],"about_ca_topic_score_codex":0.87046623,"about_ca_topic_score_gemma":0.9506007,"teacher_disagreement_score":0.12953377,"about_ca_system_score_codex":0.026657376,"about_ca_system_score_gemma":0.16295648,"threshold_uncertainty_score":0.26059318},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5730907,0.07099273,0.011819475,0.20142493,0.0020280008,0.0014522849,0.0015939836,0.0005793112,0.13701856],"genre_scores_gemma":[0.963488,0.007867195,0.005562157,0.0049517695,0.00006203943,0.0001240214,0.00023867574,0.00013423782,0.01757192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9723911,0.008626137,0.0019249651,0.001762745,0.010244913,0.005050118],"domain_scores_gemma":[0.89435756,0.0133366175,0.0034983628,0.001670404,0.07200912,0.015127939],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034430787,0.00037633083,0.00071718724,0.0036224013,0.01981442,0.008541508,0.0030595777,0.001882116,0.003252833],"category_scores_gemma":[0.06634478,0.00064303534,0.0003581301,0.0073318896,0.0061858776,0.0019650122,0.0057000155,0.0027468344,0.00024202067],"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":[0.00084001315,0.00036659802,0.08429607,0.002533766,0.00016503016,0.0026536146,0.15676473,0.0023385147,0.0023524256,0.040945232,0.15038946,0.55635446],"study_design_scores_gemma":[0.000078202895,0.00023840861,0.21313123,0.0031391417,0.00011118106,0.0005973021,0.18193214,0.0035408237,0.0031122277,0.004204937,0.5895639,0.0003504383],"about_ca_topic_score_codex":0.9885634,"about_ca_topic_score_gemma":0.9935309,"teacher_disagreement_score":0.9655692,"about_ca_system_score_codex":0.27373713,"about_ca_system_score_gemma":0.44627568,"threshold_uncertainty_score":0.842362},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8759297,0.0008982114,0.054201353,0.010985429,0.00016505296,0.0047090678,0.00011507291,0.0001306273,0.05286539],"genre_scores_gemma":[0.95847195,0.00072012667,0.03331868,0.0007360715,0.000031613014,0.0017778414,0.00005183908,0.00007377226,0.0048180697],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.8786316,0.10717416,0.0021631715,0.0014540502,0.0048976922,0.005679299],"domain_scores_gemma":[0.9364236,0.04460064,0.0032623461,0.0040815743,0.006288421,0.0053432942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08605368,0.0008800015,0.00064087164,0.0026165808,0.014109255,0.008394365,0.0033922137,0.004075118,0.0031188],"category_scores_gemma":[0.070535704,0.0008737318,0.0009169001,0.0033226982,0.008409919,0.0064329007,0.009911569,0.00510007,0.0006015627],"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":[0.00047360462,0.0073970994,0.028011259,0.0011026675,0.00009376204,0.025783526,0.67439353,0.0048897667,0.002206952,0.06571629,0.011194006,0.17873754],"study_design_scores_gemma":[0.00018748661,0.0023320296,0.009713112,0.0016385345,0.00008064268,0.0058695166,0.8546338,0.0072959317,0.005574748,0.014969486,0.09754854,0.00015620056],"about_ca_topic_score_codex":0.0059746127,"about_ca_topic_score_gemma":0.012546167,"teacher_disagreement_score":0.08605368,"about_ca_system_score_codex":0.013889644,"about_ca_system_score_gemma":0.019796547,"threshold_uncertainty_score":0.45510077},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05537521,0.006183899,0.124659054,0.6068597,0.00270026,0.005261755,0.00006341627,0.0010118195,0.19788492],"genre_scores_gemma":[0.7194207,0.003547235,0.20181051,0.055481404,0.0008343394,0.0041026003,0.00008899379,0.00050269795,0.014211531],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.69214135,0.229683,0.011386809,0.007740245,0.04740827,0.011640363],"domain_scores_gemma":[0.45209858,0.2641355,0.018234747,0.038469523,0.17143352,0.05562811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3049125,0.00092447235,0.0017012446,0.003500422,0.015974721,0.022012904,0.0057664216,0.00518769,0.008296595],"category_scores_gemma":[0.3056246,0.0011390586,0.0013278631,0.002262598,0.024148192,0.019581113,0.034034256,0.017575813,0.0020125897],"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":[0.0001990297,0.00202115,0.015749773,0.0034233087,0.00024386769,0.000879227,0.3734418,0.0012344879,0.0045847064,0.10348365,0.05446995,0.44026893],"study_design_scores_gemma":[0.0003362156,0.00065354514,0.02712517,0.013985908,0.00017534752,0.0011676687,0.23388352,0.002574485,0.004625417,0.13084997,0.584097,0.00052565814],"about_ca_topic_score_codex":0.037734088,"about_ca_topic_score_gemma":0.061725426,"teacher_disagreement_score":0.9718041,"about_ca_system_score_codex":0.028195944,"about_ca_system_score_gemma":0.17858413,"threshold_uncertainty_score":0.85716665},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048289355,0.12656458,0.03046809,0.15152963,0.013758286,0.0016304256,0.5159122,0.0027131967,0.1091343],"genre_scores_gemma":[0.4978984,0.046532642,0.11570015,0.027585097,0.0025999947,0.0022296226,0.24647924,0.0010394282,0.059935503],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99224126,0.0015578518,0.0006361098,0.0006699905,0.0041784337,0.0007164075],"domain_scores_gemma":[0.9453782,0.0049528666,0.0018127168,0.003028909,0.04067735,0.0041498668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027887464,0.0015247384,0.0017444886,0.0067139775,0.0028478387,0.005351679,0.002703681,0.0014979258,0.011751863],"category_scores_gemma":[0.0343787,0.00044606676,0.0017981259,0.010985616,0.001285682,0.0019148025,0.0044456962,0.0027301747,0.0013196901],"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":[0.00045603196,0.00009800764,0.02016781,0.0034309868,0.001338746,0.00011876784,0.0014323412,0.013525602,0.001117748,0.012411903,0.72642,0.21948218],"study_design_scores_gemma":[0.00007535279,0.00006970244,0.080490746,0.006412945,0.00079536857,0.000029557359,0.0015421599,0.005068432,0.0014209957,0.005646205,0.89828765,0.00016095956],"about_ca_topic_score_codex":0.9851795,"about_ca_topic_score_gemma":0.9877989,"teacher_disagreement_score":0.08488993,"about_ca_system_score_codex":0.08488993,"about_ca_system_score_gemma":0.20627666,"threshold_uncertainty_score":0.61592245},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020568926,0.029201362,0.08085459,0.47034338,0.002791373,0.00070537033,0.0001443078,0.00042434756,0.39496636],"genre_scores_gemma":[0.8824975,0.017018411,0.05794301,0.019708026,0.00092194404,0.00061353954,0.00010774137,0.00037234335,0.020817462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.78618413,0.17086993,0.004110039,0.00402365,0.027536254,0.0072760563],"domain_scores_gemma":[0.7353697,0.17972504,0.010854313,0.0102709355,0.047924556,0.015855538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16733113,0.0008756913,0.0013643736,0.008019516,0.027018916,0.04589815,0.0045114583,0.005940937,0.007362431],"category_scores_gemma":[0.14313433,0.00074144267,0.0007761972,0.005416686,0.07743261,0.02252699,0.022220962,0.010272965,0.0008839479],"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":[0.000085147556,0.000085116866,0.0030052538,0.0009126822,0.000065938766,0.00042625007,0.15585285,0.0011704066,0.00027211767,0.599112,0.04773622,0.1912761],"study_design_scores_gemma":[0.00004175619,0.000071231414,0.0027954543,0.004733356,0.000062659376,0.00025271362,0.1340201,0.0019848866,0.00082258886,0.331399,0.5236332,0.00018303731],"about_ca_topic_score_codex":0.2668359,"about_ca_topic_score_gemma":0.30441383,"teacher_disagreement_score":0.922067,"about_ca_system_score_codex":0.077933,"about_ca_system_score_gemma":0.14954618,"threshold_uncertainty_score":0.8849422},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7161696,0.007606482,0.004444966,0.112637416,0.00092356023,0.0002625937,0.00017744038,0.00009977395,0.15767825],"genre_scores_gemma":[0.9837247,0.0016877505,0.00046612858,0.0034169971,0.00007036439,0.000090914764,0.000030714138,0.00006601265,0.010446423],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9765465,0.016991297,0.00033492834,0.0007726418,0.0022456709,0.0031090435],"domain_scores_gemma":[0.9820753,0.012537135,0.0010749043,0.00063308474,0.0013943646,0.0022852079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017388752,0.0009843704,0.00074565405,0.0023343873,0.04378094,0.016629046,0.0038193893,0.00661086,0.0039152103],"category_scores_gemma":[0.025033502,0.00093050086,0.00053591665,0.0030129722,0.056535237,0.012430843,0.016937725,0.011563391,0.00044806505],"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":[0.000004226973,0.0000044245558,0.00016734215,0.000014455976,0.0000012864397,0.00032330205,0.9920334,0.000009108163,0.00002542235,0.0063231024,0.0006313112,0.0004626131],"study_design_scores_gemma":[0.0000014851537,0.000004763882,0.00018061837,0.0000642983,0.000002103386,0.000086017164,0.96885645,0.000024899544,0.00004385499,0.0012171823,0.029512422,0.000005838333],"about_ca_topic_score_codex":0.109021425,"about_ca_topic_score_gemma":0.18076867,"teacher_disagreement_score":0.109021425,"about_ca_system_score_codex":0.025704857,"about_ca_system_score_gemma":0.01772059,"threshold_uncertainty_score":0.21677369},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18307844,0.008888691,0.061866123,0.3353962,0.0022479617,0.001832132,0.00008475765,0.00049631414,0.40610936],"genre_scores_gemma":[0.95165104,0.0013269953,0.01938033,0.010643866,0.00023800791,0.00070050283,0.000030890216,0.00014415398,0.015884252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8827433,0.08896872,0.0033558398,0.003025544,0.014929764,0.0069768154],"domain_scores_gemma":[0.86261445,0.08022955,0.007392665,0.007900869,0.02900265,0.012859856],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.1252633,0.0004814521,0.0010692629,0.0027857719,0.02251624,0.023178585,0.0022094597,0.003180356,0.008792272],"category_scores_gemma":[0.11215103,0.0006282964,0.00063681573,0.0018459116,0.037910894,0.016402109,0.0170321,0.0071388134,0.00088757783],"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":[0.00026722165,0.0008186224,0.011448243,0.0014081277,0.00007899562,0.0006286088,0.26391265,0.00124565,0.0024045755,0.3552438,0.044649236,0.31789425],"study_design_scores_gemma":[0.00019140699,0.00065281196,0.01765643,0.005910393,0.000101568505,0.0005324332,0.26935858,0.002529095,0.005131249,0.18026505,0.5173932,0.00027783774],"about_ca_topic_score_codex":0.044895753,"about_ca_topic_score_gemma":0.071781754,"teacher_disagreement_score":0.97748375,"about_ca_system_score_codex":0.025671346,"about_ca_system_score_gemma":0.08059317,"threshold_uncertainty_score":0.66246355},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15283799,0.0074240933,0.092481405,0.14707176,0.0009975994,0.0014710223,0.00010721278,0.00025982352,0.59734917],"genre_scores_gemma":[0.9698111,0.0015551551,0.02032619,0.0023562068,0.00006539996,0.00050227623,0.000019040444,0.000068957255,0.0052957074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8940331,0.096738204,0.0009407405,0.0012449898,0.004747648,0.0022952345],"domain_scores_gemma":[0.9046675,0.07633475,0.0025862623,0.0039645205,0.008867728,0.0035792727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09512521,0.0006670096,0.0006108257,0.0029593152,0.011281797,0.020185549,0.0023344604,0.0021090615,0.0067616827],"category_scores_gemma":[0.087198645,0.00037725165,0.00046995317,0.0018647985,0.05062811,0.012173535,0.012349533,0.0054433416,0.0002829595],"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":[0.000093479175,0.00018751092,0.0038066574,0.00077328307,0.00005687291,0.00024395213,0.2435404,0.001561193,0.0003081198,0.6417181,0.010513926,0.09719648],"study_design_scores_gemma":[0.00006676995,0.00017107197,0.0047661206,0.0039373427,0.00010298827,0.00017193882,0.38146636,0.004858257,0.0017433629,0.44243544,0.1601818,0.00009858533],"about_ca_topic_score_codex":0.048030674,"about_ca_topic_score_gemma":0.08064441,"teacher_disagreement_score":0.9679633,"about_ca_system_score_codex":0.032036737,"about_ca_system_score_gemma":0.04477154,"threshold_uncertainty_score":0.5030762},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94627684,0.0016557565,0.007450293,0.005032436,0.00011819212,0.00055098924,0.00035275437,0.00010438269,0.038458303],"genre_scores_gemma":[0.9537138,0.0012706423,0.0073591294,0.0010845239,0.000053988057,0.00038372504,0.00039525467,0.000049962415,0.035689067],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97054076,0.012786328,0.0014459847,0.0016552963,0.010715228,0.002856439],"domain_scores_gemma":[0.90854037,0.04035053,0.0065099276,0.00193681,0.037958764,0.0047034943],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032594804,0.0004979401,0.0005587834,0.002644182,0.0021959739,0.005251336,0.0010038328,0.001021385,0.011952141],"category_scores_gemma":[0.058817457,0.00034906968,0.0005355224,0.0016870238,0.0010938264,0.0019766206,0.0030801701,0.0010892132,0.0023392397],"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":[0.0016893158,0.0010486804,0.32043752,0.0021722016,0.0002566155,0.0006936545,0.11603075,0.0017974743,0.010328536,0.0053290124,0.018300021,0.5219162],"study_design_scores_gemma":[0.00010257581,0.0024800133,0.67543566,0.0020122163,0.00029380742,0.00042249885,0.16061546,0.004520534,0.019223796,0.0015536047,0.133112,0.00022777129],"about_ca_topic_score_codex":0.026830278,"about_ca_topic_score_gemma":0.059200123,"teacher_disagreement_score":0.9917387,"about_ca_system_score_codex":0.008261293,"about_ca_system_score_gemma":0.010311234,"threshold_uncertainty_score":0.17237985},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006102795,0.034323048,0.11818699,0.6961049,0.0077670207,0.00075631996,0.00008925844,0.00034363678,0.13632606],"genre_scores_gemma":[0.6515962,0.02214062,0.15422504,0.1361746,0.0068511697,0.002642073,0.000110913075,0.00086761406,0.025391707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6286276,0.31962684,0.0076411325,0.007214174,0.032154724,0.0047355024],"domain_scores_gemma":[0.7007428,0.23069024,0.007041307,0.021827403,0.030310966,0.009387316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27494532,0.00161982,0.0027670865,0.0125421975,0.01388811,0.0454921,0.003683038,0.010963491,0.0064148833],"category_scores_gemma":[0.20622337,0.0011325496,0.0015359969,0.0072752163,0.16297157,0.038437165,0.022063067,0.021641215,0.0008812744],"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":[0.00005701758,0.000052134492,0.00057762023,0.00056537817,0.0000598825,0.000110116714,0.023937745,0.00031882845,0.00012912866,0.90885264,0.018463558,0.046876106],"study_design_scores_gemma":[0.000072566414,0.0001354614,0.0006762002,0.0046334825,0.00005834758,0.00016044201,0.03050996,0.000787959,0.00047546191,0.6694869,0.29284555,0.00015773466],"about_ca_topic_score_codex":0.016153434,"about_ca_topic_score_gemma":0.014161178,"teacher_disagreement_score":0.7250547,"about_ca_system_score_codex":0.041720897,"about_ca_system_score_gemma":0.047099806,"threshold_uncertainty_score":0},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43311223,0.0059550796,0.22333181,0.016323095,0.003136944,0.037490897,0.028534198,0.0030098653,0.24910583],"genre_scores_gemma":[0.56999546,0.003148729,0.3538949,0.0014657376,0.000081957936,0.03382855,0.0066988133,0.00059589965,0.030290024],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98650175,0.0067710085,0.0013421994,0.0005175399,0.0041547394,0.0007128234],"domain_scores_gemma":[0.9570873,0.0130923325,0.0010542864,0.0013356032,0.026459929,0.0009704958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019657483,0.0007996529,0.00067348283,0.004320961,0.0035808096,0.0036793058,0.0015283739,0.00056495954,0.0112744],"category_scores_gemma":[0.04848841,0.0003245723,0.0010724697,0.0046355138,0.0017613581,0.0011941292,0.002478342,0.0014132068,0.0010608996],"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":[0.00049751083,0.0005839573,0.026955307,0.0036066212,0.00014268326,0.0005041169,0.061290268,0.0025059003,0.002670505,0.02937381,0.07785816,0.7940113],"study_design_scores_gemma":[0.00041560418,0.000623096,0.15848304,0.008184489,0.00024344937,0.00056431675,0.049271986,0.006155512,0.0072142743,0.0058465363,0.76244056,0.00055707013],"about_ca_topic_score_codex":0.7229331,"about_ca_topic_score_gemma":0.8120631,"teacher_disagreement_score":0.2770669,"about_ca_system_score_codex":0.038976625,"about_ca_system_score_gemma":0.08242736,"threshold_uncertainty_score":0.5573971},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84829247,0.0016004308,0.007838365,0.02136555,0.000491133,0.00050888676,0.00027024827,0.0001604733,0.11947233],"genre_scores_gemma":[0.97918475,0.00073770934,0.0022847056,0.0007353752,0.00004900713,0.00018004309,0.00007275065,0.0001146662,0.016640985],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98239017,0.0122921895,0.000220822,0.000488853,0.0024086123,0.00219927],"domain_scores_gemma":[0.98357195,0.009058098,0.0005429618,0.0005980172,0.002425059,0.003803822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010247567,0.000954885,0.00073655345,0.0013723752,0.025175635,0.0092845345,0.0021316288,0.0021937129,0.0041469582],"category_scores_gemma":[0.016460484,0.0005416098,0.00037011728,0.0014284184,0.016702535,0.0017156777,0.0070685092,0.0051845456,0.0005376234],"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":[0.00020305743,0.00022649282,0.003918021,0.0003392167,0.000033578483,0.0028843787,0.92112386,0.0009291236,0.0015691752,0.008556333,0.018164119,0.042052757],"study_design_scores_gemma":[0.000018474277,0.00013277667,0.0044387444,0.0004769693,0.000022589029,0.0005494309,0.8729966,0.0005951845,0.0015982316,0.0017334524,0.11737354,0.00006397945],"about_ca_topic_score_codex":0.2802618,"about_ca_topic_score_gemma":0.6126303,"teacher_disagreement_score":0.7197382,"about_ca_system_score_codex":0.022280643,"about_ca_system_score_gemma":0.017903036,"threshold_uncertainty_score":0.557261},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017290605,0.8831389,0.0030525846,0.056119096,0.011590321,0.000032661428,0.00035124025,0.00018378058,0.04535856],"genre_scores_gemma":[0.0024388565,0.89098966,0.0032332654,0.007421263,0.004615257,0.0000474525,0.0003059418,0.00012821736,0.09082],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990676,0.00021132575,0.000073594565,0.00008762321,0.0005119981,0.000047891543],"domain_scores_gemma":[0.99640757,0.001940255,0.00021392926,0.00007836166,0.0010655087,0.00029446007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002258679,0.001293065,0.0009769747,0.002123648,0.00078845036,0.0049631936,0.0010324543,0.0021707655,0.028664019],"category_scores_gemma":[0.0055075083,0.0008440816,0.0005422723,0.0031068174,0.0010064499,0.0045520626,0.0011604362,0.003784902,0.029287618],"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":[0.000014058377,0.000006613713,0.0001047398,0.00048824775,0.0000062952986,0.000019919851,0.00013282135,0.0000854699,0.00004789058,0.0022904072,0.84963053,0.14717297],"study_design_scores_gemma":[0.0000044092935,0.000007381537,0.00034004299,0.0013281687,0.000011992346,0.0001357637,0.00017028711,0.00008413399,0.00008581311,0.0031287516,0.9946905,0.000012783354],"about_ca_topic_score_codex":0.014831293,"about_ca_topic_score_gemma":0.041396827,"teacher_disagreement_score":0.028664019,"about_ca_system_score_codex":0.00161679,"about_ca_system_score_gemma":0.004631294,"threshold_uncertainty_score":0.0958907},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022035136,0.25188735,0.03440481,0.6522878,0.02002246,0.0034013663,0.0026586596,0.00071688887,0.03241715],"genre_scores_gemma":[0.08459701,0.49035218,0.16374841,0.1909787,0.008751152,0.00848242,0.0029948363,0.0009856191,0.049109645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9361987,0.03850936,0.0066263457,0.001407374,0.016548267,0.0007099698],"domain_scores_gemma":[0.63684714,0.17720889,0.020951565,0.009110297,0.14780289,0.008079196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13195516,0.0011104055,0.0015343006,0.009489862,0.003002006,0.0061893254,0.0033931793,0.004966836,0.01158163],"category_scores_gemma":[0.37710822,0.0013930777,0.0012959365,0.007945166,0.004233495,0.006426875,0.004684465,0.0070768204,0.006172507],"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":[0.00019092974,0.000045505967,0.001862535,0.008071702,0.00012328009,0.00006634391,0.0020382355,0.00019210853,0.0002727545,0.004169035,0.69656855,0.286399],"study_design_scores_gemma":[0.0003214398,0.00036004183,0.013238058,0.10991279,0.0006566965,0.0002973107,0.004620395,0.0005472022,0.0015917378,0.02326875,0.8448657,0.00031977892],"about_ca_topic_score_codex":0.047575153,"about_ca_topic_score_gemma":0.12760632,"teacher_disagreement_score":0.13195516,"about_ca_system_score_codex":0.0061593726,"about_ca_system_score_gemma":0.049277093,"threshold_uncertainty_score":0.6978539},"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":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002851697,0.009061459,0.0015325465,0.37384295,0.54768884,0.00070584955,0.0015150681,0.00034704438,0.065021046],"genre_scores_gemma":[0.0038088039,0.011030795,0.0030745824,0.277899,0.28036627,0.0013528027,0.0012243246,0.00046161748,0.42078182],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99346864,0.0017320161,0.0005402023,0.00059383904,0.0030960857,0.0005691467],"domain_scores_gemma":[0.9427877,0.02513418,0.0024807127,0.0013951267,0.022719806,0.0054824664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0147834895,0.0014220171,0.001315131,0.0036771498,0.004808461,0.009147943,0.0031341042,0.015808513,0.1316318],"category_scores_gemma":[0.047910932,0.0007191128,0.0016211129,0.0026501415,0.0024733795,0.0041166586,0.003606878,0.011957593,0.055772744],"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":[0.000012831847,0.000011830318,0.000015029543,0.00007688725,0.0000016265657,0.000017744007,0.000021414178,0.000013700277,0.000044726465,0.00064978143,0.99529797,0.003836443],"study_design_scores_gemma":[0.00001512845,0.000016313123,0.00028244336,0.00042268354,0.00000503082,0.000015550955,0.000112661815,0.000022468676,0.000068419315,0.0015624646,0.99746156,0.000015354486],"about_ca_topic_score_codex":0.011022976,"about_ca_topic_score_gemma":0.031579696,"teacher_disagreement_score":0.99429566,"about_ca_system_score_codex":0.005704344,"about_ca_system_score_gemma":0.009011482,"threshold_uncertainty_score":0.44035226},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8544526,0.002705099,0.0035252115,0.004464329,0.00023197933,0.0008375124,0.0071814014,0.00029043196,0.12631154],"genre_scores_gemma":[0.97997206,0.0015581109,0.0029641662,0.0005751414,0.000040782794,0.00033751733,0.004467698,0.0000597775,0.01002472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894651,0.0010825384,0.00035352923,0.0005395331,0.006791782,0.00176754],"domain_scores_gemma":[0.9458715,0.0034303514,0.0025258872,0.0007189118,0.037456624,0.009996739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0081034135,0.00035338267,0.00030890063,0.008239012,0.0028354162,0.0025542171,0.0018030617,0.00041926283,0.004562097],"category_scores_gemma":[0.030234434,0.00025920692,0.00044374246,0.011051426,0.00091483287,0.00079202576,0.0023155217,0.0008601799,0.000459843],"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":[0.00086799474,0.0007404218,0.595954,0.00073018664,0.00015253451,0.00011532788,0.012385615,0.0012860217,0.00089421734,0.010404703,0.051732276,0.3247367],"study_design_scores_gemma":[0.000039778093,0.00015637257,0.9351622,0.00030979785,0.000050927632,0.000082391074,0.007490042,0.00074363756,0.00057443173,0.00026709173,0.0550837,0.00003965416],"about_ca_topic_score_codex":0.8785822,"about_ca_topic_score_gemma":0.94346416,"teacher_disagreement_score":0.99189657,"about_ca_system_score_codex":0.05895828,"about_ca_system_score_gemma":0.09559872,"threshold_uncertainty_score":0.42777425},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15466648,0.009080122,0.29072934,0.4527046,0.0074338648,0.0042015403,0.00009891125,0.00040098088,0.080684185],"genre_scores_gemma":[0.74982905,0.007327589,0.19025849,0.036105234,0.0011419392,0.0024516473,0.000057333582,0.00045975077,0.012369011],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.616528,0.33823153,0.008198509,0.0055044335,0.023271201,0.008266326],"domain_scores_gemma":[0.54678035,0.3706951,0.0066326973,0.012113836,0.05587939,0.007898616],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26330516,0.0015229747,0.0011572588,0.002478756,0.018682668,0.017889459,0.006107216,0.010108902,0.0014178785],"category_scores_gemma":[0.25130546,0.0014741466,0.001536201,0.0019811504,0.04078633,0.014145582,0.016493319,0.02889003,0.0006370622],"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":[0.00014330221,0.00073649536,0.0017466394,0.0012382971,0.000066914035,0.0021064463,0.7800308,0.0018960964,0.002057475,0.055503663,0.02478303,0.12969092],"study_design_scores_gemma":[0.00011809942,0.0006905606,0.0013100676,0.004004953,0.000056185858,0.002285376,0.61680156,0.0029364545,0.004678075,0.040626425,0.32610926,0.00038290786],"about_ca_topic_score_codex":0.014104355,"about_ca_topic_score_gemma":0.015592859,"teacher_disagreement_score":0.26330516,"about_ca_system_score_codex":0.017481655,"about_ca_system_score_gemma":0.03123498,"threshold_uncertainty_score":0.9084759},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7096683,0.009049438,0.033097927,0.04972192,0.0011463888,0.000646264,0.00021564406,0.00017999343,0.19627416],"genre_scores_gemma":[0.9716742,0.0026526824,0.0105431285,0.0028391646,0.00008576923,0.00046726057,0.00007070043,0.000072582334,0.011594665],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.94394183,0.039017256,0.0020868315,0.0023950879,0.009913891,0.0026450646],"domain_scores_gemma":[0.9404458,0.03220787,0.0058655227,0.002867434,0.01482984,0.003783512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039706275,0.0007889873,0.0006688206,0.0019243154,0.007981626,0.013594633,0.0014699692,0.0022661358,0.008070545],"category_scores_gemma":[0.073695,0.00052123616,0.0008916359,0.0014376102,0.009701433,0.0081894975,0.006076586,0.0038452314,0.0014767895],"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":[0.00036569394,0.0004029975,0.061545514,0.0019517873,0.00019190607,0.00061947457,0.62304103,0.000726795,0.002871965,0.067175925,0.008539463,0.23256747],"study_design_scores_gemma":[0.00006380293,0.0006943702,0.07110327,0.0060115233,0.00023640781,0.0008487973,0.71083313,0.0015690327,0.0037376601,0.039762136,0.16488864,0.00025131626],"about_ca_topic_score_codex":0.02742457,"about_ca_topic_score_gemma":0.039242703,"teacher_disagreement_score":0.039706275,"about_ca_system_score_codex":0.011748121,"about_ca_system_score_gemma":0.020380469,"threshold_uncertainty_score":0.20998937},"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":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9576769,0.012799961,0.0027587484,0.008369997,0.0000708013,0.00009936907,0.00026285765,0.00004112228,0.0179203],"genre_scores_gemma":[0.99448836,0.002250825,0.0009345092,0.00028357632,0.000013303172,0.00003152859,0.00007013746,0.000011416045,0.0019163733],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99429446,0.0022060405,0.00020524343,0.0005452377,0.0014738871,0.0012750814],"domain_scores_gemma":[0.9662846,0.01181399,0.004352811,0.0008339506,0.013943813,0.0027708893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008322367,0.000479758,0.00050191075,0.0017589343,0.003688405,0.0059073656,0.0013071968,0.0009531929,0.0037610948],"category_scores_gemma":[0.01850468,0.00034563144,0.0005020959,0.0025023369,0.0038479213,0.0023465757,0.0020042001,0.0010824575,0.00024654012],"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":[0.00023343971,0.00022372883,0.77155113,0.0012001038,0.0002327739,0.0007468461,0.070684515,0.0017826582,0.002236285,0.009183355,0.0045111557,0.13741398],"study_design_scores_gemma":[0.000009721423,0.00008167362,0.9307864,0.0008885144,0.0000980635,0.000115328614,0.04800364,0.0017675603,0.0005485099,0.0009875573,0.016618874,0.00009413979],"about_ca_topic_score_codex":0.9352498,"about_ca_topic_score_gemma":0.95979047,"teacher_disagreement_score":0.99167764,"about_ca_system_score_codex":0.041220035,"about_ca_system_score_gemma":0.055575725,"threshold_uncertainty_score":0.2990737},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004991777,0.0033837298,0.00008288905,0.96230245,0.02431458,0.000035409565,0.00028511503,0.000016879663,0.00907982],"genre_scores_gemma":[0.008656403,0.0020395117,0.0002400714,0.93400997,0.008849202,0.00008231249,0.000100584344,0.00007072121,0.045951217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9625203,0.004674062,0.0024434146,0.0024813046,0.018589156,0.009291777],"domain_scores_gemma":[0.9253468,0.030568723,0.0032883473,0.0015601955,0.029509673,0.009726271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023380673,0.0015551249,0.002160884,0.0032103914,0.020734724,0.01798834,0.008367063,0.1102338,0.014190131],"category_scores_gemma":[0.07913812,0.0016490645,0.00298924,0.004474748,0.014634106,0.006344958,0.0072986204,0.07284438,0.0031969673],"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":[0.000025636293,0.0000071962386,0.000109705834,0.00012447766,0.000013968097,0.0001201757,0.00088219234,0.000041005726,0.000062381114,0.011770684,0.9857124,0.0011300669],"study_design_scores_gemma":[0.00007263438,0.0000117487725,0.0014550128,0.0009206806,0.00006028859,0.00004613282,0.0021670265,0.000071541435,0.00012140733,0.0026999265,0.9922909,0.000082743194],"about_ca_topic_score_codex":0.91866904,"about_ca_topic_score_gemma":0.9510073,"teacher_disagreement_score":0.88368493,"about_ca_system_score_codex":0.11631505,"about_ca_system_score_gemma":0.27057987,"threshold_uncertainty_score":0.8439287},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22709495,0.005503393,0.08104807,0.07081484,0.00035295365,0.00062433525,0.00016113675,0.0003651327,0.6140351],"genre_scores_gemma":[0.8562262,0.0031549756,0.09172029,0.0019062681,0.000030287069,0.00027354975,0.00014003916,0.00006775696,0.04648054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910227,0.005557749,0.0003272014,0.00044536468,0.0014303827,0.0012165119],"domain_scores_gemma":[0.98737365,0.0053212,0.001204728,0.0013865244,0.0020344614,0.0026794234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013472395,0.0003466265,0.0002891501,0.0016951518,0.0049075987,0.009101407,0.0016584401,0.0019755738,0.0039472063],"category_scores_gemma":[0.014847146,0.000343567,0.00023882616,0.0011203769,0.011435356,0.0050213407,0.010267507,0.0031592953,0.0010421899],"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":[0.000022130962,0.00020925119,0.011202102,0.00049958745,0.000007572124,0.00076937047,0.30070066,0.00089950755,0.0015694145,0.3498358,0.015621098,0.31866348],"study_design_scores_gemma":[0.000017522036,0.00015882078,0.031318124,0.004271757,0.000015673046,0.0011869818,0.34474438,0.0015630178,0.0036121032,0.13726357,0.47575822,0.00008983992],"about_ca_topic_score_codex":0.05398571,"about_ca_topic_score_gemma":0.10999465,"teacher_disagreement_score":0.05398571,"about_ca_system_score_codex":0.011540132,"about_ca_system_score_gemma":0.06932077,"threshold_uncertainty_score":0.10734296},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01758275,0.007140194,0.7351795,0.06402627,0.005026862,0.0009416489,0.00058847474,0.00061255804,0.16890174],"genre_scores_gemma":[0.656426,0.0045012864,0.29821563,0.011041092,0.0029529112,0.0020551886,0.0006152268,0.0008889288,0.0233037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8375855,0.113888845,0.0064261467,0.011390014,0.02726659,0.0034429587],"domain_scores_gemma":[0.6595421,0.25274605,0.011506725,0.026874766,0.046946753,0.0023836598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14479312,0.0023207567,0.0018681143,0.0115852235,0.008483631,0.015471382,0.0074099763,0.005425608,0.019210324],"category_scores_gemma":[0.25244293,0.0010140443,0.0032703078,0.0095270155,0.027313624,0.031161426,0.016385986,0.010546149,0.0031451224],"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":[0.000047798476,0.00003466893,0.0014694036,0.0006378937,0.00010788484,0.00013207253,0.008657114,0.0009049669,0.0000830348,0.932396,0.00846075,0.047068484],"study_design_scores_gemma":[0.000029600145,0.000030099904,0.0007217259,0.0015215084,0.000075370815,0.0001285475,0.0040650517,0.004394604,0.00046618178,0.90526634,0.08326541,0.00003554532],"about_ca_topic_score_codex":0.0054248925,"about_ca_topic_score_gemma":0.0040994775,"teacher_disagreement_score":0.14479312,"about_ca_system_score_codex":0.0136642745,"about_ca_system_score_gemma":0.015644971,"threshold_uncertainty_score":0.7657484},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5617596,0.007341459,0.013220286,0.33404624,0.0009794947,0.00049033505,0.00024797223,0.0003281048,0.08158645],"genre_scores_gemma":[0.9585202,0.0015818952,0.010217156,0.007241149,0.00014820808,0.0003258721,0.0000909889,0.00007874921,0.021795876],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9631782,0.029649518,0.00079801003,0.0011612356,0.0019665111,0.0032464617],"domain_scores_gemma":[0.92970973,0.03890135,0.0028852469,0.0030778972,0.0053225565,0.020103283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024852177,0.00025877875,0.00046491472,0.0017519005,0.015640212,0.014513246,0.002227886,0.0046765506,0.018861946],"category_scores_gemma":[0.04149398,0.00044961236,0.00043785482,0.0028203991,0.009452224,0.008923108,0.017038487,0.0045215366,0.0013325062],"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":[0.000565303,0.0013812503,0.06660199,0.0012229064,0.000100475314,0.0022111041,0.280402,0.0011772251,0.00080543355,0.17420982,0.1178259,0.35349664],"study_design_scores_gemma":[0.00015806654,0.0005233629,0.03345609,0.0011541258,0.00005633279,0.00042995717,0.6909396,0.0009482355,0.000679087,0.03712836,0.23440991,0.00011685112],"about_ca_topic_score_codex":0.037448898,"about_ca_topic_score_gemma":0.16391264,"teacher_disagreement_score":0.037448898,"about_ca_system_score_codex":0.01351161,"about_ca_system_score_gemma":0.07126431,"threshold_uncertainty_score":0.13143241},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013203159,0.086983815,0.0075569814,0.8519762,0.0049835616,0.000112940834,0.00007938988,0.000059270944,0.046927456],"genre_scores_gemma":[0.2772728,0.2655727,0.036418032,0.35854512,0.01796369,0.00087762915,0.00028953905,0.0006718423,0.0423886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9166385,0.05442299,0.0029561003,0.002706058,0.017105056,0.0061711976],"domain_scores_gemma":[0.825864,0.10878032,0.0041136304,0.005729874,0.043193158,0.012319003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18358262,0.0013803298,0.0017430824,0.0054474664,0.00609238,0.022773206,0.003545614,0.012076992,0.014815612],"category_scores_gemma":[0.12519136,0.00052309764,0.0011952764,0.005134452,0.03441876,0.01830443,0.0113195265,0.015055981,0.0007772075],"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":[0.000117238465,0.00015420672,0.0010752443,0.0014742848,0.000075756296,0.00015137676,0.0029522572,0.0012880014,0.00032079208,0.63145137,0.21582127,0.14511822],"study_design_scores_gemma":[0.000046183333,0.000086061424,0.0017464509,0.0065871906,0.000059293336,0.00009172757,0.0051355134,0.0005490234,0.00036638297,0.22562426,0.75964165,0.00006620784],"about_ca_topic_score_codex":0.08501093,"about_ca_topic_score_gemma":0.1453404,"teacher_disagreement_score":0.18358262,"about_ca_system_score_codex":0.036578346,"about_ca_system_score_gemma":0.08563931,"threshold_uncertainty_score":0.9708893},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011702984,0.057592172,0.017166415,0.8861401,0.0040921764,0.00036952968,0.00008537005,0.0001303287,0.022720907],"genre_scores_gemma":[0.38934717,0.14189923,0.12201415,0.2875975,0.0038881076,0.0023963337,0.00026197225,0.0006180609,0.051977374],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92511195,0.05336617,0.0025359525,0.0028711588,0.014699646,0.0014151381],"domain_scores_gemma":[0.8689833,0.080959566,0.0032016207,0.0030584724,0.028769044,0.015027962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06866866,0.000466259,0.0011994763,0.0033444436,0.008360984,0.010561739,0.0015700586,0.002925349,0.0041208165],"category_scores_gemma":[0.13819906,0.0005940554,0.00051002135,0.0028082605,0.011479754,0.013071701,0.0067157745,0.011452159,0.0011044593],"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":[0.00017282856,0.0005313776,0.0036311126,0.0022251855,0.0000528012,0.0009638178,0.056515817,0.00043545046,0.0008131383,0.084777705,0.4066589,0.44322184],"study_design_scores_gemma":[0.000044033255,0.0003603855,0.002896664,0.00920986,0.000025452919,0.0010814375,0.057461724,0.00052144943,0.0012394604,0.07094551,0.8560438,0.00017021134],"about_ca_topic_score_codex":0.010589686,"about_ca_topic_score_gemma":0.020056034,"teacher_disagreement_score":0.06866866,"about_ca_system_score_codex":0.012071953,"about_ca_system_score_gemma":0.03730428,"threshold_uncertainty_score":0.36315894},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018443409,0.03267678,0.01893305,0.841044,0.014381479,0.0005009529,0.00013411955,0.00019362012,0.09029166],"genre_scores_gemma":[0.24030519,0.08431079,0.070967965,0.3245403,0.019928401,0.0018392043,0.00050951575,0.0017819855,0.25581667],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94350016,0.031104399,0.0024719099,0.0022154814,0.016514288,0.0041937013],"domain_scores_gemma":[0.8919813,0.042817615,0.0037998909,0.0046875565,0.041183583,0.015530012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14172497,0.0007705182,0.0007726504,0.00319635,0.0073241685,0.015368292,0.0020401322,0.00940232,0.02294222],"category_scores_gemma":[0.11535549,0.00047502946,0.00073075196,0.0025034987,0.01890941,0.010250798,0.009514043,0.00983761,0.0020293253],"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":[0.00007216169,0.00010224826,0.00082820037,0.0005762053,0.00003461765,0.00009897528,0.0028406996,0.00034154893,0.0005612109,0.21609513,0.62537706,0.15307201],"study_design_scores_gemma":[0.000016653557,0.000032228672,0.0011468201,0.001533642,0.000015656839,0.000039434253,0.0016652924,0.00014687641,0.00035335898,0.039261073,0.9557542,0.000034682027],"about_ca_topic_score_codex":0.096279025,"about_ca_topic_score_gemma":0.21821816,"teacher_disagreement_score":0.14172497,"about_ca_system_score_codex":0.029737696,"about_ca_system_score_gemma":0.08698196,"threshold_uncertainty_score":0.74952227},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004467133,0.9875799,0.00010980724,0.002354036,0.0003545013,0.00022747922,0.0012647121,0.000010240193,0.003632273],"genre_scores_gemma":[0.029736321,0.96719456,0.0006049576,0.00067195145,0.00006382019,0.00019331503,0.00072564906,0.0000058506052,0.00080345775],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.992922,0.0011681691,0.001500614,0.00047362194,0.0031649594,0.00077064824],"domain_scores_gemma":[0.9644684,0.01257794,0.004325146,0.0004702252,0.016777096,0.0013810871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0107649295,0.0010053483,0.0024871426,0.021490566,0.003911675,0.006204664,0.0018499399,0.0013441535,0.0028682454],"category_scores_gemma":[0.04044122,0.00074462837,0.0014870932,0.047243197,0.00217475,0.0015875992,0.002357907,0.0013407661,0.00026906427],"study_design_candidate":"systematic_review","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":[0.00033647407,0.00007403954,0.016248895,0.4487283,0.0016094419,0.0010895124,0.005392598,0.0009954297,0.0005935618,0.005907853,0.048803955,0.47021988],"study_design_scores_gemma":[0.00006992839,0.00009832428,0.07091157,0.65261674,0.0045968317,0.0006969806,0.009480202,0.00026494445,0.0004189814,0.0008208081,0.2599038,0.00012085435],"about_ca_topic_score_codex":0.9572978,"about_ca_topic_score_gemma":0.982704,"teacher_disagreement_score":0.9249171,"about_ca_system_score_codex":0.07508292,"about_ca_system_score_gemma":0.34172708,"threshold_uncertainty_score":0.54476726},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46400493,0.0063410546,0.24030456,0.07425217,0.0005414936,0.015867999,0.00024591156,0.0006405081,0.19780134],"genre_scores_gemma":[0.8893568,0.0013232471,0.10211847,0.0015308583,0.00006021563,0.003990846,0.00007172591,0.00003988468,0.0015080017],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.70376664,0.26743114,0.004288079,0.0046575745,0.012170309,0.0076862657],"domain_scores_gemma":[0.62929755,0.30570057,0.017406408,0.017052101,0.019461716,0.011081684],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22488572,0.001281828,0.0010503404,0.007246795,0.010676937,0.013276755,0.004508581,0.0028592285,0.0037275355],"category_scores_gemma":[0.17863072,0.0009515284,0.0010626758,0.0034420223,0.031561643,0.012895478,0.018473342,0.004194997,0.0003382286],"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":[0.0004202646,0.0032941788,0.045412645,0.005124912,0.00034488816,0.00080961396,0.33143094,0.012054105,0.0017627239,0.15311882,0.011941921,0.43428504],"study_design_scores_gemma":[0.0011080774,0.002224751,0.035317145,0.014817437,0.00034827355,0.000419533,0.466446,0.015829768,0.006033332,0.28849354,0.16854051,0.0004216128],"about_ca_topic_score_codex":0.029365454,"about_ca_topic_score_gemma":0.043790318,"teacher_disagreement_score":0.7751143,"about_ca_system_score_codex":0.039485704,"about_ca_system_score_gemma":0.096980184,"threshold_uncertainty_score":0.9558539},"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":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041002613,0.001164647,0.91893554,0.0045948015,0.0009878845,0.016036876,0.001652347,0.0014494156,0.051078226],"genre_scores_gemma":[0.031096369,0.00057846383,0.9394694,0.0008397324,0.0001147482,0.024658734,0.00041236987,0.0003871386,0.0024430293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6613495,0.2605043,0.021313183,0.012548118,0.042373534,0.001911479],"domain_scores_gemma":[0.5081366,0.361838,0.01579776,0.05437736,0.056987174,0.002863132],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28212705,0.0032909566,0.0040222183,0.02287575,0.005089136,0.016431144,0.005104698,0.0039181868,0.0252764],"category_scores_gemma":[0.40756664,0.0016813636,0.0063941316,0.017056018,0.014672366,0.014171087,0.012028196,0.009635904,0.0039164713],"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":[0.00055448274,0.00032711722,0.002731012,0.009958552,0.00058787875,0.00020341323,0.027479041,0.002501979,0.0027367505,0.47547555,0.025924783,0.45151946],"study_design_scores_gemma":[0.00075178494,0.00081985764,0.0071568093,0.013035968,0.0008021066,0.0005706426,0.01152517,0.014497575,0.0051530604,0.5683234,0.37693766,0.00042594338],"about_ca_topic_score_codex":0.0040885727,"about_ca_topic_score_gemma":0.0052243914,"teacher_disagreement_score":0.717873,"about_ca_system_score_codex":0.014349798,"about_ca_system_score_gemma":0.02522661,"threshold_uncertainty_score":0.8852652},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00484916,0.0429606,0.215578,0.24734382,0.01765904,0.0015117129,0.00012348824,0.0020061044,0.46796805],"genre_scores_gemma":[0.080803655,0.048553623,0.38846773,0.09070022,0.0075122723,0.0030878426,0.00023580107,0.001639221,0.3789997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9624197,0.027196743,0.0018197959,0.0010289213,0.006873496,0.0006612323],"domain_scores_gemma":[0.8128249,0.1606531,0.002803553,0.0051488816,0.014556235,0.0040133353],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.049860932,0.0005662477,0.0008969953,0.0021968526,0.0040838183,0.015553793,0.0015989292,0.0037679742,0.012094937],"category_scores_gemma":[0.082526885,0.0007734295,0.00038818098,0.0018660137,0.009185714,0.014624318,0.0062843873,0.012385883,0.009058598],"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":[0.000018415498,0.000096003656,0.00043659421,0.001001719,0.000005796269,0.0003107918,0.02605322,0.00022914722,0.0005186064,0.38850373,0.20131989,0.38150612],"study_design_scores_gemma":[0.0000059503204,0.000032860495,0.00021596061,0.0014236277,0.0000046363425,0.000441938,0.003484399,0.00031395874,0.00025627497,0.05781569,0.9359854,0.000019259927],"about_ca_topic_score_codex":0.0013706674,"about_ca_topic_score_gemma":0.004057385,"teacher_disagreement_score":0.99623203,"about_ca_system_score_codex":0.005105001,"about_ca_system_score_gemma":0.014500629,"threshold_uncertainty_score":0.26369298},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94127476,0.0012102833,0.007994457,0.0018698595,0.00010092664,0.00017257499,0.00022905333,0.000103017104,0.047045108],"genre_scores_gemma":[0.9655731,0.0004826755,0.0029183815,0.00011761442,0.000018486191,0.00007860547,0.00010679685,0.00004748686,0.030656751],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9958121,0.0018943661,0.00011900124,0.00038712847,0.00090037886,0.0008870456],"domain_scores_gemma":[0.9917184,0.0018008058,0.001007117,0.00028806188,0.002906873,0.002278782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004036787,0.00050641526,0.00032783893,0.00202598,0.0047169924,0.0044668424,0.0006446369,0.0006593751,0.009639386],"category_scores_gemma":[0.008475564,0.0003145309,0.00029857524,0.0016561649,0.0037716634,0.0016938073,0.0026362222,0.0011490909,0.0012881027],"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":[0.00029638037,0.00013346056,0.13776225,0.00030739707,0.000043338136,0.0008207252,0.6741886,0.0005419926,0.005877713,0.020130873,0.0052942396,0.15460296],"study_design_scores_gemma":[0.0000125769,0.0003169052,0.46200448,0.00042544692,0.000033974964,0.00032514366,0.39313227,0.0005106995,0.0019632506,0.0025217189,0.13865305,0.00010047229],"about_ca_topic_score_codex":0.18461998,"about_ca_topic_score_gemma":0.30017057,"teacher_disagreement_score":0.18461998,"about_ca_system_score_codex":0.01075729,"about_ca_system_score_gemma":0.012242855,"threshold_uncertainty_score":0.3670907},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958307,0.00007626121,0.0000879712,0.00031765836,0.00000941883,0.000030938838,0.00002013987,0.000004443598,0.003622509],"genre_scores_gemma":[0.9992963,0.0000450767,0.00007039078,0.00003436031,0.0000029622909,0.0000066757775,0.000016426242,0.0000012072966,0.0005264821],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979976,0.0006774102,0.000083954495,0.00010405845,0.00037798317,0.0007590036],"domain_scores_gemma":[0.9924981,0.0011490313,0.00130288,0.00013212315,0.0013616849,0.0035561603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021469349,0.00013782157,0.0001788877,0.00058019045,0.0013257433,0.002242626,0.00032927227,0.0002485351,0.0035055352],"category_scores_gemma":[0.0068477043,0.00013613445,0.00015533625,0.00047396676,0.0005231425,0.0003932493,0.0007323676,0.0006357654,0.00023983247],"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":[0.000055255925,0.0005040087,0.9455616,0.00013192568,0.000022705075,0.00048064857,0.024273919,0.0002300048,0.00076843146,0.001363033,0.0019758292,0.024632629],"study_design_scores_gemma":[0.000012610299,0.00021017667,0.9418492,0.00009381949,0.0000139584345,0.00009512823,0.050581716,0.00042456653,0.0004261079,0.0002041219,0.006078941,0.000009579312],"about_ca_topic_score_codex":0.021646945,"about_ca_topic_score_gemma":0.042389933,"teacher_disagreement_score":0.021646945,"about_ca_system_score_codex":0.0024837626,"about_ca_system_score_gemma":0.007874501,"threshold_uncertainty_score":0.043041885},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98139817,0.00019783026,0.010640151,0.0004136338,0.00002704897,0.0031149809,0.00015490469,0.00002607772,0.004027196],"genre_scores_gemma":[0.95849276,0.00028905156,0.03626323,0.00024746679,0.000022745098,0.0027224345,0.00008426365,0.000016991582,0.0018609929],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97148085,0.02131552,0.001020889,0.001027119,0.0034952932,0.0016604201],"domain_scores_gemma":[0.9344246,0.049275894,0.0027622047,0.0028265775,0.0076662665,0.0030445629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034879576,0.0008888642,0.00087518414,0.0024249188,0.003719789,0.0027944283,0.00264388,0.002558116,0.0030109258],"category_scores_gemma":[0.044721168,0.00058584055,0.0008842217,0.0014169377,0.0011913514,0.0020223074,0.0030753769,0.0016525161,0.0004338595],"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":[0.011537894,0.15657985,0.1729682,0.0027980718,0.00076784164,0.008347941,0.06861199,0.02321504,0.015226835,0.012079305,0.003956957,0.5239101],"study_design_scores_gemma":[0.0082529755,0.19327466,0.2647105,0.0047387155,0.0019060996,0.009515337,0.22288609,0.15085407,0.07892835,0.020140808,0.04364264,0.0011497055],"about_ca_topic_score_codex":0.005919447,"about_ca_topic_score_gemma":0.013243208,"teacher_disagreement_score":0.034879576,"about_ca_system_score_codex":0.0059098643,"about_ca_system_score_gemma":0.0072214394,"threshold_uncertainty_score":0.18446308},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000638786,0.12346997,0.08858793,0.5059705,0.22724007,0.00237093,0.00038570317,0.0017258592,0.04961023],"genre_scores_gemma":[0.011582287,0.14405133,0.18378127,0.31499705,0.23687625,0.004554416,0.0007749236,0.0021387707,0.10124366],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95207185,0.027732925,0.0051095965,0.0013754404,0.0129053835,0.00080487103],"domain_scores_gemma":[0.78120416,0.16562374,0.005548578,0.0032344235,0.039923217,0.004465934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049294353,0.0017511259,0.0013408643,0.006979367,0.0044498034,0.009004705,0.004255108,0.009488702,0.02045249],"category_scores_gemma":[0.13894163,0.0011100776,0.0021991963,0.0025676626,0.008507895,0.0076046702,0.005317295,0.01795378,0.012277767],"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":[0.000025763931,0.00007852892,0.00017479018,0.0012306803,0.000017045215,0.00016554107,0.0010620728,0.00015327109,0.0004456049,0.0098463725,0.87157196,0.115228415],"study_design_scores_gemma":[0.0000067733677,0.000025500964,0.0002557058,0.002310809,0.0000063560633,0.0004292062,0.00055955315,0.00013136245,0.00016648171,0.015290224,0.9807812,0.000036773115],"about_ca_topic_score_codex":0.0031724323,"about_ca_topic_score_gemma":0.010218517,"teacher_disagreement_score":0.049294353,"about_ca_system_score_codex":0.00694587,"about_ca_system_score_gemma":0.01329955,"threshold_uncertainty_score":0.2606966},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96910983,0.0010485916,0.001991317,0.002485375,0.00008016108,0.00008965278,0.00021216735,0.000020888505,0.024961961],"genre_scores_gemma":[0.9784393,0.0007386065,0.0010438336,0.00030635664,0.000012023195,0.00009800509,0.0001503237,0.0000467774,0.019164857],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99601233,0.0018358075,0.00009064263,0.0004581018,0.00074764626,0.00085547304],"domain_scores_gemma":[0.9955793,0.001401806,0.000483293,0.00031039995,0.0012928682,0.00093230396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046017594,0.00064337376,0.0006090666,0.001907565,0.015027518,0.011223147,0.0021583377,0.0012612855,0.009891379],"category_scores_gemma":[0.008119331,0.00058287417,0.00045284868,0.0030396958,0.011753581,0.0055049444,0.0069945655,0.0025179824,0.0007323422],"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":[0.000028759725,0.000026504125,0.015003301,0.00006561611,0.000010060474,0.00030032953,0.96998674,0.00004483207,0.00047665363,0.004406287,0.00080625,0.008844635],"study_design_scores_gemma":[0.0000019013169,0.000021303296,0.022819232,0.0001127183,0.000009529795,0.000065494605,0.94935995,0.00008247606,0.0001822184,0.00041997514,0.026904639,0.000020609461],"about_ca_topic_score_codex":0.6351781,"about_ca_topic_score_gemma":0.8061173,"teacher_disagreement_score":0.3648219,"about_ca_system_score_codex":0.02060141,"about_ca_system_score_gemma":0.024218306,"threshold_uncertainty_score":0.73394084},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012756118,0.07903469,0.25687072,0.048384566,0.0018242712,0.0011071995,0.00017884858,0.00037686192,0.59946674],"genre_scores_gemma":[0.30149674,0.12457845,0.36737236,0.007025231,0.0009026527,0.0020149674,0.00040756792,0.00080716267,0.19539484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9735588,0.015640872,0.0009704551,0.0015869553,0.007737741,0.0005051494],"domain_scores_gemma":[0.96017945,0.027563052,0.0007165581,0.002098806,0.008913041,0.0005290133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033305384,0.0008589493,0.00084264716,0.004737866,0.0027195753,0.01692655,0.0016702127,0.002211294,0.008249523],"category_scores_gemma":[0.039418403,0.00064464763,0.00040108187,0.005774971,0.014366196,0.016025575,0.005354436,0.0040685725,0.002303528],"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":[0.000027634918,0.00009172586,0.00036951245,0.00035637105,0.0000041111966,0.00005174811,0.0030951193,0.00076181284,0.0002527705,0.6650309,0.010788747,0.31916958],"study_design_scores_gemma":[0.000017503238,0.00014536727,0.0013486723,0.0025943017,0.000010439737,0.00016824121,0.0051378836,0.003709548,0.0027202754,0.50740665,0.47669718,0.000044104265],"about_ca_topic_score_codex":0.005915402,"about_ca_topic_score_gemma":0.0048109624,"teacher_disagreement_score":0.033305384,"about_ca_system_score_codex":0.011373788,"about_ca_system_score_gemma":0.012179409,"threshold_uncertainty_score":0.17613786},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7548477,0.0022420932,0.05866294,0.036044214,0.00054761005,0.0011982658,0.000057404854,0.00021273136,0.1461871],"genre_scores_gemma":[0.99446315,0.0000902919,0.004017712,0.00066026463,0.000056721125,0.00018457793,0.000006824269,0.00002514751,0.000495398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.66454023,0.24599332,0.02558334,0.0062096147,0.047624234,0.010049225],"domain_scores_gemma":[0.35758212,0.48585954,0.046525,0.034765653,0.05566453,0.019603258],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31234393,0.00042237417,0.00087207544,0.0037413163,0.008279907,0.016889304,0.0015090766,0.002288623,0.0033980024],"category_scores_gemma":[0.42569923,0.0011264167,0.0006648359,0.0018777425,0.020445775,0.0092645725,0.012390213,0.0060091186,0.0002691346],"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":[0.001153,0.0019203012,0.24739315,0.0021209405,0.0006439709,0.0010004974,0.11601218,0.0050703273,0.0026513247,0.3363138,0.007808003,0.27791247],"study_design_scores_gemma":[0.0006110595,0.00223242,0.41298893,0.007263016,0.0007667664,0.0018990678,0.113297835,0.025162632,0.01633442,0.37177113,0.046731487,0.00094131916],"about_ca_topic_score_codex":0.0046867933,"about_ca_topic_score_gemma":0.008791545,"teacher_disagreement_score":0.68765604,"about_ca_system_score_codex":0.0103468755,"about_ca_system_score_gemma":0.02674944,"threshold_uncertainty_score":0.8480024},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031626958,0.011459393,0.027447805,0.69588643,0.006052669,0.0026807555,0.0020806736,0.0004607755,0.2507689],"genre_scores_gemma":[0.24979301,0.010510151,0.1280932,0.53166175,0.0062178713,0.011895551,0.0023315304,0.00050246954,0.058994547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6539452,0.19882739,0.02238671,0.011613856,0.092505425,0.02072148],"domain_scores_gemma":[0.38295445,0.372275,0.014236968,0.02049093,0.19647118,0.013571532],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32731825,0.0015966857,0.0030857155,0.0062563014,0.01677251,0.040499263,0.012581495,0.029150708,0.015798716],"category_scores_gemma":[0.4869625,0.0015898811,0.0025575673,0.009454849,0.036609456,0.019065185,0.010735077,0.021050392,0.003457203],"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":[0.00008806819,0.00008717492,0.00088537927,0.00064203027,0.000042181615,0.00010437561,0.0022930643,0.0009539762,0.00010303641,0.85032016,0.12172062,0.022759905],"study_design_scores_gemma":[0.00039359447,0.00015844313,0.0030031155,0.011253022,0.00022098966,0.00015321113,0.0056808726,0.0036214092,0.0005508632,0.47494757,0.49971834,0.00029854212],"about_ca_topic_score_codex":0.69176745,"about_ca_topic_score_gemma":0.5556845,"teacher_disagreement_score":0.32731825,"about_ca_system_score_codex":0.12947348,"about_ca_system_score_gemma":0.45480168,"threshold_uncertainty_score":0.9394002},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013455401,0.028508963,0.26480946,0.46259108,0.008016544,0.14353037,0.0020603715,0.0012391785,0.07578862],"genre_scores_gemma":[0.08618327,0.012898361,0.7590334,0.04361481,0.0013278266,0.0786226,0.0014052585,0.00056100317,0.016353449],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.5796834,0.29412118,0.06524356,0.0065054893,0.046086743,0.008359685],"domain_scores_gemma":[0.54103047,0.16337645,0.019123642,0.02612995,0.22950502,0.02083444],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5289559,0.0014303427,0.002272294,0.0077467277,0.010575826,0.011641127,0.01150194,0.012393469,0.0037396369],"category_scores_gemma":[0.34538493,0.0027291246,0.0039326698,0.008066515,0.011709327,0.0053304024,0.013928066,0.014596427,0.0022856037],"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":[0.00066850136,0.0009963862,0.0066928444,0.018347992,0.00046874318,0.0023992578,0.14654446,0.005635356,0.0053576306,0.06988867,0.3969636,0.3460365],"study_design_scores_gemma":[0.0006693575,0.00044245186,0.010444967,0.050498854,0.00041018176,0.001171647,0.028371919,0.00469773,0.0022403677,0.05198929,0.8484705,0.00059268455],"about_ca_topic_score_codex":0.09410243,"about_ca_topic_score_gemma":0.20678759,"teacher_disagreement_score":0.96679145,"about_ca_system_score_codex":0.03320853,"about_ca_system_score_gemma":0.24135211,"threshold_uncertainty_score":0.5808813},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27495128,0.009917412,0.08970822,0.18176313,0.0006279667,0.0009832564,0.0001787791,0.00018608186,0.44168386],"genre_scores_gemma":[0.9616936,0.0026876368,0.027771423,0.0019099175,0.00006357448,0.00043411765,0.00003405302,0.00005486895,0.0053506726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.930696,0.051415093,0.001972066,0.0018550837,0.010272981,0.0037887474],"domain_scores_gemma":[0.92795867,0.045392696,0.0035688377,0.0041687028,0.015962154,0.0029490276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10208574,0.0005428608,0.00083732174,0.0038214112,0.019396054,0.027575461,0.0034266228,0.003058833,0.004886982],"category_scores_gemma":[0.066242,0.0005460992,0.00050013966,0.0047092303,0.042612065,0.015889412,0.015899645,0.0061131753,0.0004113731],"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":[0.000059578477,0.00013330553,0.005170624,0.0008842554,0.00003247004,0.0004478027,0.22904152,0.0008338106,0.00046778825,0.6724461,0.004389681,0.086093135],"study_design_scores_gemma":[0.00001984474,0.00008645115,0.004430189,0.0028517637,0.00006085755,0.00023088121,0.64238995,0.0022570712,0.0021365436,0.23832555,0.10712399,0.00008686934],"about_ca_topic_score_codex":0.114354216,"about_ca_topic_score_gemma":0.14562498,"teacher_disagreement_score":0.96264976,"about_ca_system_score_codex":0.037350222,"about_ca_system_score_gemma":0.062417317,"threshold_uncertainty_score":0.5398874},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001911011,0.00905234,0.0011310078,0.9740461,0.0022397041,0.00004022901,0.000017829872,0.000015136591,0.011546748],"genre_scores_gemma":[0.36042285,0.07460238,0.02671835,0.50305605,0.006367562,0.0005374898,0.00009356148,0.00020450885,0.027997212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9156445,0.05583114,0.003164805,0.0020897086,0.015766693,0.0075031905],"domain_scores_gemma":[0.73325557,0.1742046,0.0039863368,0.0060007325,0.06296996,0.019582829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12370193,0.00062784355,0.0014219419,0.0017199755,0.0117727155,0.018620348,0.006228809,0.013345608,0.013398092],"category_scores_gemma":[0.1952107,0.00036435467,0.0012587113,0.0027777413,0.03962814,0.031109521,0.008504401,0.026281927,0.0010980567],"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":[0.00014832494,0.00027854738,0.0030021882,0.0031429224,0.00005386804,0.00085746153,0.10093989,0.0009002825,0.00072709034,0.4087519,0.30377093,0.17742655],"study_design_scores_gemma":[0.00003243426,0.00018919056,0.0046533886,0.0097068865,0.00007911373,0.0004287877,0.25954646,0.00050136267,0.00088144495,0.13448995,0.5893196,0.00017137789],"about_ca_topic_score_codex":0.24900801,"about_ca_topic_score_gemma":0.32050332,"teacher_disagreement_score":0.24900801,"about_ca_system_score_codex":0.033865105,"about_ca_system_score_gemma":0.10442389,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4430474,0.0042661605,0.011266781,0.30024013,0.0010845192,0.0005238679,0.000056687688,0.00008659178,0.23942788],"genre_scores_gemma":[0.9870113,0.0009920244,0.001961495,0.003853421,0.00010934223,0.00013685047,0.0000071809286,0.000045135985,0.0058832285],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8783843,0.10812015,0.00094219745,0.0013162399,0.006887675,0.0043493453],"domain_scores_gemma":[0.87143016,0.104390755,0.0025124196,0.003044689,0.012594187,0.0060277777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09658711,0.0005791158,0.00073829346,0.0019799683,0.024906162,0.01829397,0.003229826,0.00476388,0.005025359],"category_scores_gemma":[0.095519744,0.00039703742,0.00048303732,0.0014279826,0.052545007,0.01531898,0.018799588,0.013334794,0.00042696728],"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":[0.000027509162,0.00008799708,0.00096390786,0.00011050904,0.0000063919224,0.0004462515,0.95020604,0.00009934073,0.00014185623,0.029482579,0.0038121587,0.014615421],"study_design_scores_gemma":[0.000009462916,0.000045989156,0.0007786971,0.00040051318,0.000008779612,0.00015584928,0.9455543,0.00020444664,0.00034622804,0.008415866,0.04405351,0.000026408143],"about_ca_topic_score_codex":0.081714384,"about_ca_topic_score_gemma":0.13409063,"teacher_disagreement_score":0.09658711,"about_ca_system_score_codex":0.027286336,"about_ca_system_score_gemma":0.027931252,"threshold_uncertainty_score":0.5108075},"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":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10350499,0.0036953795,0.015390765,0.03072069,0.0039058223,0.14796631,0.4065011,0.0022466918,0.2860683],"genre_scores_gemma":[0.20251274,0.002237938,0.042240795,0.018024081,0.00047967464,0.105337866,0.32014078,0.0004690183,0.3085571],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98746055,0.004769608,0.0006525597,0.0007055473,0.0042873463,0.0021242818],"domain_scores_gemma":[0.9756787,0.0027881667,0.0015291026,0.0012437729,0.012601852,0.006158491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028405879,0.0010734878,0.0008176593,0.0022098855,0.0020770698,0.0025914414,0.0031539283,0.0031114654,0.030272344],"category_scores_gemma":[0.017350998,0.00090498675,0.0007047219,0.0019306311,0.0006621194,0.001248905,0.0049489294,0.0013715181,0.014949178],"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":[0.009761324,0.004731269,0.035057317,0.0027826577,0.0002028755,0.00032289463,0.0010522794,0.0014108233,0.0035527356,0.0019287376,0.74188226,0.19731486],"study_design_scores_gemma":[0.0034645374,0.006987845,0.3131253,0.0015729549,0.00018890866,0.00015772367,0.0014957999,0.0011688138,0.007097525,0.0008681141,0.6637538,0.000118690805],"about_ca_topic_score_codex":0.17207098,"about_ca_topic_score_gemma":0.22415224,"teacher_disagreement_score":0.17207098,"about_ca_system_score_codex":0.010255018,"about_ca_system_score_gemma":0.068910696,"threshold_uncertainty_score":0.34213883},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04159581,0.020113116,0.008943391,0.72991306,0.0026950897,0.0001957744,0.00013832805,0.00011392074,0.19629164],"genre_scores_gemma":[0.88914007,0.00851557,0.012323483,0.057809424,0.00060585834,0.00038890573,0.00007587033,0.00020497458,0.030935874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9723139,0.021781452,0.00047927472,0.0011867691,0.0027508456,0.0014877192],"domain_scores_gemma":[0.95901346,0.032627128,0.00081459555,0.0018925378,0.0034013188,0.0022509866],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02999107,0.00055987237,0.00055193284,0.002698928,0.016498378,0.017731547,0.002199844,0.005628301,0.0077616125],"category_scores_gemma":[0.02999724,0.00034825385,0.00037051356,0.0024242937,0.041762527,0.016753271,0.0132099055,0.0117278155,0.0005655303],"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":[0.00006040544,0.000097623735,0.002011209,0.00046084754,0.000009863362,0.00072447106,0.23799951,0.0001898831,0.0002884595,0.6003434,0.10700435,0.050809927],"study_design_scores_gemma":[0.000014878153,0.000052528867,0.0017165642,0.0020370693,0.0000095482155,0.00045537765,0.20636395,0.0003540885,0.00065964827,0.06825422,0.72004306,0.000039146707],"about_ca_topic_score_codex":0.021908415,"about_ca_topic_score_gemma":0.05215341,"teacher_disagreement_score":0.978989,"about_ca_system_score_codex":0.021010995,"about_ca_system_score_gemma":0.015434533,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067420945,0.124645494,0.0149644185,0.6930933,0.00259934,0.001529652,0.0004868367,0.00022476765,0.09503525],"genre_scores_gemma":[0.7783988,0.10513299,0.05232215,0.044501543,0.0019202598,0.0033314107,0.00048079164,0.00016606694,0.013745969],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7267481,0.21425739,0.011919217,0.0035631105,0.03148368,0.012028521],"domain_scores_gemma":[0.49954343,0.33947116,0.017278144,0.015306985,0.09681312,0.031587146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29353416,0.0006180945,0.00245966,0.0036708203,0.01118297,0.016155427,0.0058833105,0.0034588135,0.0053822924],"category_scores_gemma":[0.20842648,0.00064109947,0.0010791323,0.005930457,0.012937761,0.009460174,0.014708478,0.0068664406,0.00054588687],"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":[0.0005524533,0.0011782668,0.04901986,0.011973751,0.00040164165,0.0010744855,0.055597812,0.0030886023,0.0004363577,0.11421446,0.060125027,0.7023372],"study_design_scores_gemma":[0.0003311783,0.0010176955,0.1394254,0.059049033,0.0003489597,0.0012201329,0.2884261,0.006910954,0.0012793262,0.11768866,0.38370916,0.0005934114],"about_ca_topic_score_codex":0.5125111,"about_ca_topic_score_gemma":0.59746957,"teacher_disagreement_score":0.9487685,"about_ca_system_score_codex":0.051231496,"about_ca_system_score_gemma":0.2798584,"threshold_uncertainty_score":0.9807197},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42623693,0.011822915,0.0040113674,0.23377332,0.0014441654,0.005580338,0.0044325762,0.00037087058,0.31232753],"genre_scores_gemma":[0.94759667,0.0046822093,0.01111827,0.013175071,0.00012447502,0.0013476368,0.0012695518,0.000077258745,0.020608833],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9565652,0.013620247,0.00092153833,0.0010486373,0.018385606,0.009458797],"domain_scores_gemma":[0.95724654,0.005354187,0.001357176,0.00071647967,0.027148215,0.008177392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035099372,0.00086258847,0.0006058383,0.0023709035,0.011445213,0.0064780083,0.0032054163,0.0021851698,0.003699617],"category_scores_gemma":[0.034293357,0.00031610974,0.0007772379,0.004050306,0.002758766,0.0018762347,0.0036728967,0.0029249792,0.0003083889],"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":[0.0052879285,0.00426713,0.07715946,0.0042026574,0.0008869209,0.00086192024,0.022353819,0.009633694,0.0051095122,0.06994379,0.21548156,0.58481157],"study_design_scores_gemma":[0.0032016514,0.006558376,0.31465933,0.004915699,0.002003399,0.000331115,0.057140555,0.007782874,0.010721167,0.008858698,0.5832151,0.00061200786],"about_ca_topic_score_codex":0.98082215,"about_ca_topic_score_gemma":0.9930201,"teacher_disagreement_score":0.8178485,"about_ca_system_score_codex":0.1821515,"about_ca_system_score_gemma":0.48583883,"threshold_uncertainty_score":0.9485884},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022789733,0.60669005,0.10834169,0.14033113,0.025036514,0.001128229,0.00037964474,0.0007569812,0.11505676],"genre_scores_gemma":[0.0417983,0.6666888,0.17962131,0.028120488,0.018018499,0.0022410105,0.00032742854,0.00065553037,0.06252865],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9866349,0.0074644256,0.0018327304,0.00060399115,0.00308629,0.00037766303],"domain_scores_gemma":[0.9767496,0.01560728,0.0007890298,0.0009901096,0.004656055,0.0012078781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025158672,0.0010649236,0.0014933733,0.0054693497,0.0025913033,0.0057671787,0.0019499172,0.0041490267,0.010174488],"category_scores_gemma":[0.029888202,0.00080201245,0.0009983567,0.0056395847,0.008870068,0.006787225,0.004550004,0.005905524,0.004060348],"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":[0.000057208672,0.00023934033,0.0006762819,0.008280532,0.000040044994,0.0004788119,0.008600338,0.0010423816,0.0011478561,0.10089006,0.25946382,0.6190833],"study_design_scores_gemma":[0.000008187027,0.00010560124,0.0021850092,0.0099609075,0.000012100702,0.00094479375,0.0028911629,0.00032017194,0.00025432126,0.07293527,0.9103207,0.00006173397],"about_ca_topic_score_codex":0.008556474,"about_ca_topic_score_gemma":0.019045563,"teacher_disagreement_score":0.97484136,"about_ca_system_score_codex":0.007934435,"about_ca_system_score_gemma":0.0117728105,"threshold_uncertainty_score":0.13305336},"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":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039370246,0.11523758,0.0016319882,0.38412642,0.4358829,0.0002933321,0.0024096037,0.00044202068,0.056039102],"genre_scores_gemma":[0.102122374,0.18934079,0.008903717,0.15591308,0.22963472,0.00046938713,0.0040932475,0.00077900675,0.30874366],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9921961,0.0007658772,0.00033845977,0.00027477986,0.005698498,0.00072630733],"domain_scores_gemma":[0.9681245,0.0042392835,0.0008661496,0.000283578,0.022514492,0.003971941],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009822275,0.0011468016,0.00070388353,0.0032554963,0.0031902716,0.0052388515,0.0022628284,0.0034697407,0.016344275],"category_scores_gemma":[0.025274375,0.00036666784,0.000999834,0.0032025075,0.0015947758,0.0020410584,0.0018251558,0.0044419775,0.002941586],"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":[0.00002606457,0.00001974485,0.00032470646,0.00024174567,0.000005853323,0.00004835494,0.000076405275,0.00008894386,0.00008202008,0.0009694896,0.97517174,0.02294498],"study_design_scores_gemma":[0.000015137421,0.00004395209,0.008051286,0.00044223157,0.000023224005,0.0000792342,0.00067261513,0.00015791586,0.00025643667,0.0012809056,0.9889176,0.000059384434],"about_ca_topic_score_codex":0.23086652,"about_ca_topic_score_gemma":0.5712657,"teacher_disagreement_score":0.99017775,"about_ca_system_score_codex":0.012229939,"about_ca_system_score_gemma":0.023439856,"threshold_uncertainty_score":0.45904547},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7139553,0.0051994077,0.003334947,0.16306612,0.0003284145,0.0010697288,0.00032250653,0.00006229033,0.11266136],"genre_scores_gemma":[0.9898497,0.0010102604,0.0014161337,0.0019176897,0.000021813583,0.00013035782,0.000043253465,0.000012036224,0.0055987285],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95328295,0.018186994,0.001854154,0.0013354919,0.012707892,0.012632505],"domain_scores_gemma":[0.91859484,0.029005434,0.0068640998,0.002887544,0.023260135,0.019387852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036524966,0.0002955632,0.00066965097,0.0018044955,0.030218715,0.013955574,0.0023979784,0.0030340725,0.0028931855],"category_scores_gemma":[0.047601294,0.0006747076,0.0005304873,0.0036833754,0.01866824,0.0033063139,0.010583323,0.003885172,0.00014153722],"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":[0.00077706383,0.00067096803,0.17506227,0.00214233,0.00030171167,0.006513126,0.3104159,0.0060375724,0.0032748762,0.28551355,0.06037915,0.14891154],"study_design_scores_gemma":[0.00023546259,0.00033715996,0.21048614,0.0017140318,0.00016215735,0.00038103602,0.45328343,0.0030780747,0.0018298415,0.019763717,0.30844712,0.00028191102],"about_ca_topic_score_codex":0.98655635,"about_ca_topic_score_gemma":0.99540436,"teacher_disagreement_score":0.31659302,"about_ca_system_score_codex":0.31659302,"about_ca_system_score_gemma":0.48426792,"threshold_uncertainty_score":0.7926552},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06755281,0.0014130834,0.8995656,0.0015981685,0.00041949833,0.013593711,0.0015567803,0.00055575825,0.013744581],"genre_scores_gemma":[0.17820542,0.0004577779,0.7900923,0.00032707755,0.00006835969,0.028923525,0.0003779718,0.0001497588,0.0013979004],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7363665,0.23667562,0.007560759,0.006175041,0.012420479,0.0008015945],"domain_scores_gemma":[0.4712714,0.46238315,0.02331467,0.022143101,0.019334363,0.0015533854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18346988,0.0016096868,0.0019540472,0.009344366,0.0026028203,0.006816916,0.0033771116,0.0018280483,0.00645298],"category_scores_gemma":[0.30336508,0.0010939462,0.003634382,0.009802483,0.005649056,0.004720349,0.0069339117,0.0033781244,0.0006333433],"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":[0.001277818,0.0014834362,0.16395454,0.008790137,0.005448068,0.00050723494,0.055557802,0.022406284,0.002963448,0.12923716,0.017100865,0.5912732],"study_design_scores_gemma":[0.0015775877,0.0063849115,0.2350095,0.011535383,0.0049439403,0.0006945196,0.07999187,0.19228005,0.008601093,0.3595571,0.09800996,0.0014141316],"about_ca_topic_score_codex":0.0058153593,"about_ca_topic_score_gemma":0.007199498,"teacher_disagreement_score":0.18346988,"about_ca_system_score_codex":0.004073071,"about_ca_system_score_gemma":0.0049094507,"threshold_uncertainty_score":0.97029305},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010764584,0.007216813,0.0067017027,0.25014663,0.0154834585,0.0014414814,0.01501897,0.0038679708,0.6990465],"genre_scores_gemma":[0.0049833083,0.005956216,0.011673806,0.014080338,0.002006139,0.00061561115,0.0056158383,0.002248947,0.95281976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9807736,0.0021839566,0.0010063503,0.0007704811,0.013643715,0.0016219527],"domain_scores_gemma":[0.76486737,0.017751409,0.0023495452,0.004664468,0.19286841,0.017498739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025068255,0.0011589178,0.0011834607,0.005702757,0.006255892,0.013154093,0.0036231363,0.0075589465,0.24514681],"category_scores_gemma":[0.09521912,0.0008551254,0.00082147977,0.009894237,0.004352948,0.0063578594,0.0029239447,0.008096246,0.12520933],"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":[0.0000059060276,0.000017593107,0.00008505196,0.000039842296,4.8181147e-7,0.000007667711,0.000063502746,0.000043671946,0.00002844209,0.00217499,0.9816974,0.015835384],"study_design_scores_gemma":[0.000014603434,0.000016685472,0.001141639,0.00041127013,0.0000037170398,0.000021517451,0.0004950335,0.00019054272,0.00012259683,0.003339038,0.994221,0.000022386517],"about_ca_topic_score_codex":0.75576675,"about_ca_topic_score_gemma":0.87731135,"teacher_disagreement_score":0.24514681,"about_ca_system_score_codex":0.03611148,"about_ca_system_score_gemma":0.26891553,"threshold_uncertainty_score":0.8200978},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061367042,0.16484961,0.15029016,0.5156995,0.009369827,0.0034202028,0.0022810963,0.00032636034,0.14762661],"genre_scores_gemma":[0.36382142,0.1878507,0.35821673,0.060582995,0.007498793,0.0067160255,0.0025629555,0.00039927618,0.0123510705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.72988427,0.18932031,0.025251044,0.0063283485,0.046010092,0.0032059469],"domain_scores_gemma":[0.42791343,0.45963082,0.028461607,0.022120617,0.054510273,0.007363278],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23050602,0.0023435706,0.0038439715,0.020051625,0.003309834,0.022756906,0.005850274,0.008938998,0.022171095],"category_scores_gemma":[0.42863965,0.0012202215,0.0027397065,0.019533873,0.00984649,0.02048778,0.012677238,0.010588287,0.004743383],"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":[0.0006963287,0.0006655596,0.0055997735,0.04326964,0.001767081,0.00033875467,0.0018048375,0.0038960518,0.0011587756,0.46436557,0.04236736,0.43407032],"study_design_scores_gemma":[0.00035401425,0.0013245096,0.006781964,0.1375935,0.0022565373,0.000413547,0.009003341,0.00430626,0.006567935,0.6008064,0.2303663,0.00022570991],"about_ca_topic_score_codex":0.003321326,"about_ca_topic_score_gemma":0.004808623,"teacher_disagreement_score":0.23050602,"about_ca_system_score_codex":0.012039909,"about_ca_system_score_gemma":0.035994172,"threshold_uncertainty_score":0.94892305},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009546658,0.008981248,0.09602163,0.065271586,0.0006524663,0.00036934408,0.000027699247,0.00015241053,0.818977],"genre_scores_gemma":[0.69318414,0.0110414745,0.09559433,0.026326314,0.0010265124,0.002004257,0.000073955314,0.000377287,0.17037179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9114021,0.056894746,0.0015837784,0.0023047652,0.024737975,0.0030766344],"domain_scores_gemma":[0.94801515,0.038524687,0.002046331,0.0038554014,0.0061488166,0.0014096199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0701395,0.0009294066,0.0007749936,0.0033823603,0.010716331,0.019077267,0.0017815975,0.0070649595,0.003620469],"category_scores_gemma":[0.053976994,0.00067764195,0.00050648913,0.005112829,0.051896814,0.016595677,0.008762017,0.00701904,0.0013815133],"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":[0.000007290666,0.000018040855,0.00021844254,0.00004040453,0.000003832861,0.000047623795,0.006596035,0.0003838443,0.00007626506,0.96025455,0.0071704444,0.025183167],"study_design_scores_gemma":[0.000014540544,0.000030172154,0.0006288612,0.00066368683,0.000008151794,0.0001133088,0.008275178,0.001384593,0.00031782346,0.6707611,0.3177617,0.000040959727],"about_ca_topic_score_codex":0.025423106,"about_ca_topic_score_gemma":0.030553961,"teacher_disagreement_score":0.0701395,"about_ca_system_score_codex":0.01983639,"about_ca_system_score_gemma":0.027491463,"threshold_uncertainty_score":0.37093753},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53622633,0.00045697528,0.26129463,0.011081728,0.00032409775,0.006405113,0.003192376,0.001230201,0.17978865],"genre_scores_gemma":[0.804772,0.00041344663,0.16654457,0.00033340504,0.000026548936,0.008008038,0.001596068,0.0003777201,0.017928096],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9703395,0.02296183,0.0010493165,0.0010072006,0.0034666618,0.0011755655],"domain_scores_gemma":[0.9540374,0.026367841,0.0028231307,0.00401793,0.010169863,0.0025837873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042256553,0.0006247116,0.00040102127,0.0046273037,0.006220791,0.0072929054,0.0018871067,0.0010612089,0.005283148],"category_scores_gemma":[0.056934346,0.0003926185,0.00030484164,0.0055058133,0.004131788,0.004599772,0.007265236,0.0020291468,0.000991743],"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":[0.00025462048,0.00053917035,0.019711744,0.00076633104,0.000018578357,0.0006560217,0.58207315,0.002146635,0.0024381848,0.061748143,0.013575574,0.31607178],"study_design_scores_gemma":[0.00009362381,0.0004349216,0.023272553,0.001289374,0.000028977509,0.0002963801,0.69641906,0.0057556247,0.0074384753,0.04180162,0.2229956,0.00017375631],"about_ca_topic_score_codex":0.014586554,"about_ca_topic_score_gemma":0.018008096,"teacher_disagreement_score":0.98541343,"about_ca_system_score_codex":0.005929096,"about_ca_system_score_gemma":0.01473852,"threshold_uncertainty_score":0.22347665},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07015779,0.011941379,0.0013415525,0.7655847,0.0025830509,0.00015674012,0.00017844667,0.0001065935,0.1479497],"genre_scores_gemma":[0.9145886,0.015673183,0.0038912396,0.03726947,0.0011845432,0.000081993414,0.00013430597,0.000217648,0.026959075],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9300646,0.03281185,0.0015878906,0.0016330201,0.027230307,0.006672272],"domain_scores_gemma":[0.751836,0.049236134,0.008404735,0.004324256,0.06858273,0.11761611],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.05090341,0.00033146533,0.0007478252,0.0053483243,0.020023657,0.06048942,0.0017172177,0.0033841517,0.008693454],"category_scores_gemma":[0.14016327,0.00036096477,0.00034140845,0.008226564,0.025514705,0.018126257,0.010045804,0.0048308354,0.0021506124],"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":[0.0003427729,0.00033949732,0.05599398,0.0010915898,0.00015637919,0.0009299193,0.124118894,0.00030054912,0.00066774467,0.10875338,0.38018748,0.32711777],"study_design_scores_gemma":[0.00005776844,0.00025708773,0.03568583,0.002047984,0.000111150635,0.00068675063,0.3145358,0.00042207522,0.00049203954,0.037252575,0.60819167,0.00025920826],"about_ca_topic_score_codex":0.24336046,"about_ca_topic_score_gemma":0.44725838,"teacher_disagreement_score":0.94909656,"about_ca_system_score_codex":0.037336636,"about_ca_system_score_gemma":0.092223115,"threshold_uncertainty_score":0.4838879},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8122797,0.0034997868,0.09823446,0.002423768,0.0005065661,0.06770763,0.0030789138,0.00038225795,0.011886889],"genre_scores_gemma":[0.69150585,0.0021448955,0.19444466,0.00076968985,0.0001292318,0.102162875,0.0037729088,0.000096581934,0.004973232],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.88473094,0.08611305,0.012755278,0.0022469335,0.012352109,0.0018016512],"domain_scores_gemma":[0.75065655,0.16953951,0.0147988135,0.009766887,0.053725842,0.0015123239],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20227264,0.0015613625,0.0010302003,0.0043704505,0.0012780336,0.0032988973,0.0018448199,0.0013857147,0.0021227389],"category_scores_gemma":[0.2125941,0.000764059,0.0024984502,0.0022483415,0.0019510197,0.0027932103,0.0017739581,0.0015816845,0.00038927194],"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":[0.0017422584,0.0050753653,0.34912878,0.005418692,0.0012606395,0.00031761473,0.04226939,0.00505743,0.0055659907,0.005670455,0.0073058396,0.57118756],"study_design_scores_gemma":[0.0017254391,0.010429773,0.87174195,0.009529903,0.0012891239,0.0004238229,0.02095061,0.022316828,0.013502754,0.0023256992,0.045422774,0.0003413235],"about_ca_topic_score_codex":0.057164397,"about_ca_topic_score_gemma":0.053190093,"teacher_disagreement_score":0.20227264,"about_ca_system_score_codex":0.009309472,"about_ca_system_score_gemma":0.024209863,"threshold_uncertainty_score":0.98373985},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019198662,0.028857064,0.0047842786,0.89952564,0.003045359,0.00004560421,0.00009140316,0.000063645784,0.0616672],"genre_scores_gemma":[0.42691603,0.08155282,0.007530978,0.44753477,0.0068256385,0.00043583527,0.0001734066,0.00017518082,0.028855277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9449728,0.04156527,0.0016442506,0.0031243158,0.005878396,0.0028149495],"domain_scores_gemma":[0.91193724,0.070414476,0.002332259,0.004098628,0.008926116,0.0022913078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034314062,0.00073897064,0.00157877,0.002594004,0.007244915,0.018013079,0.0044961832,0.011090214,0.011802355],"category_scores_gemma":[0.051402166,0.00050153316,0.0013139009,0.0029973227,0.05196359,0.028102374,0.013211827,0.01716587,0.002123549],"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":[0.000037457758,0.000038049882,0.00040089866,0.002899823,0.000044587137,0.00029596535,0.01899896,0.00086540444,0.0001996708,0.7925409,0.10731025,0.076368004],"study_design_scores_gemma":[0.000017239132,0.00005147621,0.00047296978,0.007035689,0.000055493052,0.000108549866,0.016662266,0.00030703587,0.0003632517,0.29819435,0.676677,0.00005468265],"about_ca_topic_score_codex":0.019862112,"about_ca_topic_score_gemma":0.030983081,"teacher_disagreement_score":0.034314062,"about_ca_system_score_codex":0.02344798,"about_ca_system_score_gemma":0.055976924,"threshold_uncertainty_score":0.1814723},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16564812,0.0019001525,0.086332954,0.062199738,0.0005331605,0.00057912734,0.000090518726,0.00036814343,0.68234795],"genre_scores_gemma":[0.9645814,0.00091210037,0.023972973,0.0016101502,0.00009533043,0.00031687415,0.000044438213,0.00007400554,0.00839278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9688464,0.022566713,0.0007953821,0.0024837032,0.0030845415,0.0022233163],"domain_scores_gemma":[0.94749177,0.033158477,0.003163362,0.0052626575,0.0036024442,0.0073213335],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030895704,0.00052423443,0.00043761905,0.0052757054,0.008453925,0.020334007,0.0027401587,0.0027226694,0.011082367],"category_scores_gemma":[0.05463094,0.00053906435,0.0007862441,0.0028030786,0.028337797,0.021125518,0.026578179,0.0029951802,0.001180918],"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":[0.000115928786,0.0004958402,0.020820389,0.000615859,0.00015982936,0.00095216476,0.12964617,0.003977508,0.0021023196,0.665812,0.007395547,0.16790651],"study_design_scores_gemma":[0.00008514908,0.00029001545,0.008964768,0.0013903368,0.0001112385,0.00037646378,0.10077226,0.004927461,0.0016941695,0.70049953,0.18076217,0.0001264772],"about_ca_topic_score_codex":0.007265405,"about_ca_topic_score_gemma":0.010502076,"teacher_disagreement_score":0.9691043,"about_ca_system_score_codex":0.008688109,"about_ca_system_score_gemma":0.022539232,"threshold_uncertainty_score":0.1633941},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037532426,0.0098502,0.07606554,0.1189449,0.0009795713,0.00015617508,0.00016210224,0.00011759092,0.75619143],"genre_scores_gemma":[0.965972,0.0022305965,0.010513988,0.0032742652,0.00057305966,0.00028970794,0.00008365994,0.000082015526,0.016980648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9649757,0.0224875,0.0010827252,0.0032139174,0.005100314,0.0031398775],"domain_scores_gemma":[0.9396458,0.04642736,0.0027805185,0.005793968,0.0028756447,0.0024767132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030713527,0.0007596206,0.0010775472,0.0035305745,0.00726295,0.024175052,0.0029805736,0.009110671,0.016410697],"category_scores_gemma":[0.05204895,0.00065573317,0.00090882304,0.0022018305,0.083957985,0.02365567,0.013807625,0.007471753,0.0015394782],"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":[0.000013580842,0.000019767718,0.0002627557,0.00006492374,0.000009478994,0.000047979356,0.004595865,0.00033142118,0.00006304597,0.98642,0.0012220864,0.0069491924],"study_design_scores_gemma":[0.00000927622,0.000009153018,0.00015221097,0.000094071394,0.0000035086084,0.000029083627,0.0019535797,0.0002487288,0.000069278554,0.98328066,0.01414138,0.000009088234],"about_ca_topic_score_codex":0.004287837,"about_ca_topic_score_gemma":0.0026882167,"teacher_disagreement_score":0.030713527,"about_ca_system_score_codex":0.007423997,"about_ca_system_score_gemma":0.00910102,"threshold_uncertainty_score":0.16243058},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9312244,0.0018146686,0.0009287126,0.0025176324,0.000046275043,0.00020268645,0.00016775708,0.000019873343,0.063078],"genre_scores_gemma":[0.9964797,0.0003488,0.00057461456,0.000110332934,0.000003893554,0.000022458185,0.000060202583,0.0000035697349,0.0023964732],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98736274,0.002916877,0.00046858075,0.00038069903,0.006126839,0.0027443839],"domain_scores_gemma":[0.97748303,0.0065776035,0.0015941258,0.00081499136,0.01091921,0.0026110134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009640009,0.00025167703,0.00033257794,0.0042736,0.0046232096,0.004526706,0.0013655091,0.0010398355,0.0023000108],"category_scores_gemma":[0.023725163,0.00022894022,0.0006017275,0.0057130293,0.0028616441,0.001090937,0.0020756114,0.0010093085,0.00013618286],"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":[0.0011260036,0.0012007761,0.5460146,0.000946678,0.00036493826,0.002562638,0.047910694,0.0078035495,0.0016960421,0.15518624,0.014605893,0.22058195],"study_design_scores_gemma":[0.00017053973,0.0007852566,0.8468303,0.0009170142,0.00046815778,0.000777644,0.06988508,0.009751289,0.0022831415,0.0034584578,0.06454486,0.0001282964],"about_ca_topic_score_codex":0.9172178,"about_ca_topic_score_gemma":0.9433326,"teacher_disagreement_score":0.94506776,"about_ca_system_score_codex":0.054932214,"about_ca_system_score_gemma":0.05950202,"threshold_uncertainty_score":0.39856297},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018816588,0.0050650635,0.23526233,0.68174726,0.0028925247,0.0018264494,0.000031470634,0.00063506106,0.05372333],"genre_scores_gemma":[0.6159157,0.003752449,0.32873562,0.0436524,0.0009797473,0.0026365847,0.000042290947,0.00036780685,0.0039174515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.59834844,0.29059803,0.022425495,0.011294251,0.06805465,0.009279079],"domain_scores_gemma":[0.64460564,0.23688717,0.012008303,0.049825393,0.035754047,0.020919425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30584806,0.0017387517,0.003965192,0.005780167,0.011508029,0.044786677,0.0063996594,0.017466601,0.0067156088],"category_scores_gemma":[0.28111607,0.0026516884,0.002050767,0.0030991016,0.09225346,0.07450868,0.030708928,0.03459351,0.0018089474],"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":[0.0001239227,0.0009724629,0.0026799396,0.001871889,0.00014922576,0.00049853005,0.07040754,0.0018356377,0.0010985116,0.7885591,0.008976014,0.12282731],"study_design_scores_gemma":[0.0003178795,0.00063998223,0.0018568422,0.004922266,0.0000621489,0.0004939903,0.068449095,0.0033260565,0.0010195064,0.85621744,0.062559366,0.00013546142],"about_ca_topic_score_codex":0.00294146,"about_ca_topic_score_gemma":0.002565163,"teacher_disagreement_score":0.30584806,"about_ca_system_score_codex":0.01717394,"about_ca_system_score_gemma":0.06364718,"threshold_uncertainty_score":0.85601294},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07755572,0.047485765,0.0777216,0.4887574,0.005185091,0.0010580011,0.0001467578,0.0003717591,0.30171785],"genre_scores_gemma":[0.87231296,0.019278584,0.043494534,0.0352536,0.0023405952,0.0014750866,0.00011297063,0.00031017442,0.02542163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6882272,0.28010762,0.006240508,0.00458375,0.015938804,0.004902114],"domain_scores_gemma":[0.73449445,0.18353356,0.012466437,0.008329009,0.047171976,0.014004554],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.200548,0.0009497775,0.0011125152,0.004101818,0.007989064,0.018856145,0.0019030274,0.003782603,0.0080542015],"category_scores_gemma":[0.24691017,0.0004148629,0.0005060859,0.0037171922,0.02165112,0.014788825,0.012365876,0.006504741,0.0013871322],"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":[0.00043677987,0.00041885927,0.010992543,0.0019337044,0.000112153495,0.00036980122,0.15646133,0.002135282,0.0009558141,0.43032607,0.08589153,0.30996606],"study_design_scores_gemma":[0.00010666898,0.00041074323,0.005026236,0.00579526,0.000065037944,0.00024832544,0.12511535,0.002349137,0.001352774,0.23581572,0.62355924,0.00015550335],"about_ca_topic_score_codex":0.0029398815,"about_ca_topic_score_gemma":0.0038559402,"teacher_disagreement_score":0.799452,"about_ca_system_score_codex":0.011543928,"about_ca_system_score_gemma":0.015140758,"threshold_uncertainty_score":0.98586667},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3255261,0.011981301,0.0011730897,0.32830894,0.0005184708,0.0003237522,0.00022364278,0.000032660104,0.33191204],"genre_scores_gemma":[0.94513786,0.0048610615,0.0006212887,0.012788744,0.0001181314,0.000093904615,0.000060767616,0.000017700817,0.036300573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9867975,0.0029816765,0.00027573985,0.0005001265,0.0025110473,0.0069338684],"domain_scores_gemma":[0.990044,0.0037246726,0.0009627572,0.00022879158,0.0019631877,0.0030767068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064510386,0.0003531513,0.000500349,0.001250758,0.045311783,0.013145275,0.0026632561,0.008625528,0.0039128773],"category_scores_gemma":[0.012029352,0.00048455017,0.000551855,0.003320472,0.019339342,0.0033375067,0.005811948,0.006378192,0.00018929731],"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":[0.00016122754,0.00017384438,0.025527697,0.00037928115,0.00007285942,0.0052654957,0.18399857,0.0029805116,0.0005993604,0.69687444,0.055526007,0.028440729],"study_design_scores_gemma":[0.00018338284,0.000078265504,0.04918457,0.00060422596,0.00011208214,0.00032594832,0.25569955,0.0016341804,0.00045606325,0.04213528,0.6494209,0.00016551957],"about_ca_topic_score_codex":0.9904435,"about_ca_topic_score_gemma":0.99557304,"teacher_disagreement_score":0.25598294,"about_ca_system_score_codex":0.25598294,"about_ca_system_score_gemma":0.26261404,"threshold_uncertainty_score":0.8629543},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05536489,0.0049510743,0.380105,0.13546507,0.0014208577,0.0003291663,0.00023042908,0.0003861855,0.4217474],"genre_scores_gemma":[0.89387506,0.0015599382,0.08408156,0.0050608804,0.00037208965,0.00039848874,0.00010923798,0.00020579141,0.014337033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9654052,0.02833502,0.0007028078,0.0016786827,0.002897193,0.0009810266],"domain_scores_gemma":[0.94525415,0.04038486,0.0026943898,0.004751855,0.0054247733,0.0014899174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0396688,0.0005715273,0.00042001272,0.003280475,0.008057134,0.017544167,0.0020370763,0.0025787852,0.006283453],"category_scores_gemma":[0.044964764,0.0004823667,0.00053285644,0.002463989,0.066772945,0.02135287,0.006129592,0.0057830615,0.00081874814],"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":[0.0000065855506,0.000008945771,0.0002276346,0.00002540602,0.0000027299093,0.00003116657,0.00996786,0.00013165337,0.000055844142,0.9829701,0.001773681,0.0047984826],"study_design_scores_gemma":[0.000015883968,0.000025603234,0.00027728576,0.00027448742,0.000008670037,0.000072183124,0.015061211,0.0009088079,0.0003094497,0.8453676,0.13765906,0.000019885165],"about_ca_topic_score_codex":0.008379376,"about_ca_topic_score_gemma":0.006159486,"teacher_disagreement_score":0.0396688,"about_ca_system_score_codex":0.0111321965,"about_ca_system_score_gemma":0.015362291,"threshold_uncertainty_score":0.20979118},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9369945,0.0008167783,0.0012417503,0.016338555,0.000077249744,0.00023982317,0.00031171783,0.00007736911,0.043902226],"genre_scores_gemma":[0.99553156,0.00023244617,0.000502277,0.0003343135,0.000009074583,0.00003545921,0.00005411206,0.000008277156,0.0032925792],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.97333366,0.0057839644,0.00084890105,0.0009325151,0.00945008,0.009650868],"domain_scores_gemma":[0.9308209,0.018327167,0.01042109,0.002131932,0.02458908,0.013709908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018047152,0.00021133233,0.0003313102,0.0021274602,0.011203131,0.0076691797,0.0020485714,0.0009952091,0.002211297],"category_scores_gemma":[0.05571376,0.00039367014,0.00038449655,0.0036568795,0.0054588914,0.0018220225,0.005064773,0.0019490903,0.0001211017],"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":[0.00074858696,0.00065038353,0.5750286,0.00069718633,0.0001497662,0.00069738255,0.08457495,0.010608283,0.00340879,0.069045864,0.019605432,0.23478474],"study_design_scores_gemma":[0.00006449963,0.00022029722,0.88605696,0.00025432467,0.00005042325,0.000039179773,0.042734217,0.0028704447,0.0017383515,0.0033196472,0.062555216,0.00009627379],"about_ca_topic_score_codex":0.9668834,"about_ca_topic_score_gemma":0.9820833,"teacher_disagreement_score":0.70072293,"about_ca_system_score_codex":0.29927704,"about_ca_system_score_gemma":0.31003937,"threshold_uncertainty_score":0.8127393},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905744,0.0003812939,0.00018324121,0.00074814295,0.000013038925,0.000078427925,0.0024090705,0.000015172183,0.005597236],"genre_scores_gemma":[0.9930807,0.0007108647,0.00084650825,0.00015166834,0.000008554755,0.00020957114,0.0019539928,0.000009596755,0.0030286682],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997508,0.00006167991,0.000010057709,0.000053550724,0.000031682608,0.000092268376],"domain_scores_gemma":[0.9989673,0.0001819505,0.00019593774,0.00004856269,0.00045570315,0.00015051664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005127168,0.00022927138,0.00017975991,0.0015674857,0.0016521518,0.0011239354,0.000638886,0.00028537042,0.001501627],"category_scores_gemma":[0.0020101469,0.00013807109,0.00014463712,0.0029002053,0.0006230889,0.00033015964,0.0011510936,0.00050085026,0.00012886463],"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":[0.00013194744,0.00012949831,0.95269054,0.00013556934,0.0000574859,0.00045409563,0.011827659,0.00033535803,0.0009262203,0.00086476945,0.0044569145,0.027989874],"study_design_scores_gemma":[0.000007036816,0.000025332647,0.9734021,0.0000658093,0.000026673373,0.000033480672,0.022158602,0.0001634469,0.00022955159,0.00006957519,0.003811984,0.0000063568455],"about_ca_topic_score_codex":0.81396407,"about_ca_topic_score_gemma":0.9147992,"teacher_disagreement_score":0.81396407,"about_ca_system_score_codex":0.0066656624,"about_ca_system_score_gemma":0.0051473677,"threshold_uncertainty_score":0.37426305},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4883106,0.0035736584,0.028787512,0.28753355,0.00096337707,0.002658638,0.00021637777,0.00038309186,0.18757312],"genre_scores_gemma":[0.99090475,0.00029456877,0.0046565435,0.0020072642,0.00009098013,0.0009888428,0.00002414753,0.00007225827,0.00096066133],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.57015747,0.3386091,0.015753957,0.008819198,0.029896284,0.03676394],"domain_scores_gemma":[0.36186057,0.45854306,0.032866288,0.01777577,0.059548438,0.069405876],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27490523,0.00066614343,0.0016679626,0.0049713603,0.023550497,0.050235644,0.0038193131,0.0112562785,0.009951047],"category_scores_gemma":[0.47150585,0.0016029677,0.0011206415,0.0038064336,0.03371751,0.024828771,0.023113875,0.009693927,0.0016382174],"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":[0.0010733752,0.0022147521,0.11670774,0.0030860626,0.00029001923,0.0038705594,0.44826865,0.0014457382,0.002749551,0.2267465,0.02550355,0.16804351],"study_design_scores_gemma":[0.00025396564,0.00080373226,0.0591746,0.0038860894,0.00010991182,0.0010650399,0.78734803,0.0019904405,0.0018275486,0.09749225,0.045658424,0.0003900133],"about_ca_topic_score_codex":0.00894469,"about_ca_topic_score_gemma":0.011794065,"teacher_disagreement_score":0.7250948,"about_ca_system_score_codex":0.01864859,"about_ca_system_score_gemma":0.06368684,"threshold_uncertainty_score":0.89417094},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006578746,0.014512888,0.08369155,0.0032618067,0.0010648103,0.00024178193,0.00020209557,0.00040307542,0.89004326],"genre_scores_gemma":[0.19974938,0.02148178,0.11114965,0.001431297,0.00063442835,0.00037994486,0.00078833016,0.00037202812,0.6640132],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99645317,0.0012912368,0.000068684305,0.000090354195,0.001969763,0.00012693736],"domain_scores_gemma":[0.9957991,0.002754825,0.00015058099,0.0001740765,0.000982479,0.00013900934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038117862,0.0005518042,0.0005282719,0.001071099,0.0004354732,0.0037304708,0.0008471112,0.00082830596,0.016219778],"category_scores_gemma":[0.009256593,0.00017863356,0.00022560169,0.001206156,0.0008825055,0.0019719622,0.001058516,0.0009540242,0.004319517],"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":[0.00003224553,0.000078751706,0.0008013145,0.00037028876,0.000022187573,0.000073477146,0.00036344514,0.0073475055,0.0008687694,0.16419773,0.11049693,0.71534735],"study_design_scores_gemma":[0.000019198007,0.00020453964,0.006846106,0.002016703,0.00003355045,0.00028229243,0.0014047049,0.025332479,0.006120118,0.4628585,0.49482134,0.000060526592],"about_ca_topic_score_codex":0.0026525347,"about_ca_topic_score_gemma":0.008756858,"teacher_disagreement_score":0.016219778,"about_ca_system_score_codex":0.0026050357,"about_ca_system_score_gemma":0.0023153112,"threshold_uncertainty_score":0.054260492},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.890587,0.0052981437,0.0016894349,0.005220781,0.00019442447,0.00043492427,0.00037476583,0.0000184068,0.09618214],"genre_scores_gemma":[0.99266666,0.001660305,0.0007956922,0.00090264477,0.000025542138,0.00009870271,0.00013601412,0.000015700902,0.0036988463],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95625496,0.011888362,0.0011216128,0.0022040915,0.016432237,0.0120988395],"domain_scores_gemma":[0.9215101,0.03151248,0.007598152,0.0026551208,0.028807132,0.007917007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03579017,0.00057005894,0.0011845665,0.014186003,0.04167255,0.015547712,0.0038036231,0.0021504466,0.0039862115],"category_scores_gemma":[0.08438261,0.0007253921,0.00058737246,0.02427499,0.019716548,0.007061792,0.010085006,0.004449683,0.00022138114],"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":true,"study_design_scores_codex":[0.00014925725,0.00015806769,0.08537565,0.0005438489,0.00008062598,0.0011138407,0.77318245,0.00038901766,0.0004544262,0.0857125,0.006905674,0.04593469],"study_design_scores_gemma":[0.000015282634,0.00006212027,0.1028767,0.0006324218,0.00007549593,0.000113349364,0.8400259,0.00030341125,0.00033214316,0.002339268,0.05313147,0.00009240187],"about_ca_topic_score_codex":0.9782292,"about_ca_topic_score_gemma":0.99347234,"teacher_disagreement_score":0.7824011,"about_ca_system_score_codex":0.21759894,"about_ca_system_score_gemma":0.2125957,"threshold_uncertainty_score":0.90747434},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89846015,0.0025666005,0.0040749456,0.056856956,0.00024722298,0.0051035355,0.0012138993,0.00013608414,0.031340644],"genre_scores_gemma":[0.9558433,0.0017225666,0.016437827,0.005986507,0.000066883935,0.0019377415,0.00051824044,0.00006720721,0.017419603],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9780025,0.006217468,0.0011263444,0.0019219762,0.0074225175,0.00530927],"domain_scores_gemma":[0.89685243,0.009698941,0.005290306,0.0021323347,0.046628952,0.039397016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02279724,0.00030514813,0.0005547598,0.0030509809,0.021807766,0.0074708723,0.0032325382,0.0023468349,0.0040816506],"category_scores_gemma":[0.03612299,0.0007703376,0.0003550874,0.0041435175,0.005189004,0.0026228686,0.007652063,0.0021711984,0.0005119721],"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":[0.0007880294,0.002287519,0.40609726,0.0011186977,0.00012585698,0.0030804425,0.27833724,0.0019135715,0.0059068343,0.0099093225,0.05673448,0.2337008],"study_design_scores_gemma":[0.00029104372,0.00083785463,0.43617883,0.0014307965,0.00010062365,0.00040915087,0.3425924,0.0045941547,0.0014084192,0.0025004824,0.20941919,0.0002370323],"about_ca_topic_score_codex":0.9781457,"about_ca_topic_score_gemma":0.9945597,"teacher_disagreement_score":0.8347364,"about_ca_system_score_codex":0.16526361,"about_ca_system_score_gemma":0.5366862,"threshold_uncertainty_score":0.9681759},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03555405,0.37056938,0.21584016,0.17954814,0.008434189,0.00031742666,0.0006060988,0.00027805992,0.18885241],"genre_scores_gemma":[0.7470037,0.14135975,0.075038135,0.0107912775,0.004623934,0.00062487886,0.0002650854,0.0004252936,0.019867864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9481754,0.029676406,0.0031425806,0.0035122824,0.013901306,0.0015920472],"domain_scores_gemma":[0.90288764,0.06995014,0.0070381425,0.0051451675,0.013588839,0.0013901814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.049509604,0.0008163144,0.001120964,0.011156679,0.0036068114,0.022196136,0.0023386176,0.004350973,0.0024833737],"category_scores_gemma":[0.06445919,0.00069087587,0.0010679135,0.015473212,0.055572532,0.01867976,0.00587287,0.007409811,0.00062462175],"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":[0.000050535356,0.000026947588,0.0030939453,0.0008068772,0.000031244133,0.000068617665,0.014869595,0.0008575519,0.00031890417,0.9134703,0.004878547,0.061526917],"study_design_scores_gemma":[0.000022751532,0.00015257686,0.009377671,0.0043679294,0.000038137707,0.0005788164,0.014776786,0.0021817486,0.0012257354,0.5213802,0.44573632,0.00016133429],"about_ca_topic_score_codex":0.020292638,"about_ca_topic_score_gemma":0.010671322,"teacher_disagreement_score":0.9504904,"about_ca_system_score_codex":0.019482892,"about_ca_system_score_gemma":0.0118291015,"threshold_uncertainty_score":0.26183492},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052596105,0.0024315997,0.0015371926,0.9891093,0.003099983,0.000047699545,0.000020801794,0.000049406495,0.0031780372],"genre_scores_gemma":[0.10742258,0.009389858,0.030843988,0.82717454,0.017685944,0.0007406817,0.00016301371,0.00022355592,0.0063557685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.84161556,0.10372199,0.009399811,0.005781134,0.025703885,0.013777602],"domain_scores_gemma":[0.42616323,0.32646582,0.020822586,0.02238022,0.096940085,0.10722813],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23571424,0.0017941088,0.0033242267,0.0038790372,0.012652119,0.023860814,0.0061503015,0.055803183,0.028635712],"category_scores_gemma":[0.34812978,0.0012203528,0.0053325193,0.0022793924,0.02563588,0.026617374,0.01510624,0.06078262,0.0024977147],"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":[0.0007637577,0.00092689646,0.0076791057,0.0023700616,0.00035566758,0.0010879049,0.0029167272,0.0032743518,0.0007976581,0.14884377,0.6597245,0.17125964],"study_design_scores_gemma":[0.0009150504,0.0010456315,0.01230329,0.013731823,0.00020134047,0.0012132857,0.012991004,0.0046592215,0.00069201324,0.23439336,0.71723175,0.0006221924],"about_ca_topic_score_codex":0.022965431,"about_ca_topic_score_gemma":0.042290654,"teacher_disagreement_score":0.97738683,"about_ca_system_score_codex":0.02261318,"about_ca_system_score_gemma":0.1366777,"threshold_uncertainty_score":0.9425004},"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":"review","genre_gemma":"editorial","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025487323,0.83014727,0.07868628,0.054408565,0.010182924,0.010344608,0.0011029409,0.0005331856,0.012045567],"genre_scores_gemma":[0.079741895,0.57375216,0.26592723,0.02968261,0.004781217,0.042967014,0.0009743046,0.00074294826,0.0014307018],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.12025913,0.74259645,0.08156009,0.012420414,0.041673493,0.0014904005],"domain_scores_gemma":[0.036966525,0.8667734,0.034899365,0.03157949,0.028188834,0.0015923672],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71463495,0.0046949126,0.015851928,0.10161393,0.009061471,0.051820975,0.010054272,0.01707251,0.005732192],"category_scores_gemma":[0.8500046,0.005761866,0.009390789,0.07871172,0.039497603,0.050664492,0.039158426,0.018900618,0.0019019056],"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":[0.00028341942,0.000105820436,0.0017384033,0.39734173,0.0053280005,0.0007787945,0.08928063,0.0015342528,0.00097395794,0.10502307,0.03366906,0.36394286],"study_design_scores_gemma":[0.00012176127,0.00011533614,0.0007276223,0.8029417,0.0017353339,0.00054245867,0.014146786,0.00094345957,0.000443053,0.060892556,0.11714871,0.00024124859],"about_ca_topic_score_codex":0.0114090415,"about_ca_topic_score_gemma":0.01930322,"teacher_disagreement_score":0.28536505,"about_ca_system_score_codex":0.035886798,"about_ca_system_score_gemma":0.08687015,"threshold_uncertainty_score":0.35190594},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019324245,0.0004888239,0.002039499,0.00036207453,0.00018955542,0.00005265551,0.00070230046,0.0011157334,0.9948561],"genre_scores_gemma":[0.0004921134,0.00028555395,0.0006332978,0.000111857385,0.000036194077,0.00003648832,0.0004200687,0.00024513074,0.99773943],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941003,0.00004625084,0.00004280425,0.00018811092,0.00022076997,0.00009205792],"domain_scores_gemma":[0.9977743,0.00084644463,0.00014867612,0.00033716252,0.00041323394,0.00048018148],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012772621,0.00201483,0.0013243185,0.0018888615,0.0011170497,0.004892725,0.0028054975,0.003948965,0.9743756],"category_scores_gemma":[0.0023900066,0.0008999231,0.00081223116,0.0025094957,0.0011218827,0.0051635723,0.0027896173,0.0022509207,0.9871656],"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":[0.00009782973,0.000106759486,0.00033891323,0.0003693563,0.000014606081,0.0000883695,0.00007876162,0.00037496875,0.0016862928,0.0061047487,0.3547473,0.63599205],"study_design_scores_gemma":[0.000014234675,0.000042227908,0.0005334902,0.00027634288,0.000008603225,0.0001763123,0.00008208037,0.00020881189,0.0003220034,0.0015495489,0.9967728,0.000013484422],"about_ca_topic_score_codex":0.0033679665,"about_ca_topic_score_gemma":0.0033854465,"teacher_disagreement_score":0.025624394,"about_ca_system_score_codex":0.0008852042,"about_ca_system_score_gemma":0.00086397043,"threshold_uncertainty_score":0.036549985},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005718904,0.0049298625,0.91627485,0.013363841,0.0025571864,0.004642316,0.0007049506,0.0043575023,0.0474506],"genre_scores_gemma":[0.014706331,0.0027977424,0.961904,0.0032607545,0.0004236354,0.0047579855,0.0004512439,0.0009451061,0.010753186],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7935629,0.17308365,0.006125491,0.0027463022,0.02386544,0.0006163233],"domain_scores_gemma":[0.6708353,0.261948,0.008345288,0.01657342,0.040941093,0.0013569407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14168496,0.0010810934,0.0014296215,0.0032476455,0.001200715,0.0060897274,0.0035497742,0.0019642883,0.010173283],"category_scores_gemma":[0.26933342,0.0013542436,0.0006719032,0.003302449,0.0022259387,0.004813326,0.0027372115,0.0039211004,0.0112594515],"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":[0.00007858175,0.0002026697,0.003138995,0.00213891,0.000039955445,0.00010519161,0.0042034853,0.0015944529,0.0027942788,0.03414708,0.1653624,0.7861939],"study_design_scores_gemma":[0.00014833291,0.0008577719,0.01868638,0.010486469,0.00009134222,0.00061768555,0.0050043934,0.015330525,0.00839581,0.0885494,0.85161763,0.00021427126],"about_ca_topic_score_codex":0.002999033,"about_ca_topic_score_gemma":0.008547446,"teacher_disagreement_score":0.85831505,"about_ca_system_score_codex":0.002596102,"about_ca_system_score_gemma":0.0066131908,"threshold_uncertainty_score":0.7493107},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942211,0.00014250523,0.00055366004,0.0006568501,0.000022451903,0.0001223526,0.00076595636,0.000016020116,0.0034992087],"genre_scores_gemma":[0.9983076,0.000054983804,0.00042074162,0.000052571595,0.000009536127,0.00005914843,0.000415992,0.0000048738257,0.00067452335],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941134,0.002699771,0.0006296678,0.0003555001,0.0013442964,0.00085739157],"domain_scores_gemma":[0.93940294,0.024062224,0.009888734,0.002112407,0.014897357,0.009636346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015157925,0.00013352209,0.00029685858,0.003923159,0.0008725309,0.002132081,0.0007633036,0.0004084722,0.0051101646],"category_scores_gemma":[0.080587775,0.00010257795,0.00025057708,0.0031211206,0.00061908824,0.0013228535,0.0015076172,0.00063263316,0.0008811531],"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":[0.00016650841,0.00016896722,0.9826753,0.000024774934,0.00001000641,0.000037965216,0.0008518078,0.00014857604,0.000082782455,0.00018366563,0.0010037951,0.014645909],"study_design_scores_gemma":[0.0000139410995,0.00019013301,0.9885048,0.000059385016,0.000010992071,0.00010389923,0.0060708304,0.0015419711,0.00030549537,0.00021456087,0.0029734278,0.00001052508],"about_ca_topic_score_codex":0.011177678,"about_ca_topic_score_gemma":0.015251521,"teacher_disagreement_score":0.015157925,"about_ca_system_score_codex":0.0016300242,"about_ca_system_score_gemma":0.0027951954,"threshold_uncertainty_score":0.08016372},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023713797,0.99214524,0.0010888567,0.0029337222,0.000671099,0.00087415654,0.00025610742,0.000028056993,0.0017656394],"genre_scores_gemma":[0.0034813245,0.9884588,0.0050692423,0.001192153,0.0001880472,0.0010761729,0.00018220145,0.000011664679,0.00034044858],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9719821,0.012507734,0.0068460004,0.0008629603,0.0071773287,0.00062386587],"domain_scores_gemma":[0.87069386,0.083914064,0.012068981,0.0023646578,0.029501582,0.001456786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04393735,0.0017841425,0.0045871288,0.023611583,0.0011407416,0.005119188,0.002594732,0.0023957128,0.007614645],"category_scores_gemma":[0.12336361,0.0012322459,0.00586329,0.017484473,0.0012823329,0.00581622,0.003146452,0.002760975,0.0011562934],"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":[0.00007953402,0.000042242737,0.0002636465,0.5160381,0.000977884,0.00008009875,0.00045276407,0.0002421309,0.00022380105,0.0038588364,0.017757775,0.45998317],"study_design_scores_gemma":[0.000053758133,0.00009639061,0.0011122862,0.8364339,0.002395172,0.0001294096,0.00033553364,0.00010796812,0.00018682226,0.0013311504,0.15778352,0.000033993252],"about_ca_topic_score_codex":0.012189538,"about_ca_topic_score_gemma":0.036994293,"teacher_disagreement_score":0.9560627,"about_ca_system_score_codex":0.011936412,"about_ca_system_score_gemma":0.04491284,"threshold_uncertainty_score":0.23236573},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28145885,0.17891322,0.005042935,0.44265252,0.0021471914,0.0024918478,0.007773884,0.00042206963,0.07909746],"genre_scores_gemma":[0.8865341,0.05943068,0.018902201,0.020819657,0.00014127106,0.0006580315,0.0027252145,0.00010048504,0.01068836],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.94900024,0.016010225,0.0036981052,0.0017202183,0.016321786,0.013249444],"domain_scores_gemma":[0.7930371,0.04012758,0.0061869137,0.004893066,0.12705635,0.028698994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056350593,0.0005378946,0.001121044,0.005645671,0.014256843,0.013760073,0.0031850121,0.0025433335,0.0029507116],"category_scores_gemma":[0.059045725,0.0007514249,0.0009912084,0.012759445,0.0054170126,0.0042031896,0.0066320687,0.0041320603,0.00023876995],"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":[0.0010237759,0.000521581,0.20824118,0.011758011,0.0006445058,0.0020748244,0.05047722,0.0029602884,0.0023646771,0.041549467,0.15197587,0.52640855],"study_design_scores_gemma":[0.00009964994,0.0003077618,0.50157344,0.012451907,0.00037558872,0.00062236266,0.13202606,0.0018004085,0.0015437412,0.0033327593,0.34551364,0.00035265583],"about_ca_topic_score_codex":0.990824,"about_ca_topic_score_gemma":0.9962059,"teacher_disagreement_score":0.9436494,"about_ca_system_score_codex":0.29250228,"about_ca_system_score_gemma":0.586039,"threshold_uncertainty_score":0.82059705},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012888216,0.0008628981,0.8483451,0.014416969,0.0001807155,0.0014368139,0.0001739408,0.00024945065,0.121445775],"genre_scores_gemma":[0.47308373,0.00073493744,0.51608396,0.0010265873,0.00009055904,0.0041541695,0.00017921031,0.00010711786,0.004539663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9206824,0.06669853,0.0026917774,0.002620698,0.0061764657,0.0011299886],"domain_scores_gemma":[0.91499764,0.059481498,0.0033040114,0.007251381,0.012749973,0.0022155433],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07079374,0.0012440366,0.00084898993,0.0070467023,0.0025971234,0.010180949,0.002922073,0.0032638456,0.010807172],"category_scores_gemma":[0.09594746,0.0005972565,0.0018095537,0.0057561547,0.012920691,0.016338121,0.006773606,0.0043194103,0.0011860856],"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":[0.000046537683,0.00011264188,0.0015390367,0.00029794243,0.000037618094,0.000056446628,0.003972187,0.0029269455,0.00009462223,0.9563186,0.00085805013,0.03373942],"study_design_scores_gemma":[0.00011353076,0.00025609718,0.0018572599,0.0010965291,0.00010461268,0.00016491271,0.002988809,0.028980758,0.00039157673,0.9416423,0.02236622,0.000037519356],"about_ca_topic_score_codex":0.003707984,"about_ca_topic_score_gemma":0.0037012573,"teacher_disagreement_score":0.92920625,"about_ca_system_score_codex":0.010854882,"about_ca_system_score_gemma":0.012981863,"threshold_uncertainty_score":0.37439758},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25381073,0.0013580832,0.03516005,0.6426053,0.004548545,0.0011372393,0.0000997527,0.00031395105,0.060966432],"genre_scores_gemma":[0.89939284,0.0012655517,0.023044107,0.046855863,0.0007363364,0.00092004484,0.00007260458,0.0003889597,0.027323628],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7422854,0.19789174,0.0055243927,0.0066994554,0.021975031,0.025624013],"domain_scores_gemma":[0.7514212,0.12737827,0.00880984,0.009904873,0.044079483,0.058406323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14719927,0.0009320803,0.00079516903,0.0012299125,0.054898284,0.018054625,0.008259531,0.017663822,0.007112203],"category_scores_gemma":[0.17168482,0.0017569645,0.0012423494,0.0015294622,0.0213944,0.0076783337,0.031915028,0.039965555,0.0019590363],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021953533,0.0021675567,0.005684035,0.00032297007,0.00005876536,0.0068049594,0.79086345,0.0017253372,0.0035662763,0.031026201,0.07609275,0.0814682],"study_design_scores_gemma":[0.000054605054,0.00048302923,0.0023770316,0.00049881655,0.000014636969,0.0008323947,0.8364927,0.0008393025,0.0014521582,0.004483663,0.1523278,0.00014391608],"about_ca_topic_score_codex":0.07431499,"about_ca_topic_score_gemma":0.12373121,"teacher_disagreement_score":0.9587082,"about_ca_system_score_codex":0.04129176,"about_ca_system_score_gemma":0.08957943,"threshold_uncertainty_score":0.7784735},"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":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001901185,0.027777577,0.0023264198,0.39688018,0.56188107,0.00018155598,0.000228172,0.00049294316,0.010041996],"genre_scores_gemma":[0.0026280072,0.044592336,0.0102699185,0.5065663,0.29349354,0.00070332066,0.00077962165,0.0019197385,0.13904727],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9643898,0.007817943,0.002986742,0.0016398008,0.022126041,0.0010396561],"domain_scores_gemma":[0.8058363,0.05010457,0.007960436,0.006509448,0.12246674,0.0071224887],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02988115,0.0013767364,0.003201774,0.0052313944,0.0030302324,0.018424727,0.0036858248,0.008372401,0.02643108],"category_scores_gemma":[0.1899273,0.0013827487,0.00221728,0.0042172875,0.005190048,0.016458053,0.0038004774,0.025746036,0.043935753],"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":[0.0000081507915,0.0000074174313,0.00002243017,0.00015857986,0.000008664688,0.000024267994,0.000054922402,0.000026459711,0.00007199859,0.002187741,0.98293936,0.014489999],"study_design_scores_gemma":[0.000009251873,0.000016316384,0.00008530742,0.00053563534,0.000012539768,0.000062994564,0.00009042885,0.000040745796,0.000057756697,0.0019302063,0.99713206,0.000026710386],"about_ca_topic_score_codex":0.0062151956,"about_ca_topic_score_gemma":0.012815897,"teacher_disagreement_score":0.9701189,"about_ca_system_score_codex":0.0070677134,"about_ca_system_score_gemma":0.012100231,"threshold_uncertainty_score":0.15802848},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22687986,0.0032192336,0.5781754,0.039825495,0.0007317312,0.0040337746,0.00010767076,0.001094007,0.14593281],"genre_scores_gemma":[0.8940837,0.00036648367,0.09606443,0.0025896356,0.00007140686,0.0027221446,0.000040542356,0.000249832,0.003811814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6176476,0.32014453,0.015576535,0.011674309,0.027809938,0.0071471813],"domain_scores_gemma":[0.454653,0.43919134,0.018064456,0.052708372,0.02851466,0.006868119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35110244,0.0010483889,0.0014913192,0.0041210963,0.008679108,0.016649256,0.0042330506,0.005182844,0.004000185],"category_scores_gemma":[0.34067634,0.0019969305,0.0013445402,0.0020876375,0.05045634,0.024692602,0.029442556,0.0086393,0.00073965685],"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":[0.00030439845,0.00028459882,0.010449726,0.0014191644,0.00007515753,0.0013179523,0.18338758,0.0019319075,0.0029209114,0.6624235,0.003662393,0.13182274],"study_design_scores_gemma":[0.00027183024,0.00062235584,0.005103697,0.0042539714,0.00009239878,0.0013186883,0.09124701,0.008118622,0.0082583,0.75834674,0.12215406,0.0002123277],"about_ca_topic_score_codex":0.0016870847,"about_ca_topic_score_gemma":0.0027383508,"teacher_disagreement_score":0.6488975,"about_ca_system_score_codex":0.012937208,"about_ca_system_score_gemma":0.021770101,"threshold_uncertainty_score":0.80020624},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94474244,0.0012568292,0.0020902245,0.023164896,0.00009443099,0.0138210235,0.001895416,0.000026296013,0.012908393],"genre_scores_gemma":[0.9735324,0.0010517507,0.0085709,0.0030737438,0.000032457494,0.010616427,0.0004061823,0.000021881706,0.0026941474],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9370507,0.039820634,0.0040169274,0.0012895835,0.01035006,0.007472179],"domain_scores_gemma":[0.8671114,0.0671576,0.00813289,0.0026413728,0.04253284,0.01242394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1002882,0.00044730818,0.0009405248,0.00371542,0.019933209,0.005830848,0.003105955,0.0019354977,0.0029805736],"category_scores_gemma":[0.10647544,0.0012296851,0.00094685366,0.0056910287,0.0056128995,0.0029929357,0.0071782884,0.0025522874,0.00018786799],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00058620353,0.0019897912,0.08208052,0.0040829554,0.00010580427,0.00055050454,0.81883055,0.00087938533,0.00084367994,0.0045734677,0.008801707,0.07667534],"study_design_scores_gemma":[0.00033573268,0.0010094179,0.09939766,0.0034697484,0.00015027987,0.00009477391,0.8591508,0.0010906372,0.0010017832,0.0014060525,0.03274841,0.00014468946],"about_ca_topic_score_codex":0.8207084,"about_ca_topic_score_gemma":0.9275193,"teacher_disagreement_score":0.8207084,"about_ca_system_score_codex":0.23747157,"about_ca_system_score_gemma":0.43770638,"threshold_uncertainty_score":0.8844249},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96206474,0.00047780672,0.0016634341,0.0010591459,0.000032651504,0.00009141207,0.00020469213,0.000036767728,0.03436934],"genre_scores_gemma":[0.99751604,0.00006813452,0.00030327862,0.00004372077,0.00002301889,0.00001735022,0.00009249201,0.0000056378753,0.0019303622],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9905874,0.0027414788,0.0004656906,0.0006169592,0.004172684,0.0014157156],"domain_scores_gemma":[0.9437703,0.022840355,0.013249378,0.0024992686,0.008306256,0.009334459],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0134121245,0.00023849281,0.00063716056,0.0042830417,0.0030076352,0.00312485,0.00068214233,0.0005997905,0.0077474164],"category_scores_gemma":[0.069792666,0.0001337938,0.0003288124,0.004080426,0.0018833069,0.0011321262,0.0021726089,0.00066395104,0.0007689778],"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":[0.0008360107,0.00028451998,0.9086386,0.0001050188,0.00016553035,0.00010975993,0.004718972,0.0014958216,0.0007738378,0.007218367,0.0034311693,0.072222374],"study_design_scores_gemma":[0.00003642526,0.00022408072,0.98754245,0.000028094348,0.000038355804,0.000050703304,0.003768771,0.0020300972,0.000487551,0.0023560019,0.003404528,0.000032799828],"about_ca_topic_score_codex":0.092045836,"about_ca_topic_score_gemma":0.17721595,"teacher_disagreement_score":0.99363273,"about_ca_system_score_codex":0.006367277,"about_ca_system_score_gemma":0.007525446,"threshold_uncertainty_score":0.18302017},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014859258,0.007530237,0.87412465,0.0455719,0.0011383811,0.019813852,0.00048628607,0.00053834834,0.035937022],"genre_scores_gemma":[0.12402921,0.0019013386,0.8498234,0.0044370946,0.00008438132,0.018613929,0.00021374582,0.00019358152,0.00070324674],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.1930974,0.74906766,0.022971667,0.0056986567,0.025557542,0.0036070312],"domain_scores_gemma":[0.4296036,0.44544932,0.011701753,0.049251802,0.059078686,0.0049148197],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.63889897,0.004382064,0.0069861286,0.011369746,0.009938778,0.028436111,0.01106801,0.008591832,0.0050292322],"category_scores_gemma":[0.4829717,0.0025160091,0.0073716324,0.011503675,0.025727158,0.020929458,0.02513591,0.01621875,0.0010443049],"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":[0.0006153728,0.0018948817,0.0067005414,0.022963252,0.0022898372,0.0003669145,0.055452697,0.008791982,0.0011769505,0.4388354,0.008620812,0.45229137],"study_design_scores_gemma":[0.0019590587,0.004280504,0.010502404,0.05812229,0.0044187447,0.0008839092,0.05524721,0.029226594,0.0075428737,0.7369786,0.090165265,0.00067244004],"about_ca_topic_score_codex":0.014607521,"about_ca_topic_score_gemma":0.032339055,"teacher_disagreement_score":0.63889897,"about_ca_system_score_codex":0.03732855,"about_ca_system_score_gemma":0.110619165,"threshold_uncertainty_score":0.4453019},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897822,0.0001884211,0.0015031376,0.0008996332,0.000007663801,0.000037709673,0.00032224768,0.0000174953,0.0072414246],"genre_scores_gemma":[0.998774,0.000057441677,0.00037968025,0.00004506749,0.0000022021723,0.000029357987,0.00013872593,0.0000048164634,0.00056875456],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99664956,0.0016944186,0.0002147466,0.0003823011,0.0005951836,0.00046382347],"domain_scores_gemma":[0.98428553,0.007166383,0.0032147206,0.0011422936,0.0036820415,0.0005090263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060283146,0.00006690983,0.00018427063,0.0015535598,0.0020916217,0.0026515396,0.00040463498,0.0003130396,0.0016674966],"category_scores_gemma":[0.013579218,0.0002166558,0.00020448332,0.0026969227,0.0021365292,0.002180854,0.002183345,0.00095009385,0.00010491908],"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":[0.00020125575,0.00028340257,0.7254902,0.00020282668,0.000064799235,0.00023795276,0.16887477,0.0024923936,0.0011006572,0.04377749,0.0033433246,0.053930942],"study_design_scores_gemma":[0.0000127724625,0.00014876357,0.81076753,0.00027446603,0.00006646941,0.00007899349,0.14883986,0.0043521523,0.0013201743,0.004158598,0.02993306,0.000047230882],"about_ca_topic_score_codex":0.069331385,"about_ca_topic_score_gemma":0.09513627,"teacher_disagreement_score":0.069331385,"about_ca_system_score_codex":0.008712731,"about_ca_system_score_gemma":0.0063412916,"threshold_uncertainty_score":0.13785565},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00405878,0.015280223,0.021999061,0.7513967,0.022654679,0.00058655965,0.00021999281,0.0006090757,0.18319495],"genre_scores_gemma":[0.33090255,0.025432374,0.089935586,0.34819263,0.0070181857,0.0038052427,0.0006772108,0.0009985312,0.19303766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.90995926,0.07118975,0.0018007356,0.005110877,0.00824696,0.0036923632],"domain_scores_gemma":[0.89545375,0.041340083,0.00456709,0.012845106,0.023992296,0.021801695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06698729,0.0020982458,0.001684402,0.0041945926,0.015225439,0.022959946,0.0041712704,0.012051559,0.0400576],"category_scores_gemma":[0.1112829,0.0007877346,0.001489982,0.0024367082,0.05178854,0.013901575,0.018158466,0.019269021,0.010727098],"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":[0.0001645648,0.00023904085,0.0013997387,0.0010341412,0.00008474026,0.0002569341,0.028300807,0.00041227508,0.0002827627,0.4323663,0.40910777,0.12635085],"study_design_scores_gemma":[0.00008414459,0.00010629369,0.00053228054,0.0020251935,0.000032479205,0.00015253919,0.041229185,0.00032784662,0.00017750259,0.20754121,0.7477399,0.000051441366],"about_ca_topic_score_codex":0.02331402,"about_ca_topic_score_gemma":0.03301441,"teacher_disagreement_score":0.06698729,"about_ca_system_score_codex":0.016399955,"about_ca_system_score_gemma":0.06200776,"threshold_uncertainty_score":0.35426688},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010383903,0.013010919,0.0039513265,0.39754665,0.33099648,0.002077467,0.002766457,0.0006560045,0.2479564],"genre_scores_gemma":[0.01659574,0.0088534495,0.010803663,0.19099085,0.03202277,0.0022493706,0.0048061176,0.0009467323,0.7327313],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.902712,0.008872533,0.0035663727,0.0044033527,0.06882453,0.011621278],"domain_scores_gemma":[0.7641487,0.011467193,0.003221447,0.00621161,0.10585588,0.10909519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0658888,0.001679111,0.0021247822,0.0043730903,0.015847249,0.025055625,0.006688263,0.02598536,0.1295024],"category_scores_gemma":[0.092539385,0.0014580291,0.0025113274,0.0029683597,0.0048799333,0.0070806113,0.01271645,0.022215577,0.052704975],"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":[0.000026812037,0.000020687028,0.00009827424,0.00006545696,0.000005256202,0.000041601103,0.000058083366,0.000017094857,0.00008448815,0.0035715376,0.988219,0.0077917837],"study_design_scores_gemma":[0.000013536941,0.000010495572,0.0005535184,0.00008067862,0.0000025363388,0.000019167257,0.00017285923,0.000034610373,0.000033147564,0.00060728856,0.9984492,0.000022947293],"about_ca_topic_score_codex":0.29473394,"about_ca_topic_score_gemma":0.5054208,"teacher_disagreement_score":0.9713135,"about_ca_system_score_codex":0.028686536,"about_ca_system_score_gemma":0.23987497,"threshold_uncertainty_score":0.5860368},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863317,0.00013013519,0.0021892418,0.00029286058,0.000013836413,0.002140609,0.0005964712,0.00006675138,0.008238394],"genre_scores_gemma":[0.98671365,0.00024104463,0.00862689,0.00005287191,0.000005013573,0.001079841,0.00064038014,0.00001790715,0.0026224288],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99292976,0.0014792894,0.00038793395,0.00031826878,0.00398655,0.0008982737],"domain_scores_gemma":[0.9856091,0.0017587991,0.0017496295,0.0006820011,0.008844924,0.0013555465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007680641,0.00024483574,0.0003756536,0.0013081752,0.0027927984,0.0013769107,0.0012152317,0.00021714054,0.0013357404],"category_scores_gemma":[0.023677325,0.0003162029,0.00056405424,0.0016761833,0.00076558953,0.0006188942,0.0012721041,0.0004899461,0.00010792147],"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":[0.00071785616,0.0016416854,0.60975605,0.0005519427,0.00016289212,0.00034004945,0.0302308,0.0027778668,0.0042544203,0.00077098346,0.0032638693,0.34553152],"study_design_scores_gemma":[0.000044290533,0.0014860592,0.97832924,0.00014293834,0.00005077518,0.00007264516,0.008482703,0.0019392449,0.0017038817,0.00006851516,0.0076423623,0.00003738033],"about_ca_topic_score_codex":0.8895271,"about_ca_topic_score_gemma":0.952297,"teacher_disagreement_score":0.11047292,"about_ca_system_score_codex":0.0347467,"about_ca_system_score_gemma":0.050154574,"threshold_uncertainty_score":0.25210613},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46568155,0.0062781414,0.3289952,0.017325044,0.00044584586,0.0005672115,0.00008502105,0.00032045064,0.18030159],"genre_scores_gemma":[0.9621582,0.00072575745,0.035000216,0.00071332365,0.000057245463,0.00011751463,0.000020741378,0.000042855332,0.0011642252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90719134,0.07056125,0.0034317174,0.003731327,0.011992136,0.0030921751],"domain_scores_gemma":[0.71210605,0.24901897,0.0143994745,0.009949345,0.011237207,0.003288969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06891401,0.00067022943,0.000775956,0.0039334544,0.0034911032,0.010106097,0.0013123776,0.0022373612,0.0016288573],"category_scores_gemma":[0.17944165,0.00064755994,0.0008793494,0.001682092,0.023713844,0.0099550355,0.0057747574,0.0037824344,0.00034976855],"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":[0.0004013953,0.00038945212,0.032239337,0.0013142644,0.0002618623,0.0011059884,0.22393352,0.0085086515,0.0043974197,0.4956857,0.0033742094,0.22838825],"study_design_scores_gemma":[0.0000861354,0.00046902004,0.026424702,0.0018236109,0.00009275157,0.0008841656,0.04097775,0.015131037,0.0034139885,0.87082297,0.039454605,0.0004193339],"about_ca_topic_score_codex":0.0023312056,"about_ca_topic_score_gemma":0.0021223724,"teacher_disagreement_score":0.06891401,"about_ca_system_score_codex":0.0038656453,"about_ca_system_score_gemma":0.0070195254,"threshold_uncertainty_score":0.36445647},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1899469,0.07110155,0.13446657,0.35266215,0.0025926968,0.0006814164,0.00029161724,0.00029087937,0.24796626],"genre_scores_gemma":[0.8994211,0.021773992,0.0294583,0.008625746,0.0005566261,0.00077959336,0.00013322644,0.00022352376,0.039027955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.88942534,0.08654873,0.0022474532,0.004273375,0.013326856,0.004178262],"domain_scores_gemma":[0.80316573,0.1328853,0.011982927,0.013247331,0.031982563,0.006736123],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.10032349,0.0010481512,0.0016375305,0.006605163,0.017895877,0.029905003,0.00361779,0.0066642202,0.008512506],"category_scores_gemma":[0.08232539,0.00077561376,0.0012589312,0.008292097,0.045320593,0.02835044,0.013339877,0.010925949,0.0015053435],"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":[0.00008287087,0.000093588504,0.0056799036,0.0009063818,0.00004776146,0.00025568245,0.30086762,0.0005027163,0.0005486121,0.6317882,0.0036950603,0.055531595],"study_design_scores_gemma":[0.00004703225,0.0001794483,0.01113876,0.005135456,0.00008562412,0.000358614,0.43928948,0.0015286605,0.0021026582,0.18714371,0.35282773,0.00016275604],"about_ca_topic_score_codex":0.091900714,"about_ca_topic_score_gemma":0.09165373,"teacher_disagreement_score":0.9821041,"about_ca_system_score_codex":0.037307583,"about_ca_system_score_gemma":0.07851875,"threshold_uncertainty_score":0.53056765},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076629765,0.003420535,0.5459233,0.08687682,0.0024067054,0.0071182866,0.00013713646,0.0035797874,0.2739076],"genre_scores_gemma":[0.5257627,0.0024039012,0.42708117,0.012185345,0.0005464227,0.006373995,0.000101793994,0.0014353207,0.024109362],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6821614,0.2902946,0.004625014,0.00588567,0.014154793,0.0028786024],"domain_scores_gemma":[0.82422036,0.11021578,0.0069644637,0.018455964,0.025676686,0.014466688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18009643,0.001232699,0.0010689141,0.0052143494,0.014123045,0.017829113,0.005078589,0.00442523,0.009659098],"category_scores_gemma":[0.16168351,0.0010973728,0.0011726711,0.0027454514,0.021966891,0.014894296,0.02143405,0.006730668,0.0032978442],"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":[0.00029142844,0.0010458318,0.00346065,0.0015147346,0.00013240596,0.0012772575,0.39458713,0.0016247546,0.0032816485,0.15086897,0.05233152,0.38958365],"study_design_scores_gemma":[0.00022756222,0.00086954643,0.0020059508,0.004351746,0.00014402448,0.0016737361,0.2779998,0.0043149632,0.0064303963,0.17794836,0.52364033,0.0003936325],"about_ca_topic_score_codex":0.0022395349,"about_ca_topic_score_gemma":0.0053148465,"teacher_disagreement_score":0.18009643,"about_ca_system_score_codex":0.009125361,"about_ca_system_score_gemma":0.024566334,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066422656,0.09897928,0.058392115,0.45046243,0.0038304986,0.0002493593,0.0006559732,0.00044649994,0.3205611],"genre_scores_gemma":[0.84756875,0.052766044,0.030169977,0.026728405,0.0024776813,0.00036473377,0.00047700634,0.00034215697,0.039105233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9678496,0.016847767,0.0010783583,0.0018026633,0.010479664,0.0019419447],"domain_scores_gemma":[0.9557401,0.02489362,0.0037411756,0.0028204804,0.009844524,0.0029600894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02663629,0.0010898318,0.0018085815,0.002987677,0.003010793,0.01889362,0.0021826823,0.0042560315,0.015249617],"category_scores_gemma":[0.05677205,0.00038654788,0.00093539385,0.003873466,0.012122607,0.015708553,0.006863005,0.0064345347,0.0022650298],"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":[0.00034963188,0.00033969185,0.016551396,0.0024104407,0.0003090494,0.00023385676,0.009955243,0.0024990747,0.0010422642,0.47107902,0.041934926,0.45329544],"study_design_scores_gemma":[0.0000652708,0.0007110512,0.01818103,0.007254127,0.00017669411,0.00044315707,0.015799452,0.0025748753,0.0016606294,0.40286365,0.5500459,0.00022418669],"about_ca_topic_score_codex":0.018355919,"about_ca_topic_score_gemma":0.018341778,"teacher_disagreement_score":0.02663629,"about_ca_system_score_codex":0.009374607,"about_ca_system_score_gemma":0.015175424,"threshold_uncertainty_score":0.14086783},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04525373,0.0074812463,0.03326436,0.74313504,0.009780769,0.0002037187,0.000611189,0.0004664782,0.15980338],"genre_scores_gemma":[0.6571231,0.008019308,0.17737299,0.115675904,0.003442039,0.00037665485,0.0006623346,0.00048960303,0.036838047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9555577,0.020980053,0.0024093932,0.0017975348,0.017239086,0.0020162521],"domain_scores_gemma":[0.83036876,0.07327475,0.007062331,0.013146742,0.058684345,0.017462954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051204767,0.00044478933,0.00076387875,0.0024172154,0.0035778962,0.020647435,0.0030632243,0.008108731,0.006154517],"category_scores_gemma":[0.11782383,0.00046976152,0.0005612891,0.0022395167,0.0067427093,0.008171948,0.004154829,0.012421468,0.0010076027],"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":[0.00020740184,0.00057440624,0.013525752,0.00055468257,0.00006742354,0.00027926004,0.0060855574,0.0016480729,0.0008029596,0.34828362,0.2568556,0.37111524],"study_design_scores_gemma":[0.00007405177,0.00037116394,0.015859548,0.0016409446,0.000060894916,0.00035855113,0.008979604,0.002886577,0.0015245357,0.17111732,0.796948,0.00017869938],"about_ca_topic_score_codex":0.020182388,"about_ca_topic_score_gemma":0.07508394,"teacher_disagreement_score":0.051204767,"about_ca_system_score_codex":0.012006875,"about_ca_system_score_gemma":0.029483508,"threshold_uncertainty_score":0.27079993},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03469192,0.05905931,0.2557969,0.31170392,0.002202895,0.0020064302,0.00034089296,0.00025437755,0.3339433],"genre_scores_gemma":[0.860187,0.016062852,0.090142965,0.020960135,0.0012503136,0.004934548,0.00017958823,0.00030909767,0.0059736255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.51774406,0.4238073,0.013639937,0.010964214,0.02806292,0.005781605],"domain_scores_gemma":[0.43226638,0.502135,0.015041868,0.0204436,0.023732653,0.0063805142],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29998425,0.0013252503,0.002589735,0.011098893,0.0080012,0.028291991,0.0046639866,0.008381369,0.0072083035],"category_scores_gemma":[0.41813236,0.0011973167,0.0017211674,0.008265162,0.08044515,0.044923726,0.023117363,0.009090426,0.0013948871],"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":[0.0000879637,0.00007710038,0.0027752158,0.00166955,0.00008437374,0.000118140284,0.040717,0.00057694444,0.00007513529,0.85499674,0.0048332997,0.0939886],"study_design_scores_gemma":[0.000057340603,0.00006933543,0.0011324012,0.006242794,0.00006150716,0.00016222343,0.016506404,0.0011957836,0.00026080495,0.93290013,0.041356765,0.000054602817],"about_ca_topic_score_codex":0.006235988,"about_ca_topic_score_gemma":0.0030367104,"teacher_disagreement_score":0.7000158,"about_ca_system_score_codex":0.021224082,"about_ca_system_score_gemma":0.034262616,"threshold_uncertainty_score":0.86324406},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007958797,0.054713286,0.038479064,0.7849645,0.02857984,0.00012334828,0.00015559897,0.00015729596,0.08486821],"genre_scores_gemma":[0.61177605,0.046988875,0.041401576,0.24231942,0.048906714,0.0010551761,0.00017909882,0.00062275166,0.0067503294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87104905,0.092279874,0.007091617,0.007929792,0.018982233,0.0026674464],"domain_scores_gemma":[0.74933004,0.20969702,0.011008236,0.010531094,0.015386899,0.0040467735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10191673,0.0014433538,0.0022786497,0.008314803,0.007995922,0.03536738,0.0038377119,0.011342095,0.003468028],"category_scores_gemma":[0.1842701,0.0007568052,0.0012210761,0.0088942805,0.11512385,0.045221563,0.014912666,0.02342158,0.000994384],"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":[0.000042550007,0.000019048895,0.00044282852,0.00055172323,0.00003584977,0.000069350346,0.010556845,0.00011598169,0.00018485807,0.9497095,0.01663887,0.021632632],"study_design_scores_gemma":[0.00004049569,0.000063616135,0.00071350083,0.0022421363,0.00004398965,0.00021145906,0.0168128,0.0004331635,0.0003025111,0.83221835,0.14683701,0.000081028884],"about_ca_topic_score_codex":0.0017853685,"about_ca_topic_score_gemma":0.0015847189,"teacher_disagreement_score":0.89808327,"about_ca_system_score_codex":0.010066733,"about_ca_system_score_gemma":0.010322798,"threshold_uncertainty_score":0.5389936},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13978502,0.00034545411,0.75514203,0.0048044575,0.000096633135,0.010261339,0.0012565216,0.001795013,0.08651361],"genre_scores_gemma":[0.438614,0.00016769055,0.5534629,0.0002459071,0.0000069898997,0.0030565835,0.00045601808,0.000052884567,0.0039369743],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912293,0.0062008537,0.0003453499,0.0005772114,0.0012201818,0.00042702892],"domain_scores_gemma":[0.97441465,0.016990574,0.0008741157,0.0013538144,0.005320077,0.0010468127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016692169,0.00092128396,0.00045940923,0.0021254243,0.0019891348,0.0034588745,0.0027269751,0.0015618942,0.007983484],"category_scores_gemma":[0.026142355,0.0005951242,0.0007295207,0.0018392578,0.0023437298,0.004834542,0.0019486183,0.0013876428,0.00083110237],"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":[0.0010012707,0.0020737555,0.015682347,0.0012759635,0.00009744643,0.00049728405,0.01018585,0.44235227,0.004270107,0.20281574,0.009545162,0.31020284],"study_design_scores_gemma":[0.0007764695,0.0026395833,0.008464088,0.0010378842,0.00018617902,0.0003715934,0.006751284,0.79601187,0.0061751325,0.13585399,0.04141247,0.00031949196],"about_ca_topic_score_codex":0.05612425,"about_ca_topic_score_gemma":0.07238216,"teacher_disagreement_score":0.05612425,"about_ca_system_score_codex":0.009829638,"about_ca_system_score_gemma":0.021479055,"threshold_uncertainty_score":0.111595094},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97799414,0.0012809626,0.001954721,0.0054072654,0.00011799829,0.0002265875,0.00003446814,0.00002218019,0.012961667],"genre_scores_gemma":[0.99329716,0.0011791504,0.0016434438,0.0007399314,0.000036948262,0.00014081883,0.000022656131,0.000020004838,0.0029198255],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9840686,0.010497866,0.00022032387,0.0005239835,0.0014860663,0.003203131],"domain_scores_gemma":[0.98658586,0.0072917063,0.0011867646,0.00029641087,0.0011290864,0.0035101925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010371626,0.0008356208,0.0007354197,0.0025192352,0.033806566,0.006823577,0.0040996997,0.0031266254,0.0026420096],"category_scores_gemma":[0.012432505,0.0008144575,0.00048738442,0.0027719818,0.0146503765,0.0032509535,0.009085789,0.0050027,0.0002455923],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026518583,0.00011880123,0.0038036811,0.000095615185,0.0000052344376,0.0065625547,0.9815683,0.000109862805,0.0003298779,0.0021494306,0.0008897004,0.004340462],"study_design_scores_gemma":[0.0000032947826,0.000035699184,0.0010672561,0.00010316463,0.0000031077675,0.0006078427,0.99150145,0.00009026688,0.00009769471,0.00015896498,0.00632338,0.000007801752],"about_ca_topic_score_codex":0.1397823,"about_ca_topic_score_gemma":0.36386293,"teacher_disagreement_score":0.9774572,"about_ca_system_score_codex":0.022542799,"about_ca_system_score_gemma":0.024840845,"threshold_uncertainty_score":0.27793735},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78521925,0.0073313103,0.047549456,0.09748458,0.0024902138,0.002460608,0.0003296275,0.00021751897,0.056917444],"genre_scores_gemma":[0.9652627,0.002179365,0.008980165,0.008638471,0.00015087637,0.0015423512,0.00006884277,0.00024934663,0.012927929],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7941399,0.18370734,0.003568832,0.003780171,0.007951584,0.006852138],"domain_scores_gemma":[0.51814646,0.432849,0.007093462,0.0073555503,0.02271238,0.0118431365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18502544,0.0009794874,0.0013513113,0.0030575418,0.033724323,0.018261671,0.0054330723,0.00563148,0.005847923],"category_scores_gemma":[0.2049006,0.0015215585,0.0007350298,0.0037647483,0.03491536,0.013525334,0.022892075,0.010364518,0.00093088933],"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":[0.000018244304,0.000050586827,0.00069464016,0.0001934745,0.0000028351276,0.00036627156,0.98840684,0.00002449415,0.00037550583,0.003594127,0.0008432818,0.005429714],"study_design_scores_gemma":[0.000006535867,0.000032061875,0.0003244521,0.00047085877,0.0000033589067,0.00020529532,0.9795995,0.000032120326,0.00029405992,0.0010447763,0.017974857,0.000012141134],"about_ca_topic_score_codex":0.013708588,"about_ca_topic_score_gemma":0.033318948,"teacher_disagreement_score":0.18502544,"about_ca_system_score_codex":0.025008122,"about_ca_system_score_gemma":0.03611638,"threshold_uncertainty_score":0.97851974},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33182925,0.0065841656,0.028718617,0.15733527,0.0010368209,0.0022965593,0.0020686644,0.0018783902,0.46825224],"genre_scores_gemma":[0.784071,0.00066861353,0.015964339,0.005477757,0.00005243571,0.00024747234,0.00036052917,0.00010709295,0.19305079],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944377,0.0016280981,0.00015373224,0.00045812316,0.0019369521,0.0013854236],"domain_scores_gemma":[0.9804984,0.002531274,0.0011423859,0.0009594914,0.008135491,0.0067329234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008925276,0.00023600255,0.00014162766,0.0010033185,0.0064284075,0.0048469296,0.0014709688,0.0015756869,0.015480796],"category_scores_gemma":[0.009899596,0.00027527203,0.0002847505,0.0012819543,0.0026510556,0.0014036461,0.0021342747,0.001483168,0.0010374982],"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":[0.0001996437,0.00102458,0.0877431,0.000391078,0.000052204734,0.0012753025,0.012883919,0.0033634503,0.0042083864,0.08982672,0.16293806,0.6360935],"study_design_scores_gemma":[0.0000868957,0.00034225732,0.17832235,0.00037650805,0.00001994589,0.00026336126,0.011396866,0.0038972541,0.001212081,0.0033999882,0.80057126,0.00011118963],"about_ca_topic_score_codex":0.9669017,"about_ca_topic_score_gemma":0.98294455,"teacher_disagreement_score":0.9355366,"about_ca_system_score_codex":0.06446338,"about_ca_system_score_gemma":0.1886897,"threshold_uncertainty_score":0.46771675},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017907295,0.39718413,0.11258675,0.4221947,0.010744103,0.0060126767,0.0015885975,0.00040726314,0.031374585],"genre_scores_gemma":[0.32797804,0.1633854,0.4227437,0.06410997,0.007823479,0.010843866,0.0012220762,0.00038351296,0.0015099632],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.37292588,0.41969246,0.091074325,0.015511185,0.09396443,0.00683173],"domain_scores_gemma":[0.1106124,0.8048462,0.022769392,0.01977198,0.037729755,0.004270268],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52864,0.0051534027,0.024086624,0.039994724,0.009895044,0.06461175,0.0150531735,0.03144132,0.0055629117],"category_scores_gemma":[0.71797216,0.0049838866,0.006684842,0.022622468,0.0377947,0.06475573,0.017288182,0.025233056,0.0027087813],"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":[0.0010718218,0.0013379386,0.012551869,0.15178265,0.0074777254,0.001585271,0.01521076,0.0049985056,0.001763647,0.32086605,0.02918057,0.4521732],"study_design_scores_gemma":[0.00042440798,0.0005379016,0.0032445742,0.17382437,0.0022146427,0.00044369625,0.012288062,0.0038486938,0.0020231276,0.7164899,0.08414299,0.00051758677],"about_ca_topic_score_codex":0.0067693344,"about_ca_topic_score_gemma":0.005233377,"teacher_disagreement_score":0.47136003,"about_ca_system_score_codex":0.032140665,"about_ca_system_score_gemma":0.08016141,"threshold_uncertainty_score":0.5812709},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06449418,0.13064215,0.10938242,0.5727943,0.0068836985,0.0011639257,0.00031256193,0.00034567786,0.11398115],"genre_scores_gemma":[0.76769084,0.07931591,0.08395309,0.048144143,0.0030551932,0.0026792216,0.00030185023,0.00048656197,0.014373193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8636626,0.10787358,0.0050749294,0.007494304,0.014092121,0.0018025317],"domain_scores_gemma":[0.7245769,0.22653106,0.009146258,0.021445505,0.015939713,0.002360594],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.13234329,0.0010426239,0.0022737256,0.009449108,0.006757953,0.03577626,0.005458045,0.00786086,0.0028683804],"category_scores_gemma":[0.13754751,0.001194722,0.0014983994,0.010731685,0.054716554,0.05389969,0.006480218,0.011274506,0.0011453944],"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":[0.000035541143,0.00007197648,0.0032134417,0.004082662,0.00023974251,0.00021901558,0.3352405,0.00045831388,0.00033011756,0.5893596,0.011279038,0.05547024],"study_design_scores_gemma":[0.00008044841,0.000120655815,0.0021708098,0.027112735,0.0003747408,0.0005558534,0.2904414,0.0016992907,0.001459243,0.49270412,0.18316449,0.00011622372],"about_ca_topic_score_codex":0.004445196,"about_ca_topic_score_gemma":0.0036657352,"teacher_disagreement_score":0.993242,"about_ca_system_score_codex":0.019259866,"about_ca_system_score_gemma":0.02601894,"threshold_uncertainty_score":0.6999066},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57025665,0.0014067764,0.024948226,0.26549533,0.00043482924,0.00095605844,0.00008705131,0.00028510325,0.13612993],"genre_scores_gemma":[0.963714,0.00054523075,0.007450673,0.012273772,0.00008136998,0.00044843982,0.000027607755,0.00013322518,0.015325757],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89011693,0.0862505,0.0024557267,0.002949453,0.008891759,0.0093357125],"domain_scores_gemma":[0.89200467,0.07018451,0.0039921,0.004344154,0.012348275,0.017126275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06822452,0.000816647,0.0012250836,0.0017617985,0.042984772,0.015947219,0.0045270156,0.014292403,0.009520228],"category_scores_gemma":[0.09801487,0.0014308542,0.0013028757,0.002185465,0.024915567,0.010024288,0.015312293,0.019352866,0.0013752896],"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":[0.00065661845,0.0018426905,0.038955517,0.0006190397,0.00009830279,0.082195185,0.5516702,0.0021041688,0.0020696777,0.20273769,0.042098973,0.07495187],"study_design_scores_gemma":[0.00023029263,0.0009607472,0.009557485,0.0015750348,0.00014007188,0.02598017,0.7524915,0.008436726,0.0037397372,0.046734203,0.14984168,0.00031224347],"about_ca_topic_score_codex":0.038027845,"about_ca_topic_score_gemma":0.0518901,"teacher_disagreement_score":0.93177545,"about_ca_system_score_codex":0.024376104,"about_ca_system_score_gemma":0.037792094,"threshold_uncertainty_score":0.36081004},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4654699,0.036068097,0.18738139,0.047407568,0.0026375165,0.0010222534,0.001883477,0.0024201097,0.25570968],"genre_scores_gemma":[0.9239829,0.0060977694,0.04288949,0.0014948107,0.0006910751,0.00056458643,0.0005248706,0.00041043013,0.023344083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93277645,0.04106591,0.0019965093,0.0030673838,0.018274974,0.0028187493],"domain_scores_gemma":[0.85370946,0.10494012,0.007425896,0.009379687,0.021081192,0.0034637623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04686048,0.0022257175,0.0013129014,0.0036927636,0.0023419857,0.009912228,0.0018263395,0.0037642086,0.016755925],"category_scores_gemma":[0.11109778,0.00060290523,0.0021586234,0.0034077018,0.003679542,0.009077884,0.002905218,0.00479496,0.0037760374],"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":[0.0035818745,0.0022736338,0.032891065,0.0029610258,0.0010314947,0.00024779505,0.0037219627,0.050184842,0.0071505075,0.16693048,0.02028799,0.7087373],"study_design_scores_gemma":[0.0015603922,0.010760329,0.15780638,0.0043150117,0.0016536311,0.0012163657,0.0113439085,0.13542542,0.043196857,0.13344201,0.4985521,0.0007274725],"about_ca_topic_score_codex":0.017076487,"about_ca_topic_score_gemma":0.012108106,"teacher_disagreement_score":0.04686048,"about_ca_system_score_codex":0.008233519,"about_ca_system_score_gemma":0.007276905,"threshold_uncertainty_score":0.24782485},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020238895,0.33932742,0.0065084985,0.5777247,0.026157817,0.0004985779,0.00037639658,0.00014694834,0.049057253],"genre_scores_gemma":[0.010746957,0.5646733,0.017295128,0.28889856,0.019576242,0.001660977,0.00047640828,0.0005956262,0.09607678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96525884,0.012884736,0.0023304813,0.001560781,0.016165234,0.0017999773],"domain_scores_gemma":[0.86165404,0.083262764,0.004547366,0.0022773147,0.042477597,0.005780955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06865161,0.0014295597,0.0023996388,0.015576832,0.0076502496,0.015870923,0.005452989,0.011178221,0.016700154],"category_scores_gemma":[0.09032441,0.0016559621,0.001143515,0.018194484,0.019167995,0.008331483,0.0063218097,0.012312802,0.005364695],"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":[0.000015830901,0.000023882916,0.00015496442,0.0026079908,0.000012577541,0.00012263711,0.0022915828,0.00012717047,0.00018088089,0.04992227,0.8435362,0.101004064],"study_design_scores_gemma":[0.000009596558,0.000008344022,0.0003562969,0.004254171,0.000011010823,0.00012971586,0.00079214404,0.000042354037,0.000043170698,0.0070504723,0.98727554,0.00002717372],"about_ca_topic_score_codex":0.6478011,"about_ca_topic_score_gemma":0.8188792,"teacher_disagreement_score":0.6478011,"about_ca_system_score_codex":0.10180821,"about_ca_system_score_gemma":0.15250894,"threshold_uncertainty_score":0.73867375},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016653847,0.004309856,0.0024627494,0.5339089,0.0037849047,0.00034192685,0.0032834434,0.00061973295,0.4346347],"genre_scores_gemma":[0.18788843,0.0042031603,0.0066408333,0.05203295,0.00071429805,0.00023391152,0.0014268492,0.0003190804,0.7465405],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99048644,0.0013654912,0.00023712312,0.00028509126,0.005840042,0.0017858924],"domain_scores_gemma":[0.9585231,0.00641968,0.0013238387,0.0014122042,0.016753811,0.015567291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008240481,0.00050968456,0.00043090878,0.0011589576,0.0064867847,0.0059214113,0.001134061,0.0038018187,0.051347457],"category_scores_gemma":[0.027450094,0.0006015776,0.00051562977,0.0011571947,0.0027867772,0.0016576587,0.002096231,0.0030016876,0.00597397],"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":[0.00009384642,0.00007066189,0.01040016,0.00010407725,0.000016166578,0.000059726706,0.0003880212,0.00022270114,0.00028431017,0.012513282,0.93533456,0.04051247],"study_design_scores_gemma":[0.000037945083,0.0000650171,0.038497604,0.0002068682,0.000014496737,0.000043175292,0.001159195,0.00022071887,0.00038523212,0.0020214587,0.9573024,0.00004596582],"about_ca_topic_score_codex":0.86315703,"about_ca_topic_score_gemma":0.9710905,"teacher_disagreement_score":0.13684297,"about_ca_system_score_codex":0.052732613,"about_ca_system_score_gemma":0.1345485,"threshold_uncertainty_score":0.3826037},"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":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033130434,0.09086061,0.01729035,0.022665972,0.0027478489,0.014655456,0.7997594,0.012802641,0.03590476],"genre_scores_gemma":[0.022492474,0.22224002,0.17236364,0.0119512845,0.0039325436,0.046619993,0.4927419,0.00732314,0.02033504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93447536,0.014531524,0.035702255,0.002837424,0.010719417,0.0017340523],"domain_scores_gemma":[0.6127236,0.21510154,0.08290144,0.022865588,0.048512872,0.017894898],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.04100455,0.0039600935,0.020650718,0.10784218,0.0018156369,0.021235604,0.007561838,0.009622422,0.13625188],"category_scores_gemma":[0.3144291,0.0031697808,0.0054903207,0.10389726,0.0020695117,0.009516582,0.0124991955,0.0052202344,0.03586098],"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":[0.0019089963,0.00029303675,0.001702137,0.27941793,0.0044386256,0.00027624023,0.0006225612,0.0005714754,0.0010132011,0.013931245,0.4948525,0.20097207],"study_design_scores_gemma":[0.0045028357,0.000362022,0.0071314643,0.16706835,0.009141089,0.00036723798,0.0004525299,0.00089106977,0.0009043915,0.014855747,0.79385287,0.00047043664],"about_ca_topic_score_codex":0.004108343,"about_ca_topic_score_gemma":0.006644074,"teacher_disagreement_score":0.99243814,"about_ca_system_score_codex":0.0044794087,"about_ca_system_score_gemma":0.03217668,"threshold_uncertainty_score":0.45580792},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8932522,0.00036512275,0.045732323,0.020694684,0.0002945002,0.002944383,0.00042119983,0.00054421235,0.03575135],"genre_scores_gemma":[0.9503117,0.0003610443,0.03682464,0.0021633147,0.00006853028,0.0005854867,0.00013873498,0.0001196891,0.009426725],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96625084,0.026090829,0.0012732135,0.0010603254,0.0028269992,0.0024977631],"domain_scores_gemma":[0.9227137,0.051640324,0.0044092424,0.00515029,0.009092723,0.006993838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02926939,0.0004718766,0.00036785754,0.0017089027,0.0067569227,0.0040666773,0.0017111656,0.0035433772,0.0045458917],"category_scores_gemma":[0.061560426,0.0008552017,0.00051320164,0.0026219958,0.0026911881,0.004086713,0.00518691,0.0043519004,0.0014287825],"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":[0.0013371715,0.013019381,0.14076278,0.0012141546,0.000097400174,0.055206463,0.22551724,0.015898697,0.00824145,0.027123136,0.040804733,0.4707774],"study_design_scores_gemma":[0.00041455965,0.0068101007,0.09225618,0.0010678422,0.00008481477,0.017016087,0.55943096,0.03380982,0.013564457,0.016850341,0.25822157,0.00047333766],"about_ca_topic_score_codex":0.01058546,"about_ca_topic_score_gemma":0.022421673,"teacher_disagreement_score":0.02926939,"about_ca_system_score_codex":0.005660276,"about_ca_system_score_gemma":0.011259929,"threshold_uncertainty_score":0.15479314},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20216803,0.006095643,0.54767144,0.021441955,0.00074779347,0.022009507,0.053694468,0.0027392514,0.143432],"genre_scores_gemma":[0.44085032,0.00090321974,0.5205956,0.00071694376,0.00008833284,0.027935343,0.0077302656,0.00016842701,0.0010115292],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81332284,0.12573183,0.020430172,0.005594269,0.031926904,0.0029939266],"domain_scores_gemma":[0.819049,0.109408736,0.023850929,0.010389187,0.032783866,0.004518214],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.105141,0.0012455021,0.0020241549,0.05049518,0.003073413,0.0071392427,0.0020612502,0.001825292,0.0038828477],"category_scores_gemma":[0.15366095,0.00067201623,0.0033202306,0.0359228,0.0057562934,0.010851503,0.011390523,0.0032715593,0.00043547052],"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":[0.0005967897,0.000837396,0.33167696,0.005389749,0.0016180777,0.00024424092,0.018116022,0.017166497,0.0012976525,0.18006982,0.041238032,0.40174875],"study_design_scores_gemma":[0.00061668374,0.0024268087,0.5277335,0.005938179,0.0010161691,0.0009019246,0.03123715,0.05786149,0.0029189824,0.16605423,0.20255385,0.00074107625],"about_ca_topic_score_codex":0.01880364,"about_ca_topic_score_gemma":0.014017769,"teacher_disagreement_score":0.894859,"about_ca_system_score_codex":0.02047117,"about_ca_system_score_gemma":0.023285298,"threshold_uncertainty_score":0.5560454},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875618,0.000833684,0.0010391208,0.0005902224,0.000029098013,0.00025375298,0.0007071242,0.000016216285,0.008969035],"genre_scores_gemma":[0.9918155,0.0005398285,0.0017207296,0.00016284882,0.0000043240343,0.00018266369,0.00038135445,0.000017632616,0.005175108],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9968381,0.0010901599,0.00015571792,0.00056514743,0.00071247277,0.0006383557],"domain_scores_gemma":[0.9933241,0.0018741573,0.0005000895,0.00034758326,0.0033515973,0.00060259487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004040372,0.00062750257,0.0005242682,0.0017143323,0.0052250903,0.004823879,0.0014645479,0.00063657115,0.0038314334],"category_scores_gemma":[0.008294582,0.00043901752,0.00046149633,0.002717865,0.004483272,0.0017089352,0.0027331845,0.0011107514,0.0005990147],"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":[0.00020140647,0.0001199391,0.29748207,0.0007284887,0.00007705646,0.0010170729,0.6387682,0.0005317159,0.0023702318,0.0017653216,0.0028201449,0.054118335],"study_design_scores_gemma":[0.000009172298,0.00006519028,0.29968917,0.00047003385,0.000044806802,0.00011387051,0.6847369,0.00051946205,0.000744354,0.0003280198,0.013217355,0.00006169879],"about_ca_topic_score_codex":0.9352676,"about_ca_topic_score_gemma":0.9659285,"teacher_disagreement_score":0.06473237,"about_ca_system_score_codex":0.026289182,"about_ca_system_score_gemma":0.026227692,"threshold_uncertainty_score":0.19074225},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15070863,0.029078873,0.6084885,0.054204654,0.00046317917,0.016286017,0.00056289637,0.00054084504,0.13966645],"genre_scores_gemma":[0.6541946,0.004786705,0.32619455,0.0016525285,0.00016442745,0.011833173,0.0001501301,0.000081962084,0.000941886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6853852,0.26187292,0.012066972,0.0057403096,0.03177041,0.0031641636],"domain_scores_gemma":[0.45502034,0.4859928,0.023178905,0.015277403,0.017418273,0.003112175],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25819126,0.0022804888,0.0028263303,0.0096938675,0.00240878,0.023613367,0.005528085,0.0060562645,0.00712008],"category_scores_gemma":[0.32646996,0.0015325536,0.0024373715,0.00831081,0.034701515,0.021710971,0.011743881,0.0050119865,0.0005450215],"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":[0.0006323523,0.0031150028,0.013894832,0.014521775,0.0010016795,0.00021880558,0.011699417,0.038982533,0.0012727939,0.6846028,0.0015808854,0.22847708],"study_design_scores_gemma":[0.0004938931,0.002680251,0.01081721,0.01367906,0.0007748333,0.00020092558,0.013162278,0.046135176,0.0035598879,0.88912857,0.019196868,0.00017095679],"about_ca_topic_score_codex":0.0026077998,"about_ca_topic_score_gemma":0.0019608252,"teacher_disagreement_score":0.7418088,"about_ca_system_score_codex":0.016594384,"about_ca_system_score_gemma":0.018770948,"threshold_uncertainty_score":0.9147822},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7564142,0.0005773126,0.12612373,0.013665954,0.00040598758,0.04378055,0.00022972298,0.00035871152,0.058443885],"genre_scores_gemma":[0.66705185,0.00071913184,0.30135196,0.0019833292,0.000061123035,0.022139834,0.00020689548,0.00006998406,0.0064158426],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9777414,0.01768047,0.00066015695,0.00084560143,0.001891451,0.0011808763],"domain_scores_gemma":[0.98711944,0.005122646,0.00096611714,0.0013014319,0.0029683842,0.0025219212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041557852,0.0005032507,0.00036277506,0.0010631451,0.0042663724,0.0030755964,0.0024448307,0.0008176218,0.0023065973],"category_scores_gemma":[0.019229585,0.00039669752,0.00042686984,0.0006922586,0.0022981644,0.0020792226,0.006352509,0.0023319565,0.00034451424],"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":[0.00017247093,0.014550543,0.024006894,0.0020861672,0.00005777141,0.0014130137,0.30976942,0.0033600917,0.009527493,0.019094756,0.012066397,0.603895],"study_design_scores_gemma":[0.0011228081,0.008224528,0.045003958,0.0050031384,0.00017712993,0.0015696458,0.51329905,0.009057946,0.024317114,0.03429444,0.35770872,0.00022151307],"about_ca_topic_score_codex":0.0019870366,"about_ca_topic_score_gemma":0.0053335484,"teacher_disagreement_score":0.041557852,"about_ca_system_score_codex":0.003345534,"about_ca_system_score_gemma":0.02279671,"threshold_uncertainty_score":0.21978152},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.907604,0.0045433524,0.0077264155,0.009930353,0.00033850694,0.0029114466,0.012512588,0.0006436044,0.05378975],"genre_scores_gemma":[0.97749513,0.000759825,0.0068001794,0.00039605386,0.00003292795,0.00055346783,0.0031281523,0.000041835316,0.01079245],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97528243,0.007219027,0.0012633879,0.0012054819,0.012709845,0.0023198398],"domain_scores_gemma":[0.86922467,0.020016668,0.007556362,0.0029855499,0.09350645,0.0067102583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034249827,0.0007841666,0.0008387855,0.003667139,0.0022849264,0.004665437,0.0015929571,0.00096382096,0.005847144],"category_scores_gemma":[0.065021224,0.0004360194,0.0010299663,0.005227683,0.0012054588,0.0018274914,0.0020029424,0.00135525,0.00081315776],"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":[0.0024964167,0.0013450218,0.6159407,0.0020919512,0.0009008914,0.00005779029,0.0030276945,0.015797416,0.002044652,0.004051793,0.033000655,0.31924498],"study_design_scores_gemma":[0.0002767551,0.001981699,0.95445925,0.0008065674,0.00034150286,0.000021224436,0.002386537,0.01473093,0.0028189176,0.0003855957,0.021674126,0.000116856034],"about_ca_topic_score_codex":0.92864406,"about_ca_topic_score_gemma":0.9362737,"teacher_disagreement_score":0.93114275,"about_ca_system_score_codex":0.06885724,"about_ca_system_score_gemma":0.09056415,"threshold_uncertainty_score":0.49959654},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15865146,0.005293525,0.191098,0.31961712,0.010455414,0.0013051673,0.00058640126,0.00082105125,0.312172],"genre_scores_gemma":[0.85339546,0.0021475265,0.045484293,0.027874159,0.001425115,0.0009088553,0.0002624194,0.0008197655,0.067682445],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9801558,0.016680937,0.00035839816,0.00085649005,0.0012038375,0.0007445606],"domain_scores_gemma":[0.96128505,0.028716894,0.001994112,0.0021958717,0.0038818535,0.0019261613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020143945,0.00088913913,0.0005924112,0.0014595496,0.009483419,0.010598278,0.0016263345,0.0034262615,0.0062459693],"category_scores_gemma":[0.0463007,0.0003989563,0.00060257205,0.0008023572,0.0159599,0.014608228,0.009295207,0.011000438,0.0016055629],"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":[0.000079238074,0.0000534549,0.0010056233,0.00018960319,0.000013078167,0.0010603879,0.75459176,0.00016708409,0.0013923123,0.17681718,0.041193966,0.023436317],"study_design_scores_gemma":[0.000016049911,0.00006622392,0.00045410002,0.0009817226,0.000017089995,0.0011546854,0.4477494,0.0009404673,0.0019910468,0.08212653,0.46445423,0.000048518654],"about_ca_topic_score_codex":0.001981449,"about_ca_topic_score_gemma":0.002859234,"teacher_disagreement_score":0.020143945,"about_ca_system_score_codex":0.0041074064,"about_ca_system_score_gemma":0.0065984684,"threshold_uncertainty_score":0.10653263},"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":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67978716,0.0038443408,0.15710445,0.018076908,0.0014480018,0.02969331,0.0018458616,0.000938942,0.10726107],"genre_scores_gemma":[0.91257274,0.00046736212,0.07438852,0.0010164368,0.00005512649,0.010517494,0.0003016921,0.000119058226,0.0005615062],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60042155,0.30326468,0.020611055,0.00917714,0.061015815,0.005509777],"domain_scores_gemma":[0.3572846,0.5237263,0.034104027,0.025663381,0.05514943,0.0040722326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29619458,0.0017177386,0.0022261888,0.01834447,0.0042204987,0.015390555,0.0040185372,0.0027237958,0.005406474],"category_scores_gemma":[0.47916624,0.0008646396,0.005461144,0.01204485,0.012787021,0.015283587,0.0124922395,0.004891701,0.0004777218],"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":[0.0020113753,0.0030451282,0.18155836,0.013006955,0.0027419906,0.00043542997,0.13855468,0.010543337,0.001173584,0.07133488,0.009836641,0.5657577],"study_design_scores_gemma":[0.0029729556,0.019505328,0.32070526,0.029085353,0.0055623055,0.000835508,0.26552683,0.091543265,0.015358232,0.19234602,0.055452265,0.0011066603],"about_ca_topic_score_codex":0.0060550272,"about_ca_topic_score_gemma":0.0045160395,"teacher_disagreement_score":0.70380545,"about_ca_system_score_codex":0.029525679,"about_ca_system_score_gemma":0.0253661,"threshold_uncertainty_score":0.8679174},"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":"editorial","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010223798,0.004068647,0.00012190404,0.21840213,0.77471274,0.000027991468,0.000038813043,0.000091115675,0.002434411],"genre_scores_gemma":[0.0016222969,0.0045020464,0.00038213417,0.18658529,0.79347414,0.00008914719,0.00003843721,0.00019191646,0.013114683],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94257265,0.0075917826,0.0052512717,0.0051356102,0.034223292,0.005225404],"domain_scores_gemma":[0.7960995,0.039913554,0.013788414,0.004889536,0.10046527,0.044843733],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060640242,0.0029320158,0.003415154,0.0033297183,0.013168306,0.039617687,0.008227105,0.029814498,0.02565517],"category_scores_gemma":[0.22159575,0.0019887006,0.002845509,0.003192674,0.0088571785,0.02259533,0.0055211186,0.0365465,0.022036247],"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":[0.000017667187,0.00001174638,0.000055599034,0.000093550465,0.000004464729,0.000076489225,0.0001957198,0.000007735407,0.000033208882,0.00053281215,0.99444276,0.0045282426],"study_design_scores_gemma":[0.00003556365,0.00002665177,0.00023534927,0.00044509838,0.000014593552,0.00015189133,0.0006974951,0.00004384791,0.000052087817,0.0008702096,0.99739313,0.000034169145],"about_ca_topic_score_codex":0.003043626,"about_ca_topic_score_gemma":0.008006595,"teacher_disagreement_score":0.9393598,"about_ca_system_score_codex":0.008201016,"about_ca_system_score_gemma":0.024562366,"threshold_uncertainty_score":0.3207001},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018736406,0.009117307,0.0034933581,0.78451467,0.05009567,0.00009856979,0.0002554444,0.00013446232,0.15041688],"genre_scores_gemma":[0.08624196,0.00931862,0.004772325,0.19602577,0.026611332,0.00041530392,0.00024337557,0.00055158866,0.6758197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98794645,0.005902797,0.00044540528,0.0014151785,0.0036327324,0.00065749086],"domain_scores_gemma":[0.9411753,0.032207172,0.0018428148,0.0024317745,0.014930226,0.007412619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00967398,0.00050963747,0.00065229164,0.0014938071,0.00801657,0.011525482,0.0015380715,0.0066882977,0.07511062],"category_scores_gemma":[0.07218158,0.00042976055,0.0005115375,0.0014000855,0.0049840407,0.0060217315,0.0059010154,0.0070530013,0.021149369],"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":[0.000024161547,0.000026434705,0.00036088357,0.000091692156,0.000007678791,0.00006292235,0.001567867,0.00003402606,0.000094689334,0.042342104,0.9308719,0.024515722],"study_design_scores_gemma":[0.000014607983,0.000013982306,0.00067335804,0.00036542208,0.0000065954955,0.000081580816,0.0041414415,0.00020909839,0.00026007483,0.025351292,0.96885926,0.000023318928],"about_ca_topic_score_codex":0.008778686,"about_ca_topic_score_gemma":0.019126108,"teacher_disagreement_score":0.07511062,"about_ca_system_score_codex":0.0038150377,"about_ca_system_score_gemma":0.008372963,"threshold_uncertainty_score":0.25127006},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2630022,0.0053747706,0.36694413,0.04276836,0.0003915216,0.004054234,0.00046056206,0.00020069585,0.31680351],"genre_scores_gemma":[0.92138827,0.00088301965,0.07407407,0.00054250937,0.000035844056,0.0019350327,0.000061370425,0.00003423165,0.0010458145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.93441814,0.05777122,0.0015213059,0.0020637733,0.0025405372,0.0016850702],"domain_scores_gemma":[0.91586196,0.06548947,0.0051554777,0.0043945964,0.006101624,0.0029968715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056676406,0.0009881336,0.0008813026,0.0075019663,0.010243351,0.013944987,0.002902792,0.0021784978,0.0055872193],"category_scores_gemma":[0.0494894,0.000889626,0.0013227446,0.0066561694,0.05007437,0.011882786,0.012955591,0.0031337587,0.00025067216],"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":[0.000035658664,0.00023576865,0.020865452,0.0011002393,0.00008036149,0.00043245693,0.0888306,0.0034272026,0.00019848296,0.8385581,0.0013868804,0.044848733],"study_design_scores_gemma":[0.00006439808,0.00019865044,0.028220408,0.0033998846,0.0001223256,0.0004907265,0.2890789,0.010037336,0.000613706,0.59229124,0.075375974,0.00010643848],"about_ca_topic_score_codex":0.01555362,"about_ca_topic_score_gemma":0.02070487,"teacher_disagreement_score":0.056676406,"about_ca_system_score_codex":0.025113108,"about_ca_system_score_gemma":0.033435524,"threshold_uncertainty_score":0.29973704},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48144224,0.03414541,0.019022109,0.28130788,0.0045842375,0.00096453814,0.0010136036,0.00028957898,0.1772304],"genre_scores_gemma":[0.85129213,0.021038918,0.016104,0.03916992,0.0008394701,0.00080476084,0.000597245,0.00017622768,0.06997724],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98727,0.005804934,0.00036074896,0.0007716224,0.0026667628,0.0031259442],"domain_scores_gemma":[0.97219807,0.006497159,0.003288922,0.0013076608,0.0068072407,0.009900991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013409973,0.00043066667,0.0006140338,0.0010064145,0.005551612,0.006372048,0.001973949,0.0037661488,0.019638324],"category_scores_gemma":[0.03061024,0.0004578769,0.0006007797,0.0016559559,0.0053354893,0.0041181133,0.00592845,0.0050403136,0.0032914383],"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":[0.0007389584,0.0010073223,0.08813556,0.0033910007,0.00014212017,0.0013141569,0.072650775,0.0011702763,0.0029207133,0.0889231,0.074535325,0.66507065],"study_design_scores_gemma":[0.00017490442,0.0010761659,0.14927045,0.008946318,0.00018606176,0.0009203544,0.06903803,0.0011073651,0.0017552343,0.011820475,0.7555411,0.00016353164],"about_ca_topic_score_codex":0.20538796,"about_ca_topic_score_gemma":0.3957848,"teacher_disagreement_score":0.20538796,"about_ca_system_score_codex":0.018885778,"about_ca_system_score_gemma":0.07955638,"threshold_uncertainty_score":0.40838492},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1628958,0.009946652,0.0008050079,0.5290589,0.0012035329,0.00011565882,0.0011221808,0.00007387094,0.29477853],"genre_scores_gemma":[0.84566194,0.012532458,0.0008077326,0.03543306,0.00031247456,0.000093876115,0.000619251,0.00012220062,0.10441699],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9930248,0.0009535487,0.00018936353,0.0003671801,0.0021969143,0.0032681024],"domain_scores_gemma":[0.9909272,0.0015599978,0.0007886512,0.0003224015,0.0031554503,0.0032463695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035316716,0.00031768865,0.00044007384,0.0013402081,0.03225761,0.013997676,0.0018791747,0.0033652992,0.0100424895],"category_scores_gemma":[0.008719706,0.0005519039,0.00046373252,0.005538092,0.016659265,0.0059070517,0.004341939,0.0048542838,0.00067354634],"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":[0.000093910654,0.00008853519,0.036434077,0.00078692316,0.000042232397,0.002171089,0.3539104,0.00044524999,0.0006648738,0.26493022,0.28944707,0.050985407],"study_design_scores_gemma":[0.000010595701,0.000010481289,0.027387409,0.00045414703,0.00001404262,0.00012628225,0.2124676,0.00015153378,0.00016035148,0.0043333094,0.7548315,0.00005271733],"about_ca_topic_score_codex":0.99519086,"about_ca_topic_score_gemma":0.9978866,"teacher_disagreement_score":0.28292608,"about_ca_system_score_codex":0.28292608,"about_ca_system_score_gemma":0.3329137,"threshold_uncertainty_score":0.83170414},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15922272,0.022902362,0.046931986,0.3232907,0.0031901281,0.002675837,0.0017172047,0.00018507583,0.43988395],"genre_scores_gemma":[0.90098315,0.009074228,0.030895874,0.01599619,0.00030245088,0.002113194,0.00045071385,0.00010207352,0.040082183],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.974362,0.015568366,0.00092992745,0.0013030278,0.0059573133,0.0018794512],"domain_scores_gemma":[0.95941305,0.018350005,0.001674752,0.0013998989,0.016895743,0.0022665055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034756072,0.0008419922,0.0010235455,0.006141165,0.01415,0.017398883,0.00298792,0.004136193,0.00794467],"category_scores_gemma":[0.046736322,0.00056212617,0.001178264,0.006687341,0.019393617,0.0056626783,0.0077850167,0.007203971,0.00068342587],"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":[0.00015018917,0.00010493577,0.017007023,0.002075054,0.00007663235,0.00095136993,0.33780324,0.0011452046,0.00077559333,0.4980641,0.042380445,0.09946619],"study_design_scores_gemma":[0.00010834584,0.0001502514,0.055055264,0.015495809,0.00024459275,0.0004244424,0.28662512,0.0036527552,0.0013720574,0.060705625,0.5759641,0.00020165907],"about_ca_topic_score_codex":0.77294946,"about_ca_topic_score_gemma":0.8317078,"teacher_disagreement_score":0.88464487,"about_ca_system_score_codex":0.11535513,"about_ca_system_score_gemma":0.12983236,"threshold_uncertainty_score":0.83696395},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013414487,0.42931056,0.062475104,0.30391374,0.14469816,0.0026704941,0.002270407,0.0009507095,0.052369338],"genre_scores_gemma":[0.01336074,0.47530234,0.05695139,0.1088658,0.08590533,0.0030131252,0.0017053002,0.0011020125,0.253794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865811,0.0041063516,0.0009400998,0.00073381065,0.0073547573,0.0002839618],"domain_scores_gemma":[0.9142878,0.04355763,0.0036159658,0.0022150802,0.035033144,0.0012903283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012922065,0.0013315331,0.0027278182,0.0040228833,0.0011165491,0.0052557117,0.0026312885,0.00570472,0.018629584],"category_scores_gemma":[0.07352188,0.00085842237,0.0014986863,0.006611837,0.003227661,0.0033292496,0.0013079024,0.0057650553,0.013603991],"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":[0.000024589126,0.00004587746,0.000120840574,0.0014630394,0.000030165922,0.000019999838,0.000028970639,0.00022374663,0.00015380593,0.0041814693,0.85723966,0.13646786],"study_design_scores_gemma":[0.000037883332,0.00009371118,0.0012544247,0.0040079546,0.00010157431,0.00019856867,0.000061080296,0.0006215076,0.0006192322,0.012199413,0.98074096,0.00006367558],"about_ca_topic_score_codex":0.0095205745,"about_ca_topic_score_gemma":0.02918299,"teacher_disagreement_score":0.018629584,"about_ca_system_score_codex":0.0055477777,"about_ca_system_score_gemma":0.010106975,"threshold_uncertainty_score":0.06833923},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014678284,0.0035213786,0.8407967,0.022973558,0.00088179234,0.0015373,0.00042970688,0.0002419983,0.11493935],"genre_scores_gemma":[0.69954664,0.003581203,0.28387222,0.002691414,0.00041043328,0.0035474002,0.00021204322,0.00016174269,0.00597688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9538644,0.03785364,0.00080547214,0.0017359813,0.004735942,0.001004614],"domain_scores_gemma":[0.9216486,0.069558844,0.0023473015,0.0018345072,0.0038658353,0.00074476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035998143,0.002627802,0.002473149,0.009978209,0.0023512724,0.008729459,0.0037669935,0.004051335,0.014659068],"category_scores_gemma":[0.05351125,0.0009190356,0.0038255504,0.0053642425,0.014115698,0.0063117323,0.004594982,0.006593397,0.0006266288],"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":[0.0000708402,0.0003202189,0.0016778056,0.0010301213,0.00038634543,0.00007913912,0.00091913325,0.043482825,0.0001371335,0.9190918,0.002415804,0.030388845],"study_design_scores_gemma":[0.000077397584,0.00034509247,0.001313271,0.0012590208,0.0002844528,0.00006261359,0.0018382942,0.07944666,0.00042030783,0.89895535,0.015940404,0.000057194717],"about_ca_topic_score_codex":0.0062320884,"about_ca_topic_score_gemma":0.006074107,"teacher_disagreement_score":0.035998143,"about_ca_system_score_codex":0.018111216,"about_ca_system_score_gemma":0.0135968905,"threshold_uncertainty_score":0.19037867},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81776047,0.0014779292,0.0047267806,0.010783591,0.000237712,0.0009905173,0.0008094905,0.00008253775,0.16313109],"genre_scores_gemma":[0.9889065,0.0002869584,0.0033638177,0.00045178016,0.000012651603,0.00027294946,0.00018072956,0.000016004324,0.0065086535],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9592704,0.013466615,0.001511011,0.0013786097,0.021130778,0.0032426373],"domain_scores_gemma":[0.89508456,0.042757582,0.004846012,0.0027313665,0.049752172,0.0048284344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03705103,0.00031044768,0.000453049,0.0029797605,0.0069683315,0.005861206,0.0017963389,0.00071189116,0.0015418004],"category_scores_gemma":[0.111412734,0.00023155434,0.0003174077,0.0038508303,0.0065384316,0.0014406424,0.0035586332,0.0017114858,0.00023106474],"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":[0.00091216504,0.00061465806,0.30133277,0.0013546667,0.000115104216,0.0007631596,0.16450103,0.0023783508,0.003193179,0.066383086,0.022525212,0.4359267],"study_design_scores_gemma":[0.00012390119,0.00083487155,0.66175246,0.0014956617,0.000111819965,0.00019133306,0.19740754,0.007589105,0.006502229,0.008511659,0.11520954,0.00026982388],"about_ca_topic_score_codex":0.95417535,"about_ca_topic_score_gemma":0.96932465,"teacher_disagreement_score":0.9210981,"about_ca_system_score_codex":0.07890192,"about_ca_system_score_gemma":0.17329466,"threshold_uncertainty_score":0.57247615},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04451954,0.015037232,0.7564128,0.14140578,0.001525313,0.0003186673,0.00012949987,0.00020588329,0.04044529],"genre_scores_gemma":[0.6972976,0.0049178093,0.28335962,0.008100387,0.0006799173,0.0014133612,0.00011635769,0.00022245482,0.0038924448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8079725,0.17814136,0.0025491375,0.003734765,0.006490327,0.0011119547],"domain_scores_gemma":[0.68232137,0.2933313,0.006418205,0.011031653,0.004957828,0.0019396619],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.106892176,0.0012247418,0.0025412405,0.0054690437,0.009056081,0.017041834,0.0036849962,0.005415053,0.0049451343],"category_scores_gemma":[0.23684183,0.0018032084,0.0020082768,0.0079361955,0.042636726,0.0289335,0.014171754,0.0123444395,0.00050833187],"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":[0.000029390274,0.000024668856,0.0005879676,0.00018516612,0.000049726594,0.00011607994,0.020532427,0.0010731147,0.00006073932,0.9646449,0.0010937103,0.011602096],"study_design_scores_gemma":[0.000018510384,0.00002339249,0.00016591405,0.0003885964,0.00001727824,0.00005474334,0.006406682,0.004126981,0.000079892096,0.9784144,0.010282992,0.000020629768],"about_ca_topic_score_codex":0.0048957043,"about_ca_topic_score_gemma":0.0075328294,"teacher_disagreement_score":0.89310783,"about_ca_system_score_codex":0.0082328655,"about_ca_system_score_gemma":0.009624203,"threshold_uncertainty_score":0.5653066},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14278434,0.010592335,0.16529582,0.5065297,0.001197667,0.0019737426,0.0013126993,0.0011692843,0.16914439],"genre_scores_gemma":[0.8750351,0.002335663,0.10024672,0.0093328245,0.00023660735,0.00061759196,0.00024392933,0.00006921423,0.0118824085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9596454,0.021462526,0.0012895366,0.002324331,0.012121373,0.0031568562],"domain_scores_gemma":[0.8878789,0.04552132,0.0076828874,0.0075531867,0.045272164,0.0060915505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04157157,0.0009199967,0.001079702,0.0029114916,0.0040567764,0.009071456,0.0047552697,0.003981158,0.004798912],"category_scores_gemma":[0.13278118,0.00052469363,0.0007781197,0.0060572755,0.006438337,0.007508584,0.004775245,0.0038550687,0.00059055706],"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":[0.000293098,0.00033248548,0.03254082,0.0010766069,0.00028591728,0.00033971312,0.005706951,0.024083583,0.00059698377,0.52869594,0.06532312,0.34072477],"study_design_scores_gemma":[0.00060196646,0.00038643338,0.05465543,0.0025773423,0.0001950906,0.00035771917,0.015644887,0.14389472,0.0017649838,0.6105054,0.16869184,0.0007242159],"about_ca_topic_score_codex":0.8547796,"about_ca_topic_score_gemma":0.89238197,"teacher_disagreement_score":0.95842844,"about_ca_system_score_codex":0.045491125,"about_ca_system_score_gemma":0.11574444,"threshold_uncertainty_score":0.3300628},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20106699,0.0025627832,0.667495,0.011516896,0.00041944085,0.06166014,0.00087345985,0.0005477831,0.053857498],"genre_scores_gemma":[0.35697654,0.00030575396,0.61962086,0.0003239603,0.000018177649,0.021810465,0.0002832866,0.00003738101,0.0006236627],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6696373,0.26273897,0.023337645,0.005753277,0.03489096,0.0036418205],"domain_scores_gemma":[0.4937855,0.34108385,0.017124891,0.02038994,0.12396573,0.0036500369],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2981482,0.0013073817,0.0018575921,0.010798505,0.005916305,0.008250322,0.0033937325,0.0023086634,0.0027132793],"category_scores_gemma":[0.33161783,0.0010022159,0.003075997,0.0077696443,0.008869322,0.009392967,0.008304744,0.00314172,0.00028943227],"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":[0.00058464386,0.001777413,0.062627986,0.013324166,0.0005834919,0.0003086188,0.08670515,0.010379617,0.0019885437,0.24322017,0.007078375,0.57142186],"study_design_scores_gemma":[0.0020093555,0.006525538,0.14437263,0.051495012,0.0024206017,0.0011865615,0.20652659,0.17248072,0.01546986,0.2572119,0.13929696,0.0010043114],"about_ca_topic_score_codex":0.023047742,"about_ca_topic_score_gemma":0.03404623,"teacher_disagreement_score":0.2981482,"about_ca_system_score_codex":0.04465921,"about_ca_system_score_gemma":0.0659109,"threshold_uncertainty_score":0.8655082},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5555628,0.001436177,0.15945975,0.1501399,0.00082142325,0.001662333,0.00009727693,0.0006436851,0.13017672],"genre_scores_gemma":[0.9414562,0.000481588,0.047334284,0.005797894,0.000070685106,0.00080254796,0.000035612968,0.000093564704,0.0039277105],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7864963,0.17804836,0.0075388867,0.0030946285,0.019366926,0.005454929],"domain_scores_gemma":[0.7128217,0.21239313,0.018365366,0.012003615,0.039065436,0.005350666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20494811,0.0007286348,0.000546584,0.0021037313,0.011807249,0.011796616,0.002265087,0.0038407352,0.0034579197],"category_scores_gemma":[0.23043509,0.00078548444,0.00052258285,0.0010223303,0.008970965,0.01073334,0.012860515,0.0072683766,0.0007218864],"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":[0.0003637731,0.00063232705,0.033166412,0.0011665728,0.00005788272,0.0012960306,0.63784295,0.002234197,0.009892279,0.076011345,0.022404756,0.21493144],"study_design_scores_gemma":[0.00013959178,0.0006492326,0.015050215,0.004857523,0.00010025694,0.0007334252,0.6105542,0.0120275235,0.026239235,0.10366826,0.22569439,0.00028623955],"about_ca_topic_score_codex":0.007857417,"about_ca_topic_score_gemma":0.014867594,"teacher_disagreement_score":0.7950519,"about_ca_system_score_codex":0.014394716,"about_ca_system_score_gemma":0.02477465,"threshold_uncertainty_score":0.9804405},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41282004,0.0023711321,0.36637586,0.04602993,0.0004438834,0.041560657,0.0012443664,0.0029847752,0.12616938],"genre_scores_gemma":[0.52838916,0.00041384774,0.4560281,0.0013384431,0.000042816457,0.009250313,0.00057054317,0.00018475913,0.0037820486],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.82425946,0.14918369,0.0036687732,0.003237897,0.0127312895,0.0069188364],"domain_scores_gemma":[0.8302565,0.100702085,0.0074909045,0.011966186,0.035506375,0.014078007],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20026498,0.0010848633,0.00062823977,0.004010244,0.008424186,0.00733691,0.00476846,0.0022451016,0.004414686],"category_scores_gemma":[0.16155705,0.0010280606,0.0010024722,0.0029280349,0.0038463948,0.0056025246,0.010338266,0.003327997,0.00067974604],"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":[0.00090991077,0.0040268837,0.02197468,0.0025776047,0.00018475975,0.0004255547,0.052299604,0.011318744,0.004347983,0.03514341,0.03741247,0.82937825],"study_design_scores_gemma":[0.003556283,0.013082172,0.19904548,0.020214986,0.0008009978,0.0010072262,0.11344254,0.10405359,0.03684149,0.116163895,0.3901703,0.0016211242],"about_ca_topic_score_codex":0.09740346,"about_ca_topic_score_gemma":0.22072715,"teacher_disagreement_score":0.96448463,"about_ca_system_score_codex":0.035515353,"about_ca_system_score_gemma":0.07908502,"threshold_uncertainty_score":0.98621565},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03598342,0.0724828,0.36819428,0.4474249,0.007252379,0.040392034,0.0012690717,0.001623189,0.025377985],"genre_scores_gemma":[0.16224326,0.010161224,0.7721846,0.026922716,0.0008553928,0.026013043,0.00033186245,0.0003219633,0.00096595945],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.23512642,0.71717954,0.01787479,0.005219791,0.020152878,0.00444669],"domain_scores_gemma":[0.14423393,0.75645846,0.014188223,0.030517153,0.04888972,0.0057125282],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7267435,0.0025914586,0.0034570685,0.004236529,0.0047298437,0.019516574,0.008684003,0.006117149,0.004505458],"category_scores_gemma":[0.6963518,0.0018685065,0.0043537957,0.004168209,0.009870144,0.022707993,0.011580157,0.012044198,0.0007738409],"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":[0.0010889999,0.0013199155,0.014955511,0.0385281,0.0017618058,0.00058024935,0.04546462,0.008940518,0.0006449586,0.08726566,0.0561898,0.7432599],"study_design_scores_gemma":[0.0021361373,0.005628108,0.017662484,0.3001945,0.0024733115,0.00088019297,0.051118966,0.016970232,0.0058393553,0.29440013,0.30182832,0.0008682596],"about_ca_topic_score_codex":0.00804033,"about_ca_topic_score_gemma":0.020226534,"teacher_disagreement_score":0.7267435,"about_ca_system_score_codex":0.024881369,"about_ca_system_score_gemma":0.09655441,"threshold_uncertainty_score":0.33697397},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47695923,0.0055423765,0.18763803,0.041964814,0.00056701724,0.0019274392,0.00024406046,0.00027360793,0.2848834],"genre_scores_gemma":[0.94069403,0.00088951015,0.055321615,0.00076570373,0.000053686905,0.0004492394,0.000031372565,0.000027534947,0.0017673454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9230964,0.06672866,0.00095179974,0.0006174859,0.0070649027,0.0015408094],"domain_scores_gemma":[0.92578924,0.06365482,0.0012215645,0.001003394,0.007413571,0.0009173418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03255696,0.0004904493,0.00056185725,0.0039565084,0.0036781295,0.007422939,0.0014152816,0.0019886077,0.003275432],"category_scores_gemma":[0.04242825,0.00024499593,0.0008646465,0.0037562414,0.007631228,0.0041478095,0.004293941,0.0025973779,0.00017134887],"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":[0.0008054229,0.0010711236,0.017260958,0.0020944632,0.00023161757,0.0009332303,0.015734518,0.03074139,0.001311648,0.7844559,0.005811529,0.13954821],"study_design_scores_gemma":[0.0016557095,0.006047803,0.045459285,0.004583758,0.0009779918,0.0010816312,0.073939495,0.26833138,0.013571657,0.4811064,0.1028716,0.00037325706],"about_ca_topic_score_codex":0.02840171,"about_ca_topic_score_gemma":0.037379995,"teacher_disagreement_score":0.03255696,"about_ca_system_score_codex":0.017408025,"about_ca_system_score_gemma":0.012921147,"threshold_uncertainty_score":0.17217976},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44894013,0.008155606,0.0062295697,0.1630272,0.00054697314,0.00024931613,0.00019907586,0.000050012764,0.37260205],"genre_scores_gemma":[0.98856235,0.0019571714,0.0012631255,0.002547059,0.000032099913,0.000056806366,0.000031175805,0.00001544557,0.0055349045],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9698037,0.013121811,0.00082652445,0.0013819983,0.011002092,0.0038638895],"domain_scores_gemma":[0.96289885,0.02087013,0.0033463393,0.00093614956,0.009527431,0.002421114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019641653,0.00044517196,0.0005114453,0.0042162803,0.03495974,0.021311058,0.002458594,0.0030488523,0.0016614912],"category_scores_gemma":[0.031195972,0.00040704236,0.0003008555,0.00858178,0.05910542,0.007696211,0.006454224,0.0076574855,0.00011795676],"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":true,"study_design_scores_codex":[0.000018731866,0.000025186848,0.0041348566,0.00017576622,0.000009855526,0.00025862773,0.5859605,0.00031785763,0.00023440829,0.38912052,0.005290325,0.014453436],"study_design_scores_gemma":[0.000007383417,0.000012257107,0.0070042335,0.0008751861,0.00001810364,0.000078581645,0.8192877,0.00049082306,0.00037392837,0.022621412,0.14917423,0.000056204728],"about_ca_topic_score_codex":0.91160756,"about_ca_topic_score_gemma":0.9189273,"teacher_disagreement_score":0.79160476,"about_ca_system_score_codex":0.20839524,"about_ca_system_score_gemma":0.26500413,"threshold_uncertainty_score":0.9181493},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023000098,0.87693596,0.019967163,0.09056303,0.0032137744,0.0002031685,0.00006651358,0.00006357135,0.006686924],"genre_scores_gemma":[0.11032146,0.8366564,0.028393421,0.020931022,0.0020695734,0.0007611088,0.00013698901,0.00006657859,0.0006635361],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9423748,0.036280263,0.0056820787,0.0037256768,0.010931102,0.0010060742],"domain_scores_gemma":[0.5903162,0.36532426,0.008294511,0.0050310143,0.028958807,0.0020751946],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10829022,0.0016055591,0.0036065695,0.024720615,0.004183078,0.017990408,0.006761186,0.0077458113,0.002885476],"category_scores_gemma":[0.17111535,0.0009989961,0.0024164107,0.020570789,0.029449878,0.021006042,0.006216215,0.012321097,0.0006602599],"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":[0.00009457614,0.00018105644,0.0022119237,0.07663037,0.0005726552,0.00034505484,0.01599032,0.0048658536,0.00022529098,0.3234645,0.022102972,0.55331546],"study_design_scores_gemma":[0.00004825703,0.00026033,0.003100295,0.2873466,0.000776638,0.00056610355,0.027995635,0.005258761,0.0008548646,0.3572784,0.31634113,0.00017302706],"about_ca_topic_score_codex":0.016129406,"about_ca_topic_score_gemma":0.026406664,"teacher_disagreement_score":0.8917098,"about_ca_system_score_codex":0.029746033,"about_ca_system_score_gemma":0.044166815,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011975464,0.0060008373,0.67263913,0.012505717,0.0008210319,0.0004388006,0.0021088922,0.000490803,0.29301926],"genre_scores_gemma":[0.39274475,0.012180402,0.43511418,0.0020996425,0.0004802897,0.0020389091,0.0012128123,0.0005421151,0.15358694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963291,0.001020483,0.00010525389,0.0003470173,0.0018741188,0.00032400232],"domain_scores_gemma":[0.99777335,0.00076230854,0.00012700883,0.00021851786,0.0010189824,0.00009981196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052226298,0.0011052644,0.0008256559,0.002238379,0.0016687328,0.0034100004,0.0019506261,0.0015037068,0.015026691],"category_scores_gemma":[0.009477786,0.00057755806,0.001239005,0.004720116,0.0036178262,0.0021313445,0.0023728497,0.0040226807,0.0019791045],"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":[0.000010789404,0.00001601265,0.00067457807,0.000107413514,0.000022089198,0.000023697165,0.0002698545,0.012763873,0.00008649417,0.9500543,0.0070705526,0.028900426],"study_design_scores_gemma":[0.00005915731,0.000074474396,0.002967652,0.0005595758,0.000077976176,0.00012327715,0.00038810744,0.061036076,0.0009908517,0.6157939,0.3178545,0.0000744653],"about_ca_topic_score_codex":0.3291239,"about_ca_topic_score_gemma":0.31299,"teacher_disagreement_score":0.6708761,"about_ca_system_score_codex":0.018594524,"about_ca_system_score_gemma":0.024837617,"threshold_uncertainty_score":0.65441644},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20959249,0.038195137,0.48143333,0.084056154,0.013938212,0.011647103,0.005756306,0.0011520267,0.1542293],"genre_scores_gemma":[0.8611698,0.0033453952,0.094480656,0.018699495,0.002149242,0.013265407,0.002544597,0.0006578345,0.0036874386],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.35319445,0.5056979,0.04303892,0.03331342,0.06112357,0.0036317927],"domain_scores_gemma":[0.13820627,0.6047602,0.041505538,0.14579688,0.06793674,0.0017944169],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6268005,0.001821939,0.0040739765,0.009383632,0.0042589363,0.011620544,0.006141243,0.005134783,0.008104191],"category_scores_gemma":[0.82116324,0.0013622306,0.0050188615,0.011735705,0.0127903195,0.012798168,0.014921993,0.0084376205,0.0013298139],"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":[0.0019906252,0.000665704,0.2831659,0.011098546,0.014358556,0.0008617697,0.03851868,0.0073456597,0.0012008458,0.23345368,0.03810445,0.36923563],"study_design_scores_gemma":[0.00089744676,0.0020664153,0.2759279,0.023343962,0.0057557477,0.0010288949,0.031384446,0.016414246,0.006583712,0.49062276,0.14539704,0.000577501],"about_ca_topic_score_codex":0.013156241,"about_ca_topic_score_gemma":0.011618523,"teacher_disagreement_score":0.6268005,"about_ca_system_score_codex":0.0093760025,"about_ca_system_score_gemma":0.010434599,"threshold_uncertainty_score":0.46022153},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05000588,0.002781208,0.63760465,0.09111087,0.00082570134,0.0007708202,0.00006464371,0.0007264045,0.21610983],"genre_scores_gemma":[0.86407894,0.00076411816,0.12344603,0.0035648588,0.00021969905,0.00085690484,0.000039727514,0.00039274397,0.006636995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79009694,0.14481604,0.010117671,0.011620995,0.037885986,0.0054623596],"domain_scores_gemma":[0.7119609,0.17753115,0.021221288,0.046216074,0.038780358,0.004290233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18215804,0.000946833,0.0017924451,0.0050682705,0.007684204,0.029247569,0.0035524992,0.0044267094,0.0042018467],"category_scores_gemma":[0.30011588,0.0009048432,0.0011382992,0.004463451,0.07757322,0.037815787,0.0152475685,0.0100909015,0.00093312387],"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":[0.000028581548,0.00004458386,0.0013062787,0.00016021139,0.000029194922,0.000044349854,0.013851622,0.0010037106,0.00036016948,0.93021303,0.0012514404,0.051706802],"study_design_scores_gemma":[0.00002763244,0.00003774617,0.00056416733,0.00051460735,0.000018549457,0.000053416246,0.005714875,0.0028410903,0.0016801709,0.96389526,0.02460365,0.00004880587],"about_ca_topic_score_codex":0.0042004865,"about_ca_topic_score_gemma":0.0031312034,"teacher_disagreement_score":0.81784195,"about_ca_system_score_codex":0.017055882,"about_ca_system_score_gemma":0.030438129,"threshold_uncertainty_score":0.9633553},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85141623,0.003122471,0.0019944857,0.08742819,0.0001858926,0.0007241434,0.0000846634,0.000052828935,0.054991007],"genre_scores_gemma":[0.9684144,0.0023488433,0.0034450868,0.0071765557,0.000041357518,0.00032481292,0.000049384933,0.000045035533,0.018154535],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97805107,0.015765112,0.00016316799,0.0003206792,0.0022272735,0.0034727782],"domain_scores_gemma":[0.98353034,0.0054535535,0.0004541201,0.0003280814,0.004972514,0.0052613765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023177432,0.0004069603,0.00041307032,0.00083399523,0.023212515,0.0056534046,0.0018319468,0.0020827022,0.003089075],"category_scores_gemma":[0.012299008,0.0005819854,0.0002727336,0.0017768084,0.009934838,0.0017318849,0.0073804446,0.0048388336,0.00026608183],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003467923,0.0023450532,0.030691365,0.00046333726,0.000049613234,0.0024737646,0.8231285,0.0008800448,0.0016980667,0.021800382,0.028874021,0.08724909],"study_design_scores_gemma":[0.00012463203,0.0006417004,0.0347175,0.0005698895,0.000042261243,0.0003600255,0.75493604,0.0011608927,0.0020046781,0.0028386877,0.20250331,0.0001002904],"about_ca_topic_score_codex":0.5727548,"about_ca_topic_score_gemma":0.8389304,"teacher_disagreement_score":0.96520394,"about_ca_system_score_codex":0.03479605,"about_ca_system_score_gemma":0.111117825,"threshold_uncertainty_score":0.85952264},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087604284,0.11162246,0.382291,0.31211483,0.019929267,0.0039019694,0.009055963,0.0023653316,0.071114905],"genre_scores_gemma":[0.79495716,0.015155312,0.10213218,0.069674335,0.007449848,0.004581311,0.0033969246,0.0006216338,0.0020312865],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.521172,0.38886476,0.023812728,0.023272218,0.03933449,0.003543798],"domain_scores_gemma":[0.19394794,0.66494536,0.029482733,0.084955424,0.024449123,0.0022194094],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43976566,0.003149829,0.009643949,0.008763031,0.002830533,0.015081402,0.0070491415,0.0080744745,0.0069825538],"category_scores_gemma":[0.79860437,0.0014125757,0.009151151,0.008533524,0.017080242,0.02524135,0.009448791,0.014353812,0.0018240989],"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":[0.0026749412,0.0007101773,0.081833765,0.020063782,0.030947432,0.00079770543,0.008842325,0.022436248,0.00062354474,0.23382346,0.093732096,0.5035146],"study_design_scores_gemma":[0.0005440893,0.00091969396,0.026952574,0.011405145,0.004896136,0.0002739973,0.0032780615,0.011867434,0.0009041481,0.89210826,0.04652406,0.0003264615],"about_ca_topic_score_codex":0.0052162916,"about_ca_topic_score_gemma":0.0032502136,"teacher_disagreement_score":0.5602343,"about_ca_system_score_codex":0.0063350545,"about_ca_system_score_gemma":0.005641226,"threshold_uncertainty_score":0.6908687},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3409939,0.010838503,0.5440068,0.009926396,0.00240448,0.004056494,0.05690901,0.0021744918,0.028689938],"genre_scores_gemma":[0.82785326,0.0043687955,0.13238369,0.0010284657,0.00057329657,0.004896394,0.02621856,0.0003087004,0.0023688574],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97081697,0.01707503,0.0036285042,0.0022971057,0.0056665866,0.00051574665],"domain_scores_gemma":[0.8377069,0.13088585,0.014071626,0.0087293545,0.0073965937,0.0012095745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038964372,0.0016563485,0.0012006011,0.0066461097,0.00061194017,0.002838315,0.002073353,0.0020185625,0.005816909],"category_scores_gemma":[0.1582573,0.00043956234,0.0028617124,0.007577754,0.0014119168,0.004866526,0.0028517477,0.0021721006,0.0009760183],"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":[0.002038486,0.0015020808,0.24769534,0.0071282154,0.006459689,0.00082589756,0.0019504981,0.27759483,0.0018362601,0.0840789,0.021736152,0.34715363],"study_design_scores_gemma":[0.00057945674,0.0063768243,0.23004405,0.0049349857,0.0029106745,0.0006702721,0.004582694,0.4374039,0.005198432,0.21407658,0.09256433,0.00065781263],"about_ca_topic_score_codex":0.0055836574,"about_ca_topic_score_gemma":0.0033511033,"teacher_disagreement_score":0.038964372,"about_ca_system_score_codex":0.001563808,"about_ca_system_score_gemma":0.0015464688,"threshold_uncertainty_score":0.20606577},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9129169,0.0022160006,0.0074620172,0.0049346094,0.00010495869,0.0005727283,0.0019331331,0.00038041355,0.06947927],"genre_scores_gemma":[0.97178483,0.0007942636,0.0053294445,0.00028312296,0.000018163684,0.00031530924,0.00064606627,0.000037451417,0.020791339],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98396367,0.004345763,0.0007576781,0.001092134,0.008169932,0.0016709466],"domain_scores_gemma":[0.8897203,0.020249233,0.0061633345,0.002423244,0.07404033,0.007403598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022692617,0.00038487703,0.0007021731,0.003979901,0.0035007063,0.006039991,0.001198533,0.00078111107,0.0073380074],"category_scores_gemma":[0.05299826,0.00035391332,0.00050539826,0.004676295,0.0016745428,0.0020230128,0.0024655377,0.0013266172,0.0012815814],"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":[0.000686819,0.000433268,0.49923405,0.0020838364,0.00035737062,0.00028842062,0.09278247,0.002576022,0.0050528212,0.0062429756,0.02268575,0.36757624],"study_design_scores_gemma":[0.000035524023,0.00040509918,0.9181567,0.0007813244,0.00013007886,0.00004966213,0.03373373,0.0026637814,0.0033760811,0.0005354878,0.040002767,0.00012986195],"about_ca_topic_score_codex":0.7434263,"about_ca_topic_score_gemma":0.8236088,"teacher_disagreement_score":0.9613133,"about_ca_system_score_codex":0.03868668,"about_ca_system_score_gemma":0.055695318,"threshold_uncertainty_score":0.51616937},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750821,0.0011361025,0.001407904,0.0018321421,0.000057233396,0.0001074642,0.00057120004,0.000051838782,0.01975404],"genre_scores_gemma":[0.9933715,0.0004462919,0.0011472862,0.00013513792,0.0000114655995,0.00005155135,0.00014641312,0.000014949854,0.0046753553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9846384,0.00522099,0.0007861919,0.0008955871,0.0064006285,0.0020582587],"domain_scores_gemma":[0.9463713,0.021015273,0.006501089,0.002115451,0.01802913,0.005967737],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013172037,0.00035655315,0.00044534024,0.0024293063,0.0024935687,0.0036259603,0.0007022223,0.0004028977,0.002794487],"category_scores_gemma":[0.028832795,0.0003211321,0.0004071543,0.0036386205,0.0024365506,0.00068380864,0.0021160084,0.00067709555,0.00028455403],"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":[0.000384967,0.000080596445,0.88962793,0.00022219906,0.00019067165,0.00016108293,0.02237899,0.0006141271,0.003320665,0.003453431,0.0015647149,0.078000575],"study_design_scores_gemma":[0.0000126141285,0.00006025312,0.9867063,0.000053363543,0.000023400546,0.000028439745,0.0067062816,0.00021401758,0.00044362815,0.000087022214,0.005643828,0.000020796488],"about_ca_topic_score_codex":0.8570769,"about_ca_topic_score_gemma":0.90011024,"teacher_disagreement_score":0.98682797,"about_ca_system_score_codex":0.020046402,"about_ca_system_score_gemma":0.03929866,"threshold_uncertainty_score":0.2875296},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07956642,0.003311129,0.85212153,0.027025532,0.0005188168,0.0041191913,0.00013936305,0.00077603443,0.03242201],"genre_scores_gemma":[0.48276395,0.00087201095,0.5101307,0.0008876313,0.00007300151,0.0040181708,0.00010664917,0.00009792597,0.0010499537],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3329741,0.59949046,0.016852725,0.011236445,0.036648665,0.0027975435],"domain_scores_gemma":[0.43993556,0.39412552,0.040262826,0.058778897,0.059995495,0.00690165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.40798986,0.0020890387,0.0019294848,0.012190659,0.004958752,0.030963853,0.0075043845,0.007954605,0.0016351116],"category_scores_gemma":[0.4189055,0.0018986091,0.0016451378,0.00652717,0.023573432,0.021668708,0.01603075,0.0069035897,0.000780421],"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":[0.00048001113,0.0027356774,0.031616956,0.0038815683,0.0007464289,0.00032150937,0.20591442,0.015684888,0.0036180227,0.2485241,0.006499796,0.47997668],"study_design_scores_gemma":[0.00063238567,0.0031688476,0.023577388,0.023834828,0.00053807127,0.00078233966,0.17366554,0.09628722,0.016760822,0.5825242,0.07716442,0.0010639753],"about_ca_topic_score_codex":0.0075329645,"about_ca_topic_score_gemma":0.0067358306,"teacher_disagreement_score":0.40798986,"about_ca_system_score_codex":0.018583154,"about_ca_system_score_gemma":0.024713218,"threshold_uncertainty_score":0.7300539},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038683787,0.80605686,0.04355016,0.04644099,0.0029516078,0.006743317,0.006382109,0.000292943,0.048898254],"genre_scores_gemma":[0.34507474,0.5243825,0.10762462,0.0037486036,0.0013610664,0.010456968,0.0042283963,0.00019420781,0.0029290156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.86944133,0.06400537,0.027543532,0.0042793327,0.03269528,0.0020351089],"domain_scores_gemma":[0.5519429,0.37842178,0.022136131,0.006406105,0.039976258,0.0011168574],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.09521055,0.0012518747,0.003084129,0.1240827,0.003492238,0.012254861,0.0025558104,0.003341884,0.004926104],"category_scores_gemma":[0.33643898,0.00085108826,0.0031297912,0.13151099,0.004863513,0.011547901,0.0069177374,0.002033302,0.0004893832],"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":[0.00016202567,0.00007458659,0.006668244,0.26182622,0.0015767252,0.00080842234,0.02632792,0.0018548957,0.0004949675,0.1412887,0.020048216,0.53886914],"study_design_scores_gemma":[0.00007311654,0.0001891241,0.015425949,0.5641637,0.0047738734,0.0011817687,0.029692754,0.0035698256,0.0010040853,0.05418196,0.32550874,0.00023510875],"about_ca_topic_score_codex":0.004876563,"about_ca_topic_score_gemma":0.0061445534,"teacher_disagreement_score":0.8759173,"about_ca_system_score_codex":0.016777316,"about_ca_system_score_gemma":0.029844929,"threshold_uncertainty_score":0.5035275},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87155807,0.00636022,0.0034673836,0.024339741,0.0003735263,0.0003600153,0.0011287561,0.00006664627,0.0923456],"genre_scores_gemma":[0.94829595,0.002914497,0.0021298241,0.0008151656,0.000049059985,0.00011196546,0.0003613862,0.000015589392,0.04530653],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9970552,0.0006807243,0.000116050534,0.00020319001,0.0012617011,0.0006832224],"domain_scores_gemma":[0.98340964,0.0018555893,0.0015255112,0.0003289895,0.008628321,0.004251865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007113995,0.00027523423,0.00034172888,0.0022252917,0.004108987,0.004074042,0.0008412893,0.0005255828,0.013618139],"category_scores_gemma":[0.013260691,0.00013860929,0.00025382632,0.0030830575,0.0023864815,0.002128906,0.0022440688,0.0012308013,0.0007098375],"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":[0.00045569675,0.00026977135,0.38259673,0.0012092906,0.0000668954,0.00048009565,0.073690824,0.0009161764,0.0029522546,0.019279834,0.04430839,0.47377405],"study_design_scores_gemma":[0.000012260813,0.00024060204,0.7734389,0.0011395445,0.000028674742,0.0001089955,0.10575073,0.0007854182,0.00071825087,0.0010735036,0.11663773,0.00006552256],"about_ca_topic_score_codex":0.8516114,"about_ca_topic_score_gemma":0.9494859,"teacher_disagreement_score":0.96176535,"about_ca_system_score_codex":0.03823466,"about_ca_system_score_gemma":0.05961361,"threshold_uncertainty_score":0.29852498},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21108444,0.0054649874,0.38398337,0.06949283,0.0011507685,0.01227984,0.0007557645,0.0016140313,0.31417397],"genre_scores_gemma":[0.75518686,0.0019265041,0.22872911,0.002090316,0.00015686172,0.0036433358,0.00033279718,0.00017536075,0.0077589485],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5901329,0.32213384,0.012210662,0.009417632,0.057396673,0.008708349],"domain_scores_gemma":[0.57639253,0.22445315,0.030223234,0.034270186,0.124291115,0.010369792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2993426,0.001195384,0.0015669372,0.010877309,0.008953199,0.022595655,0.0036960875,0.003213202,0.0045137634],"category_scores_gemma":[0.29250872,0.00082899065,0.00095881236,0.008930207,0.01028586,0.0168721,0.010579699,0.003977775,0.0012504327],"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":[0.00038952485,0.0014111148,0.065131284,0.0016277061,0.00018413369,0.00021949297,0.025710734,0.008542897,0.0020722293,0.19070944,0.01759301,0.68640846],"study_design_scores_gemma":[0.0004623206,0.002888949,0.1260172,0.011168102,0.00037763338,0.00052552496,0.09145222,0.05666984,0.017179457,0.34168693,0.35072628,0.0008455811],"about_ca_topic_score_codex":0.03766097,"about_ca_topic_score_gemma":0.03842037,"teacher_disagreement_score":0.2993426,"about_ca_system_score_codex":0.03251068,"about_ca_system_score_gemma":0.06241012,"threshold_uncertainty_score":0.8640353},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97712916,0.0014396979,0.00064303196,0.0024270322,0.00000977698,0.000022551707,0.00043219118,0.0000106214475,0.01788596],"genre_scores_gemma":[0.99820745,0.0006434253,0.00036424928,0.000060604925,0.000004237372,0.000008904691,0.00015501757,0.0000049714263,0.0005511197],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99949193,0.00015019465,0.000026379386,0.00008438232,0.00011314767,0.0001339942],"domain_scores_gemma":[0.99824214,0.00061860867,0.0004277958,0.00013245105,0.00033429152,0.00024469933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010667157,0.00009809921,0.00016613191,0.005980798,0.0012583517,0.0030207785,0.00034391947,0.00032741288,0.0049108276],"category_scores_gemma":[0.0018940701,0.00012536357,0.00018708628,0.012066114,0.0023704355,0.0022987013,0.002569493,0.00068427314,0.0002279696],"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":[0.000102579026,0.000120886645,0.7389788,0.00050510716,0.00004960861,0.0010365738,0.07376506,0.0011748681,0.0013048227,0.070172586,0.003844319,0.10894482],"study_design_scores_gemma":[0.000005426599,0.00004067338,0.80105513,0.00051078433,0.00002008837,0.00032777415,0.15128405,0.0010917879,0.00023004439,0.007539457,0.037879445,0.000015223076],"about_ca_topic_score_codex":0.021272752,"about_ca_topic_score_gemma":0.044434965,"teacher_disagreement_score":0.021272752,"about_ca_system_score_codex":0.002255126,"about_ca_system_score_gemma":0.0027317214,"threshold_uncertainty_score":0.04229784},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035772707,0.0089531485,0.75144106,0.16563188,0.0029268828,0.0006080988,0.0028752554,0.00046257797,0.031328335],"genre_scores_gemma":[0.78779083,0.00842183,0.16501135,0.019528689,0.006628095,0.0007055689,0.0011031877,0.00013975787,0.010670647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95870453,0.03204394,0.0011704006,0.0038000646,0.003738698,0.00054236193],"domain_scores_gemma":[0.7426005,0.23785214,0.006545755,0.008123883,0.0038052695,0.0010724589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051247805,0.0022798912,0.003511545,0.0039809635,0.0010391299,0.0067887395,0.005291283,0.006411016,0.013780724],"category_scores_gemma":[0.24900588,0.0013317195,0.0028005876,0.0031174081,0.0059263594,0.0059845834,0.0024634863,0.006712041,0.0014304345],"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":[0.0005014194,0.0004563475,0.019956399,0.001605087,0.0033701789,0.0004082512,0.00043244558,0.04793687,0.0005532551,0.7976769,0.014437783,0.11266516],"study_design_scores_gemma":[0.00032324914,0.00015412508,0.0029592894,0.00033012297,0.00083980965,0.000121012024,0.00023879354,0.041462284,0.0006028636,0.9474424,0.0054847114,0.000041388947],"about_ca_topic_score_codex":0.015100402,"about_ca_topic_score_gemma":0.0081555275,"teacher_disagreement_score":0.051247805,"about_ca_system_score_codex":0.0030444304,"about_ca_system_score_gemma":0.0075299065,"threshold_uncertainty_score":0.27102757},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051240223,0.019306187,0.08223766,0.8703664,0.001367495,0.00018187748,0.000118470525,0.00018527181,0.021112598],"genre_scores_gemma":[0.6369303,0.03589148,0.23790637,0.07636204,0.0048166174,0.0012825346,0.00022275401,0.00022512714,0.0063627725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.76537704,0.19377768,0.009752982,0.006165127,0.020257613,0.0046696044],"domain_scores_gemma":[0.28384912,0.6437146,0.014946785,0.017623857,0.03420785,0.0056577874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27021074,0.0021898556,0.0039196797,0.018872255,0.012658445,0.03930761,0.005674717,0.034236453,0.008737955],"category_scores_gemma":[0.41788834,0.0021238958,0.0023096732,0.014837252,0.04155343,0.04628548,0.017034551,0.024458721,0.0011663979],"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":[0.00010509314,0.0003619769,0.0047752396,0.0025112068,0.00027369638,0.00010914211,0.0066433107,0.01040726,0.00014811197,0.7850454,0.02794122,0.16167837],"study_design_scores_gemma":[0.000038772865,0.000025934976,0.0008753018,0.0029213717,0.00007598211,0.000019497897,0.0021673816,0.0046239304,0.00026149396,0.9700447,0.018884702,0.00006090609],"about_ca_topic_score_codex":0.028563244,"about_ca_topic_score_gemma":0.042265814,"teacher_disagreement_score":0.27021074,"about_ca_system_score_codex":0.036312852,"about_ca_system_score_gemma":0.111919805,"threshold_uncertainty_score":0.8999601},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917903,0.0011052106,0.00017164827,0.0005819959,0.00004851971,0.0000668203,0.00082067336,0.000011263793,0.005403587],"genre_scores_gemma":[0.98180455,0.0022421416,0.00048434394,0.0003448389,0.00002366189,0.00009732399,0.0012528873,0.00001408608,0.013736185],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977665,0.00031950237,0.00010167141,0.00014643252,0.0011138921,0.00055202324],"domain_scores_gemma":[0.9876637,0.0005435178,0.0010914161,0.00015171124,0.009286956,0.0012625899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033583543,0.00043013887,0.0004621333,0.0017129685,0.0048730006,0.0028146787,0.00069947843,0.0005021067,0.0023613384],"category_scores_gemma":[0.007712682,0.00021403363,0.00047338815,0.0027484978,0.001393947,0.0005215796,0.0014653249,0.0008182197,0.00035322603],"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":[0.00019011003,0.0000776866,0.87847555,0.00022810747,0.00007788578,0.0002565322,0.06621983,0.0001572193,0.0007729492,0.00034402573,0.0038808957,0.04931909],"study_design_scores_gemma":[0.000005487921,0.00012728134,0.9077254,0.00017609756,0.000045556575,0.00007591622,0.07724098,0.00012990973,0.00036757262,0.00004105697,0.014012943,0.000051760686],"about_ca_topic_score_codex":0.95621204,"about_ca_topic_score_gemma":0.9755916,"teacher_disagreement_score":0.043787956,"about_ca_system_score_codex":0.014468746,"about_ca_system_score_gemma":0.03286171,"threshold_uncertainty_score":0.10497856},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029466231,0.06428065,0.08439565,0.04299164,0.0015253546,0.0009106553,0.00028243265,0.00029572434,0.8023714],"genre_scores_gemma":[0.2260483,0.1993684,0.15765408,0.04173803,0.0035843814,0.0041283327,0.0005926956,0.00067065045,0.36621517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9840925,0.009549385,0.0005919249,0.00056417135,0.004774249,0.0004277075],"domain_scores_gemma":[0.97167283,0.024120636,0.00087917777,0.0009907427,0.0019989186,0.00033773048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01590678,0.0009434479,0.0010313705,0.0036144278,0.0017780209,0.0058306083,0.0010680391,0.002635513,0.025881615],"category_scores_gemma":[0.030224858,0.00045019903,0.0007272433,0.0032569803,0.006695984,0.0068648574,0.0046110405,0.0039198995,0.0028159034],"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":[0.000024714747,0.00010329296,0.00041805275,0.0010063024,0.000022904102,0.00009892171,0.0009097933,0.0016391475,0.00014120775,0.703337,0.06286319,0.22943541],"study_design_scores_gemma":[0.000029642999,0.00015647848,0.0014279799,0.00423704,0.00004698143,0.00030202774,0.0010633988,0.0014030673,0.0009793695,0.5408567,0.44945043,0.00004689213],"about_ca_topic_score_codex":0.0033180034,"about_ca_topic_score_gemma":0.0047316514,"teacher_disagreement_score":0.025881615,"about_ca_system_score_codex":0.006016383,"about_ca_system_score_gemma":0.0070732804,"threshold_uncertainty_score":0.08658266},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069735227,0.024045032,0.06377264,0.7517403,0.00524179,0.0002984246,0.00031692375,0.00037642193,0.14723495],"genre_scores_gemma":[0.70458215,0.04671171,0.13245003,0.08154664,0.011214095,0.0011345185,0.0005813273,0.00040520538,0.021374278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79043645,0.15320554,0.008786019,0.006045102,0.03598674,0.005540118],"domain_scores_gemma":[0.5151402,0.397619,0.017340336,0.021571433,0.041085664,0.007243315],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.15373638,0.0017126993,0.002702929,0.0092663495,0.0070640864,0.024338607,0.003670388,0.023305124,0.0129433945],"category_scores_gemma":[0.421403,0.0011471857,0.0012794336,0.01061753,0.026369428,0.01678044,0.011615419,0.017965132,0.0029715637],"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":[0.00009003906,0.000113103706,0.0010493835,0.0012535299,0.00014429356,0.00016525346,0.003457195,0.0069505908,0.00013092998,0.84223837,0.05608944,0.08831787],"study_design_scores_gemma":[0.00005569651,0.000019620013,0.00040633613,0.0012681128,0.000039961207,0.000025953208,0.0007549473,0.0019061371,0.00020394399,0.9141213,0.08115984,0.00003812383],"about_ca_topic_score_codex":0.01034156,"about_ca_topic_score_gemma":0.008145436,"teacher_disagreement_score":0.9929359,"about_ca_system_score_codex":0.022288036,"about_ca_system_score_gemma":0.044823356,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040523767,0.0035947931,0.7536959,0.015543854,0.00046847577,0.0017820558,0.0011760409,0.0016247126,0.1815904],"genre_scores_gemma":[0.48525918,0.003854579,0.49777845,0.0012324486,0.0002600748,0.0028491912,0.0010604955,0.00045695287,0.0072486443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86409295,0.096331045,0.008995543,0.006731015,0.01968725,0.0041621896],"domain_scores_gemma":[0.90221363,0.049192384,0.016782718,0.010206643,0.019258885,0.0023458896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09399619,0.0021407502,0.0018972298,0.015461738,0.004027989,0.030279849,0.0031444363,0.0045815757,0.0027356057],"category_scores_gemma":[0.14600712,0.0012568149,0.0009145845,0.024318527,0.011846444,0.027323747,0.009407869,0.004845768,0.0019740644],"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":[0.00016003738,0.000277978,0.013065005,0.0009659086,0.000066046974,0.00007107646,0.005044113,0.017791154,0.0009011273,0.6615655,0.009520933,0.2905711],"study_design_scores_gemma":[0.000100809964,0.00057293463,0.019813621,0.0029542171,0.00011007815,0.00013792129,0.014302129,0.04844836,0.009662383,0.79314023,0.11030637,0.00045097107],"about_ca_topic_score_codex":0.012130439,"about_ca_topic_score_gemma":0.007842224,"teacher_disagreement_score":0.09399619,"about_ca_system_score_codex":0.016135257,"about_ca_system_score_gemma":0.021475662,"threshold_uncertainty_score":0.4971053},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17853764,0.0018863372,0.51024455,0.18160868,0.0015338175,0.0009931751,0.00027890634,0.0023206891,0.12259614],"genre_scores_gemma":[0.83393335,0.0006352757,0.15462793,0.0044894745,0.00021594262,0.00039938648,0.00014267438,0.00018957374,0.005366415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97506297,0.017844353,0.0007265842,0.0008899978,0.004311301,0.0011647331],"domain_scores_gemma":[0.8556269,0.103607595,0.010187318,0.01539077,0.013073516,0.002113912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023893526,0.00068315887,0.00056840957,0.002828379,0.0019960857,0.0075609935,0.002149334,0.005577156,0.006293026],"category_scores_gemma":[0.141194,0.00053498603,0.0007234073,0.0011197932,0.006144917,0.0153914355,0.0036976102,0.0032371322,0.0010395374],"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":[0.00019983457,0.0007572105,0.018035911,0.00078924024,0.00019996191,0.00046451943,0.017039707,0.00551696,0.0018863628,0.7185934,0.020910863,0.21560602],"study_design_scores_gemma":[0.00014536745,0.00010363125,0.0032715306,0.00069397537,0.00013688592,0.00017178037,0.00638219,0.01302522,0.0037949423,0.9265948,0.045588996,0.00009082186],"about_ca_topic_score_codex":0.002367162,"about_ca_topic_score_gemma":0.003895106,"teacher_disagreement_score":0.023893526,"about_ca_system_score_codex":0.0025250656,"about_ca_system_score_gemma":0.005851766,"threshold_uncertainty_score":0.1263625},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8544783,0.0026578219,0.0030992455,0.010975693,0.000089032335,0.0004209613,0.008615997,0.00026447524,0.119398616],"genre_scores_gemma":[0.98865896,0.0010757247,0.0023014378,0.00027938347,0.0000144697715,0.000074900454,0.0016073685,0.000024969902,0.005962728],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.988576,0.001454297,0.0004198429,0.00046605075,0.0072365254,0.0018471864],"domain_scores_gemma":[0.98123115,0.001457274,0.002001945,0.00037300854,0.012306431,0.0026302047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049495073,0.00045173653,0.00043274905,0.0070825256,0.0054515777,0.0068245786,0.0013756977,0.00055493804,0.0019966606],"category_scores_gemma":[0.018266471,0.00022827172,0.00029931628,0.018453704,0.003159683,0.0012666887,0.0024420181,0.001164144,0.00032442872],"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":[0.0003819845,0.0003627693,0.58683145,0.0007672663,0.00018970699,0.00034564358,0.012008126,0.011149266,0.0015485007,0.037078,0.036626566,0.31271067],"study_design_scores_gemma":[0.000037833903,0.00025023916,0.92685264,0.00040022176,0.000077589786,0.000058270674,0.017089358,0.006000691,0.0020544,0.0039031606,0.043150496,0.00012499407],"about_ca_topic_score_codex":0.99258786,"about_ca_topic_score_gemma":0.99372476,"teacher_disagreement_score":0.9950505,"about_ca_system_score_codex":0.1267142,"about_ca_system_score_gemma":0.2152015,"threshold_uncertainty_score":0.9193802},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041328233,0.0046761343,0.44209218,0.22879271,0.0015253553,0.0006811601,0.00016701208,0.0006320866,0.28010508],"genre_scores_gemma":[0.891447,0.002114432,0.08798244,0.00738138,0.0006719775,0.0007272797,0.000068972244,0.00031310925,0.009293391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.83438265,0.12530126,0.006890634,0.008064339,0.021917876,0.003443207],"domain_scores_gemma":[0.7086424,0.1825811,0.02166544,0.04731501,0.032840572,0.0069554793],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12825382,0.0010548579,0.0012158939,0.0054021147,0.006960644,0.033067953,0.0046678977,0.010130464,0.005000329],"category_scores_gemma":[0.23422304,0.0012282511,0.00092166936,0.005104991,0.055974327,0.032930188,0.015698705,0.011696834,0.0011800409],"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":[0.000025981522,0.00013460545,0.0027308397,0.00025827554,0.0000508678,0.00007478958,0.019597797,0.002160749,0.00048150538,0.8942661,0.0027428903,0.07747538],"study_design_scores_gemma":[0.000013645751,0.000027066093,0.0011412168,0.00040409053,0.00001451176,0.00004123215,0.005368215,0.0021686715,0.00063569704,0.95501,0.035125267,0.00005034886],"about_ca_topic_score_codex":0.0050651454,"about_ca_topic_score_gemma":0.004580845,"teacher_disagreement_score":0.8717462,"about_ca_system_score_codex":0.010576655,"about_ca_system_score_gemma":0.0366083,"threshold_uncertainty_score":0.67827916},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5389609,0.0012764405,0.22462559,0.042353027,0.00018415457,0.0021925701,0.0001542558,0.00024393189,0.19000913],"genre_scores_gemma":[0.9691798,0.0002947545,0.026962036,0.00069429906,0.000022240782,0.0005485972,0.000029186456,0.000030401634,0.0022385623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98010445,0.014797031,0.0005941331,0.001030354,0.0020473718,0.0014267295],"domain_scores_gemma":[0.97364646,0.01687047,0.0034474577,0.0007533793,0.003155926,0.0021263915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025201475,0.0008606087,0.00049346266,0.0044972333,0.0037879848,0.009336975,0.0015803733,0.0029184863,0.0029744953],"category_scores_gemma":[0.02727286,0.0006793814,0.001241202,0.002369786,0.011792642,0.012114011,0.0047962638,0.0029903373,0.0005714957],"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":[0.0002249651,0.000910101,0.074539825,0.0006042282,0.00008196882,0.00066165515,0.10382483,0.0027170505,0.0012508418,0.7609497,0.0022640252,0.051970873],"study_design_scores_gemma":[0.00018140455,0.00074642967,0.055358563,0.0016821872,0.00019202927,0.0012335987,0.15697737,0.06209501,0.001989208,0.6694768,0.049837522,0.0002299182],"about_ca_topic_score_codex":0.0026257532,"about_ca_topic_score_gemma":0.0032321957,"teacher_disagreement_score":0.025201475,"about_ca_system_score_codex":0.006133341,"about_ca_system_score_gemma":0.008399046,"threshold_uncertainty_score":0.13327968},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039736137,0.039243374,0.11565102,0.75860125,0.007649695,0.007538866,0.0006392297,0.0004796766,0.030460812],"genre_scores_gemma":[0.44099903,0.02977952,0.34272304,0.14941128,0.004838013,0.02593873,0.0005959104,0.00082299253,0.0048914305],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.14337842,0.7827358,0.02484602,0.00777484,0.03584044,0.005424469],"domain_scores_gemma":[0.094154015,0.7384558,0.028094932,0.03923291,0.08371227,0.016350059],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.7069043,0.0011980097,0.0036361178,0.0067862286,0.018425845,0.041282073,0.009832836,0.008209305,0.0052892356],"category_scores_gemma":[0.6823929,0.0020772535,0.0022763947,0.007247086,0.041052125,0.04156986,0.022864334,0.021901233,0.0019831492],"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":[0.0007768139,0.0008943947,0.018991718,0.022465207,0.00069037155,0.0014489243,0.27986854,0.002643227,0.0016135833,0.12987904,0.13503312,0.4056951],"study_design_scores_gemma":[0.00029229067,0.0009549138,0.010758026,0.0558936,0.00025128067,0.0011380964,0.24031036,0.0027345838,0.0016669993,0.21629974,0.46914646,0.00055367907],"about_ca_topic_score_codex":0.0094104735,"about_ca_topic_score_gemma":0.017364124,"teacher_disagreement_score":0.7069043,"about_ca_system_score_codex":0.03535559,"about_ca_system_score_gemma":0.11529088,"threshold_uncertainty_score":0.36143923},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035949876,0.4260241,0.0735167,0.028212406,0.008635558,0.0017057286,0.24816848,0.00785614,0.2022859],"genre_scores_gemma":[0.044664044,0.41792935,0.18087411,0.0070716636,0.003923518,0.005122105,0.16795222,0.0038163906,0.16864653],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925241,0.001657352,0.000968638,0.00037324667,0.0041101035,0.00036654723],"domain_scores_gemma":[0.9751218,0.010703628,0.0017224202,0.0016504828,0.0102817705,0.00051996345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011810333,0.0019672436,0.0019409567,0.010897721,0.0011092394,0.0045264824,0.0030345211,0.0014320688,0.051691905],"category_scores_gemma":[0.033603493,0.0016739165,0.001190127,0.023565834,0.0017899487,0.0038051014,0.0019690346,0.003057151,0.014039139],"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":[0.000021213054,0.00004437227,0.0020016877,0.0009430713,0.000027050992,0.000018752566,0.00022689663,0.00038419775,0.000082111896,0.006327338,0.76907897,0.22084434],"study_design_scores_gemma":[0.000015571055,0.000028535846,0.018479573,0.0031017861,0.000039930426,0.00010183501,0.00051112915,0.00035959636,0.0003306244,0.007216021,0.96975684,0.000058608854],"about_ca_topic_score_codex":0.34812713,"about_ca_topic_score_gemma":0.3345986,"teacher_disagreement_score":0.34812713,"about_ca_system_score_codex":0.007917929,"about_ca_system_score_gemma":0.025453955,"threshold_uncertainty_score":0.6922016},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6627247,0.024750862,0.06012649,0.114088036,0.0026618561,0.0044202204,0.044094928,0.00061954226,0.08651341],"genre_scores_gemma":[0.9075201,0.005996785,0.061787203,0.007320856,0.00053362735,0.003393029,0.008742012,0.00011570576,0.0045904946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9677376,0.021122824,0.0027690865,0.0007845898,0.0071046236,0.0004812524],"domain_scores_gemma":[0.8232799,0.12658136,0.012691203,0.0076326323,0.02575048,0.0040644375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05778017,0.00042143563,0.00101803,0.002996586,0.00095129036,0.0031055238,0.0018601578,0.0017247465,0.0030033546],"category_scores_gemma":[0.1528356,0.0003710717,0.00075780984,0.0051518874,0.001476963,0.001974224,0.002559893,0.0023096455,0.0008215095],"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":[0.0006926759,0.00027599002,0.6530676,0.0010297598,0.00044675005,0.0001727865,0.0051833065,0.0008816427,0.0003679981,0.015613917,0.06796236,0.2543052],"study_design_scores_gemma":[0.00022208787,0.00058344466,0.89635146,0.003449455,0.0004051867,0.0004079248,0.01205147,0.006422882,0.0009343999,0.021748273,0.057239942,0.00018349064],"about_ca_topic_score_codex":0.04943415,"about_ca_topic_score_gemma":0.07654389,"teacher_disagreement_score":0.94221985,"about_ca_system_score_codex":0.0018197777,"about_ca_system_score_gemma":0.0058881175,"threshold_uncertainty_score":0.30557436},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023450425,0.17336556,0.0098981885,0.7824641,0.009506638,0.000023162944,0.000052220454,0.00004410591,0.022300977],"genre_scores_gemma":[0.40104368,0.19197239,0.021447789,0.22074944,0.15681751,0.00033663938,0.00018454164,0.00049359625,0.0069544967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8806687,0.077484086,0.00648646,0.009169436,0.023099275,0.0030920818],"domain_scores_gemma":[0.6413171,0.3202227,0.006205114,0.008485709,0.01691627,0.00685302],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17284851,0.0018588566,0.0056743696,0.008888734,0.0129158385,0.05031483,0.007679293,0.05609922,0.008191857],"category_scores_gemma":[0.19513486,0.0012218945,0.0018857223,0.0077984734,0.09157774,0.09205031,0.016231293,0.048373505,0.0018906639],"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":[0.000054864056,0.000048399997,0.00011952115,0.00042762028,0.00003619721,0.000049719172,0.0025730198,0.00035404,0.00006123645,0.9423901,0.017667444,0.036217783],"study_design_scores_gemma":[0.000030165695,0.00002835005,0.000096204334,0.0014827113,0.000013752139,0.00003335874,0.0027121245,0.00031035242,0.00006404545,0.9327452,0.062456578,0.000027120052],"about_ca_topic_score_codex":0.0036772022,"about_ca_topic_score_gemma":0.0021929825,"teacher_disagreement_score":0.8271515,"about_ca_system_score_codex":0.016138224,"about_ca_system_score_gemma":0.015822245,"threshold_uncertainty_score":0.9141212},"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":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02335271,0.0012285201,0.8052289,0.012058854,0.0002517642,0.00030922375,0.00017445852,0.00031622968,0.1570794],"genre_scores_gemma":[0.72309333,0.00063465995,0.26881808,0.00084634114,0.00018146378,0.00069936976,0.00015916587,0.00023586919,0.005331684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97409976,0.01369618,0.0013344827,0.0026514137,0.005563437,0.0026548447],"domain_scores_gemma":[0.97794926,0.009943187,0.0019699587,0.0054766233,0.0031607822,0.0015002328],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027436068,0.0020440454,0.002216939,0.007263857,0.0056907507,0.020411346,0.009073167,0.00620809,0.009713796],"category_scores_gemma":[0.038187608,0.0016953609,0.0027633314,0.0060744984,0.03305568,0.024605343,0.013579167,0.007292757,0.0010968524],"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":[0.0000046586765,0.000007551711,0.000060159364,0.00001801895,0.000009279148,0.000011510131,0.00033534638,0.00078063225,0.00003759062,0.9966612,0.00016522186,0.0019088392],"study_design_scores_gemma":[0.000010550898,0.000010176265,0.00009176431,0.000057542995,0.000013421044,0.000022682436,0.00034766647,0.0034133422,0.00010193229,0.9931566,0.002759035,0.000015189714],"about_ca_topic_score_codex":0.0056063747,"about_ca_topic_score_gemma":0.0057501076,"teacher_disagreement_score":0.9725639,"about_ca_system_score_codex":0.008908755,"about_ca_system_score_gemma":0.01204114,"threshold_uncertainty_score":0.1450975},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038040052,0.010276786,0.0020761846,0.8040058,0.021808503,0.000015730628,0.00007224353,0.00006621111,0.15787455],"genre_scores_gemma":[0.3155608,0.03693025,0.012804174,0.4058003,0.043534435,0.00010930589,0.00035972826,0.0003924711,0.1845086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884769,0.005655498,0.00032134916,0.000633644,0.0035018816,0.0014107712],"domain_scores_gemma":[0.98501915,0.0061458307,0.0007166852,0.0010270253,0.0038400765,0.0032512913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015341617,0.0006467766,0.00048373608,0.0016679371,0.006793004,0.027672702,0.0018499197,0.008451091,0.021765927],"category_scores_gemma":[0.016970651,0.00028385007,0.0006954525,0.0020654916,0.01709804,0.0155732855,0.007614685,0.016487224,0.0030275758],"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":[0.00001871478,0.00006180388,0.000745825,0.00015897705,0.000008352982,0.0003536729,0.007171637,0.00011408309,0.0002553865,0.5264292,0.4092592,0.055423178],"study_design_scores_gemma":[0.0000036649994,0.000009700355,0.00041708257,0.0002832338,0.000004874125,0.00014617942,0.01247004,0.000075362266,0.00012262135,0.10101405,0.8854402,0.000013049259],"about_ca_topic_score_codex":0.0054841926,"about_ca_topic_score_gemma":0.010338593,"teacher_disagreement_score":0.027672702,"about_ca_system_score_codex":0.0061054938,"about_ca_system_score_gemma":0.013608587,"threshold_uncertainty_score":0.08113521},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0700561,0.013285615,0.008776679,0.58811116,0.008725758,0.000041132327,0.00016500715,0.00015273188,0.31068572],"genre_scores_gemma":[0.61067384,0.0088732345,0.004634839,0.030074105,0.003249288,0.00011801596,0.00018104727,0.00026339715,0.34193227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9864275,0.0071431897,0.00035358284,0.0012924115,0.0030751303,0.0017082014],"domain_scores_gemma":[0.9917367,0.0035976907,0.00081252505,0.00046629002,0.0021065932,0.0012800684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012544801,0.0006541905,0.0005401161,0.00095530495,0.007846469,0.015898945,0.0016845842,0.006756846,0.01634117],"category_scores_gemma":[0.030280942,0.00040106045,0.00059281336,0.0016427869,0.014356956,0.017025873,0.0041349675,0.008629317,0.0035480978],"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":[0.0001089809,0.00007075344,0.002525053,0.000098986566,0.000014838833,0.0003923468,0.02549953,0.00045486036,0.00036592095,0.8632743,0.05888124,0.048313152],"study_design_scores_gemma":[0.00003025703,0.000042007166,0.00296994,0.00025836378,0.000009764179,0.00038504534,0.032418862,0.00034590904,0.00065694225,0.07184661,0.8909932,0.00004305829],"about_ca_topic_score_codex":0.04439731,"about_ca_topic_score_gemma":0.038432617,"teacher_disagreement_score":0.04439731,"about_ca_system_score_codex":0.011675515,"about_ca_system_score_gemma":0.008922357,"threshold_uncertainty_score":0.08827776},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7787235,0.0004271353,0.0019421539,0.19222458,0.0008557102,0.0003453788,0.000071192204,0.000067711,0.025342656],"genre_scores_gemma":[0.9802142,0.00021281351,0.0014300874,0.011270472,0.000053834832,0.000050754865,0.000020053225,0.00004306852,0.006704743],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96061665,0.014788654,0.0010485256,0.0016825789,0.009361356,0.012502274],"domain_scores_gemma":[0.886342,0.045841232,0.0070470837,0.0028739874,0.022437787,0.0354579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027129851,0.0004683013,0.0005747243,0.0014406061,0.055146016,0.012526173,0.0047666775,0.0120435795,0.0035988002],"category_scores_gemma":[0.083860345,0.00075690553,0.0008153714,0.002270675,0.020281762,0.003118463,0.0074882316,0.019292247,0.00026075938],"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":[0.00019740281,0.00069500704,0.054933067,0.00024633194,0.000086951506,0.020330533,0.7620188,0.0014000124,0.0019051466,0.041031085,0.06232038,0.05483527],"study_design_scores_gemma":[0.00003161503,0.00014833383,0.01623164,0.00031744476,0.000037897065,0.0010180917,0.890501,0.0012435626,0.00076869375,0.0031877365,0.086379595,0.00013430053],"about_ca_topic_score_codex":0.88433397,"about_ca_topic_score_gemma":0.9423028,"teacher_disagreement_score":0.89546114,"about_ca_system_score_codex":0.10453886,"about_ca_system_score_gemma":0.34464863,"threshold_uncertainty_score":0.75848603},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08494525,0.0024282369,0.85445833,0.016151091,0.00044596757,0.0074740094,0.00039755684,0.00028639045,0.033413157],"genre_scores_gemma":[0.43661302,0.0010834893,0.5515522,0.0013961868,0.00011765647,0.007830136,0.00018104196,0.00011310014,0.0011132873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7846592,0.17346656,0.010563878,0.0068056993,0.022704603,0.0018000156],"domain_scores_gemma":[0.6348695,0.28595644,0.022346733,0.028061245,0.025787639,0.0029784548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15616217,0.001847768,0.0018954589,0.009223294,0.0035333,0.013299501,0.0038399529,0.0026106788,0.0041054175],"category_scores_gemma":[0.29115543,0.001000342,0.0024406558,0.0052839173,0.02298707,0.014636396,0.011146415,0.005342805,0.00048378584],"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":[0.000599892,0.00075850956,0.02914615,0.006601638,0.000626312,0.0002083437,0.04721341,0.009097085,0.0022351092,0.37062302,0.0032310646,0.52965945],"study_design_scores_gemma":[0.00040830032,0.0026340275,0.035234075,0.007481984,0.0008705805,0.0005907204,0.024294883,0.03200957,0.013049664,0.811477,0.071490705,0.00045840553],"about_ca_topic_score_codex":0.0037683162,"about_ca_topic_score_gemma":0.0050275745,"teacher_disagreement_score":0.15616217,"about_ca_system_score_codex":0.015615324,"about_ca_system_score_gemma":0.015133855,"threshold_uncertainty_score":0.8258744},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25782782,0.002680383,0.3678417,0.02573195,0.0017588761,0.0024598923,0.00021399783,0.0046855393,0.33679995],"genre_scores_gemma":[0.65897983,0.0014113571,0.2905909,0.003522701,0.00027523213,0.0017626375,0.0002544697,0.00041291633,0.042789947],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9867191,0.009435653,0.0002476649,0.0006687084,0.0019500931,0.0009787746],"domain_scores_gemma":[0.98097414,0.0098058535,0.00047764304,0.0017142419,0.0021680228,0.0048602135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01776916,0.00056178897,0.0004216153,0.0010127549,0.0029769423,0.007847267,0.0033610046,0.0018040875,0.006796791],"category_scores_gemma":[0.01873977,0.00035177096,0.00040883914,0.0005490745,0.003602461,0.0032528949,0.0116412975,0.0036468117,0.0019369483],"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":[0.00046755985,0.00547055,0.0041021295,0.00069872977,0.000037358084,0.0008864404,0.0530769,0.0028055143,0.0060296603,0.046020027,0.06133261,0.8190725],"study_design_scores_gemma":[0.0003842564,0.0017807572,0.007327276,0.0017865775,0.000033722186,0.0017197698,0.06098057,0.011238296,0.010047375,0.09651721,0.8079672,0.0002170409],"about_ca_topic_score_codex":0.0022129978,"about_ca_topic_score_gemma":0.008233676,"teacher_disagreement_score":0.01776916,"about_ca_system_score_codex":0.0025047662,"about_ca_system_score_gemma":0.008320349,"threshold_uncertainty_score":0.0939734},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9444177,0.0005854671,0.0086549735,0.010254127,0.0006818716,0.0003743487,0.00019027971,0.00018439816,0.034656793],"genre_scores_gemma":[0.97783846,0.0004234712,0.003167086,0.0014450266,0.00009912923,0.00014311889,0.00009149709,0.000113931004,0.016678495],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99468756,0.0027758633,0.00021371768,0.00038518172,0.0011291419,0.000808502],"domain_scores_gemma":[0.98323405,0.009272991,0.0010825536,0.0006171947,0.0026049998,0.0031882154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058139204,0.00072828284,0.00051001454,0.00078320404,0.0058520352,0.00653445,0.0014809896,0.002437681,0.0053079864],"category_scores_gemma":[0.029814657,0.00028180776,0.00040316337,0.0005781612,0.0037382815,0.0029360545,0.0050369236,0.004388941,0.001327318],"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":[0.00030887016,0.0010059677,0.012210148,0.00032367234,0.000032221556,0.0028063834,0.8575455,0.0004780835,0.005802987,0.0051850462,0.02392954,0.090371504],"study_design_scores_gemma":[0.000041599258,0.001451736,0.016428374,0.00062572566,0.00004986729,0.0021832515,0.82342124,0.0010369807,0.010418433,0.0028627026,0.14128989,0.00019010658],"about_ca_topic_score_codex":0.004120427,"about_ca_topic_score_gemma":0.008698407,"teacher_disagreement_score":0.00653445,"about_ca_system_score_codex":0.0035238303,"about_ca_system_score_gemma":0.0028191106,"threshold_uncertainty_score":0.030747354},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06854765,0.022709467,0.19795261,0.26962888,0.008259231,0.00040421542,0.000108418935,0.0008979391,0.4314916],"genre_scores_gemma":[0.8432249,0.010915277,0.085827425,0.020674594,0.0018503558,0.0006315494,0.00007685311,0.0006718271,0.036127143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9610808,0.03160464,0.0011234322,0.0009990297,0.0043529617,0.0008391144],"domain_scores_gemma":[0.8829892,0.087447256,0.0035903812,0.010478258,0.011970289,0.0035245453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042428873,0.00057621865,0.0007754272,0.0026240044,0.0047661006,0.019977702,0.0021633592,0.0027990323,0.0065650637],"category_scores_gemma":[0.12766387,0.00043875774,0.00039091418,0.0015779239,0.037785105,0.019247193,0.011008373,0.0074477103,0.0016083813],"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":[0.000040928535,0.00014870631,0.0013518492,0.00053329254,0.000012120498,0.00026991332,0.092465356,0.00045752904,0.00039263055,0.68025875,0.027919576,0.19614944],"study_design_scores_gemma":[0.000030798714,0.00015282638,0.0013512095,0.005047262,0.000025260266,0.00048529782,0.06163423,0.0010735567,0.001446315,0.4970422,0.43164206,0.000069064474],"about_ca_topic_score_codex":0.0031529013,"about_ca_topic_score_gemma":0.0067550186,"teacher_disagreement_score":0.042428873,"about_ca_system_score_codex":0.009889236,"about_ca_system_score_gemma":0.010890041,"threshold_uncertainty_score":0.22438794},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048184413,0.0011576568,0.9039151,0.0027149522,0.00065612904,0.014083463,0.00014361227,0.00062424666,0.028520435],"genre_scores_gemma":[0.19734307,0.0003518197,0.78813136,0.0003943382,0.00010693456,0.010974065,0.00007165648,0.00008949026,0.0025371236],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6149786,0.3411847,0.011413343,0.0069251987,0.02399255,0.0015055169],"domain_scores_gemma":[0.59536827,0.2741047,0.020844083,0.047053628,0.057493087,0.0051361625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.22941281,0.0011357204,0.0010512763,0.0028675403,0.003295389,0.0074767694,0.003949089,0.002280707,0.005639892],"category_scores_gemma":[0.31646207,0.00078332087,0.0011719185,0.0013747162,0.0054049133,0.0068122596,0.0074272477,0.003030519,0.0011811564],"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":[0.0011001033,0.00178609,0.006713759,0.0036724252,0.00031019057,0.0002722544,0.026099335,0.0103352,0.004783177,0.1818735,0.0113614425,0.75169253],"study_design_scores_gemma":[0.0036213973,0.013729758,0.010986412,0.00991104,0.00070397014,0.0011162505,0.021654174,0.07528019,0.03983303,0.41628528,0.4061023,0.00077616086],"about_ca_topic_score_codex":0.0006546105,"about_ca_topic_score_gemma":0.0011671942,"teacher_disagreement_score":0.22941281,"about_ca_system_score_codex":0.004629832,"about_ca_system_score_gemma":0.009658656,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037265696,0.020479424,0.48499098,0.21084575,0.0049463953,0.00077923137,0.000043343607,0.0007652915,0.23988383],"genre_scores_gemma":[0.8079251,0.0071850354,0.15926468,0.012312742,0.0014117523,0.0009012195,0.000024718316,0.0005277198,0.0104471035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8547837,0.12749995,0.003077077,0.0029063027,0.0094314385,0.002301413],"domain_scores_gemma":[0.68980986,0.2729781,0.004736535,0.010767686,0.016720809,0.0049869227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10646729,0.00082091097,0.00077841117,0.003583485,0.008360553,0.02454098,0.0029317746,0.0027823125,0.0043221344],"category_scores_gemma":[0.115719214,0.00070632144,0.00072945154,0.0018855849,0.04747445,0.013765153,0.009282039,0.015705138,0.00072377484],"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":[0.00009195503,0.00025671592,0.0015476807,0.0009937908,0.000033472475,0.00027994587,0.15851244,0.0014385957,0.0007847129,0.634097,0.014985537,0.18697818],"study_design_scores_gemma":[0.00006704145,0.00020680769,0.0011519834,0.004539677,0.00003299183,0.00053420983,0.07666662,0.005637053,0.0035376912,0.62132496,0.28617054,0.000130483],"about_ca_topic_score_codex":0.0041993894,"about_ca_topic_score_gemma":0.004984005,"teacher_disagreement_score":0.10646729,"about_ca_system_score_codex":0.014802366,"about_ca_system_score_gemma":0.017315382,"threshold_uncertainty_score":0.56305957},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8111172,0.011469858,0.013743322,0.03385582,0.0009666284,0.0011930547,0.0009929317,0.00041697614,0.12624425],"genre_scores_gemma":[0.94546735,0.0045640995,0.012150081,0.002305855,0.00014009431,0.0005539451,0.00029325247,0.00010554753,0.034419708],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.987721,0.0067663398,0.00042927556,0.0006100538,0.0034122043,0.001061115],"domain_scores_gemma":[0.9737273,0.016101204,0.0020824922,0.0007829928,0.0052802823,0.0020257833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012702617,0.0005036722,0.00070567016,0.0008097482,0.0017431504,0.0026114986,0.0008507067,0.00135129,0.014451751],"category_scores_gemma":[0.0326894,0.0002121354,0.0008202474,0.0010448721,0.0014466728,0.0011419904,0.0020226606,0.0018379433,0.0017342237],"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":[0.0033424722,0.0029448112,0.046486385,0.0060829334,0.0006152266,0.0003963967,0.020921681,0.0046372497,0.009234444,0.009265716,0.015918542,0.88015413],"study_design_scores_gemma":[0.00106181,0.017926546,0.65164137,0.00798097,0.0017140101,0.00049525325,0.04160109,0.0041651023,0.01707802,0.010735918,0.2452357,0.00036419014],"about_ca_topic_score_codex":0.09088088,"about_ca_topic_score_gemma":0.1847053,"teacher_disagreement_score":0.09088088,"about_ca_system_score_codex":0.0048232377,"about_ca_system_score_gemma":0.009608318,"threshold_uncertainty_score":0.18070376},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79466575,0.0010212606,0.11011852,0.013367808,0.00055937684,0.0031180305,0.00015818952,0.00072237535,0.076268606],"genre_scores_gemma":[0.90979576,0.0004448218,0.08271798,0.0007847653,0.000056950437,0.0011271515,0.00016013386,0.00005302369,0.0048593977],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9611442,0.026531396,0.0024000478,0.0016595229,0.0065059387,0.0017588654],"domain_scores_gemma":[0.84851295,0.055634543,0.016423762,0.015044431,0.051396433,0.012987887],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08967573,0.00026285736,0.00038904307,0.0026750434,0.0033729076,0.005923663,0.0011225545,0.0009140561,0.0028280348],"category_scores_gemma":[0.13436273,0.00049883465,0.00040866988,0.000717069,0.0023696711,0.0034318834,0.0067036985,0.002110263,0.0010311351],"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":[0.0003273986,0.001843762,0.2114976,0.0007513263,0.000065829845,0.000441157,0.074250914,0.0014161353,0.005725055,0.031231172,0.021628058,0.65082157],"study_design_scores_gemma":[0.00036710576,0.004392581,0.41549397,0.0070888773,0.0002596198,0.0016449244,0.1898563,0.018487316,0.033887565,0.07514394,0.25277638,0.00060141727],"about_ca_topic_score_codex":0.0015513528,"about_ca_topic_score_gemma":0.00413949,"teacher_disagreement_score":0.99584204,"about_ca_system_score_codex":0.0041579516,"about_ca_system_score_gemma":0.016920084,"threshold_uncertainty_score":0.47425628},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96110904,0.0004938905,0.00096076657,0.0037515669,0.0001551572,0.00072717975,0.00044952412,0.00009710008,0.03225581],"genre_scores_gemma":[0.98589236,0.00051683467,0.0019801,0.001176083,0.000042078493,0.00058814,0.0004625896,0.00007386907,0.009267953],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9838254,0.0046019736,0.00046323627,0.0009342886,0.00458337,0.0055917506],"domain_scores_gemma":[0.9477955,0.0071246657,0.0022743684,0.001245784,0.017776001,0.023783715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017996632,0.00050257734,0.0006101746,0.0028131278,0.011950081,0.007247361,0.0026718853,0.0015501486,0.004885767],"category_scores_gemma":[0.03876998,0.00056822837,0.0005247626,0.0041619632,0.0035746591,0.0020565952,0.008902132,0.003224496,0.00077365316],"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":[0.0023082194,0.0056716413,0.19466141,0.00067617407,0.000115581046,0.0005428638,0.4139664,0.00096973084,0.002526002,0.007095904,0.031877827,0.33958822],"study_design_scores_gemma":[0.00021401967,0.0021643161,0.4153022,0.00085579953,0.000073413736,0.00013825516,0.4525928,0.0013618956,0.0024000679,0.0011842966,0.12342268,0.00029028417],"about_ca_topic_score_codex":0.81905746,"about_ca_topic_score_gemma":0.9336818,"teacher_disagreement_score":0.18094254,"about_ca_system_score_codex":0.066554725,"about_ca_system_score_gemma":0.13060594,"threshold_uncertainty_score":0.4828906},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6177268,0.000775284,0.2766605,0.027718915,0.0015832324,0.005738309,0.00036740288,0.0011214659,0.06830809],"genre_scores_gemma":[0.79479516,0.00062558823,0.16414148,0.0028408577,0.0002992907,0.002189571,0.0003171945,0.0004944405,0.034296405],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9708939,0.01853825,0.0011084871,0.0016059143,0.0058915266,0.0019619244],"domain_scores_gemma":[0.9259949,0.039074067,0.0031439383,0.0060273213,0.021887673,0.0038721657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028335609,0.00067774946,0.0006453217,0.0029301597,0.00615981,0.007528478,0.00231609,0.0016773527,0.0038682756],"category_scores_gemma":[0.10543664,0.00055298075,0.0005162472,0.0014320455,0.0036871852,0.003865023,0.005352697,0.004725688,0.001455381],"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":[0.00043804295,0.001150914,0.011359893,0.00050720235,0.000032938584,0.0017995327,0.37060454,0.0012028933,0.0176162,0.024484359,0.03334883,0.5374547],"study_design_scores_gemma":[0.000109580564,0.001790236,0.026445268,0.0022863557,0.00008580578,0.0014626287,0.50486666,0.009718806,0.034144837,0.030290358,0.38838056,0.00041883596],"about_ca_topic_score_codex":0.0019602962,"about_ca_topic_score_gemma":0.0030075654,"teacher_disagreement_score":0.028335609,"about_ca_system_score_codex":0.0052779634,"about_ca_system_score_gemma":0.010268166,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04540456,0.0064725634,0.295865,0.5252581,0.0023249874,0.003327973,0.00010356817,0.0017448111,0.119498394],"genre_scores_gemma":[0.49385783,0.004778376,0.45316863,0.023750033,0.00062811695,0.001804036,0.00014982937,0.00021127814,0.021651886],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96426845,0.021861786,0.0023464905,0.00082854566,0.008937219,0.0017575525],"domain_scores_gemma":[0.930004,0.0312174,0.0031531868,0.005800079,0.017572744,0.012252507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06587691,0.0007285477,0.00059974386,0.0017533654,0.005267879,0.013190247,0.0020959997,0.0041022897,0.0037220072],"category_scores_gemma":[0.06455199,0.0005932842,0.0005558422,0.000874984,0.012325828,0.010011842,0.009645775,0.011206655,0.0012942158],"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":[0.00013152209,0.0010780949,0.00946945,0.0016941561,0.000038979542,0.00046890258,0.032305416,0.00089271617,0.0024305906,0.21500437,0.074192904,0.66229284],"study_design_scores_gemma":[0.00019283168,0.0010933997,0.023452142,0.009687872,0.00009066672,0.002494993,0.06340746,0.0075200023,0.011283775,0.37978953,0.500557,0.00043023343],"about_ca_topic_score_codex":0.0061093373,"about_ca_topic_score_gemma":0.012256176,"teacher_disagreement_score":0.06587691,"about_ca_system_score_codex":0.007686724,"about_ca_system_score_gemma":0.053615198,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002574261,0.034058176,0.0011037362,0.5039063,0.4408544,0.00011273005,0.000113880626,0.00020637152,0.019386938],"genre_scores_gemma":[0.006949963,0.06116824,0.0033019627,0.24547555,0.5671749,0.00027765075,0.00037908438,0.0008340671,0.11443867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98760843,0.0021596758,0.0010751963,0.0011096859,0.0068302257,0.0012166629],"domain_scores_gemma":[0.9454633,0.015224603,0.0021583259,0.0024821386,0.02347348,0.011198128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015420027,0.0015355839,0.0015884005,0.0051615844,0.00745187,0.01383418,0.0041277655,0.014108737,0.03525206],"category_scores_gemma":[0.050258093,0.0011552343,0.001253206,0.0037688084,0.01295253,0.0099968985,0.0055162334,0.019216837,0.01168026],"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":[0.0000032221164,0.000013005306,0.000051461073,0.00008933418,0.0000015962487,0.00002277814,0.00012724864,0.000016767044,0.00004135238,0.0015381596,0.9859561,0.0121389665],"study_design_scores_gemma":[0.0000030011188,0.000007740206,0.00031735582,0.00030940885,0.0000022640652,0.000072918505,0.0002816149,0.000028353403,0.000023643908,0.0010785843,0.9978611,0.000014064211],"about_ca_topic_score_codex":0.11170521,"about_ca_topic_score_gemma":0.27646974,"teacher_disagreement_score":0.11170521,"about_ca_system_score_codex":0.022008933,"about_ca_system_score_gemma":0.030977683,"threshold_uncertainty_score":0.22211003},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008616904,0.001531438,0.7389443,0.144749,0.0014012717,0.0018379099,0.00007750651,0.00015501797,0.10268663],"genre_scores_gemma":[0.488133,0.0009993988,0.47343135,0.019923368,0.00094489154,0.006530928,0.00009199064,0.00017787567,0.009767199],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5856849,0.326994,0.01795623,0.014201597,0.04954304,0.0056201587],"domain_scores_gemma":[0.6512765,0.25159207,0.013915262,0.030450428,0.04628352,0.0064821597],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2898375,0.001199052,0.001680309,0.00435949,0.012830922,0.02147766,0.0061656395,0.021583207,0.003134648],"category_scores_gemma":[0.25429597,0.0011992148,0.0023449145,0.002277789,0.08857335,0.021369347,0.018899372,0.02256438,0.001446932],"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":[0.000004683843,0.00001170287,0.0000691656,0.000033042394,0.0000037458776,0.000029108463,0.0028391408,0.00019365866,0.0000607289,0.9940614,0.0007908812,0.001902594],"study_design_scores_gemma":[0.000036108017,0.00003237795,0.000103305945,0.0004594774,0.00001074824,0.00011249572,0.0023740593,0.0019754672,0.00047083228,0.9398475,0.054533355,0.000044200406],"about_ca_topic_score_codex":0.0036993814,"about_ca_topic_score_gemma":0.0028903247,"teacher_disagreement_score":0.7101625,"about_ca_system_score_codex":0.012777279,"about_ca_system_score_gemma":0.029269978,"threshold_uncertainty_score":0.8757568},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2756423,0.008147212,0.025505139,0.5745076,0.032745194,0.00027738995,0.0008617136,0.000970394,0.081343085],"genre_scores_gemma":[0.8592476,0.003124222,0.018688293,0.056913335,0.006988252,0.00034504186,0.0007292613,0.0007772295,0.053186864],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9721691,0.021578824,0.00085924,0.0011083243,0.002881969,0.0014025718],"domain_scores_gemma":[0.86776024,0.08777322,0.0071185813,0.009224982,0.017618665,0.0105042895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04565332,0.0006943813,0.0005726852,0.0013374654,0.0073017483,0.011596745,0.0019020648,0.005899578,0.014648656],"category_scores_gemma":[0.23743412,0.0006017094,0.00071254413,0.0010876413,0.006065261,0.016185572,0.009314676,0.013325323,0.0030811895],"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":[0.0006083903,0.0006458026,0.02620194,0.00030906865,0.00008325073,0.00073598634,0.3765073,0.00027563254,0.0011540205,0.051088084,0.27179155,0.27059892],"study_design_scores_gemma":[0.000037238573,0.00045239067,0.022418233,0.0010520916,0.000073321055,0.0005328635,0.33959678,0.00082310097,0.0010741286,0.04074377,0.5929612,0.00023491732],"about_ca_topic_score_codex":0.0075094933,"about_ca_topic_score_gemma":0.015932485,"teacher_disagreement_score":0.04565332,"about_ca_system_score_codex":0.0035175756,"about_ca_system_score_gemma":0.003803408,"threshold_uncertainty_score":0.24144077},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031788517,0.005100841,0.39778456,0.31627885,0.006087188,0.0013787359,0.000054333057,0.0017519878,0.239775],"genre_scores_gemma":[0.6376491,0.0028870632,0.21305081,0.028152961,0.0016352554,0.0011466364,0.000106879015,0.0011140455,0.11425726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.93649083,0.049265586,0.0013376814,0.003526878,0.00750275,0.00187628],"domain_scores_gemma":[0.9231198,0.0321934,0.0029988047,0.01181619,0.018402265,0.011469526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07809066,0.0009248913,0.0010157722,0.0031862902,0.01626325,0.031789377,0.004486785,0.0064989566,0.009155082],"category_scores_gemma":[0.07108867,0.0007176936,0.00081239874,0.0015680597,0.046861395,0.027412685,0.026174573,0.015121949,0.0029718024],"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":[0.000054664284,0.00042704152,0.0018973226,0.0003014023,0.00005478902,0.000462218,0.11994697,0.00074254465,0.0011853089,0.68391067,0.07130006,0.119717054],"study_design_scores_gemma":[0.000083770174,0.0001585019,0.000787169,0.000829131,0.000034401215,0.000507751,0.06084105,0.0021640954,0.0009044759,0.45706618,0.47654313,0.00008029858],"about_ca_topic_score_codex":0.0091234725,"about_ca_topic_score_gemma":0.02474937,"teacher_disagreement_score":0.07809066,"about_ca_system_score_codex":0.011447921,"about_ca_system_score_gemma":0.036950845,"threshold_uncertainty_score":0.41298783},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20930347,0.0016061959,0.47904944,0.12740502,0.0011218424,0.0018401548,0.00007701671,0.001256039,0.17834081],"genre_scores_gemma":[0.7885906,0.0012037614,0.18163188,0.0065539596,0.00016517896,0.0010008998,0.00004000382,0.00044612316,0.020367587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93413156,0.05610856,0.0010665242,0.0017395965,0.005004417,0.0019492927],"domain_scores_gemma":[0.9254313,0.04566803,0.0030810747,0.008868491,0.010648652,0.006302406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06414047,0.00069593516,0.00053896155,0.0017603817,0.0092845475,0.016092226,0.0032941941,0.0024762198,0.009560849],"category_scores_gemma":[0.06749608,0.0007684929,0.00048173007,0.001340551,0.012218493,0.015119995,0.0147425635,0.0069857347,0.0020567402],"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":[0.00024056596,0.0014781619,0.009708111,0.00082910486,0.00004498088,0.0010599919,0.34121677,0.0017558136,0.0059083807,0.24076872,0.035966434,0.361023],"study_design_scores_gemma":[0.00020150236,0.00085483585,0.004403181,0.0036783095,0.000102486374,0.002154453,0.27875146,0.015714705,0.02087581,0.1717855,0.50126064,0.00021717897],"about_ca_topic_score_codex":0.003930108,"about_ca_topic_score_gemma":0.009897447,"teacher_disagreement_score":0.06414047,"about_ca_system_score_codex":0.011483815,"about_ca_system_score_gemma":0.02621077,"threshold_uncertainty_score":0.3392113},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10764997,0.011678892,0.1584254,0.61606735,0.004446734,0.0019311304,0.00012353352,0.00091353775,0.09876354],"genre_scores_gemma":[0.7887649,0.008209102,0.15648785,0.032899812,0.0007951255,0.0018673623,0.0001235189,0.0002848937,0.010567398],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.91847444,0.06384899,0.0028290823,0.0020544715,0.008349392,0.0044435062],"domain_scores_gemma":[0.70014936,0.16765174,0.019311959,0.013682977,0.069310285,0.029893681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12481144,0.00048075456,0.00097178493,0.0015206792,0.006136393,0.014941983,0.0017676321,0.0035970614,0.004827627],"category_scores_gemma":[0.23708259,0.00053433544,0.0006525248,0.00097450096,0.007482563,0.015593167,0.0067458106,0.0071812323,0.0020769206],"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":[0.00027630987,0.0013140148,0.03893055,0.0030014445,0.00014865313,0.0006000064,0.064575754,0.001300492,0.0021800536,0.07013626,0.12302417,0.69451225],"study_design_scores_gemma":[0.00029568307,0.001795087,0.04639325,0.024769256,0.0002847456,0.0014649027,0.19268456,0.007613569,0.013158532,0.25808367,0.4528527,0.0006040595],"about_ca_topic_score_codex":0.0053237826,"about_ca_topic_score_gemma":0.0129696475,"teacher_disagreement_score":0.12481144,"about_ca_system_score_codex":0.0088142,"about_ca_system_score_gemma":0.027336592,"threshold_uncertainty_score":0.6600739},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016492505,0.0014207094,0.0020668409,0.9178772,0.0031033868,0.0028191467,0.0032311152,0.0003708454,0.052618224],"genre_scores_gemma":[0.18690345,0.0029967425,0.022292553,0.5754416,0.0033625872,0.003250885,0.0030473548,0.00020546891,0.2024995],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9308051,0.015302578,0.0047667576,0.002549293,0.028036986,0.018539358],"domain_scores_gemma":[0.71894354,0.09875615,0.0100927735,0.007468892,0.1121981,0.052540567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08692353,0.00077774836,0.0010800343,0.0037951877,0.01633383,0.019554893,0.0068680076,0.033885222,0.01604665],"category_scores_gemma":[0.16073859,0.0016719429,0.0018681261,0.003599626,0.0075801504,0.008285993,0.0062147123,0.012307549,0.0019234016],"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":true,"study_design_scores_codex":[0.0003173579,0.00030427103,0.010263053,0.0012513574,0.00009544064,0.0006388837,0.004620817,0.002181014,0.001987742,0.056522224,0.8941058,0.027712027],"study_design_scores_gemma":[0.0004539944,0.00024886808,0.03736873,0.0012790124,0.00013811771,0.00013080188,0.006987031,0.0025288665,0.0011213509,0.007057442,0.94238615,0.0002995885],"about_ca_topic_score_codex":0.95380175,"about_ca_topic_score_gemma":0.9783735,"teacher_disagreement_score":0.95380175,"about_ca_system_score_codex":0.182037,"about_ca_system_score_gemma":0.7078733,"threshold_uncertainty_score":0.9487212},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80785424,0.0042176857,0.0018537669,0.050934337,0.0001797779,0.00024238061,0.0002914921,0.000045443787,0.13438088],"genre_scores_gemma":[0.99358106,0.0014234866,0.001012513,0.0007541624,0.000019925206,0.000022785767,0.00004849836,0.0000087139715,0.0031289228],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9898318,0.0033724057,0.00022459848,0.00036334657,0.0027312136,0.0034766793],"domain_scores_gemma":[0.9872416,0.0033590402,0.0012817268,0.00043645315,0.0033949504,0.004286171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067537585,0.00028193754,0.00028389608,0.002201382,0.014993873,0.0077912086,0.0016869378,0.0008125389,0.0016825172],"category_scores_gemma":[0.020923376,0.00019868634,0.00022826409,0.0033775321,0.007963445,0.0013580589,0.0046551563,0.0021723332,0.00011874516],"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":[0.00018578522,0.00038524525,0.3213507,0.00041552936,0.00011039094,0.0010612863,0.19326852,0.004792928,0.000900589,0.16678537,0.018347748,0.29239583],"study_design_scores_gemma":[0.00004436309,0.00019511905,0.54973286,0.0014536326,0.00013979374,0.00034272327,0.2772858,0.004659961,0.0011346076,0.01992995,0.14489067,0.00019049554],"about_ca_topic_score_codex":0.9911918,"about_ca_topic_score_gemma":0.9924285,"teacher_disagreement_score":0.8671745,"about_ca_system_score_codex":0.1328255,"about_ca_system_score_gemma":0.32450455,"threshold_uncertainty_score":0.9637209},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022137644,0.9890745,0.0015638449,0.006650611,0.0012563857,0.000058560938,0.000094701354,0.000030562493,0.0010493702],"genre_scores_gemma":[0.01028665,0.96941245,0.00945535,0.0074473405,0.0020843563,0.00025176146,0.00026187563,0.000039728217,0.0007604619],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9686821,0.014689063,0.0051803,0.0019264282,0.008742595,0.00077955046],"domain_scores_gemma":[0.8141282,0.112987444,0.016209155,0.0028088023,0.051212214,0.0026540859],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.067801096,0.002447181,0.005731439,0.009642058,0.00090431236,0.005592876,0.0042536943,0.0034304922,0.0028575708],"category_scores_gemma":[0.15144068,0.00080974936,0.0024986558,0.007955922,0.0027656488,0.005207221,0.0025911606,0.0068114595,0.0011545533],"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":[0.00010328914,0.000057048477,0.001230261,0.022077737,0.0005844489,0.000020800024,0.000118685246,0.0004991282,0.00009536581,0.008191488,0.034897573,0.9321241],"study_design_scores_gemma":[0.00029345357,0.00057899667,0.012107276,0.24329168,0.004718017,0.0003982997,0.0006914028,0.0023728283,0.0011733508,0.03610923,0.69797534,0.00029018387],"about_ca_topic_score_codex":0.012759476,"about_ca_topic_score_gemma":0.028243612,"teacher_disagreement_score":0.9321989,"about_ca_system_score_codex":0.009517698,"about_ca_system_score_gemma":0.02855854,"threshold_uncertainty_score":0.35857075},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22367261,0.034430675,0.50693035,0.053152014,0.011754969,0.027519127,0.005058567,0.0013041389,0.1361777],"genre_scores_gemma":[0.8351368,0.0023279763,0.11830944,0.011927068,0.0012021043,0.026086904,0.0016913622,0.00050749944,0.002810838],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.21247463,0.6560084,0.051258743,0.024440981,0.052476637,0.0033405507],"domain_scores_gemma":[0.116203226,0.59918433,0.048235565,0.16692041,0.06761096,0.001845459],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73120767,0.0017936254,0.0044994475,0.008840801,0.0043055527,0.010021331,0.00644238,0.0046704374,0.0061652306],"category_scores_gemma":[0.85284525,0.001669321,0.0064578764,0.010561411,0.012408086,0.011719423,0.014927209,0.0079554105,0.0010240049],"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":[0.0035931035,0.00095517386,0.28459412,0.0154687455,0.021977246,0.00065791665,0.04229751,0.009786345,0.0009919968,0.15877791,0.027509458,0.43339062],"study_design_scores_gemma":[0.0020881572,0.0054785535,0.36315024,0.03553491,0.010294464,0.0010546622,0.031093357,0.026317805,0.008405341,0.362488,0.15331796,0.0007765229],"about_ca_topic_score_codex":0.011181025,"about_ca_topic_score_gemma":0.010615202,"teacher_disagreement_score":0.26879233,"about_ca_system_score_codex":0.010678312,"about_ca_system_score_gemma":0.013442627,"threshold_uncertainty_score":0.33146888},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015661882,0.018352129,0.1875844,0.67830014,0.006501625,0.0006518832,0.00015189903,0.0007409477,0.09205508],"genre_scores_gemma":[0.64881,0.011967136,0.2270802,0.090427235,0.0035293286,0.0018989579,0.00012234354,0.00090173824,0.015263074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8068815,0.15583144,0.0049218577,0.007941756,0.018010149,0.006413386],"domain_scores_gemma":[0.7941531,0.1484524,0.0108568445,0.020897644,0.018549709,0.007090376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1504393,0.0014311485,0.002858745,0.0067084655,0.0048009073,0.025860302,0.0029097688,0.011008699,0.011284562],"category_scores_gemma":[0.21444342,0.0012065489,0.0030674227,0.0061658407,0.05022237,0.04735251,0.01391283,0.013212895,0.0020313505],"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":[0.0002794047,0.0003171201,0.0067262975,0.0015094122,0.0005050539,0.000120989214,0.007949926,0.0027774759,0.00043285158,0.8040283,0.017669799,0.15768337],"study_design_scores_gemma":[0.00023092872,0.00032274087,0.0035574178,0.0045365337,0.00026207312,0.00011093498,0.0066508777,0.0044556656,0.0010464744,0.9003037,0.07829826,0.000224351],"about_ca_topic_score_codex":0.0072955745,"about_ca_topic_score_gemma":0.0069865985,"teacher_disagreement_score":0.1504393,"about_ca_system_score_codex":0.010229857,"about_ca_system_score_gemma":0.021517236,"threshold_uncertainty_score":0.79560864},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063517867,0.96907526,0.009492522,0.007487922,0.00038169496,0.0005822935,0.000030755622,0.000018757446,0.00657897],"genre_scores_gemma":[0.0748312,0.90222615,0.018379783,0.002529225,0.00028818662,0.00097295357,0.00004938244,0.00003970811,0.0006834455],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9086448,0.06586393,0.012884864,0.0015955265,0.009829516,0.0011813907],"domain_scores_gemma":[0.7041903,0.27290317,0.00785008,0.0034455392,0.010695073,0.0009158704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.061381966,0.001000737,0.0024007189,0.010180405,0.0025311208,0.006693723,0.0026812737,0.0053926078,0.0015596992],"category_scores_gemma":[0.14645939,0.00097380765,0.001999394,0.015901705,0.0061897393,0.006137141,0.004369147,0.0033637914,0.00037784086],"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":[0.00019965204,0.0003722482,0.0031326527,0.09716688,0.0005279313,0.0075151767,0.02798536,0.0017459065,0.00068333687,0.041945122,0.013261457,0.80546427],"study_design_scores_gemma":[0.00010213476,0.000623799,0.0064117243,0.36744615,0.0012948499,0.022550486,0.03592383,0.0018146482,0.0021862173,0.026319925,0.5350646,0.00026166657],"about_ca_topic_score_codex":0.007926549,"about_ca_topic_score_gemma":0.015203256,"teacher_disagreement_score":0.061381966,"about_ca_system_score_codex":0.008887323,"about_ca_system_score_gemma":0.014818026,"threshold_uncertainty_score":0.32462275},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015609296,0.033989448,0.009339351,0.24403453,0.5151828,0.0013083478,0.021783313,0.008770334,0.16403092],"genre_scores_gemma":[0.01584902,0.028835544,0.020853026,0.0756523,0.11381158,0.0027430626,0.020327257,0.011756035,0.7101721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9819095,0.0054599573,0.0013257496,0.002478187,0.00824036,0.00058623345],"domain_scores_gemma":[0.7671459,0.01635027,0.0061954213,0.0059805796,0.19641566,0.007912165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012328962,0.002289517,0.002521363,0.011882316,0.004772531,0.011719948,0.0036095146,0.002527917,0.2816132],"category_scores_gemma":[0.14878711,0.00086031016,0.001247151,0.0096720485,0.0015201168,0.008020082,0.004326532,0.00397902,0.24973653],"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":[0.0000061645683,0.0000019340616,0.0000621205,0.00007277195,0.000003184182,0.000021884574,0.000075706586,0.000007539536,0.000016221737,0.00025156667,0.9914322,0.008048686],"study_design_scores_gemma":[0.000006171375,0.0000043822242,0.00029023635,0.00032074712,0.000010311323,0.00009534356,0.00038869632,0.000040761934,0.000040482846,0.00049499824,0.9982901,0.000017665587],"about_ca_topic_score_codex":0.009849293,"about_ca_topic_score_gemma":0.019363612,"teacher_disagreement_score":0.2816132,"about_ca_system_score_codex":0.004859015,"about_ca_system_score_gemma":0.0096001765,"threshold_uncertainty_score":0.94209003},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04114788,0.060286663,0.006087557,0.31374064,0.0011962095,0.00009856688,0.00043414018,0.000082165956,0.5769262],"genre_scores_gemma":[0.7820639,0.08884377,0.014120202,0.027799506,0.001040649,0.00026997787,0.00037867666,0.00007812617,0.08540529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99789655,0.001279755,0.00006200784,0.000082353035,0.00038690632,0.0002925318],"domain_scores_gemma":[0.9950235,0.003873559,0.00014995845,0.00013209503,0.0005755643,0.00024539238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007466362,0.00033723866,0.0003527161,0.0018046828,0.002070811,0.009174701,0.00068667025,0.0019590345,0.010624425],"category_scores_gemma":[0.007939151,0.00023199632,0.00017995233,0.0061775986,0.002734663,0.0055055316,0.002892725,0.0016524759,0.0007047635],"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":[0.00006249337,0.000043892695,0.0023214573,0.00062225066,0.000017043758,0.00036718583,0.0027155525,0.0023753436,0.00027448047,0.7467091,0.040512014,0.20397907],"study_design_scores_gemma":[0.00002182444,0.00003556409,0.004544461,0.0019256144,0.000018181276,0.00014356666,0.0106784655,0.0018063762,0.00047854325,0.34326902,0.63705087,0.000027498947],"about_ca_topic_score_codex":0.008525572,"about_ca_topic_score_gemma":0.014179477,"teacher_disagreement_score":0.010624425,"about_ca_system_score_codex":0.010404906,"about_ca_system_score_gemma":0.014073343,"threshold_uncertainty_score":0.07549316},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8806655,0.0043964367,0.042295143,0.006144067,0.0000789811,0.0005821778,0.0021924756,0.00016899931,0.06347632],"genre_scores_gemma":[0.9924615,0.000579752,0.005123852,0.00014812556,0.000017675444,0.00006795077,0.0005144147,0.0000059452345,0.0010808802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917293,0.0038343547,0.0005430476,0.0004592188,0.0028917831,0.0005423709],"domain_scores_gemma":[0.98643506,0.0052746353,0.0021497288,0.0007082837,0.004523728,0.0009085774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012678767,0.00029961235,0.00055858056,0.0050049196,0.00081845594,0.0031783173,0.00042705765,0.0005571874,0.0020924779],"category_scores_gemma":[0.01820117,0.00011449112,0.00062637776,0.0036109968,0.0009992275,0.0025519899,0.0019568345,0.00043133865,0.00016861144],"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":[0.00019858562,0.0005920055,0.6030199,0.0007408419,0.0006889057,0.0001379693,0.0017689989,0.028669177,0.0011995871,0.04042006,0.006011663,0.31655234],"study_design_scores_gemma":[0.000021637086,0.0006127872,0.8736579,0.0005202656,0.00040919427,0.000082226805,0.006703813,0.053013816,0.0028176021,0.04318908,0.01887771,0.00009399807],"about_ca_topic_score_codex":0.009967501,"about_ca_topic_score_gemma":0.017396836,"teacher_disagreement_score":0.012678767,"about_ca_system_score_codex":0.005036085,"about_ca_system_score_gemma":0.00800106,"threshold_uncertainty_score":0.06705254},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31475917,0.007597335,0.36859816,0.03679455,0.0004678211,0.0033111104,0.0007387783,0.0010961698,0.26663685],"genre_scores_gemma":[0.9714661,0.00053815654,0.025053313,0.0005228909,0.000119896205,0.00075045414,0.000099050354,0.00010137674,0.0013486691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.61202514,0.30838543,0.019361554,0.0130309835,0.038453758,0.008743192],"domain_scores_gemma":[0.4578035,0.3342011,0.072873354,0.05584194,0.07254038,0.00673974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26489106,0.00071384944,0.0016864424,0.012003685,0.006209023,0.035153095,0.002635785,0.0029779829,0.00245681],"category_scores_gemma":[0.37143648,0.0014332688,0.0010318221,0.011518215,0.020898724,0.015344132,0.006616066,0.0035373196,0.00054894073],"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":[0.00028054096,0.0005099028,0.11282732,0.0012775068,0.00078432314,0.00016134874,0.016828844,0.02191017,0.002357175,0.6685588,0.0037885965,0.1707155],"study_design_scores_gemma":[0.0005278259,0.00093290623,0.15647171,0.0030716036,0.0006365849,0.00028633347,0.019601839,0.050949723,0.011487956,0.6803333,0.07513336,0.00056677597],"about_ca_topic_score_codex":0.010602444,"about_ca_topic_score_gemma":0.0070809703,"teacher_disagreement_score":0.26489106,"about_ca_system_score_codex":0.02368243,"about_ca_system_score_gemma":0.033527315,"threshold_uncertainty_score":0.9065202},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9018812,0.0008313388,0.007070947,0.013749211,0.00036081194,0.00032412956,0.0002582756,0.00017253336,0.0753515],"genre_scores_gemma":[0.940167,0.0005400842,0.002404629,0.0012460076,0.000024398481,0.00022225677,0.00009337075,0.000095220224,0.055207003],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9906769,0.0055810027,0.00016879739,0.0007287004,0.001686953,0.0011577839],"domain_scores_gemma":[0.98902726,0.0041817697,0.0005455182,0.0007201844,0.0028526427,0.0026725756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007960775,0.00047421965,0.0006587112,0.0011500628,0.0111676585,0.008267789,0.0013425017,0.0019969437,0.010461354],"category_scores_gemma":[0.011771429,0.0003430152,0.00041404171,0.0014927151,0.012568232,0.002785708,0.0061213626,0.0037838107,0.0011891309],"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":[0.000041717256,0.0000522712,0.0028458587,0.000113374714,0.000005468409,0.0005707546,0.9726733,0.000119128956,0.0014013314,0.0069012693,0.0033358946,0.01193971],"study_design_scores_gemma":[0.000009219435,0.00007043904,0.0091585275,0.0003250823,0.000009592329,0.00017718846,0.8613468,0.00021412647,0.00090019515,0.001181613,0.1265544,0.000052793854],"about_ca_topic_score_codex":0.30497873,"about_ca_topic_score_gemma":0.41594923,"teacher_disagreement_score":0.30497873,"about_ca_system_score_codex":0.02156382,"about_ca_system_score_gemma":0.026189854,"threshold_uncertainty_score":0.6064071},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021798572,0.038477194,0.5783028,0.28930968,0.009627947,0.0010714473,0.0007015719,0.00050581957,0.060204994],"genre_scores_gemma":[0.67597365,0.013653463,0.26673886,0.031323545,0.004068775,0.0048863124,0.00041881765,0.00053014874,0.002406467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6436801,0.318242,0.009980213,0.009712643,0.016335746,0.0020491662],"domain_scores_gemma":[0.43847016,0.45793855,0.016042318,0.06281145,0.020445665,0.0042918613],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25541624,0.0018677758,0.0031164482,0.011706165,0.0059624366,0.021446837,0.0047562923,0.0060530882,0.0047971127],"category_scores_gemma":[0.3716617,0.0014248828,0.002396285,0.007797373,0.088435024,0.033009365,0.01655428,0.0173295,0.0008306448],"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":[0.0000803512,0.00007361026,0.0024838182,0.0020888376,0.00017817548,0.0001520807,0.03151282,0.00068079104,0.00026004136,0.89260274,0.006524571,0.063362256],"study_design_scores_gemma":[0.000032808683,0.00008118786,0.00092212233,0.0032851154,0.000049245886,0.000091914764,0.0086871125,0.0008821869,0.00033947045,0.96019167,0.025378603,0.000058552425],"about_ca_topic_score_codex":0.0018507588,"about_ca_topic_score_gemma":0.0015075849,"teacher_disagreement_score":0.25541624,"about_ca_system_score_codex":0.01208068,"about_ca_system_score_gemma":0.0143908,"threshold_uncertainty_score":0.9182043},"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":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8000286,0.0024029575,0.020738767,0.017649123,0.007239907,0.004308851,0.004059946,0.00032516618,0.14324676],"genre_scores_gemma":[0.96294636,0.0004901001,0.012569264,0.009080815,0.0006796366,0.0040662144,0.0013507388,0.00032119424,0.008495596],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.87530273,0.08576805,0.007860182,0.00930295,0.019541504,0.0022246717],"domain_scores_gemma":[0.44003975,0.33006236,0.033254296,0.08088939,0.10430345,0.011450697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09370307,0.00053609855,0.0014070416,0.0042413757,0.007904442,0.010697153,0.0031718593,0.004466401,0.014490608],"category_scores_gemma":[0.4517765,0.0006774253,0.0015759659,0.006113813,0.00637731,0.005965987,0.007643848,0.0041767186,0.0035602772],"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":[0.010496242,0.007099207,0.3606216,0.005649942,0.0025435959,0.0012173909,0.25334483,0.0007916042,0.0047520516,0.04973582,0.066546604,0.23720117],"study_design_scores_gemma":[0.0028829898,0.0052519925,0.6883409,0.0027089948,0.0029121106,0.0008963485,0.11096828,0.0022499529,0.0071655824,0.03037265,0.14541952,0.0008306721],"about_ca_topic_score_codex":0.010555827,"about_ca_topic_score_gemma":0.013374137,"teacher_disagreement_score":0.9062969,"about_ca_system_score_codex":0.0052362652,"about_ca_system_score_gemma":0.00951438,"threshold_uncertainty_score":0.4955551},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99490595,0.00019720958,0.00054066686,0.0002412417,0.000026946935,0.00049862463,0.00021207093,0.00001604042,0.0033613539],"genre_scores_gemma":[0.9949228,0.00035093326,0.0018773295,0.00013913879,0.000028575994,0.0004981659,0.00029189463,0.0000053795216,0.0018856626],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99753404,0.0006406252,0.00021513489,0.0001524566,0.0011279003,0.0003298069],"domain_scores_gemma":[0.99130136,0.0016451931,0.0015975479,0.00038761995,0.0030260484,0.0020422828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006742623,0.00026105388,0.00055182393,0.001261619,0.00052579277,0.0008545528,0.00042486255,0.00042554145,0.00387619],"category_scores_gemma":[0.012129284,0.00016176963,0.00077875244,0.0006512959,0.00052011356,0.0006883974,0.0014552736,0.00078672904,0.00069476187],"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":[0.00046699983,0.0046304776,0.8009284,0.0006029495,0.00008268759,0.00021903083,0.0057500084,0.00038361363,0.0009415634,0.00024229525,0.0026220533,0.18312995],"study_design_scores_gemma":[0.00011104515,0.0059469603,0.9745238,0.00035789557,0.00010213679,0.00033307908,0.009815035,0.00067062234,0.001437005,0.00019263136,0.006477917,0.000031841377],"about_ca_topic_score_codex":0.0014405175,"about_ca_topic_score_gemma":0.0025002228,"teacher_disagreement_score":0.006742623,"about_ca_system_score_codex":0.00087162596,"about_ca_system_score_gemma":0.0031705434,"threshold_uncertainty_score":0.035658836},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80619866,0.0032176732,0.022895822,0.0219685,0.00044015874,0.0025332307,0.0018991198,0.00024699193,0.1405999],"genre_scores_gemma":[0.9648637,0.00065937714,0.023364443,0.0020678816,0.00008135588,0.001743832,0.0008547781,0.00002330267,0.006341319],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98003805,0.011921004,0.0010548083,0.0005375683,0.004887206,0.0015613767],"domain_scores_gemma":[0.9744834,0.005996513,0.002249502,0.0008501478,0.010730162,0.005690342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034989193,0.00048823952,0.00062192604,0.004578595,0.0058576115,0.0056606038,0.0018316295,0.0013167044,0.002847703],"category_scores_gemma":[0.04094808,0.00024073926,0.0007959199,0.0017328853,0.0014446093,0.0019326904,0.006063077,0.0017044718,0.00049750577],"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":[0.0019364133,0.0028334057,0.52795696,0.00031221352,0.00024678782,0.0002846813,0.010346624,0.013170702,0.0011817443,0.039747197,0.03142084,0.37056234],"study_design_scores_gemma":[0.0005577041,0.0050757043,0.71963584,0.0036008938,0.00042821746,0.0005331794,0.08038406,0.040703166,0.008441697,0.06492555,0.075403154,0.00031087446],"about_ca_topic_score_codex":0.05066619,"about_ca_topic_score_gemma":0.10146965,"teacher_disagreement_score":0.05066619,"about_ca_system_score_codex":0.0068205856,"about_ca_system_score_gemma":0.025039114,"threshold_uncertainty_score":0.18504274},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00076032715,0.0678129,0.11395375,0.020919431,0.0037602615,0.00015042258,0.00014979584,0.00026675058,0.7922263],"genre_scores_gemma":[0.052734107,0.11982188,0.18091375,0.01193977,0.0064490777,0.00072678295,0.00029537463,0.00062986003,0.62648946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948714,0.0023660515,0.0001454542,0.00023032873,0.0022897634,0.00009703784],"domain_scores_gemma":[0.9883133,0.010251972,0.00017855516,0.00033376634,0.00080808136,0.00011418445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00535845,0.0010023725,0.0011403869,0.0018808031,0.0010051645,0.008989315,0.0013766408,0.0026720667,0.011839484],"category_scores_gemma":[0.009696353,0.00055090245,0.00032571363,0.002514088,0.0051364205,0.008116052,0.0017786674,0.00438932,0.0058705374],"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":[0.000010271589,0.000029062134,0.000060385257,0.00041998664,0.000009307074,0.00003644235,0.0003316165,0.0012074817,0.00019148074,0.71219736,0.07633769,0.20916897],"study_design_scores_gemma":[0.0000037047678,0.000013488684,0.00017092512,0.0005714076,0.0000073641436,0.00007759441,0.00018509862,0.0020407136,0.00026740998,0.6501231,0.34651926,0.000019958761],"about_ca_topic_score_codex":0.0030789287,"about_ca_topic_score_gemma":0.00503339,"teacher_disagreement_score":0.011839484,"about_ca_system_score_codex":0.002839558,"about_ca_system_score_gemma":0.0032910644,"threshold_uncertainty_score":0.03960699},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009455817,0.009578034,0.07898744,0.020852635,0.0016154819,0.000077145916,0.000083258536,0.00019803466,0.88766235],"genre_scores_gemma":[0.032326967,0.013205347,0.070685856,0.0098057175,0.0017078803,0.0002370229,0.00016900875,0.00036488593,0.87149733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973942,0.0010507605,0.0000861983,0.00017499703,0.0011863785,0.00010742192],"domain_scores_gemma":[0.9963366,0.0026727845,0.00009210194,0.00024827267,0.0005235791,0.00012676574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004269343,0.00036310512,0.00045661133,0.0009515923,0.0011793572,0.009004578,0.0008309833,0.002394685,0.011196799],"category_scores_gemma":[0.005757721,0.00037979058,0.00018617517,0.0015427447,0.004909399,0.007605434,0.0016027419,0.004250797,0.0066473912],"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":[0.0000032602516,0.000028328895,0.00011950831,0.00008084772,0.0000030176304,0.000025725945,0.0007249327,0.0004224156,0.00030708918,0.7730976,0.09298096,0.13220644],"study_design_scores_gemma":[0.0000013624863,0.000008289191,0.00030802883,0.00022694533,0.0000032206267,0.00006655787,0.00043878288,0.0006542792,0.00037026193,0.39396086,0.6039509,0.0000106161115],"about_ca_topic_score_codex":0.0035497926,"about_ca_topic_score_gemma":0.009372053,"teacher_disagreement_score":0.011196799,"about_ca_system_score_codex":0.0024914807,"about_ca_system_score_gemma":0.0041839504,"threshold_uncertainty_score":0.03745699},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002960661,0.98020834,0.0021510038,0.010102895,0.0023685594,0.00001228394,0.00009343547,0.00004600601,0.0047214935],"genre_scores_gemma":[0.0052466737,0.9846864,0.0022264798,0.00086607237,0.0022464849,0.000041018124,0.00015223667,0.000029741967,0.0045049214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731606,0.0010988909,0.00022741586,0.00022697623,0.0009896543,0.00014094955],"domain_scores_gemma":[0.9927805,0.0048830328,0.000524786,0.00017215998,0.0012811755,0.00035843157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005794599,0.002187809,0.002434756,0.0051625315,0.0014423885,0.0059887064,0.0019172081,0.0024792098,0.009153581],"category_scores_gemma":[0.007525988,0.0013577259,0.0010514631,0.00830322,0.0020191188,0.009478842,0.001810467,0.003219557,0.0065153595],"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":[0.00018877002,0.00007976341,0.0010078152,0.0072363946,0.00017764802,0.00016605489,0.003418032,0.0006856477,0.00045324618,0.037874978,0.56552005,0.38319165],"study_design_scores_gemma":[0.00005314757,0.00006822552,0.0057371138,0.008342406,0.0003077141,0.0005099333,0.0026038177,0.0009919554,0.0010628542,0.060619295,0.91961104,0.00009253838],"about_ca_topic_score_codex":0.0076376977,"about_ca_topic_score_gemma":0.019687984,"teacher_disagreement_score":0.009153581,"about_ca_system_score_codex":0.0029726517,"about_ca_system_score_gemma":0.0057250387,"threshold_uncertainty_score":0.030645132},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5572001,0.00076779246,0.1260584,0.009597365,0.002335338,0.036698796,0.005299003,0.020789158,0.24125414],"genre_scores_gemma":[0.5983841,0.00031711647,0.20328203,0.0010378243,0.00041977485,0.0046078195,0.0054639876,0.001307548,0.18517971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9877664,0.0036136964,0.0008581702,0.002418297,0.002528092,0.0028153295],"domain_scores_gemma":[0.9244925,0.006294553,0.003557949,0.0062814564,0.021350497,0.038023096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010510275,0.00072544115,0.0007639199,0.003624481,0.0047693863,0.005618475,0.0032643804,0.0010469217,0.057976693],"category_scores_gemma":[0.026960699,0.00074718054,0.00036104614,0.0025667178,0.0007772645,0.0014165537,0.0052122893,0.0019671894,0.016886795],"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":[0.0013133937,0.0037654275,0.031479422,0.0001802746,0.000031496373,0.00035922797,0.003462545,0.004102299,0.01220201,0.0020165879,0.11855318,0.82253414],"study_design_scores_gemma":[0.0006411536,0.0034673542,0.124843426,0.0002284615,0.00007227038,0.00029507538,0.022923814,0.020544767,0.025439383,0.0038021868,0.79742396,0.000318228],"about_ca_topic_score_codex":0.028101051,"about_ca_topic_score_gemma":0.059118774,"teacher_disagreement_score":0.057976693,"about_ca_system_score_codex":0.010209709,"about_ca_system_score_gemma":0.030213105,"threshold_uncertainty_score":0.19395137},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9657993,0.00068564387,0.0016725893,0.0071219434,0.000062283805,0.00044473237,0.000034812463,0.0000174868,0.024161136],"genre_scores_gemma":[0.99459296,0.0006462758,0.0014262422,0.00058447605,0.000008915824,0.00013194296,0.000011114521,0.0000052613404,0.0025928165],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9943504,0.0033487116,0.00007993364,0.00014268288,0.00035049143,0.0017278441],"domain_scores_gemma":[0.9931902,0.0026542451,0.0006403478,0.0002577503,0.00054747885,0.0027100309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059543448,0.00027524264,0.0002495533,0.0007861389,0.022176472,0.004192287,0.0015442153,0.0028630584,0.0029287487],"category_scores_gemma":[0.0066283285,0.00039756164,0.00027312626,0.0015450249,0.0057805725,0.0026848465,0.0073596817,0.0030077111,0.00024400542],"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":[0.00018946933,0.0024838066,0.043084543,0.00037676952,0.000035566434,0.02043636,0.8267395,0.0010106983,0.0010646298,0.044236302,0.0056833373,0.05465902],"study_design_scores_gemma":[0.00003007954,0.00027068672,0.008596763,0.00022681023,0.00001959048,0.0018692885,0.9501111,0.00064902107,0.00041797964,0.001448257,0.03633898,0.00002142796],"about_ca_topic_score_codex":0.1206499,"about_ca_topic_score_gemma":0.31800044,"teacher_disagreement_score":0.1206499,"about_ca_system_score_codex":0.011534672,"about_ca_system_score_gemma":0.026379291,"threshold_uncertainty_score":0.23989528},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020682503,0.007445175,0.15411972,0.010047345,0.0038434062,0.051334318,0.045503553,0.0022854472,0.7047385],"genre_scores_gemma":[0.06915305,0.013852825,0.25736645,0.0120861,0.0013115334,0.117693014,0.039474186,0.0011179099,0.4879449],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94308984,0.03995924,0.003414075,0.003371932,0.008972485,0.0011922668],"domain_scores_gemma":[0.9526342,0.028130276,0.0019835986,0.005203259,0.010850007,0.0011986223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030883238,0.0009849619,0.00089014025,0.005651595,0.00285093,0.004196485,0.0022489072,0.002120296,0.09714753],"category_scores_gemma":[0.065050416,0.00083562045,0.00043270018,0.010761298,0.0018010074,0.0037999754,0.0045031463,0.002517963,0.043478664],"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":[0.00024138398,0.00036886783,0.0022101295,0.0028262245,0.000031418087,0.00022974183,0.033417974,0.0007703579,0.0017010368,0.07682379,0.36376643,0.5176126],"study_design_scores_gemma":[0.000032427997,0.00009232125,0.00089246803,0.0006888143,0.0000040174027,0.000088448556,0.007037434,0.00018014153,0.0003410789,0.006692384,0.9839336,0.000016774016],"about_ca_topic_score_codex":0.0028209547,"about_ca_topic_score_gemma":0.0040625776,"teacher_disagreement_score":0.09714753,"about_ca_system_score_codex":0.0040345774,"about_ca_system_score_gemma":0.007879237,"threshold_uncertainty_score":0.32499087},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20690589,0.009566444,0.3434058,0.046919238,0.0007300151,0.0020026627,0.00044412585,0.0006511479,0.38937467],"genre_scores_gemma":[0.755951,0.0056818076,0.17002818,0.0018480439,0.00012088611,0.0010338749,0.00029568627,0.00016734228,0.06487324],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9811458,0.010733592,0.0007003638,0.0014319783,0.0045590517,0.001429236],"domain_scores_gemma":[0.98079485,0.008796316,0.0011355288,0.0017321882,0.005710742,0.0018304401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019263119,0.00087660295,0.00048145393,0.00262437,0.004791307,0.007898905,0.0013534507,0.0017961977,0.008370054],"category_scores_gemma":[0.020666419,0.0004138014,0.00076814427,0.0033286659,0.009549097,0.0049862806,0.0064977002,0.0029177691,0.0012022961],"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":[0.000097931705,0.00031380611,0.01977703,0.0022071637,0.00004421581,0.00024018371,0.12982939,0.0023901279,0.0056000333,0.3473723,0.008830322,0.48329738],"study_design_scores_gemma":[0.000057672038,0.0003444696,0.038867474,0.0028665776,0.00007057707,0.00036987854,0.06553621,0.002990383,0.0065904316,0.061730687,0.82045466,0.00012107575],"about_ca_topic_score_codex":0.25725392,"about_ca_topic_score_gemma":0.397363,"teacher_disagreement_score":0.25725392,"about_ca_system_score_codex":0.031712063,"about_ca_system_score_gemma":0.07430845,"threshold_uncertainty_score":0.51151305},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96356034,0.00074200385,0.009309752,0.012821319,0.00007179799,0.00035090497,0.000052615072,0.000020226133,0.013071136],"genre_scores_gemma":[0.99262434,0.0006371503,0.0033552225,0.0015068036,0.000037918246,0.00030156987,0.000024933264,0.000014045147,0.0014980818],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9435546,0.047267944,0.0017848343,0.0013275266,0.0022611383,0.0038040443],"domain_scores_gemma":[0.83649504,0.14132023,0.006470966,0.002420934,0.008016272,0.0052765524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07192578,0.00034998704,0.0006125908,0.0027838952,0.0130604245,0.008076048,0.0016363115,0.0036292989,0.0020051864],"category_scores_gemma":[0.09034042,0.00089422025,0.00030831748,0.0028840455,0.010972221,0.009771001,0.0062859836,0.0058021005,0.00024105371],"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":[0.000025921247,0.00014532024,0.006112574,0.00007516429,0.0000032613,0.00029821988,0.9777541,0.0001612511,0.0005187251,0.008486974,0.0006047361,0.005813755],"study_design_scores_gemma":[0.0000065682766,0.000047760197,0.001393371,0.0001468876,0.0000029521862,0.00008193329,0.980648,0.000427126,0.0002717076,0.0014171697,0.015542857,0.000013699141],"about_ca_topic_score_codex":0.004700779,"about_ca_topic_score_gemma":0.005780962,"teacher_disagreement_score":0.92807424,"about_ca_system_score_codex":0.012348824,"about_ca_system_score_gemma":0.013575854,"threshold_uncertainty_score":0.38038445},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02206578,0.010574526,0.2799289,0.061254386,0.005246543,0.0017952288,0.0015293062,0.012986429,0.60461885],"genre_scores_gemma":[0.19615681,0.006880052,0.2950056,0.027956214,0.0009941756,0.0049383594,0.0023363202,0.004854956,0.46087748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917174,0.00598995,0.000201806,0.0004581737,0.0008597175,0.0007730402],"domain_scores_gemma":[0.99081224,0.005567602,0.00019570447,0.00058001827,0.00045917343,0.0023851146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008663376,0.0008597522,0.0004067941,0.0010141409,0.0044700434,0.0069710244,0.0016595213,0.0050476505,0.05097685],"category_scores_gemma":[0.014368336,0.00068886305,0.00060620974,0.0008690916,0.004025106,0.009177073,0.015195233,0.004786557,0.02017287],"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":[0.0003317076,0.00045048408,0.0007603782,0.00069256534,0.000022031752,0.0011995352,0.10243722,0.0003404727,0.0061836266,0.042664602,0.5188142,0.3261033],"study_design_scores_gemma":[0.0000721013,0.000085751606,0.0005591414,0.0005058421,0.000009834044,0.00057928753,0.02078045,0.00034504815,0.0012337385,0.02437826,0.95140886,0.000041709216],"about_ca_topic_score_codex":0.0016288093,"about_ca_topic_score_gemma":0.0048913276,"teacher_disagreement_score":0.05097685,"about_ca_system_score_codex":0.0011215509,"about_ca_system_score_gemma":0.0038426074,"threshold_uncertainty_score":0.17053455},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.324672,0.002604505,0.45829836,0.07779949,0.00082285865,0.013269991,0.0002802423,0.0013534932,0.12089904],"genre_scores_gemma":[0.636129,0.0010989703,0.33738232,0.004680252,0.00006748793,0.008610157,0.00013797912,0.0003215054,0.011572259],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.79234755,0.17669603,0.0033731977,0.0061373254,0.015142919,0.0063029276],"domain_scores_gemma":[0.82620126,0.10797608,0.008778625,0.027175061,0.017561488,0.012307555],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.19218004,0.00081509916,0.00079697144,0.0025462117,0.01139287,0.009852386,0.004855954,0.003791483,0.0030233387],"category_scores_gemma":[0.1307972,0.0009294704,0.0010449408,0.0015637387,0.03667002,0.007409338,0.039131865,0.009721707,0.000588992],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003056706,0.0016889002,0.0068497304,0.001815229,0.00009801161,0.00074798515,0.50282407,0.002446251,0.0040943567,0.15418679,0.013140957,0.31180215],"study_design_scores_gemma":[0.0006041663,0.0027661608,0.01596864,0.0045658895,0.00015175194,0.0016748358,0.31509665,0.009839427,0.012665326,0.19762656,0.43858218,0.0004583854],"about_ca_topic_score_codex":0.016576147,"about_ca_topic_score_gemma":0.026086483,"teacher_disagreement_score":0.9886071,"about_ca_system_score_codex":0.014013546,"about_ca_system_score_gemma":0.078792445,"threshold_uncertainty_score":0.99618584},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002431293,0.20158488,0.38924795,0.20016117,0.045426574,0.01348727,0.008450335,0.020194465,0.11901597],"genre_scores_gemma":[0.012088067,0.18343742,0.614105,0.04175692,0.018593034,0.025371745,0.0047557326,0.0056766067,0.09421543],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9843137,0.009472707,0.001894321,0.00051571295,0.003467415,0.00033617596],"domain_scores_gemma":[0.89201516,0.081694536,0.004554853,0.0043346244,0.01476503,0.0026357644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04423896,0.0023578191,0.0018248379,0.007130396,0.002631176,0.005821359,0.0034202426,0.0032835873,0.031142479],"category_scores_gemma":[0.06662714,0.0025242982,0.0012357614,0.0050963913,0.0055530104,0.006557946,0.0044602444,0.006747277,0.03297007],"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":[0.00003336695,0.000054506654,0.00024580368,0.0025274882,0.000014051753,0.0001356106,0.0033761072,0.00018375025,0.0015975725,0.003238489,0.7512865,0.23730676],"study_design_scores_gemma":[0.000018108356,0.000049275048,0.0012339738,0.004858904,0.000013704682,0.00041326208,0.0032134096,0.00033503995,0.00077764323,0.009525164,0.9794862,0.00007535822],"about_ca_topic_score_codex":0.007417682,"about_ca_topic_score_gemma":0.024313755,"teacher_disagreement_score":0.955761,"about_ca_system_score_codex":0.0028804373,"about_ca_system_score_gemma":0.011528025,"threshold_uncertainty_score":0.23396075},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007433842,0.005706164,0.9041824,0.025110366,0.0008012142,0.00084278366,0.0005019464,0.0005284331,0.054892823],"genre_scores_gemma":[0.27241287,0.005739728,0.71279585,0.0024758386,0.0007604481,0.0024052956,0.0010216365,0.00032687443,0.0020613933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8717062,0.08696309,0.016194293,0.0044401735,0.018817075,0.0018791697],"domain_scores_gemma":[0.75640327,0.16707675,0.014998055,0.025264148,0.03294519,0.00331265],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14355704,0.001978322,0.0020989587,0.030372294,0.0054166713,0.02683072,0.0054014563,0.006461643,0.003815275],"category_scores_gemma":[0.17429012,0.0014898884,0.002856412,0.022961866,0.045111895,0.05279907,0.01092932,0.008908512,0.00108246],"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":[0.0000099647505,0.00001536892,0.00027810404,0.0003091013,0.000024182025,0.000025401778,0.0017022231,0.0007075072,0.00010100974,0.98591805,0.0007396584,0.010169368],"study_design_scores_gemma":[0.00001251571,0.000019697602,0.00035645865,0.0012334869,0.000055095967,0.00005953932,0.0025016828,0.002393882,0.00031487443,0.9643639,0.028663443,0.000025519292],"about_ca_topic_score_codex":0.004927848,"about_ca_topic_score_gemma":0.0028544553,"teacher_disagreement_score":0.8564429,"about_ca_system_score_codex":0.0136686135,"about_ca_system_score_gemma":0.015407464,"threshold_uncertainty_score":0.7592113},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22239819,0.10553786,0.46643552,0.049435873,0.0038110141,0.022047807,0.0017171602,0.0008765429,0.12774006],"genre_scores_gemma":[0.8303401,0.0148064,0.14409085,0.002323204,0.00024325069,0.0066670487,0.00024398952,0.00008892781,0.0011962501],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7510795,0.19268712,0.01539647,0.0072405776,0.031469036,0.0021273438],"domain_scores_gemma":[0.49801952,0.39635867,0.036450792,0.020036008,0.046345737,0.00278919],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24529496,0.0014375158,0.00229275,0.009386039,0.0030112665,0.011177868,0.0028544918,0.002833164,0.0022642144],"category_scores_gemma":[0.39370838,0.0005446006,0.0032140526,0.006143621,0.012655461,0.0153175695,0.007192633,0.0032204415,0.00026780815],"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":[0.00094856427,0.0006753117,0.032122232,0.03147701,0.0024718114,0.00019690984,0.014219542,0.012262084,0.0014060846,0.23296112,0.0058060163,0.6654533],"study_design_scores_gemma":[0.0007501529,0.01270751,0.073251955,0.12610291,0.012245868,0.00076631334,0.03667605,0.033830717,0.031284977,0.48454562,0.18673554,0.0011023737],"about_ca_topic_score_codex":0.0050638192,"about_ca_topic_score_gemma":0.0069079,"teacher_disagreement_score":0.24529496,"about_ca_system_score_codex":0.019519778,"about_ca_system_score_gemma":0.035100214,"threshold_uncertainty_score":0.9306857},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03672469,0.034473903,0.05336807,0.79911196,0.0032190098,0.0012352094,0.0001643262,0.00028267215,0.07142026],"genre_scores_gemma":[0.81268775,0.021913478,0.08330489,0.06219544,0.0026219757,0.0015209154,0.00015162658,0.00031696647,0.015286854],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.83146757,0.13137539,0.0052532693,0.0049496344,0.01943589,0.0075182933],"domain_scores_gemma":[0.6644271,0.20007578,0.029879078,0.023006065,0.057104394,0.025507584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14643903,0.0006012259,0.0011486291,0.003143011,0.006968707,0.016105896,0.0021632388,0.0052516703,0.0045189857],"category_scores_gemma":[0.21164241,0.000766089,0.00067892217,0.0031426237,0.01645675,0.011304637,0.011198092,0.010957665,0.0008688378],"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":[0.00025783776,0.00054294243,0.021279262,0.0063694804,0.00015622909,0.00070863235,0.046607606,0.0018085195,0.0028025764,0.31012124,0.062853694,0.5464919],"study_design_scores_gemma":[0.00015718494,0.0005598525,0.031331982,0.01650966,0.00009562469,0.001077381,0.030948875,0.0020028057,0.0026318769,0.21113046,0.70336163,0.00019275607],"about_ca_topic_score_codex":0.009617765,"about_ca_topic_score_gemma":0.0070480807,"teacher_disagreement_score":0.14643903,"about_ca_system_score_codex":0.015265773,"about_ca_system_score_gemma":0.115126275,"threshold_uncertainty_score":0.77445287},"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":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034595077,0.7454893,0.0064532952,0.04128843,0.049591612,0.00034194495,0.0011009916,0.00075014576,0.15463828],"genre_scores_gemma":[0.0031331175,0.5163939,0.0074342554,0.01881801,0.017545162,0.00047765428,0.0022557897,0.00044388897,0.43349826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967595,0.00050336606,0.00015014618,0.00018498827,0.0023022152,0.000099764366],"domain_scores_gemma":[0.9902114,0.0030770916,0.0004332599,0.00026644886,0.0056001097,0.0004116597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023435315,0.0010954469,0.0015380732,0.0048723533,0.0008710614,0.0030217478,0.0014746591,0.001896363,0.060265068],"category_scores_gemma":[0.01145819,0.00052143,0.00096043665,0.005392158,0.00087565166,0.0028266232,0.0012118944,0.0041214274,0.047413737],"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":[0.0000067664787,0.000008540956,0.000020645168,0.0004364016,0.0000065518257,0.00001748542,0.000016680902,0.000049298942,0.00007270038,0.0010352599,0.9136596,0.084670015],"study_design_scores_gemma":[0.0000044861845,0.000009900919,0.00018924172,0.00067280896,0.000008220653,0.00011082388,0.000010976096,0.00005620658,0.000054411918,0.0009041024,0.9979722,0.0000065824265],"about_ca_topic_score_codex":0.004630316,"about_ca_topic_score_gemma":0.01009894,"teacher_disagreement_score":0.060265068,"about_ca_system_score_codex":0.0025664554,"about_ca_system_score_gemma":0.006469301,"threshold_uncertainty_score":0.20160675},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002272667,0.02210106,0.03961796,0.04606887,0.0043557724,0.00057427946,0.0011042007,0.0009407957,0.88296443],"genre_scores_gemma":[0.1832852,0.09161588,0.19317667,0.0623809,0.0030150677,0.001626428,0.0040844064,0.0011829954,0.45963252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98043525,0.0024744922,0.00050989137,0.0009893572,0.014232593,0.001358417],"domain_scores_gemma":[0.98553294,0.002541371,0.00024819496,0.0013847534,0.009680792,0.00061199564],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012445421,0.0008944912,0.00057088595,0.0044004973,0.0044862074,0.01418301,0.0036458035,0.0036923322,0.012927675],"category_scores_gemma":[0.017643018,0.0005633896,0.001384142,0.002532066,0.008431639,0.0076205432,0.006174379,0.005481214,0.0040805344],"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":[0.0000121464755,0.000028531278,0.00091461756,0.00034023589,0.000017569902,0.00011397709,0.0011913747,0.0014222137,0.0004923089,0.64076614,0.20893791,0.14576298],"study_design_scores_gemma":[0.000002452612,0.000009407815,0.00076105003,0.0006878646,0.000010505891,0.00007704125,0.00045855733,0.00045839886,0.00025878524,0.05301881,0.9442301,0.000027073182],"about_ca_topic_score_codex":0.39566666,"about_ca_topic_score_gemma":0.37861967,"teacher_disagreement_score":0.98755455,"about_ca_system_score_codex":0.031104619,"about_ca_system_score_gemma":0.09077602,"threshold_uncertainty_score":0.78672725},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083955914,0.067067884,0.5544153,0.0878014,0.0075105573,0.013439573,0.003070226,0.0006524392,0.18208669],"genre_scores_gemma":[0.68823445,0.018060291,0.23793478,0.022299463,0.0022045553,0.022960996,0.0029673288,0.0013037823,0.0040344545],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.18039726,0.56569016,0.082635514,0.028460598,0.13826351,0.004552877],"domain_scores_gemma":[0.026951646,0.8483456,0.028241906,0.04634461,0.04921635,0.00089984335],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.69458455,0.0018176126,0.0028870746,0.010707154,0.0057824086,0.016177079,0.006308811,0.009538685,0.018254071],"category_scores_gemma":[0.90643656,0.0025112233,0.0059784227,0.013441622,0.022645716,0.018514061,0.012058379,0.009864502,0.0035919107],"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":[0.0021176797,0.00091851194,0.07469164,0.052923117,0.0039749877,0.00047309804,0.043975234,0.0029321883,0.0018239276,0.37623358,0.018331872,0.42160425],"study_design_scores_gemma":[0.001488047,0.002732647,0.07919694,0.125629,0.0035340993,0.001305983,0.020736147,0.010836427,0.014989385,0.48414445,0.25476128,0.00064561935],"about_ca_topic_score_codex":0.0040738643,"about_ca_topic_score_gemma":0.0033540223,"teacher_disagreement_score":0.69458455,"about_ca_system_score_codex":0.011498475,"about_ca_system_score_gemma":0.022010894,"threshold_uncertainty_score":0.37663168},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9803278,0.0032794052,0.00072040485,0.007379397,0.000117362746,0.00039044264,0.0008337589,0.000075735064,0.0068757376],"genre_scores_gemma":[0.99617934,0.0008084067,0.0008907446,0.00051680335,0.000017850394,0.00009495189,0.00019695249,0.00001216148,0.0012828961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9930542,0.0017923751,0.0003979325,0.0006793383,0.0023676055,0.0017085143],"domain_scores_gemma":[0.969477,0.0049133883,0.003958635,0.00072000927,0.012703503,0.008227427],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007633796,0.00019405913,0.00022828674,0.001583311,0.002658039,0.0016317284,0.0016969709,0.0006060866,0.0017234168],"category_scores_gemma":[0.029059097,0.00024986756,0.00015997629,0.0019657004,0.00094170304,0.0006024446,0.0015253447,0.001182464,0.00023778349],"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":[0.00027768165,0.0004359506,0.83401656,0.00028015848,0.000030085755,0.00011671312,0.008807037,0.00044479943,0.000872635,0.0005483749,0.011968663,0.14220123],"study_design_scores_gemma":[0.000013028183,0.000119097276,0.98759055,0.0002314665,0.000008132505,0.00006749956,0.0054892194,0.00063868944,0.00030228103,0.00010712772,0.005413828,0.000019092598],"about_ca_topic_score_codex":0.9109828,"about_ca_topic_score_gemma":0.9516795,"teacher_disagreement_score":0.9923662,"about_ca_system_score_codex":0.03051505,"about_ca_system_score_gemma":0.069911726,"threshold_uncertainty_score":0.22140324},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34773543,0.38722995,0.15146782,0.020078668,0.009138639,0.058774214,0.0064986125,0.0020684665,0.017008219],"genre_scores_gemma":[0.85659873,0.03982757,0.07081957,0.0040594516,0.00086140865,0.025652893,0.0014529375,0.00016658416,0.00056089764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.69636625,0.27009705,0.013881337,0.0054322784,0.012427004,0.0017961094],"domain_scores_gemma":[0.4579752,0.46636924,0.03613812,0.022270383,0.014634673,0.0026123219],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17664038,0.0018295263,0.0074740946,0.0031118959,0.0014016004,0.0033179799,0.0041284165,0.004205432,0.008148614],"category_scores_gemma":[0.45988682,0.0014161168,0.01258361,0.004411014,0.0034248792,0.0036207219,0.002659425,0.00506386,0.000622766],"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":[0.22454704,0.011679543,0.036757186,0.16635361,0.15546016,0.00039117425,0.002372471,0.0452891,0.0004117565,0.019187331,0.014008633,0.32354194],"study_design_scores_gemma":[0.30921972,0.09523541,0.03464632,0.17079736,0.18466724,0.0004919149,0.0015283152,0.124068186,0.0027976031,0.04194119,0.03383366,0.0007732129],"about_ca_topic_score_codex":0.013810957,"about_ca_topic_score_gemma":0.009075825,"teacher_disagreement_score":0.8233596,"about_ca_system_score_codex":0.008145874,"about_ca_system_score_gemma":0.015009072,"threshold_uncertainty_score":0.9341748},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03756245,0.90215635,0.0049214126,0.028873974,0.00089509797,0.001366404,0.00016260847,0.0000435332,0.024018236],"genre_scores_gemma":[0.17177509,0.80989116,0.01097548,0.003750359,0.00018362247,0.002062065,0.00016513364,0.000032395965,0.0011647064],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.95532614,0.029822176,0.004952079,0.0010413864,0.0075173713,0.0013408315],"domain_scores_gemma":[0.8625405,0.10054769,0.008358493,0.0025754725,0.02391852,0.0020593752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09134414,0.00075235235,0.0016526813,0.01262659,0.006636509,0.010291821,0.002241972,0.0022073141,0.0013365988],"category_scores_gemma":[0.13252047,0.00092335616,0.0012842354,0.020929482,0.0064331996,0.005843442,0.0055248276,0.003365149,0.0001934126],"study_design_candidate":"systematic_review","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":[0.00015057859,0.0002846912,0.013135603,0.1499087,0.00079815683,0.0011065545,0.24612617,0.0011563824,0.00092553743,0.02526493,0.01030461,0.5508381],"study_design_scores_gemma":[0.000050749706,0.00022623705,0.0215317,0.60658187,0.001626203,0.0005586508,0.16310662,0.0005914895,0.00082146894,0.005481468,0.19931884,0.00010477355],"about_ca_topic_score_codex":0.17108598,"about_ca_topic_score_gemma":0.3403047,"teacher_disagreement_score":0.9086559,"about_ca_system_score_codex":0.030454526,"about_ca_system_score_gemma":0.16964439,"threshold_uncertainty_score":0.48307973},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041516972,0.050114382,0.002043955,0.9369376,0.007281173,0.000033312404,0.000056215355,0.000019335534,0.0030989829],"genre_scores_gemma":[0.06632336,0.10333632,0.030173948,0.77759963,0.019063482,0.000565028,0.00011771033,0.0002085092,0.0026120946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.673803,0.18782882,0.03711053,0.011454507,0.07905433,0.01074884],"domain_scores_gemma":[0.09518451,0.8268553,0.012382335,0.012483348,0.04592892,0.007165703],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4657592,0.0017990385,0.00637492,0.011116345,0.006191734,0.04720337,0.007932619,0.049315095,0.007495185],"category_scores_gemma":[0.601028,0.0019774456,0.004152474,0.010203616,0.064484715,0.050656546,0.024659911,0.060950257,0.0016792086],"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":[0.0003933713,0.00019051741,0.0017024688,0.010341545,0.0005497987,0.0002446034,0.007841732,0.0008489126,0.00036540866,0.5383019,0.33051288,0.108706884],"study_design_scores_gemma":[0.00036486585,0.00018836098,0.0016855064,0.039743718,0.00043887142,0.00025886216,0.009090711,0.0007534637,0.0006355341,0.45434242,0.4922572,0.00024049764],"about_ca_topic_score_codex":0.0264061,"about_ca_topic_score_gemma":0.05388627,"teacher_disagreement_score":0.53424084,"about_ca_system_score_codex":0.02977352,"about_ca_system_score_gemma":0.12862289,"threshold_uncertainty_score":0.6588141},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050392542,0.0033167112,0.67222977,0.022090007,0.00029014918,0.0017408215,0.0002830739,0.00022056531,0.24943635],"genre_scores_gemma":[0.70731765,0.0013407515,0.28309923,0.0006415731,0.00007806506,0.0016017812,0.000151574,0.000038867922,0.005730387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97899836,0.014330671,0.0012296258,0.0013030082,0.0035709846,0.000567454],"domain_scores_gemma":[0.98835605,0.005669502,0.0011827317,0.00091971847,0.0031829013,0.0006890482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015770419,0.00087739265,0.00060458377,0.004011459,0.0021276057,0.008789767,0.00119014,0.0015363949,0.0027077121],"category_scores_gemma":[0.019212045,0.00034553226,0.0013476574,0.0026048373,0.007678097,0.0062151337,0.0039417753,0.0021469481,0.00040761995],"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":[0.000031412357,0.00012817555,0.004516061,0.0002430601,0.00005205142,0.00013752331,0.0077365055,0.006939378,0.00047074273,0.9297755,0.0014187633,0.048550945],"study_design_scores_gemma":[0.00007063713,0.000318544,0.008863313,0.0008995513,0.00011480156,0.0005115488,0.010389796,0.06248728,0.0009105587,0.8639668,0.051336866,0.00013018648],"about_ca_topic_score_codex":0.003644899,"about_ca_topic_score_gemma":0.003735844,"teacher_disagreement_score":0.98422956,"about_ca_system_score_codex":0.008137407,"about_ca_system_score_gemma":0.00811211,"threshold_uncertainty_score":0.08340293},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89431304,0.0034176912,0.000486453,0.03897214,0.00064821384,0.00015453417,0.000117798285,0.00003657478,0.06185356],"genre_scores_gemma":[0.98961323,0.0014069806,0.00056270015,0.0018016831,0.00006387228,0.000043495267,0.000040297808,0.000007703538,0.0064601353],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99336034,0.0030295888,0.00015791137,0.00023209941,0.0015452235,0.0016747981],"domain_scores_gemma":[0.97354436,0.0075773145,0.0012100105,0.00074167806,0.0057540047,0.011172693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010102234,0.00014276826,0.00023326038,0.0008495605,0.0067855343,0.0037223077,0.0010399836,0.0009077607,0.010582295],"category_scores_gemma":[0.026210673,0.0001546893,0.00016297975,0.0012167628,0.0030809843,0.0017712589,0.0037567539,0.0022055442,0.0005937899],"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":[0.00019204806,0.0013571203,0.1127727,0.00078999344,0.000019890018,0.0015762026,0.521096,0.00014334093,0.0012675329,0.015458587,0.050317314,0.29500932],"study_design_scores_gemma":[0.00002917057,0.0005610318,0.09121159,0.0011453172,0.000012253979,0.00072286907,0.73428315,0.00014446258,0.0004418173,0.00083343266,0.17058189,0.00003298122],"about_ca_topic_score_codex":0.09798942,"about_ca_topic_score_gemma":0.25497028,"teacher_disagreement_score":0.09798942,"about_ca_system_score_codex":0.008551297,"about_ca_system_score_gemma":0.030736689,"threshold_uncertainty_score":0.1948381},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015919002,0.9957889,0.00064599485,0.0022540072,0.00030737897,0.00004848053,0.000029459383,0.000004874067,0.00076179026],"genre_scores_gemma":[0.007150604,0.9872291,0.0029808988,0.0018571087,0.00024936371,0.0002923147,0.000046479676,0.0000104859055,0.0001837017],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.95613563,0.025691966,0.006720818,0.002623962,0.007976341,0.0008513178],"domain_scores_gemma":[0.71975034,0.25537807,0.00820261,0.002904664,0.0130966995,0.0006675845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065578744,0.0015324521,0.006047579,0.013936713,0.0018041881,0.011145627,0.0029084785,0.0058383252,0.003817318],"category_scores_gemma":[0.19057418,0.0015654728,0.0033232872,0.013590975,0.0070370827,0.012653405,0.0038367603,0.005221483,0.0006603336],"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":[0.00012228912,0.00006981646,0.0010219003,0.33419642,0.0016735741,0.00011030678,0.0022881483,0.000656466,0.00016557523,0.037056535,0.009150406,0.6134886],"study_design_scores_gemma":[0.00006813911,0.00011740855,0.0020890674,0.7702009,0.0033032058,0.00018923162,0.0024228543,0.00039712852,0.0002981596,0.021607934,0.19922757,0.000078340025],"about_ca_topic_score_codex":0.019149529,"about_ca_topic_score_gemma":0.035859957,"teacher_disagreement_score":0.065578744,"about_ca_system_score_codex":0.011133331,"about_ca_system_score_gemma":0.030307837,"threshold_uncertainty_score":0.34681767},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874349,0.00038846047,0.0018303266,0.000896327,0.000026387435,0.00008226112,0.00003167924,0.000025870246,0.009283941],"genre_scores_gemma":[0.9982145,0.00019267415,0.0011019997,0.00008677136,0.000013472333,0.00003335977,0.000015813637,0.000006534096,0.00033487592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9615881,0.025355,0.002347956,0.0005328979,0.008674366,0.0015016776],"domain_scores_gemma":[0.8597965,0.09044551,0.02556789,0.0054815756,0.01429176,0.0044167745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026827011,0.00022680752,0.00025382583,0.0017764245,0.000809953,0.0035395373,0.00042483278,0.00033622343,0.0015895994],"category_scores_gemma":[0.09350289,0.00021346257,0.00039834462,0.0012683106,0.0012657034,0.0010945795,0.0015359685,0.00070584845,0.00021945439],"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":[0.00019870425,0.00091190636,0.7287162,0.0005545284,0.00016528269,0.000540332,0.040302232,0.0005948458,0.002477337,0.0011770772,0.0012724927,0.22308905],"study_design_scores_gemma":[0.00005185081,0.0014415976,0.9084529,0.00079164066,0.0000941508,0.0008897918,0.074685074,0.0013686487,0.00249451,0.0016600869,0.007978907,0.00009087266],"about_ca_topic_score_codex":0.00095662836,"about_ca_topic_score_gemma":0.0016291637,"teacher_disagreement_score":0.026827011,"about_ca_system_score_codex":0.001087173,"about_ca_system_score_gemma":0.002129585,"threshold_uncertainty_score":0.14187646},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58675736,0.003981771,0.027724873,0.016213601,0.00016876358,0.0001384582,0.00012075838,0.000102680206,0.36479163],"genre_scores_gemma":[0.9859542,0.00081864017,0.0017168528,0.0002732948,0.000023822164,0.00004110393,0.000024438681,0.000018133649,0.011129461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99606043,0.0022618365,0.00014297529,0.00042948133,0.00065093784,0.000454378],"domain_scores_gemma":[0.99579203,0.002384307,0.0005993858,0.0005202427,0.00035923062,0.00034483836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031509704,0.0003048399,0.0002708358,0.0012748878,0.0030233732,0.006376352,0.00082842127,0.0011848254,0.0068911845],"category_scores_gemma":[0.0059713055,0.00017775784,0.00036844387,0.001808808,0.014673276,0.004508153,0.0045160973,0.001974398,0.0005717381],"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":[0.00007392285,0.000114037895,0.017877372,0.00032456705,0.000027898923,0.00055392296,0.23832494,0.0013828155,0.0013001417,0.6794945,0.0013677417,0.059158217],"study_design_scores_gemma":[0.00004309931,0.00026916296,0.058227655,0.0009292496,0.000059522612,0.0008942372,0.27277032,0.0026537592,0.0025194092,0.3327581,0.32877502,0.000100597266],"about_ca_topic_score_codex":0.009602439,"about_ca_topic_score_gemma":0.008689017,"teacher_disagreement_score":0.009602439,"about_ca_system_score_codex":0.004839525,"about_ca_system_score_gemma":0.003915562,"threshold_uncertainty_score":0.035113394},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005569915,0.057699874,0.025247738,0.8377828,0.002141724,0.000098813434,0.000067758476,0.000029134804,0.071362175],"genre_scores_gemma":[0.7974184,0.07146238,0.031381126,0.08512458,0.008773374,0.0006194958,0.00009381048,0.00006637932,0.005060541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.7375047,0.21459483,0.010925577,0.0069613038,0.024927186,0.005086397],"domain_scores_gemma":[0.45630926,0.5005283,0.014678016,0.012211896,0.012633178,0.0036393406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17277244,0.0008178385,0.0028771372,0.005776316,0.005147312,0.026118303,0.0030267208,0.013327436,0.004856574],"category_scores_gemma":[0.32428133,0.00078759686,0.0010322989,0.0062760613,0.071071275,0.033072557,0.013890134,0.02223814,0.0006314887],"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":[0.000030265266,0.000023807119,0.00035294806,0.0003415295,0.00003136587,0.00003731054,0.0010549888,0.000368067,0.000023070514,0.9808941,0.002709133,0.014133307],"study_design_scores_gemma":[0.00002827632,0.000029096162,0.0002788732,0.0008988064,0.000014473871,0.00004405502,0.00066010945,0.00024545708,0.00007299485,0.97820926,0.0195021,0.00001635768],"about_ca_topic_score_codex":0.0028312423,"about_ca_topic_score_gemma":0.002552154,"teacher_disagreement_score":0.8272276,"about_ca_system_score_codex":0.012359692,"about_ca_system_score_gemma":0.0212825,"threshold_uncertainty_score":0.9137189},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86216754,0.00056393497,0.085716255,0.0029576146,0.00016308672,0.02875914,0.004570704,0.00059297617,0.014508748],"genre_scores_gemma":[0.8057263,0.00064234843,0.15360904,0.0008463023,0.000055249777,0.03354489,0.0037799457,0.000104639774,0.0016913452],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96838176,0.019272376,0.0040814853,0.0009624115,0.006261731,0.0010402622],"domain_scores_gemma":[0.88436294,0.073269404,0.009143131,0.0073388517,0.02378846,0.002097229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08529423,0.00055887585,0.00061853445,0.002505946,0.0008915124,0.0018952191,0.0011335787,0.0007958733,0.002517556],"category_scores_gemma":[0.106865235,0.0005916438,0.0016128063,0.00222032,0.001329788,0.001577166,0.0019505742,0.0019899039,0.00054297416],"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":[0.00047135734,0.0037656857,0.5104116,0.0019383709,0.00039982868,0.00021685424,0.031474784,0.008607997,0.002177327,0.004826849,0.0137078725,0.42200145],"study_design_scores_gemma":[0.0006554904,0.0033841978,0.8622364,0.0017527819,0.0003230838,0.0002987356,0.015335304,0.03206108,0.0050477376,0.007793605,0.070773505,0.00033805912],"about_ca_topic_score_codex":0.010589817,"about_ca_topic_score_gemma":0.014612422,"teacher_disagreement_score":0.08529423,"about_ca_system_score_codex":0.004399501,"about_ca_system_score_gemma":0.010984922,"threshold_uncertainty_score":0.45108438},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006719073,0.9607411,0.011592717,0.006087847,0.0005603586,0.0018809478,0.00008989941,0.000045623026,0.012282463],"genre_scores_gemma":[0.10241132,0.8405789,0.050424002,0.0025091707,0.0002290312,0.002676094,0.00017236079,0.00003160276,0.00096741115],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.89458525,0.08557206,0.0050912094,0.0020119003,0.0112716565,0.0014679661],"domain_scores_gemma":[0.85175943,0.123681545,0.008425537,0.0023591823,0.012539612,0.0012347917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11054212,0.0013561776,0.0027507085,0.008118256,0.001375437,0.0064334557,0.0020122707,0.0021285648,0.0014597567],"category_scores_gemma":[0.11904358,0.00064146746,0.0014109341,0.008101895,0.0030486928,0.006322289,0.0034741987,0.0027098518,0.00026773592],"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":[0.0001433548,0.00018173251,0.0016118283,0.063473724,0.00080674345,0.00006198251,0.0017704709,0.0019451114,0.0005167542,0.036657065,0.0031927961,0.88963854],"study_design_scores_gemma":[0.00057209533,0.0026283702,0.013989295,0.34019482,0.00565465,0.0004946259,0.011332874,0.0029184609,0.0058532464,0.06535048,0.5507066,0.00030448526],"about_ca_topic_score_codex":0.00867328,"about_ca_topic_score_gemma":0.020839503,"teacher_disagreement_score":0.8894579,"about_ca_system_score_codex":0.010174565,"about_ca_system_score_gemma":0.041683376,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8868902,0.00040380307,0.016254494,0.011811241,0.00026503086,0.00081112236,0.00005087864,0.00012447847,0.083388686],"genre_scores_gemma":[0.94198215,0.00024035847,0.023691675,0.0020609724,0.000037892987,0.0005089656,0.000042014934,0.000031719705,0.031404343],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97807294,0.014002658,0.00051038427,0.0014439933,0.0031806228,0.002789483],"domain_scores_gemma":[0.97215515,0.0074398085,0.0025044868,0.0035227325,0.0053971536,0.0089806765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021883802,0.0004379028,0.000540218,0.0011664862,0.015746204,0.014446326,0.0018493799,0.0021018994,0.006946699],"category_scores_gemma":[0.026189199,0.00044503342,0.0003781803,0.0009230359,0.008846811,0.00715683,0.014225942,0.003360486,0.001385621],"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":[0.00020265869,0.0017480988,0.037715457,0.00036243442,0.00012391916,0.000955235,0.7331278,0.00034118173,0.007489785,0.018178998,0.005985931,0.19376844],"study_design_scores_gemma":[0.000039617513,0.0007735867,0.025095684,0.00053637824,0.000065988934,0.0006811196,0.8804943,0.0006080238,0.0025608095,0.015358646,0.073648565,0.00013738056],"about_ca_topic_score_codex":0.0068526673,"about_ca_topic_score_gemma":0.018809803,"teacher_disagreement_score":0.021883802,"about_ca_system_score_codex":0.003357084,"about_ca_system_score_gemma":0.019029364,"threshold_uncertainty_score":0.11573398},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017377399,0.24330838,0.40687487,0.25637504,0.025497878,0.011360803,0.0013005505,0.0018142954,0.05173039],"genre_scores_gemma":[0.022654576,0.27714458,0.6395122,0.026689861,0.0134463385,0.013408878,0.0010882114,0.0012288314,0.004826531],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.31603724,0.52298456,0.066279404,0.016125895,0.07533789,0.0032349732],"domain_scores_gemma":[0.15034644,0.64611053,0.030823942,0.052332416,0.114432804,0.005953923],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.589359,0.004340861,0.009375223,0.043740407,0.008880106,0.049652457,0.009837108,0.018582141,0.016385846],"category_scores_gemma":[0.68807536,0.006123617,0.007947557,0.0441175,0.037563477,0.047078643,0.041582845,0.03172621,0.015605556],"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":[0.0001348249,0.00013039306,0.0011830113,0.06480149,0.0007450402,0.00049042876,0.02083499,0.0012245552,0.0008008496,0.21868785,0.109459184,0.5815074],"study_design_scores_gemma":[0.00014522513,0.0001524519,0.0010018939,0.19664891,0.00048449857,0.00052970997,0.0048427656,0.0012758654,0.00080354174,0.19841345,0.59535414,0.0003474731],"about_ca_topic_score_codex":0.007180206,"about_ca_topic_score_gemma":0.0077927336,"teacher_disagreement_score":0.410641,"about_ca_system_score_codex":0.01936133,"about_ca_system_score_gemma":0.117152706,"threshold_uncertainty_score":0.50639355},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073263975,0.0052856975,0.008427773,0.9717011,0.0048470045,0.00009253343,0.000028650597,0.00006425227,0.008820285],"genre_scores_gemma":[0.19664593,0.0421768,0.23360392,0.43632755,0.027047014,0.0035091543,0.0005851896,0.00045640726,0.05964811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8874842,0.08530278,0.0040766275,0.0032163118,0.014569354,0.005350698],"domain_scores_gemma":[0.7169568,0.20731424,0.0044920375,0.009005079,0.041140605,0.021091338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23091614,0.0014987355,0.002192324,0.0045289584,0.01670988,0.04696918,0.0060420213,0.03519886,0.01551521],"category_scores_gemma":[0.12227282,0.001138386,0.0023055715,0.0027998602,0.033470687,0.042745527,0.020827034,0.047389716,0.0035844285],"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":[0.00010148551,0.0004040356,0.00039642875,0.0005499346,0.00001859656,0.00018626281,0.0069373534,0.0006915218,0.00023245889,0.7886399,0.13979891,0.06204302],"study_design_scores_gemma":[0.00009011104,0.00014273533,0.0002542187,0.0031624169,0.000021587886,0.00011205209,0.021766627,0.0015121228,0.00037429572,0.4849784,0.48748916,0.00009629417],"about_ca_topic_score_codex":0.0053630266,"about_ca_topic_score_gemma":0.0050735055,"teacher_disagreement_score":0.23091614,"about_ca_system_score_codex":0.023225812,"about_ca_system_score_gemma":0.08922476,"threshold_uncertainty_score":0.9484173},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16821562,0.07840067,0.51220894,0.09649812,0.004732037,0.00990442,0.004595739,0.0013355269,0.12410891],"genre_scores_gemma":[0.709997,0.0068900497,0.2701198,0.0040367283,0.0007491513,0.006250464,0.0007556972,0.00016281962,0.0010383617],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5690457,0.3140189,0.035964943,0.0111700455,0.0664008,0.0033996203],"domain_scores_gemma":[0.2913031,0.5301515,0.075501055,0.024743462,0.07447234,0.0038284445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2710896,0.0018843102,0.0023825238,0.012973354,0.002347106,0.011785931,0.0033978296,0.0031046106,0.003683549],"category_scores_gemma":[0.48825654,0.0007321241,0.0024739772,0.015268883,0.010306364,0.0147631485,0.0043493453,0.0037746655,0.0011054128],"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":[0.0004268889,0.0008155491,0.16662458,0.021358488,0.0023916732,0.00008667664,0.012553566,0.0067453994,0.0013365614,0.11098103,0.024641642,0.6520379],"study_design_scores_gemma":[0.0005208525,0.0053931787,0.3538479,0.06304494,0.003431307,0.0008522594,0.048576422,0.037367333,0.014073665,0.24951422,0.22216628,0.0012116907],"about_ca_topic_score_codex":0.004256167,"about_ca_topic_score_gemma":0.0028589352,"teacher_disagreement_score":0.2710896,"about_ca_system_score_codex":0.011460155,"about_ca_system_score_gemma":0.014854804,"threshold_uncertainty_score":0.8988763},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021492771,0.49311006,0.11209678,0.26511914,0.024421789,0.0009063494,0.0007069637,0.00040992393,0.101079695],"genre_scores_gemma":[0.06920272,0.6011276,0.1878337,0.06786297,0.0373251,0.0033852432,0.0005965391,0.00057379936,0.032092325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9788159,0.014933281,0.0016924834,0.0008532145,0.0032732284,0.00043192357],"domain_scores_gemma":[0.9158549,0.073945284,0.002183668,0.0016299362,0.005074736,0.001311441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024138834,0.0010699837,0.0012309572,0.008949646,0.004066679,0.013001649,0.0015747607,0.0058463486,0.008969664],"category_scores_gemma":[0.038593676,0.0007639079,0.0012394218,0.0081378035,0.014006103,0.011548903,0.004717198,0.010706973,0.00257341],"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":[0.000059849226,0.00016739858,0.0009841742,0.0033988284,0.000029328792,0.00020115933,0.0043575405,0.0008645074,0.00040412138,0.607442,0.16270956,0.21938147],"study_design_scores_gemma":[0.000010686496,0.00006617831,0.00082143233,0.009038984,0.00001010298,0.00034321187,0.0014944194,0.0005413572,0.0001567873,0.20399098,0.78347296,0.000052950923],"about_ca_topic_score_codex":0.003155035,"about_ca_topic_score_gemma":0.0040046386,"teacher_disagreement_score":0.024138834,"about_ca_system_score_codex":0.00736585,"about_ca_system_score_gemma":0.010225242,"threshold_uncertainty_score":0.12765992},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38856483,0.1011065,0.3511124,0.05531132,0.0060122116,0.004419861,0.0027724896,0.0010192166,0.08968115],"genre_scores_gemma":[0.7334599,0.015775695,0.22837129,0.00580916,0.00114626,0.0042126686,0.001662301,0.00042855693,0.009134132],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7787072,0.14353797,0.020579558,0.00871349,0.045224786,0.0032369606],"domain_scores_gemma":[0.44414747,0.37206316,0.015976164,0.045808766,0.11785082,0.0041536433],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29382333,0.0011370649,0.0010500451,0.007744558,0.0028428002,0.0066816825,0.0028888118,0.0024554841,0.0011690358],"category_scores_gemma":[0.4004347,0.0007624566,0.0017215624,0.0059763263,0.0077546164,0.0049747624,0.0060847015,0.005603417,0.0006778603],"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":[0.00080728915,0.00039507935,0.08992672,0.0018728053,0.0003524519,0.0002203083,0.0386763,0.0010413541,0.0057734097,0.030160196,0.0102571165,0.820517],"study_design_scores_gemma":[0.00039637816,0.0023984127,0.50681716,0.012331157,0.00060516474,0.0025357595,0.026484294,0.005530253,0.028405616,0.021566724,0.39248377,0.00044526695],"about_ca_topic_score_codex":0.062450353,"about_ca_topic_score_gemma":0.052053493,"teacher_disagreement_score":0.99225545,"about_ca_system_score_codex":0.009571009,"about_ca_system_score_gemma":0.029911483,"threshold_uncertainty_score":0.87084156},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033632882,0.0010315088,0.8915009,0.0027412835,0.00057808566,0.0047950335,0.0018917887,0.0021547691,0.06167375],"genre_scores_gemma":[0.35530335,0.00051971537,0.6301973,0.00053574215,0.00017421306,0.008461528,0.0005099965,0.00045214625,0.0038460207],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80054855,0.15563601,0.007905859,0.006075598,0.028572597,0.001261403],"domain_scores_gemma":[0.42756796,0.50194436,0.01801471,0.023292689,0.027511492,0.0016687614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15864317,0.0025990745,0.0020629615,0.02199066,0.0034022683,0.008886466,0.0033808867,0.0022489117,0.017076278],"category_scores_gemma":[0.38583562,0.0010121651,0.0033552914,0.014081496,0.0067678406,0.011198437,0.0070231427,0.0039681382,0.0018370601],"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":[0.0020603633,0.00072732155,0.037675854,0.0046216124,0.001673442,0.0002639436,0.017323636,0.007871129,0.0038361275,0.30951184,0.016036939,0.5983978],"study_design_scores_gemma":[0.0009098262,0.0030157922,0.039566368,0.0045473957,0.0015895261,0.0009388039,0.01849456,0.1118024,0.01836095,0.7010918,0.09889362,0.00078890007],"about_ca_topic_score_codex":0.003145752,"about_ca_topic_score_gemma":0.002746035,"teacher_disagreement_score":0.15864317,"about_ca_system_score_codex":0.004120034,"about_ca_system_score_gemma":0.0059584496,"threshold_uncertainty_score":0.83899534},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00449222,0.009270862,0.3465315,0.5250461,0.013788958,0.025243698,0.00040640042,0.0025969734,0.072623156],"genre_scores_gemma":[0.12019704,0.0061103688,0.67341167,0.081299834,0.0076920465,0.08567145,0.0004060316,0.0016083736,0.023603184],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.15579289,0.7610909,0.03397039,0.005320617,0.039620377,0.0042048665],"domain_scores_gemma":[0.07767825,0.662416,0.027154218,0.06737406,0.14697546,0.018402003],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7604818,0.0019954361,0.0035572334,0.007348035,0.017366873,0.037428286,0.011757409,0.022521289,0.023001522],"category_scores_gemma":[0.8246855,0.0031413184,0.002529413,0.009628253,0.02122856,0.038188193,0.019367903,0.021087283,0.013540733],"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":[0.00091894245,0.0005373446,0.002443277,0.0047874395,0.00017886718,0.00044305722,0.023222001,0.002098235,0.00074799743,0.1873815,0.30288774,0.4743536],"study_design_scores_gemma":[0.0010436028,0.0008586919,0.0024328653,0.020705853,0.00018681528,0.00050832337,0.018717462,0.006069063,0.0009877452,0.20815669,0.7399121,0.0004207563],"about_ca_topic_score_codex":0.005656249,"about_ca_topic_score_gemma":0.007651643,"teacher_disagreement_score":0.23951823,"about_ca_system_score_codex":0.022286851,"about_ca_system_score_gemma":0.08745787,"threshold_uncertainty_score":0.29536867},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20149128,0.0032225065,0.01950207,0.041998267,0.00024367255,0.0011162533,0.0010109385,0.00013572189,0.73127925],"genre_scores_gemma":[0.9706652,0.0009035241,0.008060671,0.00045654032,0.000038763166,0.00016257595,0.00018560632,0.000022857403,0.019504312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9849888,0.0033172192,0.0004198814,0.000892857,0.004684667,0.0056965277],"domain_scores_gemma":[0.9870083,0.0015108037,0.00086251454,0.00034379258,0.004738884,0.0055356817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070750387,0.00056856504,0.0005149483,0.0068319677,0.019166818,0.018887997,0.0027121855,0.0020134079,0.007365163],"category_scores_gemma":[0.010694384,0.00046840846,0.0005685049,0.008107033,0.021150377,0.0040369364,0.005771706,0.0019947307,0.00044668734],"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":[0.000035081004,0.00007455403,0.01459075,0.00010595901,0.000018516545,0.00031849102,0.024591431,0.0048615173,0.00025154307,0.9179264,0.0086251665,0.028600566],"study_design_scores_gemma":[0.00006527523,0.00012308788,0.15528764,0.0010654109,0.000045772416,0.00020716172,0.2008085,0.019542584,0.00044112388,0.2218605,0.4002685,0.00028442472],"about_ca_topic_score_codex":0.9751483,"about_ca_topic_score_gemma":0.9775473,"teacher_disagreement_score":0.72383595,"about_ca_system_score_codex":0.27616403,"about_ca_system_score_gemma":0.31682086,"threshold_uncertainty_score":0.83954716},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025681776,0.83438975,0.0026890473,0.09796096,0.016268464,0.000044864602,0.0010595182,0.0002913214,0.047039323],"genre_scores_gemma":[0.002694498,0.9056168,0.0029353944,0.0073142066,0.0035305566,0.00006313481,0.0010545554,0.00022262079,0.076568134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971506,0.0005415483,0.00019547774,0.00023778014,0.0017152742,0.00015943462],"domain_scores_gemma":[0.9935368,0.0024624038,0.0004411564,0.000110180335,0.0026058028,0.0008436685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044717244,0.0024949126,0.00161832,0.0027683012,0.0018423796,0.006870633,0.0019351414,0.0037791904,0.040392518],"category_scores_gemma":[0.008567439,0.0014098247,0.0007593293,0.0048820153,0.0012149944,0.008392255,0.0018527075,0.004991578,0.04469284],"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":[0.000015675827,0.000008382348,0.00011767057,0.00040993033,0.0000065818404,0.000013294048,0.00009066051,0.000055126053,0.000035942776,0.00092764234,0.90956366,0.088755436],"study_design_scores_gemma":[0.000010814811,0.000012024531,0.0006514283,0.0015814936,0.00003212541,0.00008004327,0.0003293481,0.00008822722,0.00013403677,0.001775349,0.99528307,0.000022073134],"about_ca_topic_score_codex":0.07961105,"about_ca_topic_score_gemma":0.19676358,"teacher_disagreement_score":0.07961105,"about_ca_system_score_codex":0.0035593587,"about_ca_system_score_gemma":0.0136534,"threshold_uncertainty_score":0.15829533},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42127758,0.0025967339,0.06568712,0.03446166,0.00031701723,0.0008362613,0.00007247347,0.0002288338,0.4745223],"genre_scores_gemma":[0.97751355,0.00072277524,0.017691167,0.0012212738,0.000034505654,0.00018560844,0.000022378394,0.000022787843,0.0025859778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97972775,0.01454976,0.00053702795,0.000953844,0.0030716392,0.0011599814],"domain_scores_gemma":[0.9604805,0.022535373,0.003195857,0.003978023,0.0051612174,0.0046489886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028319275,0.00045418993,0.0004527891,0.0021930616,0.0034137084,0.0082090525,0.0012255907,0.0012672492,0.004696314],"category_scores_gemma":[0.042446777,0.0002521908,0.0004197633,0.0009766165,0.010308971,0.0040013553,0.018981228,0.002504554,0.00064041524],"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":[0.0001009441,0.001815919,0.030228509,0.0013862639,0.000107747815,0.0006693709,0.10262859,0.0018127717,0.0064323614,0.39800307,0.013858843,0.44295555],"study_design_scores_gemma":[0.00018901326,0.0013993714,0.06276729,0.0074074087,0.0002501737,0.0013165745,0.12950696,0.008233656,0.016727118,0.4272925,0.3447048,0.00020513812],"about_ca_topic_score_codex":0.0028659892,"about_ca_topic_score_gemma":0.0044159414,"teacher_disagreement_score":0.028319275,"about_ca_system_score_codex":0.0049649253,"about_ca_system_score_gemma":0.015372896,"threshold_uncertainty_score":0.14976841},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6494888,0.020885205,0.06676033,0.096508235,0.0029041667,0.05619795,0.0034416504,0.00047573674,0.10333795],"genre_scores_gemma":[0.80505764,0.011138608,0.12388856,0.008656789,0.00039267205,0.03312025,0.0010640708,0.00023184516,0.016449507],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.77177984,0.19772568,0.009551936,0.0027739326,0.015222512,0.002946099],"domain_scores_gemma":[0.620745,0.29883775,0.01009285,0.014996763,0.050696034,0.004631512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23456806,0.0009456934,0.0011098423,0.002978276,0.008527644,0.0032891664,0.0027532747,0.0024250364,0.005034613],"category_scores_gemma":[0.23170958,0.0010511341,0.0016072318,0.0044075367,0.0033641767,0.0029671083,0.007864915,0.0033976228,0.0006043009],"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":[0.002276642,0.003361068,0.014366671,0.017108671,0.0006661436,0.002301998,0.26242426,0.0027067275,0.0030742008,0.008283934,0.042503946,0.64092577],"study_design_scores_gemma":[0.005262436,0.01754191,0.033744372,0.055838116,0.0021356437,0.0018854991,0.3986527,0.0022066496,0.01676114,0.013934158,0.45144415,0.0005932776],"about_ca_topic_score_codex":0.021393307,"about_ca_topic_score_gemma":0.0645745,"teacher_disagreement_score":0.23456806,"about_ca_system_score_codex":0.015361561,"about_ca_system_score_gemma":0.030460864,"threshold_uncertainty_score":0.9439139},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011792807,0.019680224,0.0675969,0.65624225,0.0019139872,0.00031018216,0.00014935709,0.00023370991,0.24208061],"genre_scores_gemma":[0.8789356,0.012066994,0.06512589,0.0278518,0.0016163383,0.0006561608,0.00011325679,0.00020757936,0.013426369],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93035036,0.053247668,0.0017406618,0.0020178468,0.008954577,0.0036888996],"domain_scores_gemma":[0.844893,0.11287359,0.0024957103,0.008203682,0.019616922,0.011917001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14209332,0.0006126314,0.0013493366,0.004494672,0.01002778,0.029085018,0.003113685,0.010088525,0.010624074],"category_scores_gemma":[0.062702276,0.00045402348,0.00093105074,0.0038718637,0.06833034,0.025324795,0.01620573,0.0096302265,0.0006436743],"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":[0.00003322923,0.00006399863,0.0005933473,0.00018619254,0.000005984071,0.00013644007,0.0040975944,0.00022294789,0.00012614805,0.93027824,0.009247506,0.05500844],"study_design_scores_gemma":[0.00003463264,0.00008293515,0.00078522024,0.0015409491,0.000012715693,0.00018213633,0.015428943,0.0011825925,0.00044092612,0.7523744,0.22787967,0.000054856326],"about_ca_topic_score_codex":0.016845072,"about_ca_topic_score_gemma":0.02502723,"teacher_disagreement_score":0.14209332,"about_ca_system_score_codex":0.030924585,"about_ca_system_score_gemma":0.054320794,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059832293,0.011965614,0.053489186,0.8735017,0.0077145007,0.00042223986,0.00018649615,0.0004034474,0.046333656],"genre_scores_gemma":[0.5144612,0.023773916,0.119274236,0.3002791,0.0126276035,0.0054843808,0.0005058062,0.0010116689,0.022581944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5986979,0.30139616,0.008899871,0.02328611,0.06197882,0.0057411273],"domain_scores_gemma":[0.686712,0.20256817,0.016386362,0.044474315,0.034091357,0.015767766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24752223,0.0020824804,0.0031848792,0.003204248,0.017051062,0.027067024,0.007052557,0.01585068,0.009334419],"category_scores_gemma":[0.24959368,0.0013436928,0.0015127229,0.0044114953,0.088570274,0.05902748,0.03471864,0.030333256,0.0038723014],"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":[0.000102194375,0.00014853293,0.001572854,0.0010219946,0.0001187852,0.00047213078,0.031691305,0.00022854758,0.00017999999,0.8584827,0.061198305,0.04478268],"study_design_scores_gemma":[0.0000941895,0.0001325755,0.00056096585,0.0021158417,0.00003309381,0.00035407854,0.018006554,0.0005769245,0.00025743555,0.7529565,0.22482282,0.000088996705],"about_ca_topic_score_codex":0.0026273946,"about_ca_topic_score_gemma":0.0020643617,"teacher_disagreement_score":0.24752223,"about_ca_system_score_codex":0.00938037,"about_ca_system_score_gemma":0.024031756,"threshold_uncertainty_score":0.92793906},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011183418,0.98951983,0.0029404573,0.002761074,0.00041462664,0.0009197474,0.00025210646,0.000023399221,0.0020504233],"genre_scores_gemma":[0.016012272,0.97255784,0.0075911614,0.0010326327,0.00019461851,0.0020250916,0.00030545692,0.000027453656,0.00025339136],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.8831443,0.06618196,0.028251035,0.0032737223,0.01793993,0.0012090234],"domain_scores_gemma":[0.56652033,0.34349766,0.030329645,0.0073116445,0.051085044,0.0012555915],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17074722,0.0018487164,0.004163675,0.035633203,0.0023758665,0.007143104,0.002581965,0.0028559405,0.0031844128],"category_scores_gemma":[0.35214257,0.0016521544,0.0054588346,0.02698022,0.002985786,0.009955379,0.0046141054,0.003138896,0.0005955464],"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":[0.00013938113,0.000056326073,0.0016012695,0.4223826,0.0015198087,0.00014339648,0.0033501722,0.0005047263,0.00030374498,0.005759147,0.008148799,0.5560906],"study_design_scores_gemma":[0.000030854782,0.00007082749,0.0019553187,0.918065,0.0032461816,0.00014615459,0.0014680005,0.00020542809,0.00031377954,0.0023197618,0.07213477,0.000043838434],"about_ca_topic_score_codex":0.010697138,"about_ca_topic_score_gemma":0.024896147,"teacher_disagreement_score":0.8292528,"about_ca_system_score_codex":0.009703105,"about_ca_system_score_gemma":0.045269195,"threshold_uncertainty_score":0.9030084},"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":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005811185,0.0068706707,0.6832229,0.25691152,0.0015659018,0.00042037497,0.0003004015,0.00091940607,0.04397767],"genre_scores_gemma":[0.19122486,0.0074707316,0.75980294,0.029815705,0.000844669,0.0018827337,0.0002160995,0.0005887783,0.008153477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8867143,0.087648,0.006189625,0.0030090485,0.013725625,0.0027134086],"domain_scores_gemma":[0.73333734,0.20329423,0.011693576,0.021527793,0.0256196,0.0045274487],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13526611,0.0034496547,0.0023153496,0.010197193,0.007021025,0.023953253,0.0066811573,0.010534984,0.016232397],"category_scores_gemma":[0.19938056,0.0020021733,0.0041731545,0.009866575,0.031096162,0.046181925,0.01383625,0.017562151,0.00262132],"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":[0.00012879635,0.000060343187,0.00051588647,0.0005242855,0.00007196351,0.00007535751,0.0014812937,0.0014888886,0.00012154603,0.9488213,0.009260462,0.037449926],"study_design_scores_gemma":[0.00007838908,0.00006419137,0.00016649722,0.0011701725,0.00007119406,0.00009212193,0.0013047889,0.004308925,0.0005761785,0.9661943,0.025861325,0.00011199457],"about_ca_topic_score_codex":0.006454142,"about_ca_topic_score_gemma":0.01042634,"teacher_disagreement_score":0.8647339,"about_ca_system_score_codex":0.013014523,"about_ca_system_score_gemma":0.015031427,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049244385,0.02213929,0.03301077,0.7488096,0.002039265,0.00046921053,0.00007950552,0.00022565016,0.14398237],"genre_scores_gemma":[0.9511169,0.0057064584,0.015690472,0.021431074,0.00046282852,0.0003350617,0.00003989928,0.00008749222,0.005129704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7660972,0.20100054,0.005468497,0.004691394,0.014813663,0.007928692],"domain_scores_gemma":[0.7466571,0.18109864,0.0072259614,0.012926741,0.033110105,0.018981446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1880239,0.0005039469,0.0013340407,0.0035349743,0.010893944,0.023964677,0.0024117117,0.0049678497,0.0060449573],"category_scores_gemma":[0.14101927,0.00042493665,0.0010275705,0.0029397935,0.03386069,0.017871497,0.023878569,0.010142431,0.00067145954],"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":[0.00029795236,0.000245872,0.010181705,0.0016732202,0.000105648745,0.00044016683,0.06258026,0.0013001222,0.0004543283,0.6220421,0.025283115,0.27539548],"study_design_scores_gemma":[0.00011176498,0.0003792304,0.011014087,0.009031746,0.000083102874,0.00048885634,0.16665983,0.00189906,0.00079542794,0.55313975,0.25626212,0.00013510596],"about_ca_topic_score_codex":0.024868038,"about_ca_topic_score_gemma":0.02787636,"teacher_disagreement_score":0.1880239,"about_ca_system_score_codex":0.029456606,"about_ca_system_score_gemma":0.09032187,"threshold_uncertainty_score":0.99437726},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010148688,0.0014336972,0.004878956,0.97924715,0.0075335987,0.00014076204,0.00011017112,0.00014420418,0.005496657],"genre_scores_gemma":[0.081218466,0.0032417288,0.027858082,0.8653024,0.008250955,0.0006332938,0.0003598659,0.00021671326,0.012918473],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95983285,0.022091832,0.0029640857,0.0019027111,0.01124834,0.0019601071],"domain_scores_gemma":[0.82769966,0.070351794,0.007535187,0.0077259643,0.072123885,0.014563477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05018012,0.00071379537,0.00052871194,0.0009664163,0.0025489284,0.00715646,0.0032722482,0.010358087,0.021851318],"category_scores_gemma":[0.20288767,0.00024707874,0.0010216526,0.001021311,0.005875621,0.009960103,0.006379461,0.011234768,0.00763333],"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":[0.0002557873,0.00018641516,0.00344347,0.0019360544,0.00007919652,0.0003372944,0.0025284393,0.00043027554,0.00039067568,0.04394257,0.84827924,0.098190546],"study_design_scores_gemma":[0.00021588113,0.00016970886,0.0062792767,0.009691582,0.00014803823,0.0008726297,0.013904585,0.0011148141,0.0015408647,0.14072892,0.8251987,0.00013500106],"about_ca_topic_score_codex":0.007997817,"about_ca_topic_score_gemma":0.01199146,"teacher_disagreement_score":0.05018012,"about_ca_system_score_codex":0.0066758874,"about_ca_system_score_gemma":0.03706459,"threshold_uncertainty_score":0.26538104},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022836037,0.0054322802,0.0013980425,0.05494052,0.012560239,0.00056984235,0.046649016,0.0013216067,0.87484485],"genre_scores_gemma":[0.0067517404,0.00282795,0.0027971766,0.002727033,0.0007521595,0.00060623355,0.020341609,0.00037957486,0.9628166],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818915,0.00034683014,0.00006694606,0.00023349028,0.000932389,0.00023109377],"domain_scores_gemma":[0.99531037,0.0003420622,0.000114639384,0.00014007612,0.0020422712,0.0020505604],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004215646,0.0008031819,0.0005145528,0.0010806441,0.0027882976,0.003791099,0.00090701936,0.0018346101,0.39331603],"category_scores_gemma":[0.0058940803,0.00033745897,0.00022085027,0.0013204437,0.0005254822,0.0016319125,0.0024554257,0.0019092015,0.15696572],"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":[0.000015424734,0.000013647361,0.00012210601,0.000020075287,9.534906e-7,0.000004468906,0.000016550217,0.000011594212,0.000024997134,0.0003962221,0.989808,0.009565975],"study_design_scores_gemma":[0.0000101301775,0.000010344243,0.0018615543,0.000056185476,0.0000016493259,0.0000042214,0.00011475738,0.000031915788,0.000032971013,0.00020278139,0.99766976,0.0000037903158],"about_ca_topic_score_codex":0.05372943,"about_ca_topic_score_gemma":0.21091972,"teacher_disagreement_score":0.39331603,"about_ca_system_score_codex":0.0035024981,"about_ca_system_score_gemma":0.018131495,"threshold_uncertainty_score":0.86536103},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037430964,0.008599939,0.27677685,0.43664354,0.0017987639,0.0018574911,0.00089327234,0.0013169713,0.2346822],"genre_scores_gemma":[0.7503338,0.0052930596,0.22206052,0.013814055,0.00086417125,0.0014626549,0.00042859514,0.00051277294,0.005230416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75388515,0.20096162,0.0061056134,0.005374395,0.028184028,0.0054892506],"domain_scores_gemma":[0.46911523,0.39444226,0.014920923,0.054502267,0.055679604,0.011339776],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29168347,0.00096683024,0.0016113321,0.010751217,0.0071016117,0.03247223,0.0040552625,0.00439639,0.007337917],"category_scores_gemma":[0.3863321,0.0008763666,0.0012865921,0.007354476,0.030315235,0.025495892,0.028255202,0.009085196,0.0012335018],"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":[0.00025264506,0.00032034024,0.01445762,0.0016564878,0.00021644765,0.00023302672,0.016271628,0.006796411,0.0010413254,0.50544757,0.03871245,0.41459423],"study_design_scores_gemma":[0.0001667841,0.00029438708,0.00705254,0.007164982,0.00015141109,0.00013934137,0.022254148,0.017871717,0.0028497379,0.7081873,0.23361577,0.00025188885],"about_ca_topic_score_codex":0.035115913,"about_ca_topic_score_gemma":0.040245265,"teacher_disagreement_score":0.70831656,"about_ca_system_score_codex":0.02103991,"about_ca_system_score_gemma":0.085032985,"threshold_uncertainty_score":0.8734804},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3580056,0.004671845,0.30241552,0.060223587,0.00066111697,0.0025401593,0.000128205,0.0006977804,0.27065608],"genre_scores_gemma":[0.8899449,0.0018544388,0.09907007,0.0016885985,0.00011980005,0.0008634146,0.00007418987,0.00029335383,0.0060913158],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7824162,0.18828224,0.003842007,0.0044532837,0.015454425,0.0055518877],"domain_scores_gemma":[0.77210945,0.19037807,0.006190107,0.016457016,0.010409931,0.004455343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14450368,0.0010996399,0.0010882849,0.0047523933,0.0143273035,0.025672197,0.0041113175,0.0035096633,0.004658425],"category_scores_gemma":[0.1409175,0.0010507826,0.0008615296,0.0049672793,0.040490244,0.024430975,0.03845503,0.006794838,0.0013565433],"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":[0.000100889585,0.00029021513,0.0035529751,0.0008632347,0.000050840994,0.0007248338,0.68882275,0.0010899641,0.0011077928,0.087367915,0.003782032,0.21224654],"study_design_scores_gemma":[0.00009922158,0.0003996041,0.002716248,0.004130207,0.00007932512,0.0009215772,0.65477103,0.003782847,0.0038166582,0.1856723,0.14344478,0.00016621969],"about_ca_topic_score_codex":0.0044906866,"about_ca_topic_score_gemma":0.005206295,"teacher_disagreement_score":0.14450368,"about_ca_system_score_codex":0.01075694,"about_ca_system_score_gemma":0.030017216,"threshold_uncertainty_score":0.7642177},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8337874,0.0040885573,0.13529131,0.0020454957,0.00034963345,0.013808451,0.0036605017,0.00034416397,0.006624524],"genre_scores_gemma":[0.9708527,0.00028700932,0.021257669,0.00087418064,0.000075017946,0.004355119,0.0014514003,0.000085672196,0.00076124346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.48172444,0.45974758,0.016775545,0.014141157,0.0242649,0.0033464346],"domain_scores_gemma":[0.09748184,0.8389078,0.02846525,0.027594624,0.0067491387,0.0008013463],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46775803,0.0016880762,0.0033362298,0.001987375,0.0025879594,0.0041682366,0.0035698393,0.0031267637,0.0034404115],"category_scores_gemma":[0.567759,0.0011004757,0.007864869,0.0038619782,0.005747186,0.0032667613,0.0043591773,0.005558988,0.0003693656],"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":[0.14588943,0.015403617,0.43255904,0.007648292,0.08410888,0.002010055,0.010201201,0.12556145,0.005223612,0.02575929,0.005854119,0.13978098],"study_design_scores_gemma":[0.028595686,0.061694484,0.47365364,0.0020011351,0.062180143,0.0014600357,0.007201477,0.23888637,0.036394075,0.058778718,0.027412457,0.0017417987],"about_ca_topic_score_codex":0.045614198,"about_ca_topic_score_gemma":0.01851203,"teacher_disagreement_score":0.53224194,"about_ca_system_score_codex":0.00800491,"about_ca_system_score_gemma":0.007471902,"threshold_uncertainty_score":0.65634906},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016261302,0.016437937,0.0023297393,0.20177864,0.07338272,0.00075858773,0.022183407,0.0021387872,0.6793641],"genre_scores_gemma":[0.004596487,0.0075047254,0.0026546319,0.010754387,0.0047562663,0.00066410896,0.01029767,0.0004831556,0.95828867],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995862,0.0010746768,0.00017398657,0.0005210367,0.0018639308,0.0005042027],"domain_scores_gemma":[0.99052435,0.0011107149,0.00035662847,0.00039008542,0.0038738044,0.0037444092],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011372892,0.0013177345,0.0007799114,0.0015004034,0.0024139418,0.008020108,0.0015800227,0.005071734,0.38101473],"category_scores_gemma":[0.011688013,0.00051091955,0.0005550396,0.0016705531,0.0009931476,0.0032339199,0.0039215586,0.004264029,0.25507522],"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":[0.000015817011,0.000015582174,0.000054010387,0.000027242173,0.0000013734806,0.0000052075316,0.000012612045,0.000005733292,0.000026210138,0.00027350348,0.99026006,0.009302485],"study_design_scores_gemma":[0.000016050162,0.00001614427,0.0007534989,0.00010288698,0.0000025928712,0.000006889936,0.00011077265,0.0000196364,0.000042000393,0.00028674013,0.99863786,0.000005033161],"about_ca_topic_score_codex":0.010714694,"about_ca_topic_score_gemma":0.039210066,"teacher_disagreement_score":0.38101473,"about_ca_system_score_codex":0.0031915968,"about_ca_system_score_gemma":0.014088635,"threshold_uncertainty_score":0.88290733},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22070085,0.048511524,0.020347299,0.38088575,0.0011546031,0.00030029318,0.00020369723,0.00012945055,0.3277665],"genre_scores_gemma":[0.9570488,0.006059143,0.0043260846,0.0054677106,0.000103303544,0.000118032855,0.000046498702,0.000046992598,0.026783578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98542076,0.009307442,0.00025437985,0.00069059565,0.0026855366,0.0016414234],"domain_scores_gemma":[0.9654717,0.017819269,0.0010678172,0.0008395292,0.012026252,0.0027754263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024703575,0.00056826737,0.0005465153,0.0030605346,0.017406905,0.013241632,0.0025411379,0.003994664,0.0054407096],"category_scores_gemma":[0.02256805,0.0003052849,0.00045642245,0.0030973342,0.036245164,0.006270393,0.0033546027,0.004947387,0.00029482387],"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":[0.00009509578,0.00017621618,0.008616312,0.00042698465,0.000035897243,0.00093499216,0.2526322,0.0016580815,0.0006825284,0.61662287,0.02918802,0.0889308],"study_design_scores_gemma":[0.000044853987,0.000116974756,0.02297181,0.002496679,0.000044467124,0.00047733594,0.36822587,0.0034590848,0.00092763535,0.09468485,0.50638753,0.00016294324],"about_ca_topic_score_codex":0.9585827,"about_ca_topic_score_gemma":0.955846,"teacher_disagreement_score":0.82672006,"about_ca_system_score_codex":0.17327993,"about_ca_system_score_gemma":0.15509035,"threshold_uncertainty_score":0.9588781},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15363565,0.00426116,0.25048482,0.39750805,0.003611955,0.01248597,0.000180001,0.0052800346,0.17255239],"genre_scores_gemma":[0.43076038,0.0038463094,0.48843923,0.01958639,0.0012652552,0.007877609,0.00014033716,0.00040483873,0.04767963],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94597346,0.039990574,0.0024670858,0.0016691507,0.0065080184,0.003391763],"domain_scores_gemma":[0.89473057,0.03702006,0.0090930145,0.008859856,0.02113128,0.029165257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0710845,0.0011773912,0.00055442046,0.0030105652,0.01021387,0.008609843,0.0046427515,0.0041058213,0.011821112],"category_scores_gemma":[0.10706273,0.0006938044,0.0009193413,0.0016031815,0.003969835,0.0055413386,0.017200755,0.0059019667,0.0036267494],"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":[0.000121734636,0.0015903824,0.008189211,0.00049085566,0.000044003038,0.0017123735,0.09878545,0.000682511,0.0022263979,0.012252017,0.09663271,0.7772724],"study_design_scores_gemma":[0.00028431803,0.0017469808,0.014795472,0.003053035,0.00010345914,0.0036624665,0.37336883,0.0035603282,0.005010598,0.04737437,0.5465591,0.00048105058],"about_ca_topic_score_codex":0.0026643798,"about_ca_topic_score_gemma":0.014172472,"teacher_disagreement_score":0.9289155,"about_ca_system_score_codex":0.004904805,"about_ca_system_score_gemma":0.024654517,"threshold_uncertainty_score":0.37593526},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9046724,0.0007553137,0.00969328,0.0031436055,0.000063466396,0.0013880698,0.0001294564,0.00006250754,0.08009203],"genre_scores_gemma":[0.9826172,0.00044516084,0.006767864,0.00015122323,0.000015869087,0.00046420787,0.00006688161,0.0000136073,0.009458157],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9710278,0.02364623,0.00046719582,0.0006314944,0.002246324,0.001980965],"domain_scores_gemma":[0.97657436,0.017510012,0.0009617428,0.001296618,0.0023143478,0.0013429209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015591492,0.00031622127,0.00055674306,0.0013192741,0.0126635125,0.0065217386,0.0022826076,0.0018642045,0.00274316],"category_scores_gemma":[0.018832482,0.0004506389,0.0003392583,0.003961181,0.004685252,0.002418393,0.0047528828,0.0020206152,0.00045097477],"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":[0.0010777162,0.009123355,0.09430733,0.0014115969,0.000098112534,0.016583527,0.36247474,0.026485126,0.0024591375,0.19938235,0.025859347,0.26073766],"study_design_scores_gemma":[0.000671962,0.0043979255,0.07560878,0.00065135525,0.00014864345,0.0031640446,0.66629493,0.02231074,0.0049617263,0.03506435,0.1865465,0.00017906465],"about_ca_topic_score_codex":0.045750294,"about_ca_topic_score_gemma":0.10981748,"teacher_disagreement_score":0.045750294,"about_ca_system_score_codex":0.015458182,"about_ca_system_score_gemma":0.010986761,"threshold_uncertainty_score":0.112157464},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045880207,0.00042001263,0.00066852977,0.0008091641,0.00038400997,0.00006602948,0.0008692326,0.0009057006,0.99541855],"genre_scores_gemma":[0.0016466768,0.00030338982,0.0003791534,0.00036322128,0.00006057118,0.000038997674,0.0003594447,0.00028867394,0.9965599],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991216,0.00010662586,0.000074440395,0.00026436933,0.00029208788,0.00014088527],"domain_scores_gemma":[0.99827516,0.0003593507,0.00010581993,0.00040533158,0.00053285755,0.0003215024],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015903588,0.0020663233,0.001095549,0.0025151933,0.0017638264,0.004595571,0.001517593,0.0034229318,0.97489184],"category_scores_gemma":[0.0027514347,0.0007400855,0.0009558402,0.0020328406,0.0019108799,0.0035270047,0.0035396449,0.0018835821,0.98122233],"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":[0.00019152332,0.00024977326,0.001328144,0.00041641045,0.000019981011,0.0003028321,0.0001691308,0.0002172476,0.0017043253,0.010239848,0.48403424,0.50112647],"study_design_scores_gemma":[0.000023926934,0.00002494127,0.0010004295,0.00029354234,0.000007986304,0.0002859467,0.00010975416,0.00014279736,0.0003876274,0.0013991414,0.9963038,0.000020259868],"about_ca_topic_score_codex":0.004704841,"about_ca_topic_score_gemma":0.0075811865,"teacher_disagreement_score":0.025108159,"about_ca_system_score_codex":0.0019400581,"about_ca_system_score_gemma":0.0012847149,"threshold_uncertainty_score":0.03581375},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033678047,0.0056698327,0.80071396,0.10897535,0.001326548,0.002908287,0.00038842982,0.0011611854,0.04517829],"genre_scores_gemma":[0.44462788,0.001209202,0.54520243,0.0042190566,0.00020627068,0.0022021024,0.00015655407,0.00027521793,0.0019013622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6824718,0.259341,0.01716818,0.007315892,0.028568992,0.005134043],"domain_scores_gemma":[0.6681752,0.2322072,0.023089135,0.024207104,0.045571472,0.006749816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32480627,0.0026226728,0.003946492,0.008911013,0.0070361337,0.025806751,0.0064542,0.0068351687,0.0027795606],"category_scores_gemma":[0.3977423,0.0017213804,0.003298167,0.005843588,0.0280391,0.023273159,0.011557997,0.009740159,0.0004963069],"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":[0.00034935365,0.0005559613,0.03339042,0.0025901813,0.0007916432,0.00018720955,0.01768691,0.00873406,0.0019942187,0.46688232,0.010109857,0.45672792],"study_design_scores_gemma":[0.00021846991,0.00095613033,0.016059846,0.0068138773,0.0008003142,0.00030104344,0.015834484,0.046618525,0.0106719,0.8447472,0.05641384,0.0005644148],"about_ca_topic_score_codex":0.014701797,"about_ca_topic_score_gemma":0.019173667,"teacher_disagreement_score":0.32480627,"about_ca_system_score_codex":0.015042998,"about_ca_system_score_gemma":0.06696175,"threshold_uncertainty_score":0.8326341},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0991094,0.0015188593,0.8144909,0.021782441,0.0012323821,0.006818546,0.0005018174,0.00059580297,0.053949807],"genre_scores_gemma":[0.3660932,0.00079766463,0.6121991,0.0031714581,0.000117507065,0.011880133,0.00011438015,0.00032675487,0.005299801],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8209238,0.16443752,0.002484288,0.0031400826,0.007561845,0.0014524461],"domain_scores_gemma":[0.8513432,0.11347174,0.0058745025,0.012806442,0.014536933,0.0019672033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09100316,0.0009909091,0.0007010758,0.006463226,0.008515871,0.011273742,0.003040962,0.002002728,0.004515855],"category_scores_gemma":[0.120757885,0.00070576166,0.0010238932,0.0042907703,0.013999592,0.009483984,0.011239823,0.005014484,0.0011674918],"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":[0.00009239136,0.0001896489,0.0045481785,0.001273582,0.00007656124,0.0005001808,0.7317268,0.00093484233,0.005247855,0.076912194,0.0106988065,0.16779894],"study_design_scores_gemma":[0.00008699493,0.0003447134,0.0079173725,0.0031304709,0.00008321429,0.0020713499,0.4951248,0.0063533513,0.013637249,0.20809388,0.26275605,0.00040056708],"about_ca_topic_score_codex":0.003460918,"about_ca_topic_score_gemma":0.008002854,"teacher_disagreement_score":0.9089968,"about_ca_system_score_codex":0.003972551,"about_ca_system_score_gemma":0.0067860517,"threshold_uncertainty_score":0.48127645},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020229965,0.6718072,0.1633321,0.091071926,0.011639784,0.016921837,0.0018133189,0.00028189586,0.022901991],"genre_scores_gemma":[0.45114765,0.16655007,0.25585034,0.04055775,0.0062895897,0.07465424,0.0018444443,0.00061667943,0.0024892553],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.11042055,0.62189496,0.1656405,0.013843197,0.085396565,0.0028041638],"domain_scores_gemma":[0.038562916,0.8371855,0.047244567,0.022390658,0.053678803,0.0009375088],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7841782,0.002051413,0.0072789816,0.044363193,0.009381278,0.026217185,0.009383921,0.0066812495,0.004898704],"category_scores_gemma":[0.9119747,0.0039263186,0.008185079,0.037316635,0.02658072,0.01705262,0.017612068,0.007411926,0.00079655764],"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":[0.00085516786,0.00022724312,0.033851344,0.3469078,0.010507763,0.00069697585,0.06462515,0.002039955,0.00057233835,0.14236663,0.015183474,0.3821662],"study_design_scores_gemma":[0.00071835244,0.00065249676,0.019871121,0.6266518,0.00907462,0.0011889407,0.024174005,0.0030093528,0.001978619,0.18285137,0.12933904,0.00049033423],"about_ca_topic_score_codex":0.011306422,"about_ca_topic_score_gemma":0.014397809,"teacher_disagreement_score":0.2158218,"about_ca_system_score_codex":0.029865714,"about_ca_system_score_gemma":0.06252098,"threshold_uncertainty_score":0.26614678},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8110771,0.017507004,0.047987632,0.020990536,0.00016408066,0.00091253954,0.00079827884,0.00016622501,0.10039662],"genre_scores_gemma":[0.9885667,0.0028095138,0.0061899293,0.00024725776,0.0000418956,0.00034593107,0.00007915194,0.000024344932,0.0016952627],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9598498,0.028753024,0.0017547554,0.0011607088,0.0071877935,0.0012938965],"domain_scores_gemma":[0.78110486,0.18043582,0.012358041,0.005108969,0.019818798,0.0011735134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07863556,0.000648767,0.00088048464,0.0043824553,0.0015126271,0.0071835,0.0014916934,0.0010936784,0.004040614],"category_scores_gemma":[0.18910739,0.00047982886,0.0010026046,0.0038279735,0.00664256,0.0039420687,0.0038206652,0.002520453,0.0002270399],"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":[0.0013701183,0.0007302727,0.2874512,0.0032250746,0.0006146962,0.00021543117,0.07685436,0.010318106,0.00096071255,0.13956043,0.00383252,0.4748671],"study_design_scores_gemma":[0.00022670926,0.0017906716,0.6179244,0.012719655,0.0011256356,0.00052739243,0.11665185,0.039736073,0.0071834824,0.14780948,0.053983174,0.0003215533],"about_ca_topic_score_codex":0.058890264,"about_ca_topic_score_gemma":0.044601064,"teacher_disagreement_score":0.07863556,"about_ca_system_score_codex":0.009508307,"about_ca_system_score_gemma":0.0088162115,"threshold_uncertainty_score":0.41586953},"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":"other","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02317495,0.004932984,0.30988735,0.13906907,0.01670392,0.15027249,0.014742683,0.005714628,0.33550194],"genre_scores_gemma":[0.3059461,0.0038435317,0.34917983,0.01982672,0.0020831535,0.24463736,0.00634803,0.0027961808,0.06533908],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.37526727,0.4894977,0.041664544,0.009569067,0.07475533,0.0092462115],"domain_scores_gemma":[0.17475499,0.42375332,0.014726132,0.12638757,0.25233856,0.008039432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.59851307,0.0016531181,0.0025790082,0.012170319,0.0068750987,0.019724144,0.0050485968,0.005272366,0.031154897],"category_scores_gemma":[0.7608679,0.0021518029,0.0020552464,0.008802763,0.008915558,0.012407776,0.016344337,0.009453599,0.006755393],"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":[0.0011436008,0.00041029524,0.002524755,0.006884947,0.00018979957,0.0003375064,0.0623078,0.0018277573,0.0013831125,0.14137204,0.27602908,0.5055893],"study_design_scores_gemma":[0.0005633742,0.00058411085,0.0060270717,0.0152619695,0.00012185478,0.00007560379,0.017867018,0.0017014181,0.0036541654,0.0373929,0.9164373,0.00031308347],"about_ca_topic_score_codex":0.014082232,"about_ca_topic_score_gemma":0.012932183,"teacher_disagreement_score":0.59851307,"about_ca_system_score_codex":0.030539513,"about_ca_system_score_gemma":0.13259123,"threshold_uncertainty_score":0.4951049},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07070444,0.030407876,0.49801928,0.06627612,0.0037201154,0.00049583166,0.00064687396,0.00062837626,0.3291011],"genre_scores_gemma":[0.8389796,0.006478063,0.1435617,0.0025886996,0.0015176699,0.0003949566,0.00014329264,0.0002838913,0.006052052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9617692,0.022794645,0.0015194151,0.0012662541,0.012063408,0.00058702234],"domain_scores_gemma":[0.9243748,0.059346493,0.0035402288,0.0050980267,0.006527323,0.0011130809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04477082,0.002451008,0.0019464848,0.009048865,0.003811654,0.015160011,0.0028110244,0.003800356,0.009803288],"category_scores_gemma":[0.10519657,0.0008079007,0.0014385819,0.004383481,0.030266406,0.015515247,0.0067369854,0.004330548,0.0009315991],"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":[0.00019114076,0.00016624267,0.007989322,0.0015845258,0.00022926176,0.0002039279,0.0018332505,0.01236051,0.0010223455,0.80050725,0.0064888587,0.16742346],"study_design_scores_gemma":[0.000024914158,0.00013107214,0.0036633685,0.00091657473,0.00006940216,0.00023392,0.0023839015,0.0102337785,0.0008175799,0.96357673,0.017857766,0.00009105289],"about_ca_topic_score_codex":0.0027916129,"about_ca_topic_score_gemma":0.0045444225,"teacher_disagreement_score":0.04477082,"about_ca_system_score_codex":0.004795306,"about_ca_system_score_gemma":0.004190593,"threshold_uncertainty_score":0.23677355},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99100035,0.0025655937,0.00044404948,0.0011083947,0.00007560992,0.00016705856,0.0001977768,0.000017703213,0.0044234935],"genre_scores_gemma":[0.99480456,0.0010504468,0.00069346617,0.000091121205,0.000032238717,0.00016892781,0.00015073434,0.000005408691,0.0030029977],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.986616,0.008375356,0.0008292255,0.00040319873,0.0027093166,0.0010669453],"domain_scores_gemma":[0.9517999,0.02349334,0.0061907037,0.00079957,0.011649012,0.0060673878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014952633,0.00042198118,0.00051148335,0.0026032026,0.001346713,0.002034204,0.0008557841,0.0009627944,0.0036802534],"category_scores_gemma":[0.08963417,0.00014351569,0.000569239,0.0017692518,0.0011371667,0.0015629259,0.0021507957,0.0008044361,0.00045121124],"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":[0.002922059,0.002066983,0.65516853,0.0006034733,0.00024777703,0.00074802566,0.036784474,0.00087539176,0.0009333795,0.0016998663,0.0041303877,0.2938197],"study_design_scores_gemma":[0.00012570845,0.00354567,0.9502856,0.000477847,0.0002115202,0.0003453488,0.02483228,0.0009902986,0.0012658878,0.00074292964,0.01711488,0.00006203802],"about_ca_topic_score_codex":0.03062342,"about_ca_topic_score_gemma":0.035631005,"teacher_disagreement_score":0.03062342,"about_ca_system_score_codex":0.0030782833,"about_ca_system_score_gemma":0.006257591,"threshold_uncertainty_score":0.07907802},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015994355,0.013402606,0.47377062,0.3556545,0.0013507289,0.0059403344,0.0007032575,0.0007737707,0.13240984],"genre_scores_gemma":[0.30742553,0.0046832403,0.6722683,0.008657883,0.00027362816,0.0040489095,0.00045329725,0.00010132491,0.0020879311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6291523,0.27541214,0.027809,0.009029886,0.052170083,0.0064265844],"domain_scores_gemma":[0.26248172,0.50705105,0.02502943,0.03166759,0.16026026,0.0135099515],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45350224,0.0022984748,0.0033581199,0.041409187,0.01343477,0.040999543,0.012296349,0.009515404,0.006197182],"category_scores_gemma":[0.5079316,0.0021040516,0.0025270756,0.01865628,0.03492717,0.03437676,0.03540042,0.018550163,0.0011320097],"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":[0.000109945904,0.00072668074,0.01442271,0.006121863,0.00045964355,0.00026384727,0.014853979,0.0072030197,0.00040590853,0.63185424,0.030090164,0.29348794],"study_design_scores_gemma":[0.0003071216,0.00033321205,0.0122060655,0.044801846,0.00051773415,0.00021073662,0.03663895,0.019179873,0.0022755377,0.76335484,0.11975632,0.00041770685],"about_ca_topic_score_codex":0.09764801,"about_ca_topic_score_gemma":0.14288,"teacher_disagreement_score":0.9342066,"about_ca_system_score_codex":0.06579341,"about_ca_system_score_gemma":0.24839985,"threshold_uncertainty_score":0.6739291},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8476691,0.016967675,0.0067325,0.044624057,0.0007783943,0.00041402588,0.0001999646,0.00003127534,0.08258304],"genre_scores_gemma":[0.9873871,0.0043258583,0.0021978884,0.001116519,0.000054408847,0.00031310157,0.000040989384,0.000016687583,0.0045474037],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9673216,0.025214264,0.0009395628,0.00094930216,0.0027661228,0.00280908],"domain_scores_gemma":[0.97931814,0.011925428,0.0017440649,0.0006376939,0.004873996,0.0015006202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03556881,0.0005714358,0.00074755837,0.0026836605,0.012389955,0.014515163,0.0014993143,0.0020875223,0.0049009714],"category_scores_gemma":[0.031043617,0.0003386369,0.00051945116,0.0034245588,0.018098276,0.00852812,0.007257887,0.0033090932,0.00037366594],"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":[0.000109517205,0.00008031308,0.012505279,0.0007965416,0.000026777881,0.0006240606,0.8935834,0.00019213336,0.00044246358,0.04707432,0.0017571911,0.0428081],"study_design_scores_gemma":[0.0000067917226,0.00006559486,0.007955496,0.00090311497,0.00001576282,0.00007879705,0.9688757,0.000051142797,0.00022217876,0.0036176932,0.018191516,0.000016230833],"about_ca_topic_score_codex":0.045643102,"about_ca_topic_score_gemma":0.083213486,"teacher_disagreement_score":0.045643102,"about_ca_system_score_codex":0.024498535,"about_ca_system_score_gemma":0.030360475,"threshold_uncertainty_score":0.18810815},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034089902,0.0012878595,0.00004541747,0.9812796,0.01695591,0.0000042575875,0.000022390372,0.00000828978,0.00036209414],"genre_scores_gemma":[0.0012113362,0.0010758543,0.000102803926,0.9792031,0.016581535,0.000029029748,0.0000125107,0.00001578278,0.0017680158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906,0.004029097,0.00083426613,0.0014481406,0.0023234915,0.0007649387],"domain_scores_gemma":[0.9467507,0.038570262,0.001533352,0.0010182624,0.00935172,0.0027757222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0127367005,0.0013642027,0.001932442,0.0015829115,0.0052088317,0.008914951,0.0057164705,0.046691753,0.010109271],"category_scores_gemma":[0.072425075,0.00089722394,0.0017598213,0.0018777442,0.012435368,0.009934955,0.004411311,0.083344586,0.00583441],"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":[0.000016505694,0.0000045129686,0.000033273518,0.000052400534,0.0000065967724,0.000044978467,0.00012633388,0.000021475335,0.000010618011,0.0016460414,0.9960485,0.001988771],"study_design_scores_gemma":[0.00005739656,0.000019376817,0.000326536,0.0010816064,0.000029369608,0.00027867526,0.0009442881,0.00015289335,0.00014769749,0.012878106,0.9840052,0.00007876546],"about_ca_topic_score_codex":0.022949228,"about_ca_topic_score_gemma":0.030653356,"teacher_disagreement_score":0.046691753,"about_ca_system_score_codex":0.009083033,"about_ca_system_score_gemma":0.011643239,"threshold_uncertainty_score":0.06735885},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037880542,0.13811801,0.7443975,0.023142533,0.0069006486,0.0044688787,0.0007672441,0.00041835135,0.07799872],"genre_scores_gemma":[0.04655007,0.053241078,0.86439496,0.0072306837,0.0016660462,0.01801722,0.00040300156,0.00030515343,0.008191773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.703714,0.27561024,0.0042336076,0.0050743297,0.010770053,0.0005977248],"domain_scores_gemma":[0.688613,0.28587925,0.0048068985,0.015128582,0.0047586276,0.00081365695],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2001841,0.0018700901,0.0035408929,0.005363818,0.0023838684,0.0077216793,0.005745178,0.0059000757,0.012640597],"category_scores_gemma":[0.19613723,0.0015516919,0.0025425304,0.00872955,0.010124078,0.008158857,0.0075658937,0.0060217488,0.0021693448],"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":[0.0002082315,0.00011426697,0.00054802396,0.0061727036,0.00047611105,0.00011525393,0.0055071986,0.0026173424,0.00016827452,0.6698577,0.02249781,0.29171717],"study_design_scores_gemma":[0.00017322409,0.00031221815,0.0006727076,0.0088854665,0.00021390013,0.00019255246,0.0014162875,0.0042587547,0.00056076935,0.83131045,0.15190424,0.00009940509],"about_ca_topic_score_codex":0.0019620939,"about_ca_topic_score_gemma":0.004475428,"teacher_disagreement_score":0.2001841,"about_ca_system_score_codex":0.006997037,"about_ca_system_score_gemma":0.009506789,"threshold_uncertainty_score":0.98631537},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07365704,0.0002495231,0.8897608,0.0016439379,0.00015437021,0.0030984622,0.0012316924,0.005336986,0.024867257],"genre_scores_gemma":[0.23660538,0.00029692063,0.7568535,0.00013499217,0.000028100661,0.001585213,0.0018379791,0.00065505883,0.002002897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9132994,0.050932746,0.0080334,0.0031854254,0.023489652,0.0010594587],"domain_scores_gemma":[0.55406123,0.23387717,0.018383482,0.07195572,0.12043304,0.0012893573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08932733,0.0009206587,0.000773494,0.009822683,0.0028806126,0.0075565334,0.002776207,0.0017744604,0.0072092796],"category_scores_gemma":[0.25901818,0.0009752394,0.0010003247,0.0050243502,0.0035078814,0.008023189,0.0052746017,0.0025794832,0.0015870671],"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":[0.000629308,0.0019403202,0.015787613,0.0031004765,0.00018062329,0.0008872964,0.01594966,0.05448838,0.009299829,0.20007779,0.014342467,0.6833163],"study_design_scores_gemma":[0.0010377176,0.0020515039,0.011178699,0.009289809,0.0004107869,0.0009843486,0.015837833,0.44727087,0.13506734,0.21867858,0.15765703,0.0005354874],"about_ca_topic_score_codex":0.011548359,"about_ca_topic_score_gemma":0.008350936,"teacher_disagreement_score":0.08932733,"about_ca_system_score_codex":0.006622567,"about_ca_system_score_gemma":0.022047393,"threshold_uncertainty_score":0.47241372},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002558499,0.004856568,0.0002526561,0.89645094,0.021450805,0.00002979241,0.000112082525,0.000029156528,0.074259475],"genre_scores_gemma":[0.14497997,0.02452345,0.0009837177,0.5182969,0.057175703,0.00027046032,0.00044135758,0.00021483461,0.25311366],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9790491,0.0053704553,0.0011995427,0.0010796351,0.008655747,0.004645635],"domain_scores_gemma":[0.9057045,0.0149067165,0.0032144843,0.0012547788,0.04300599,0.03191358],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030288622,0.0007753175,0.0012301004,0.0025604179,0.012458233,0.02626486,0.00379211,0.021034725,0.04563543],"category_scores_gemma":[0.08178877,0.00036092452,0.00096698647,0.0029919185,0.0051569683,0.0072884425,0.00800783,0.012677376,0.0101038935],"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":[0.000034680248,0.00006463804,0.0008201865,0.000046520512,0.000005280277,0.00017341942,0.00043460482,0.000057456175,0.00002513404,0.028547443,0.956689,0.013101544],"study_design_scores_gemma":[0.000021582511,0.0000520856,0.001668632,0.00026282403,0.000008574946,0.00016588627,0.0040848125,0.00009544635,0.000079271005,0.004800736,0.98873466,0.000025600015],"about_ca_topic_score_codex":0.012174861,"about_ca_topic_score_gemma":0.024292078,"teacher_disagreement_score":0.9899651,"about_ca_system_score_codex":0.010034922,"about_ca_system_score_gemma":0.022953777,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20592149,0.008867167,0.6942181,0.010016355,0.0019577995,0.012833771,0.0073272446,0.001992692,0.056865316],"genre_scores_gemma":[0.46467826,0.0044000354,0.4656077,0.0029927632,0.0004773272,0.04459207,0.004373666,0.00079621817,0.012082],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.76675886,0.14511216,0.0217705,0.009276675,0.05425173,0.0028300288],"domain_scores_gemma":[0.46956134,0.36740595,0.031319298,0.05042615,0.077832974,0.0034543397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16234154,0.0023066336,0.0024893864,0.008739331,0.002577233,0.01082751,0.004098615,0.0028861305,0.0067917528],"category_scores_gemma":[0.354718,0.0016531015,0.0024599489,0.00834983,0.0060002217,0.009135655,0.0064309714,0.0039517493,0.0028974158],"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":[0.0015320384,0.0011275297,0.1491144,0.015431981,0.0016431843,0.00040206837,0.050977215,0.0032864898,0.010094978,0.070846036,0.018927498,0.67661667],"study_design_scores_gemma":[0.0005484326,0.003814321,0.43571907,0.015028393,0.0013156816,0.0013886398,0.050109215,0.014256827,0.029221673,0.13646574,0.31100237,0.0011296751],"about_ca_topic_score_codex":0.003264084,"about_ca_topic_score_gemma":0.0025584518,"teacher_disagreement_score":0.16234154,"about_ca_system_score_codex":0.003496507,"about_ca_system_score_gemma":0.010904333,"threshold_uncertainty_score":0.85855436},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9559593,0.017873082,0.0019181131,0.008939339,0.0014413046,0.004743587,0.00032803998,0.00008014012,0.008717124],"genre_scores_gemma":[0.9751559,0.006618603,0.008579271,0.0042974562,0.0006987335,0.0020339785,0.00028732492,0.000017519982,0.002311275],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99525934,0.002416526,0.0004096035,0.00046508646,0.0009479352,0.0005015548],"domain_scores_gemma":[0.988815,0.0027634462,0.0018876289,0.0007056484,0.0008857143,0.004942535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008706037,0.0002902862,0.0011695392,0.00035254564,0.0013101209,0.0011702653,0.00092893204,0.001564969,0.0044256607],"category_scores_gemma":[0.015901713,0.00017334832,0.0011564619,0.0005783458,0.00092707534,0.0012275442,0.0015869886,0.0026222216,0.0003798152],"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":[0.0915363,0.05037053,0.016857302,0.0075622387,0.0026782006,0.000103967686,0.001153872,0.00091920025,0.001639158,0.0013872699,0.00673755,0.8190544],"study_design_scores_gemma":[0.1705585,0.525835,0.22320905,0.0091845915,0.0040490865,0.00033356703,0.0024228182,0.0010654567,0.0025286863,0.0024068714,0.05814986,0.00025654424],"about_ca_topic_score_codex":0.009345457,"about_ca_topic_score_gemma":0.027610824,"teacher_disagreement_score":0.009345457,"about_ca_system_score_codex":0.0026012843,"about_ca_system_score_gemma":0.008258781,"threshold_uncertainty_score":0.046042442},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02360477,0.042506516,0.14736225,0.68090487,0.007856296,0.0018715891,0.00020297665,0.000385135,0.09530558],"genre_scores_gemma":[0.62602025,0.024646226,0.21028784,0.09333453,0.011619574,0.019261366,0.00030556245,0.0007731581,0.013751555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.22851957,0.66152924,0.026392275,0.020497743,0.05659244,0.006468738],"domain_scores_gemma":[0.11402935,0.7925745,0.011564202,0.038456924,0.030733058,0.01264194],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.686859,0.0017383429,0.0057019508,0.012581642,0.03490861,0.05321833,0.014928899,0.014646661,0.009088004],"category_scores_gemma":[0.6344645,0.0027233956,0.0032136543,0.01177362,0.11202984,0.06152224,0.06816453,0.023782685,0.003400954],"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":[0.00020345236,0.00034968543,0.0037429987,0.0049594995,0.00018525007,0.000652958,0.20060122,0.0006442707,0.00031607418,0.62345463,0.020001953,0.14488794],"study_design_scores_gemma":[0.00010003488,0.00015047133,0.0012710983,0.0065396097,0.00004851892,0.00084673276,0.17203748,0.00096023135,0.00022567363,0.69418615,0.12352987,0.00010411847],"about_ca_topic_score_codex":0.0048054727,"about_ca_topic_score_gemma":0.0053398483,"teacher_disagreement_score":0.686859,"about_ca_system_score_codex":0.014474194,"about_ca_system_score_gemma":0.045912918,"threshold_uncertainty_score":0.38615865},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86113685,0.0013683602,0.009141314,0.017552651,0.000104999155,0.0016617422,0.00014876341,0.00005889722,0.108826324],"genre_scores_gemma":[0.9890387,0.00043254337,0.005723679,0.00068338646,0.000021320437,0.0005464759,0.000050034636,0.000020941967,0.0034829949],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8839516,0.099172115,0.0015190751,0.0011589194,0.0057368125,0.008461383],"domain_scores_gemma":[0.88997567,0.087869585,0.0031869044,0.0027655966,0.0101560205,0.006046278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085928425,0.00052527507,0.00072093937,0.00200509,0.019499017,0.008094515,0.002379572,0.005995926,0.0046544624],"category_scores_gemma":[0.08572606,0.00047776435,0.00093260483,0.0040769605,0.0073651834,0.0051151826,0.0074094357,0.006074493,0.00040540853],"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":[0.0025573904,0.0147827435,0.098324515,0.0015905031,0.00029878214,0.021678235,0.22667444,0.029620558,0.001572972,0.34302148,0.023998845,0.23587961],"study_design_scores_gemma":[0.0017656591,0.007550547,0.07726232,0.0027871893,0.00040690447,0.004325872,0.6274647,0.038070332,0.006912163,0.06785945,0.16518655,0.00040838975],"about_ca_topic_score_codex":0.103295185,"about_ca_topic_score_gemma":0.16235432,"teacher_disagreement_score":0.8967048,"about_ca_system_score_codex":0.03634255,"about_ca_system_score_gemma":0.039257932,"threshold_uncertainty_score":0.4544384},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9090829,0.001320048,0.0035551847,0.011426149,0.0000860305,0.00031763074,0.0003011558,0.00012433558,0.07378649],"genre_scores_gemma":[0.9859365,0.0012220539,0.0017103,0.00044671955,0.000048362763,0.00010656975,0.00009859485,0.000015209532,0.010415759],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9921755,0.0036901827,0.00015007383,0.00020829965,0.0013232866,0.0024526466],"domain_scores_gemma":[0.986597,0.006963815,0.00085612526,0.0005550274,0.0019889323,0.003039106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071915714,0.0004162131,0.00044395233,0.0023690555,0.010866028,0.005324684,0.0023786442,0.004134135,0.004616487],"category_scores_gemma":[0.010694979,0.0003796351,0.00040242326,0.006844468,0.0030357318,0.0020381012,0.0030747252,0.0018082097,0.00061131787],"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":[0.0012755833,0.009763733,0.1720476,0.0014304444,0.0001356623,0.069381505,0.14767107,0.032079093,0.0036625415,0.19115153,0.053935975,0.3174653],"study_design_scores_gemma":[0.00032501877,0.002341025,0.097642735,0.0011246111,0.00017420412,0.011010865,0.4609572,0.02409741,0.0054832124,0.01808158,0.37854806,0.0002141351],"about_ca_topic_score_codex":0.16530973,"about_ca_topic_score_gemma":0.2527591,"teacher_disagreement_score":0.16530973,"about_ca_system_score_codex":0.026619382,"about_ca_system_score_gemma":0.024529817,"threshold_uncertainty_score":0.32869506},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015495327,0.018363986,0.0046809944,0.8084849,0.004118715,0.0002009966,0.00056093076,0.00044677051,0.14764737],"genre_scores_gemma":[0.64514464,0.024645252,0.014768167,0.2779225,0.0034200281,0.00069158187,0.0014646591,0.00092809554,0.031015085],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.952962,0.02764418,0.0024278185,0.0021811775,0.0069913263,0.007793612],"domain_scores_gemma":[0.8367375,0.05594713,0.010605887,0.012776067,0.042641632,0.041291833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050150633,0.00075065694,0.0011291563,0.0025899322,0.0055215564,0.025800057,0.002643495,0.0051112724,0.028540555],"category_scores_gemma":[0.13072076,0.0007368406,0.0007253941,0.004125357,0.016985405,0.029521119,0.016088149,0.00820793,0.0049918527],"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":[0.00012506866,0.000111956535,0.021709433,0.0016382926,0.000064445005,0.00051872927,0.0074921562,0.00060812477,0.00041321514,0.13551635,0.66782796,0.16397427],"study_design_scores_gemma":[0.000083857565,0.00014482629,0.023206204,0.006622779,0.00006366449,0.00056308677,0.03079184,0.00060991594,0.00051362964,0.10427387,0.8329376,0.00018870436],"about_ca_topic_score_codex":0.03041554,"about_ca_topic_score_gemma":0.01909822,"teacher_disagreement_score":0.050150633,"about_ca_system_score_codex":0.010166303,"about_ca_system_score_gemma":0.046037626,"threshold_uncertainty_score":0.26522505},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013832635,0.025118418,0.0063436534,0.93666536,0.0037421882,0.00058327726,0.0008624386,0.00016355059,0.025137842],"genre_scores_gemma":[0.21940497,0.07976113,0.19067094,0.47108835,0.008734562,0.004237533,0.003257754,0.00034118345,0.022503624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7221615,0.11481652,0.023740064,0.008574017,0.108567566,0.022140367],"domain_scores_gemma":[0.42472413,0.2731948,0.022098307,0.014587622,0.22318956,0.042205606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.39804325,0.004177645,0.0067498055,0.027684676,0.017421765,0.05144659,0.01674015,0.05197017,0.014759036],"category_scores_gemma":[0.50706536,0.0033817932,0.0057132784,0.024089897,0.029490167,0.0203914,0.021752626,0.045502763,0.0015817258],"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":[0.0003741374,0.00026270864,0.003128133,0.0061827893,0.000797018,0.0002284511,0.002710324,0.008123895,0.0002933159,0.6474684,0.25026217,0.080168694],"study_design_scores_gemma":[0.0013603333,0.00017242764,0.011915458,0.034887157,0.0012614997,0.00008695088,0.0054402906,0.007732293,0.00086694997,0.43717656,0.49845922,0.00064094004],"about_ca_topic_score_codex":0.9521751,"about_ca_topic_score_gemma":0.9494347,"teacher_disagreement_score":0.39804325,"about_ca_system_score_codex":0.30040964,"about_ca_system_score_gemma":0.79837096,"threshold_uncertainty_score":0.8114257},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028691897,0.027841145,0.0038046273,0.95560265,0.0019080826,0.00002937421,0.000023505127,0.000026139272,0.007895342],"genre_scores_gemma":[0.4835374,0.07882366,0.019675344,0.39399153,0.018027628,0.000519213,0.00009372935,0.00014761442,0.0051838197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8030905,0.13982087,0.0079840915,0.007195438,0.03845137,0.0034577763],"domain_scores_gemma":[0.5850821,0.33678576,0.010958823,0.013353053,0.041819233,0.012001022],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20190334,0.0012621453,0.0021534825,0.007788444,0.006991692,0.029829027,0.008082181,0.025685608,0.004163444],"category_scores_gemma":[0.24276501,0.0013025581,0.0011099735,0.0063705817,0.08343217,0.030804237,0.0222409,0.037062746,0.0012699565],"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":[0.00016699903,0.00026406787,0.002963955,0.0036032547,0.00017622186,0.0005186532,0.052530173,0.0013934044,0.00027457916,0.7357457,0.10243314,0.09992988],"study_design_scores_gemma":[0.00010187786,0.00011483528,0.0008969789,0.007479758,0.00006638935,0.0003623424,0.044804376,0.0013839183,0.00023907016,0.7601321,0.18435785,0.000060546154],"about_ca_topic_score_codex":0.0050797625,"about_ca_topic_score_gemma":0.0041260896,"teacher_disagreement_score":0.20190334,"about_ca_system_score_codex":0.016412899,"about_ca_system_score_gemma":0.030016009,"threshold_uncertainty_score":0.9841953},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95243335,0.00042432154,0.005005562,0.005850092,0.00004747924,0.00061445666,0.000052735675,0.00003538224,0.035536602],"genre_scores_gemma":[0.9917898,0.00026972624,0.0045244326,0.00044062536,0.000015536823,0.00018129127,0.000038449496,0.000024545658,0.00271569],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97433794,0.019190963,0.00067229365,0.0006336879,0.0021279017,0.003037271],"domain_scores_gemma":[0.9653997,0.02276347,0.0017642789,0.0014996049,0.004792566,0.0037803622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028498497,0.0006050135,0.0005858285,0.0019897248,0.014689582,0.0064983773,0.003312706,0.004667499,0.0037132562],"category_scores_gemma":[0.026590504,0.00070410967,0.00058333046,0.0020604734,0.0070003974,0.00372182,0.0063589048,0.0057890243,0.00058410823],"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":[0.00043188126,0.009546266,0.07960134,0.00079747685,0.00008940995,0.031069115,0.6901072,0.0058329077,0.0035572757,0.0560385,0.009987618,0.112940945],"study_design_scores_gemma":[0.0001802674,0.0010492161,0.022321757,0.0010691686,0.00006387132,0.0048692096,0.8838966,0.0071616475,0.0058632134,0.006729799,0.06666825,0.00012707489],"about_ca_topic_score_codex":0.019735629,"about_ca_topic_score_gemma":0.037567858,"teacher_disagreement_score":0.028498497,"about_ca_system_score_codex":0.015811414,"about_ca_system_score_gemma":0.012111654,"threshold_uncertainty_score":0.1507163},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4510598,0.0066877087,0.14761141,0.12101958,0.0038963957,0.025029395,0.022824086,0.0054491973,0.2164225],"genre_scores_gemma":[0.6414475,0.0033370093,0.3222338,0.007532998,0.00040342772,0.0036740096,0.0056236046,0.0009328416,0.014814776],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9690382,0.010694911,0.0015736623,0.00087736314,0.014993734,0.0028221519],"domain_scores_gemma":[0.9084496,0.017488131,0.0020053408,0.0024941606,0.06505456,0.0045082145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04110521,0.00071951933,0.00044481267,0.0031872597,0.0044615655,0.0036876516,0.0027277546,0.0012971566,0.0049097487],"category_scores_gemma":[0.10608748,0.00041514004,0.0008399948,0.003935695,0.0013893243,0.0016326747,0.0024002232,0.0026034873,0.0013899144],"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":[0.0011474735,0.0009535442,0.10223773,0.0011388869,0.00015232166,0.000758109,0.0064196144,0.018755712,0.0033166977,0.017557533,0.22986856,0.6176938],"study_design_scores_gemma":[0.0010135522,0.0020262916,0.2684163,0.0028623813,0.00037687906,0.001027622,0.020749481,0.043734416,0.010613269,0.008900981,0.6392111,0.0010677414],"about_ca_topic_score_codex":0.9320339,"about_ca_topic_score_gemma":0.9636003,"teacher_disagreement_score":0.0679661,"about_ca_system_score_codex":0.03956017,"about_ca_system_score_gemma":0.11327683,"threshold_uncertainty_score":0.28703046},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0342509,0.00908643,0.0011506093,0.4623158,0.0025214034,0.00013771937,0.0028914474,0.0002284943,0.4874172],"genre_scores_gemma":[0.6920204,0.009470955,0.0015164384,0.07126753,0.0015325119,0.00011052263,0.0007507541,0.00013982487,0.22319104],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98895174,0.002142835,0.00018433314,0.00035353523,0.00438196,0.003985629],"domain_scores_gemma":[0.9748556,0.009258335,0.0011251222,0.0006444897,0.009788184,0.004328268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010292424,0.00043826905,0.0007981734,0.0021521286,0.0053617526,0.007638175,0.0018354895,0.0051360843,0.04178948],"category_scores_gemma":[0.036053214,0.00032237536,0.00071450963,0.0027785734,0.0027976912,0.0029404464,0.0029533696,0.0035186033,0.0014853878],"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":[0.0006827942,0.00019652341,0.01676016,0.00024472692,0.000118142154,0.00017412538,0.00046063235,0.003942044,0.00018951797,0.3328368,0.54516834,0.09922622],"study_design_scores_gemma":[0.0005356908,0.00013623649,0.0447355,0.0007812976,0.00041279846,0.00008669435,0.0018263354,0.0042867307,0.0010073341,0.083579734,0.8624182,0.0001935768],"about_ca_topic_score_codex":0.8713247,"about_ca_topic_score_gemma":0.91938496,"teacher_disagreement_score":0.8713247,"about_ca_system_score_codex":0.050982527,"about_ca_system_score_gemma":0.12217403,"threshold_uncertainty_score":0.36990583},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94581753,0.0008506148,0.0006911375,0.0074337022,0.000054105687,0.00012946074,0.00033232753,0.000038524846,0.04465259],"genre_scores_gemma":[0.9891978,0.0005971419,0.0005239799,0.00085744367,0.000021176314,0.000034053777,0.00015437415,0.0000068005193,0.008607115],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99235487,0.0010703672,0.00024331886,0.0005107895,0.0019840961,0.0038364932],"domain_scores_gemma":[0.9875131,0.004353994,0.0013024093,0.00050394674,0.0027430563,0.0035835034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049364204,0.0001557545,0.00020458493,0.001506538,0.0074984487,0.0031820086,0.0017925586,0.0011523234,0.003650266],"category_scores_gemma":[0.013628225,0.00038304998,0.0002041971,0.0022868977,0.0031018548,0.0010449045,0.002407489,0.001626265,0.00022288403],"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":[0.00082279614,0.0007081672,0.52865565,0.00064034044,0.000065955326,0.006613396,0.05161742,0.011023163,0.008351506,0.13363126,0.03400957,0.22386093],"study_design_scores_gemma":[0.00006626839,0.0003038811,0.75149035,0.00030128114,0.000037919133,0.0007965938,0.07007714,0.0043830317,0.0024134207,0.005557558,0.1644493,0.00012327406],"about_ca_topic_score_codex":0.9427147,"about_ca_topic_score_gemma":0.9687918,"teacher_disagreement_score":0.9054469,"about_ca_system_score_codex":0.09455311,"about_ca_system_score_gemma":0.121858835,"threshold_uncertainty_score":0.6860341},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007391524,0.005241815,0.0028896544,0.42839152,0.06854135,0.0027779755,0.028226955,0.002678206,0.45386097],"genre_scores_gemma":[0.02303171,0.0022949448,0.005244862,0.0525364,0.0034174172,0.0006333878,0.0055805626,0.0011748817,0.9060857],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9703958,0.0011873977,0.0007391969,0.0007426943,0.02252626,0.0044086142],"domain_scores_gemma":[0.94441247,0.0051851734,0.0006954793,0.0015360063,0.038525496,0.0096454285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013818914,0.0010058173,0.0012788086,0.0032424908,0.015681818,0.01680802,0.0030284093,0.013601137,0.0891068],"category_scores_gemma":[0.041243874,0.0010474145,0.0013325276,0.0044190683,0.0036489519,0.0022792588,0.0032412782,0.010669948,0.021129655],"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":[0.000013173618,0.000012360924,0.00009493348,0.000020422794,0.0000029880164,0.00006380137,0.00014682021,0.000044929144,0.00007272891,0.0023003381,0.9944383,0.0027891141],"study_design_scores_gemma":[0.000015925174,0.0000059477043,0.0010692201,0.00007293074,0.000004676026,0.000016796464,0.0004610737,0.00010295277,0.00012282928,0.00043287707,0.9976623,0.000032475982],"about_ca_topic_score_codex":0.9418511,"about_ca_topic_score_gemma":0.9705906,"teacher_disagreement_score":0.9130735,"about_ca_system_score_codex":0.08692652,"about_ca_system_score_gemma":0.32008833,"threshold_uncertainty_score":0.63069904},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08903323,0.0023642958,0.8950424,0.0034152977,0.00030417505,0.00040562672,0.0012877937,0.0004057329,0.0077413553],"genre_scores_gemma":[0.679411,0.0028237374,0.30406442,0.00058715884,0.00033164697,0.0010006985,0.0012398256,0.0001387077,0.010402786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99416155,0.0039850622,0.00021593383,0.00086024334,0.0005142854,0.00026293373],"domain_scores_gemma":[0.97246045,0.02361,0.00075368216,0.0009478514,0.0019405369,0.00028765193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011514328,0.001318246,0.0022511939,0.0027226694,0.0011107128,0.0035032355,0.0026420448,0.0017028895,0.0073265675],"category_scores_gemma":[0.04703244,0.0012198299,0.0025962552,0.0025209577,0.0012149435,0.0021480955,0.0013724949,0.0028863214,0.0009667976],"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":[0.000644693,0.00025908934,0.08646392,0.00090957776,0.0018631215,0.00079365086,0.002095706,0.5558622,0.001273091,0.12274554,0.0059977393,0.22109173],"study_design_scores_gemma":[0.00012347936,0.0001376691,0.015458577,0.00067845295,0.00047290442,0.00018223032,0.00083545106,0.82593405,0.0005226977,0.14669542,0.0088510495,0.000108054104],"about_ca_topic_score_codex":0.078071214,"about_ca_topic_score_gemma":0.05687472,"teacher_disagreement_score":0.078071214,"about_ca_system_score_codex":0.002065595,"about_ca_system_score_gemma":0.0042635594,"threshold_uncertainty_score":0.15523356},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050563975,0.06470744,0.0075629996,0.8887637,0.0077138916,0.000039536026,0.00006114484,0.00009333395,0.026001584],"genre_scores_gemma":[0.47118822,0.110489435,0.0307541,0.22896363,0.0138405,0.00044729243,0.00018724309,0.00076710386,0.14336246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9107725,0.06451582,0.0019473225,0.0057726596,0.013163427,0.00382825],"domain_scores_gemma":[0.8412471,0.08969977,0.005855731,0.012639028,0.03360665,0.016951729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.080525324,0.0009245507,0.0019544305,0.0030594089,0.020437239,0.034330547,0.003576878,0.011977084,0.011011727],"category_scores_gemma":[0.117337026,0.0007549094,0.0014162429,0.0046618804,0.057540763,0.032672998,0.013923856,0.027589658,0.0030787387],"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":[0.000195565,0.00012060159,0.0016431946,0.00064514147,0.000097059536,0.00045396085,0.0779866,0.0004191821,0.00088537415,0.6057814,0.219015,0.092757],"study_design_scores_gemma":[0.000033694683,0.000110841334,0.0012610347,0.001796086,0.000030181489,0.00029437008,0.05093448,0.00041704692,0.0006255629,0.13653105,0.80784357,0.00012208964],"about_ca_topic_score_codex":0.1075402,"about_ca_topic_score_gemma":0.11443783,"teacher_disagreement_score":0.1075402,"about_ca_system_score_codex":0.033465117,"about_ca_system_score_gemma":0.07486979,"threshold_uncertainty_score":0.42586368},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49680865,0.0013200907,0.0064385193,0.16267541,0.0004881796,0.0006719785,0.001527848,0.00012926184,0.3299401],"genre_scores_gemma":[0.9669052,0.00041007216,0.0027801117,0.005614502,0.00006034083,0.00011471708,0.00014896804,0.000023626113,0.023942394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9898443,0.0015223636,0.00039268078,0.000708012,0.0041068415,0.0034257134],"domain_scores_gemma":[0.9656106,0.011837667,0.0026604985,0.0012243879,0.012255684,0.006411077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009500302,0.00019509214,0.00018071145,0.00095473346,0.011895367,0.008108199,0.0019073834,0.0026122078,0.0044153067],"category_scores_gemma":[0.02680486,0.0003691639,0.00034378128,0.0014047761,0.008027216,0.003135344,0.002546489,0.0026358876,0.0002554973],"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":[0.00029815492,0.00019927233,0.110891,0.00038130448,0.000050754654,0.0011423954,0.05958829,0.006135554,0.0037689395,0.6446461,0.09860717,0.07429097],"study_design_scores_gemma":[0.00010306744,0.00016089412,0.17978299,0.00063121744,0.000051359908,0.00013833205,0.06548339,0.0069846115,0.0028038821,0.03617227,0.70743996,0.00024800494],"about_ca_topic_score_codex":0.97219175,"about_ca_topic_score_gemma":0.98912,"teacher_disagreement_score":0.19369909,"about_ca_system_score_codex":0.19369909,"about_ca_system_score_gemma":0.28527942,"threshold_uncertainty_score":0.9351948},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015403128,0.9980715,0.0003385463,0.00076578074,0.00011767917,0.00002988893,0.0000150006745,0.0000035494843,0.0005040875],"genre_scores_gemma":[0.0042569507,0.99416083,0.00091208995,0.0004009273,0.00013007406,0.000062893756,0.000020786934,0.000003208051,0.00005214404],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97167385,0.014341608,0.005176777,0.0013216708,0.006984128,0.00050196185],"domain_scores_gemma":[0.84315366,0.13716221,0.0062416964,0.0017193237,0.011110618,0.00061258435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029491084,0.0014054518,0.0036519314,0.01460783,0.0011131867,0.0054656523,0.0018269696,0.003309189,0.0034626685],"category_scores_gemma":[0.08439766,0.0007759232,0.0027405496,0.019508058,0.0026850419,0.005435448,0.0022761954,0.0026880351,0.00049596006],"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":[0.00008948675,0.00007080726,0.00064358144,0.23049839,0.00054454687,0.000083267674,0.00072070386,0.0005030302,0.00014493115,0.007051521,0.006234969,0.75341475],"study_design_scores_gemma":[0.000049261416,0.0002391645,0.0041610347,0.7791514,0.0029159577,0.0006230336,0.0015037968,0.00050565787,0.00052250485,0.008228932,0.20201375,0.000085563064],"about_ca_topic_score_codex":0.0060294773,"about_ca_topic_score_gemma":0.009275745,"teacher_disagreement_score":0.029491084,"about_ca_system_score_codex":0.007369529,"about_ca_system_score_gemma":0.018041585,"threshold_uncertainty_score":0.15596563},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037373585,0.0031092574,0.0050827493,0.0073953914,0.0057949494,0.00013325652,0.0030357328,0.00081479124,0.97426015],"genre_scores_gemma":[0.0016038872,0.0026068045,0.0022764213,0.0017902316,0.00092316436,0.00009283729,0.0022135808,0.00027243313,0.9882207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990036,0.00011943035,0.000041996824,0.00019023732,0.00054672395,0.00009799565],"domain_scores_gemma":[0.9987123,0.00024120009,0.000055084205,0.00015393554,0.00061310065,0.00022430747],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009667215,0.00081291917,0.00050858344,0.0014280675,0.0014406753,0.005198896,0.0014112486,0.0018991153,0.4955613],"category_scores_gemma":[0.003871665,0.00027198548,0.00046952738,0.001751291,0.00069435243,0.00344466,0.0025222003,0.002020327,0.3728161],"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":[0.000014418891,0.000036334157,0.00015689584,0.0001707924,0.0000015884978,0.00003877098,0.00021085942,0.000113017864,0.0002101674,0.036860578,0.7939465,0.16824001],"study_design_scores_gemma":[9.09633e-7,0.0000031631537,0.00010582474,0.00008002496,6.2665544e-7,0.000017127362,0.00005717479,0.000014573073,0.0000399192,0.002573536,0.9971054,0.000001698446],"about_ca_topic_score_codex":0.005199658,"about_ca_topic_score_gemma":0.007851415,"teacher_disagreement_score":0.5044387,"about_ca_system_score_codex":0.0022856211,"about_ca_system_score_gemma":0.0035700987,"threshold_uncertainty_score":0.71952057},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38579917,0.05225768,0.10421526,0.21991332,0.003742436,0.009843855,0.0036970424,0.00088247575,0.21964876],"genre_scores_gemma":[0.92283124,0.008031976,0.047398843,0.0032873645,0.00073195086,0.0013593695,0.00089666556,0.00008656621,0.015376133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.936147,0.042626027,0.00510598,0.0011338157,0.010787426,0.00419973],"domain_scores_gemma":[0.8869467,0.0586368,0.009345839,0.0037832407,0.02725135,0.014036044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04430033,0.0006058609,0.00145097,0.0044331546,0.0025706172,0.005736093,0.0016135827,0.0015533223,0.006052451],"category_scores_gemma":[0.15349653,0.00037977446,0.0011861761,0.0026335083,0.0012211715,0.00169137,0.003128057,0.0025282768,0.0013323462],"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":[0.0018566059,0.0016522879,0.109227374,0.0010839896,0.00034962475,0.00068228086,0.002522572,0.0053576445,0.00064342393,0.013499704,0.031990655,0.8311337],"study_design_scores_gemma":[0.0013163106,0.005885185,0.5284654,0.011731934,0.0016764117,0.0039592115,0.01637965,0.059079517,0.00959085,0.100073,0.26106215,0.0007804064],"about_ca_topic_score_codex":0.06102287,"about_ca_topic_score_gemma":0.05145933,"teacher_disagreement_score":0.06102287,"about_ca_system_score_codex":0.012249402,"about_ca_system_score_gemma":0.054703053,"threshold_uncertainty_score":0.23428535},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073848874,0.0041472027,0.37561542,0.023776043,0.005549089,0.41766542,0.016553026,0.009420685,0.13988821],"genre_scores_gemma":[0.010973106,0.0027269556,0.56550306,0.008516853,0.00047123202,0.36144248,0.0042206356,0.0011011839,0.045044582],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8579988,0.10156978,0.013621736,0.003497137,0.020050537,0.0032620365],"domain_scores_gemma":[0.7365124,0.107815064,0.005934048,0.036478586,0.10267491,0.010584901],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1668404,0.0026189971,0.002784185,0.00884687,0.008994035,0.010056284,0.0044803377,0.005675029,0.084841214],"category_scores_gemma":[0.20357509,0.004530384,0.0027436165,0.008982869,0.003907159,0.007229785,0.005613086,0.012422936,0.07209042],"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":[0.0004042235,0.0023362504,0.0046988297,0.004376559,0.00007692972,0.00031593264,0.009062622,0.0011170154,0.0038541367,0.021040523,0.56099886,0.3917181],"study_design_scores_gemma":[0.0009903925,0.0011860582,0.0131354,0.007392289,0.000092019436,0.00034081584,0.020715427,0.0020400295,0.0023001581,0.02597131,0.9256119,0.00022420846],"about_ca_topic_score_codex":0.011836756,"about_ca_topic_score_gemma":0.029102335,"teacher_disagreement_score":0.83315957,"about_ca_system_score_codex":0.007963528,"about_ca_system_score_gemma":0.05207689,"threshold_uncertainty_score":0.8823469},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009831535,0.030378534,0.21053194,0.7156228,0.0046085343,0.0003010006,0.00014711544,0.00021389153,0.02836473],"genre_scores_gemma":[0.720529,0.030828567,0.10985783,0.122019224,0.009152817,0.0020782375,0.00017836186,0.0005233677,0.004832588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.797249,0.17246099,0.005400839,0.010126839,0.012247879,0.0025144706],"domain_scores_gemma":[0.34361884,0.6142442,0.010403206,0.018641962,0.011192624,0.0018991394],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29646704,0.0018049756,0.0026235024,0.010300544,0.0110361185,0.01989069,0.008845173,0.011960089,0.005471246],"category_scores_gemma":[0.35557672,0.0018693685,0.0028870692,0.005766881,0.17353165,0.0673995,0.01324008,0.042910665,0.0011329466],"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":[0.000034481265,0.000023169505,0.00043028194,0.00032511007,0.000040353265,0.00007767613,0.014694388,0.0005045344,0.00002582025,0.9712436,0.003318929,0.009281614],"study_design_scores_gemma":[0.000027286016,0.000016504508,0.00013102035,0.00081148173,0.000017554887,0.0000790893,0.0034591323,0.0011463213,0.00011265046,0.9785265,0.015643533,0.000029025572],"about_ca_topic_score_codex":0.00725495,"about_ca_topic_score_gemma":0.0042271274,"teacher_disagreement_score":0.70353293,"about_ca_system_score_codex":0.01979279,"about_ca_system_score_gemma":0.012355106,"threshold_uncertainty_score":0.86758137},"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":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025173088,0.00008080735,0.0028548455,0.0007774155,0.00032851376,0.0011559637,0.9704138,0.0014135946,0.020457808],"genre_scores_gemma":[0.027675077,0.00062345783,0.0336459,0.00235762,0.00047037017,0.01302533,0.81922895,0.0024600232,0.10051324],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99917054,0.00024877948,0.0001341604,0.00008915421,0.0002323269,0.00012510024],"domain_scores_gemma":[0.9719802,0.019486152,0.0011458606,0.00123799,0.005228678,0.0009211263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022039593,0.00088493846,0.0009054284,0.0025627753,0.00087320874,0.0011950538,0.0015579744,0.0013336893,0.7449684],"category_scores_gemma":[0.026360959,0.00061578053,0.0008005954,0.0029665187,0.00019548168,0.00092920876,0.0013422429,0.0009767839,0.20822814],"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":[0.00009727505,0.0002737158,0.0028801712,0.0004666026,0.000021199996,0.000032050048,0.00010568727,0.00012377996,0.00008684996,0.0006556355,0.9693973,0.025859615],"study_design_scores_gemma":[0.0014121851,0.0003731048,0.12212328,0.0017175357,0.00013850289,0.00045545786,0.0017451717,0.0019460908,0.0011890567,0.011160395,0.85756487,0.0001743263],"about_ca_topic_score_codex":0.026386488,"about_ca_topic_score_gemma":0.061627287,"teacher_disagreement_score":0.99779606,"about_ca_system_score_codex":0.0010535482,"about_ca_system_score_gemma":0.0021647215,"threshold_uncertainty_score":0.36377156},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034086173,0.004278513,0.0006739216,0.23850879,0.7360351,0.00005822216,0.00075688376,0.00028547694,0.019062323],"genre_scores_gemma":[0.011775199,0.005566591,0.0011334476,0.22839515,0.42130047,0.0002991828,0.001043081,0.00052240095,0.3299645],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99535143,0.0007688394,0.00032216826,0.0009826425,0.002168418,0.00040644364],"domain_scores_gemma":[0.9756613,0.0036496022,0.0009055415,0.0010204768,0.016068147,0.0026949262],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030482665,0.0013938686,0.0015555382,0.0013936688,0.0038010997,0.0063885874,0.0020163753,0.0038638515,0.08798493],"category_scores_gemma":[0.05269956,0.00037040177,0.0011517912,0.0006487673,0.0016987441,0.0035167031,0.003395628,0.01375573,0.0664022],"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":[0.000016893686,0.000005671832,0.0000448333,0.000024640627,0.0000034479044,0.000087684886,0.00005269476,0.000011904287,0.00003889873,0.0008618052,0.99425226,0.0045991703],"study_design_scores_gemma":[0.000007086279,0.000009580432,0.00014818489,0.0000905216,0.0000056316103,0.00020545495,0.00010620335,0.000040430827,0.00007385706,0.0009422633,0.99836034,0.000010588594],"about_ca_topic_score_codex":0.0036762515,"about_ca_topic_score_gemma":0.006010674,"teacher_disagreement_score":0.9120151,"about_ca_system_score_codex":0.004783705,"about_ca_system_score_gemma":0.0039880066,"threshold_uncertainty_score":0.29433888},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2543885,0.089517616,0.38913777,0.14205022,0.007615583,0.030702407,0.006826148,0.0013304143,0.07843136],"genre_scores_gemma":[0.8024854,0.011046445,0.1593232,0.006097486,0.001271221,0.014059121,0.0007661243,0.00014256882,0.004808444],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.70717067,0.26107246,0.008687553,0.004204008,0.016696064,0.0021692426],"domain_scores_gemma":[0.6165663,0.35020426,0.010861483,0.00852985,0.011577272,0.0022608119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18841408,0.0025693194,0.004874155,0.0027898946,0.0014648101,0.010389486,0.0019213961,0.0061194045,0.015061914],"category_scores_gemma":[0.34419256,0.0009871131,0.004017749,0.0030275772,0.0040943488,0.0077165104,0.004493881,0.0050481367,0.0010207128],"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":[0.023021437,0.0035665235,0.015412826,0.0279008,0.0070231557,0.00019078694,0.004382771,0.04240565,0.0018155128,0.119707346,0.010745084,0.74382806],"study_design_scores_gemma":[0.043371413,0.05492505,0.083671995,0.061666436,0.025252521,0.0009302712,0.008365409,0.2276858,0.02244537,0.3544794,0.11625794,0.0009485083],"about_ca_topic_score_codex":0.013575246,"about_ca_topic_score_gemma":0.008752795,"teacher_disagreement_score":0.8115859,"about_ca_system_score_codex":0.012587165,"about_ca_system_score_gemma":0.02824693,"threshold_uncertainty_score":0.9964408},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6233564,0.0040358603,0.14852555,0.11657243,0.0007099091,0.0005942828,0.00007237006,0.0008398237,0.10529347],"genre_scores_gemma":[0.96240985,0.000665097,0.027659293,0.0032380857,0.000051848783,0.00020364401,0.00003378511,0.0002324854,0.0055058063],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9500564,0.037571706,0.0014242386,0.0029032638,0.0052407826,0.002803702],"domain_scores_gemma":[0.92371196,0.048350506,0.0035110838,0.0073695313,0.0086442,0.008412626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05686505,0.0005055809,0.0006979892,0.004063216,0.011373386,0.020680234,0.0022788274,0.004866639,0.003107154],"category_scores_gemma":[0.072631165,0.0010947677,0.0005130688,0.0020782403,0.041910253,0.022651726,0.025137816,0.010794879,0.0008282591],"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":[0.000106043,0.0003249172,0.015008969,0.00037605374,0.000021425762,0.0008370548,0.6327965,0.00040852313,0.0033391123,0.19151796,0.00511819,0.15014525],"study_design_scores_gemma":[0.000021819542,0.00037524363,0.008220717,0.0012552903,0.000013260321,0.0016476428,0.5413043,0.0018760312,0.003845427,0.17690766,0.2643734,0.00015917327],"about_ca_topic_score_codex":0.0038209409,"about_ca_topic_score_gemma":0.0039802995,"teacher_disagreement_score":0.05686505,"about_ca_system_score_codex":0.010096176,"about_ca_system_score_gemma":0.019245403,"threshold_uncertainty_score":0.30073476},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005836302,0.01360623,0.07628417,0.7774123,0.0038374453,0.0003506055,0.0000525006,0.0002662201,0.1223543],"genre_scores_gemma":[0.69066644,0.016846951,0.11592373,0.14648521,0.0038868529,0.0016871133,0.00014161623,0.00074833434,0.023613792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.78252757,0.16933212,0.005886762,0.012486425,0.023116577,0.0066506234],"domain_scores_gemma":[0.7129901,0.20228283,0.00882467,0.032263268,0.025230573,0.018408466],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19780387,0.0015731893,0.0020974972,0.0042743813,0.017984837,0.043081127,0.007417489,0.019548956,0.016817486],"category_scores_gemma":[0.17914043,0.001485665,0.0016090093,0.0024609282,0.14769103,0.05998934,0.03730943,0.030099906,0.0042654974],"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":[0.000039674396,0.00021281921,0.0013084325,0.0010351768,0.00006129989,0.00024533496,0.05908991,0.00049286644,0.00028347727,0.8184251,0.038526177,0.08027967],"study_design_scores_gemma":[0.00003468356,0.00009629206,0.0004248106,0.0026017681,0.000024275172,0.00017526797,0.03143638,0.00042796734,0.0003254984,0.67032695,0.29408002,0.00004614164],"about_ca_topic_score_codex":0.005509253,"about_ca_topic_score_gemma":0.0054061897,"teacher_disagreement_score":0.19780387,"about_ca_system_score_codex":0.023651011,"about_ca_system_score_gemma":0.06661462,"threshold_uncertainty_score":0.98925066},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1380811,0.0027047044,0.02099671,0.08054935,0.0015292303,0.0020003899,0.00026180563,0.00059717847,0.7532795],"genre_scores_gemma":[0.82873285,0.0024241996,0.0303572,0.0073128995,0.00022815386,0.00073042174,0.00029066284,0.00012792085,0.12979573],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99192965,0.0040250784,0.0001744427,0.00055210956,0.0014618965,0.0018569054],"domain_scores_gemma":[0.9927637,0.0012520526,0.00045686896,0.00042606075,0.0016243153,0.0034770996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076420833,0.00056719646,0.0003343774,0.0020156116,0.011918475,0.0066712378,0.0019824216,0.0017056267,0.02117539],"category_scores_gemma":[0.009109014,0.00036551492,0.00041824393,0.0015023241,0.0066623893,0.003632468,0.009678142,0.002134556,0.0015890782],"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":[0.00014008617,0.0012917385,0.025413848,0.00074431737,0.000050976163,0.0008561144,0.046474647,0.001605291,0.0007175172,0.18624933,0.19274639,0.5437098],"study_design_scores_gemma":[0.00011727758,0.0005432393,0.017720344,0.0013315673,0.000034017256,0.00034603936,0.10998335,0.0021526783,0.000874073,0.049611997,0.8172085,0.00007686309],"about_ca_topic_score_codex":0.10884587,"about_ca_topic_score_gemma":0.2922671,"teacher_disagreement_score":0.10884587,"about_ca_system_score_codex":0.012921276,"about_ca_system_score_gemma":0.052990697,"threshold_uncertainty_score":0.21642458},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76725274,0.0067915493,0.0012682091,0.084251486,0.0002993787,0.000112826056,0.0002766339,0.000050748244,0.13969643],"genre_scores_gemma":[0.984591,0.0015894863,0.0005683433,0.0023908145,0.000036639995,0.000024345754,0.00007402054,0.00001739677,0.010707982],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98300534,0.0044453493,0.0003718861,0.0009101934,0.00588657,0.005380548],"domain_scores_gemma":[0.96779084,0.017998219,0.0014402454,0.0005930927,0.0076502496,0.00452721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014430691,0.00035787394,0.000480145,0.0036316412,0.039289787,0.01900058,0.0034772723,0.0039616833,0.0028269028],"category_scores_gemma":[0.023061607,0.0005266186,0.00023669211,0.0075299456,0.023329763,0.0033711675,0.0058308654,0.0043458077,0.00013937934],"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":[0.00027064778,0.0001378255,0.031089801,0.0004289525,0.00005054775,0.0025207358,0.47959638,0.0021313522,0.0017556988,0.3568312,0.037607726,0.08757908],"study_design_scores_gemma":[0.000053491553,0.000053894844,0.04334872,0.0006650541,0.00007117235,0.00015573871,0.64519817,0.001819515,0.0011072281,0.027818741,0.27956688,0.00014136464],"about_ca_topic_score_codex":0.99204445,"about_ca_topic_score_gemma":0.99527967,"teacher_disagreement_score":0.3322346,"about_ca_system_score_codex":0.3322346,"about_ca_system_score_gemma":0.35492018,"threshold_uncertainty_score":0.77451324},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9304579,0.0013332736,0.0016378992,0.013281308,0.00014574107,0.00009593099,0.00008433494,0.000026574067,0.05293706],"genre_scores_gemma":[0.9816628,0.0014543822,0.0010424476,0.0015885776,0.000027223985,0.000038376053,0.00007059385,0.00000965319,0.0141060045],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9916244,0.003175554,0.0002908021,0.0004022813,0.0024043215,0.0021026155],"domain_scores_gemma":[0.9883271,0.0034447128,0.0008084668,0.00027570964,0.003957104,0.0031868597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008986889,0.00036423397,0.00043270178,0.0011027587,0.0059125097,0.0065419762,0.00071672024,0.0016071659,0.0051608174],"category_scores_gemma":[0.016833916,0.00017300356,0.0004368536,0.0010788846,0.0041721854,0.002250487,0.0023247956,0.0022418054,0.0006884614],"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":[0.00019767211,0.0005414649,0.17263621,0.00043311532,0.00009170516,0.0029966806,0.6451951,0.00088373176,0.0025728154,0.013232282,0.01655122,0.144668],"study_design_scores_gemma":[0.000026966141,0.00023454061,0.08712162,0.0004968034,0.00006652367,0.0012113603,0.8236081,0.00077515456,0.001045032,0.00230443,0.08300577,0.000103798724],"about_ca_topic_score_codex":0.22216076,"about_ca_topic_score_gemma":0.32088134,"teacher_disagreement_score":0.22216076,"about_ca_system_score_codex":0.007082626,"about_ca_system_score_gemma":0.02030769,"threshold_uncertainty_score":0.44173527},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025676226,0.0082562985,0.0002165207,0.16597618,0.8150382,0.00003777173,0.00010887791,0.00008643908,0.010022932],"genre_scores_gemma":[0.0031806754,0.0073474566,0.00024441368,0.19194321,0.70661664,0.000063586056,0.00011240964,0.00007879389,0.090412766],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981713,0.00033081928,0.00022851067,0.00031406467,0.0007251721,0.00023013802],"domain_scores_gemma":[0.9885361,0.0028831607,0.000919908,0.0005924409,0.0046657296,0.0024026178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019674243,0.0013050665,0.0014811278,0.001426336,0.0015816988,0.0039614327,0.0021228974,0.01116978,0.0642507],"category_scores_gemma":[0.019550223,0.0006342391,0.0010388156,0.0005719829,0.0011198907,0.0026527743,0.001586817,0.009573677,0.04003783],"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":[0.00004090084,0.000011826807,0.0000884231,0.000113650065,0.000010599843,0.00042542594,0.000013205186,0.0000132236355,0.0000689306,0.0002955721,0.99004644,0.0088719],"study_design_scores_gemma":[0.000026878957,0.000028492392,0.00028426238,0.0001531671,0.000017400944,0.00083278166,0.00004882655,0.0000453558,0.00013901843,0.00028684424,0.99812526,0.0000117495365],"about_ca_topic_score_codex":0.0010000269,"about_ca_topic_score_gemma":0.0020659026,"teacher_disagreement_score":0.0642507,"about_ca_system_score_codex":0.0012008369,"about_ca_system_score_gemma":0.0017767991,"threshold_uncertainty_score":0.21494001},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025536568,0.007919663,0.0002167496,0.1643085,0.81745523,0.000036922265,0.000107225394,0.00008771234,0.009612534],"genre_scores_gemma":[0.0031987056,0.0068343384,0.00023768356,0.18979163,0.71459,0.00006254038,0.00011025476,0.00007961918,0.08509524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810874,0.0003436069,0.000232113,0.00032533598,0.00074584153,0.0002443733],"domain_scores_gemma":[0.988304,0.0029612267,0.0009458721,0.00061422004,0.0046886154,0.0024861777],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020328455,0.0012958939,0.0014782689,0.0014123296,0.001600094,0.004017707,0.0021646505,0.011375027,0.06617294],"category_scores_gemma":[0.01994853,0.0006440203,0.0010461794,0.0005581705,0.0011534123,0.0027046995,0.0016522619,0.009871234,0.04065704],"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":[0.00004051332,0.000011841579,0.000090257425,0.000111945716,0.0000108409295,0.00043714247,0.000013314202,0.000013288097,0.000070709604,0.00029839296,0.99024,0.008661714],"study_design_scores_gemma":[0.000027733433,0.000029417228,0.0002855579,0.00015601657,0.00001720711,0.00085975364,0.000049772956,0.000047172693,0.00014381873,0.00029557454,0.99807584,0.000012172856],"about_ca_topic_score_codex":0.00093405973,"about_ca_topic_score_gemma":0.0019517646,"teacher_disagreement_score":0.93382704,"about_ca_system_score_codex":0.0012076665,"about_ca_system_score_gemma":0.0018054792,"threshold_uncertainty_score":0.22137052},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9801641,0.00011669611,0.0002977397,0.0028693255,0.000014844199,0.00003189844,0.00017793523,0.000007119309,0.016320422],"genre_scores_gemma":[0.9989042,0.000058927075,0.00005437197,0.000083013685,0.0000040619684,0.000008643141,0.000049834987,0.0000021487658,0.00083470787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894735,0.003498004,0.00061178464,0.00036259298,0.0032165158,0.002837561],"domain_scores_gemma":[0.9502717,0.014183473,0.014104328,0.0014968773,0.010890254,0.009053392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010389153,0.00013285103,0.000223469,0.0008850827,0.0022331583,0.0049738116,0.0005568611,0.0008012715,0.0046179416],"category_scores_gemma":[0.0463293,0.0002731609,0.0003330739,0.0010093446,0.0019474206,0.0017245584,0.0016366233,0.0010879636,0.00032836536],"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":[0.00036788816,0.00016296099,0.87319136,0.00011669088,0.000061285464,0.00083319057,0.089524396,0.0010115964,0.000740907,0.009792203,0.0066481996,0.017549314],"study_design_scores_gemma":[0.000033325243,0.00019478536,0.78293324,0.00023372905,0.000041099724,0.0001849658,0.19017068,0.0016854014,0.0005995636,0.0020945373,0.021744424,0.00008434315],"about_ca_topic_score_codex":0.37258556,"about_ca_topic_score_gemma":0.4114919,"teacher_disagreement_score":0.37258556,"about_ca_system_score_codex":0.016695997,"about_ca_system_score_gemma":0.009912837,"threshold_uncertainty_score":0.74083376},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038677815,0.020407762,0.02201624,0.5423283,0.003217693,0.00021153396,0.000019460556,0.00020754065,0.37291372],"genre_scores_gemma":[0.89478564,0.0074365833,0.01650894,0.042812504,0.0012964697,0.00022350113,0.000012812803,0.0002144312,0.036709234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.929325,0.056849588,0.0010534633,0.001814103,0.00817013,0.002787739],"domain_scores_gemma":[0.951072,0.034100834,0.0022901199,0.0028035543,0.004375214,0.00535837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06342756,0.0003903924,0.00064408843,0.0025068924,0.018774638,0.022891605,0.001597123,0.005594398,0.0073528118],"category_scores_gemma":[0.052785743,0.0004979586,0.0005230448,0.0013340412,0.08629176,0.01893137,0.0253484,0.012435901,0.0007355854],"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":[0.00006034051,0.00013747478,0.00079069636,0.0004092704,0.000031450454,0.00041793345,0.21067046,0.00023041824,0.00073960325,0.6301791,0.036581997,0.119751334],"study_design_scores_gemma":[0.0000401867,0.00013414488,0.0018846178,0.0015458073,0.000043537886,0.00056236103,0.1339264,0.00060055003,0.0011188184,0.3626297,0.49741325,0.00010065227],"about_ca_topic_score_codex":0.011964169,"about_ca_topic_score_gemma":0.03371295,"teacher_disagreement_score":0.98151225,"about_ca_system_score_codex":0.018487748,"about_ca_system_score_gemma":0.025692806,"threshold_uncertainty_score":0.335441},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015154992,0.0009841216,0.0008045414,0.0036339147,0.012101359,0.0004584335,0.025235545,0.0017672679,0.9548633],"genre_scores_gemma":[0.00048331422,0.00070949626,0.0004309557,0.0011576405,0.0015216803,0.00013943456,0.0112668965,0.0003308537,0.98395985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987716,0.00012926666,0.00007329327,0.00014224621,0.000755447,0.00012811765],"domain_scores_gemma":[0.9948487,0.0006195813,0.00028628652,0.00043657684,0.002466348,0.0013425807],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001300779,0.0017622925,0.0012070892,0.0047775027,0.0016616336,0.008005891,0.0022531247,0.0030848696,0.9175557],"category_scores_gemma":[0.007713025,0.0006803456,0.0011057183,0.004325318,0.00066209806,0.003885877,0.002442514,0.0021708193,0.86585104],"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":[0.000010208411,0.000016802662,0.000022601333,0.00010093151,8.787976e-7,0.000007747744,0.0000028962802,0.000024048533,0.00004234793,0.0006592114,0.9777256,0.021386804],"study_design_scores_gemma":[0.000014392048,0.000011266216,0.00017104456,0.00009628765,0.0000014043374,0.000012947711,0.000012786668,0.00003793503,0.000044776723,0.0008421743,0.99875104,0.0000038884273],"about_ca_topic_score_codex":0.00412773,"about_ca_topic_score_gemma":0.008643029,"teacher_disagreement_score":0.9175557,"about_ca_system_score_codex":0.0016158905,"about_ca_system_score_gemma":0.003911298,"threshold_uncertainty_score":0.117596745},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9670269,0.0012690856,0.0041776034,0.0021375378,0.00016228198,0.013865763,0.0020248282,0.0001388699,0.009197167],"genre_scores_gemma":[0.9776854,0.0008572462,0.0108914375,0.00059048843,0.000028503646,0.0071091084,0.0012080829,0.000037129026,0.0015925007],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.91687036,0.037056454,0.005935497,0.0034045803,0.029567113,0.0071659735],"domain_scores_gemma":[0.8369006,0.027367845,0.020506756,0.0075201574,0.08861851,0.019086093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09228921,0.0005949144,0.0011358005,0.0017450899,0.005123829,0.002966024,0.002920084,0.0008679847,0.0014891983],"category_scores_gemma":[0.16223669,0.0007186247,0.001485941,0.0021962444,0.0020986032,0.001696542,0.0043706116,0.0019177801,0.00024808646],"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":[0.0026798006,0.005367927,0.62937057,0.0025489214,0.00069038296,0.0001476596,0.029369945,0.00331414,0.0008800682,0.00094730913,0.0106485225,0.3140347],"study_design_scores_gemma":[0.0004895572,0.005150854,0.96205634,0.0018595041,0.00026393076,0.00005781606,0.01112325,0.0030656666,0.0016017259,0.00018701897,0.0139761325,0.000168261],"about_ca_topic_score_codex":0.8287516,"about_ca_topic_score_gemma":0.9152842,"teacher_disagreement_score":0.9237988,"about_ca_system_score_codex":0.07620123,"about_ca_system_score_gemma":0.22355147,"threshold_uncertainty_score":0.55288124},"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":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021034756,0.014876448,0.0027811222,0.88682914,0.09085054,0.000102763544,0.00011894729,0.00012881939,0.004101792],"genre_scores_gemma":[0.010928437,0.026281856,0.020096572,0.8345073,0.0884899,0.00056301546,0.0001935783,0.00021930735,0.018720042],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.838544,0.07943487,0.022533037,0.005641385,0.050516754,0.003329919],"domain_scores_gemma":[0.25043476,0.3700138,0.017575718,0.047243275,0.2740594,0.040673055],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22265077,0.0014890367,0.0043110554,0.0030592897,0.005640534,0.013805612,0.007029887,0.022946,0.018929573],"category_scores_gemma":[0.5689131,0.0010717518,0.002970555,0.0033348573,0.013820298,0.019956287,0.006180735,0.028911563,0.018195331],"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":[0.00029560336,0.00010202908,0.0008539804,0.0042560897,0.00029193333,0.00017888432,0.00044621222,0.0001266304,0.00030327516,0.016755793,0.87771577,0.09867374],"study_design_scores_gemma":[0.00020434891,0.00024188634,0.0013836792,0.017225677,0.00044480292,0.0007379372,0.0030995056,0.00042983482,0.0005202103,0.06182529,0.91361916,0.00026753676],"about_ca_topic_score_codex":0.004106342,"about_ca_topic_score_gemma":0.010316009,"teacher_disagreement_score":0.77734923,"about_ca_system_score_codex":0.005719303,"about_ca_system_score_gemma":0.03701464,"threshold_uncertainty_score":0.95861},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042591663,0.06938324,0.14098224,0.4173514,0.024583712,0.019236768,0.0068210606,0.0032987196,0.31408373],"genre_scores_gemma":[0.1220065,0.0921557,0.425704,0.12131295,0.013129766,0.038340054,0.026198586,0.0016684134,0.15948413],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9191326,0.0437901,0.009395992,0.0032152685,0.019748805,0.0047171554],"domain_scores_gemma":[0.7968341,0.059697498,0.0060679335,0.008287201,0.11441603,0.014697181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1281828,0.0023436174,0.0028240723,0.009672911,0.0035509092,0.013220396,0.0066049662,0.012853144,0.06984567],"category_scores_gemma":[0.13504028,0.001421355,0.0032412475,0.003694692,0.0037509883,0.012606406,0.010510568,0.00898348,0.020359313],"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":[0.0006042707,0.0006150186,0.0010746617,0.0070746564,0.00008190993,0.00029702316,0.00024034224,0.0036541617,0.0005013927,0.17972916,0.3114224,0.49470502],"study_design_scores_gemma":[0.0004261414,0.0009783957,0.0027261178,0.011935599,0.00013127782,0.0004338703,0.00053537526,0.004990765,0.0010864849,0.13606268,0.8405613,0.00013201604],"about_ca_topic_score_codex":0.010364958,"about_ca_topic_score_gemma":0.008836051,"teacher_disagreement_score":0.1281828,"about_ca_system_score_codex":0.011648064,"about_ca_system_score_gemma":0.10761111,"threshold_uncertainty_score":0.67790353},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89038867,0.00080379355,0.034290392,0.013134503,0.00018385134,0.00045745217,0.00007500233,0.00033518064,0.060331296],"genre_scores_gemma":[0.9887673,0.00033031782,0.00963357,0.00027971403,0.000030755797,0.000059573078,0.000025320656,0.000017984203,0.0008555561],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95344657,0.036869984,0.0012958545,0.0012334706,0.0056467564,0.0015073733],"domain_scores_gemma":[0.7016456,0.24825528,0.017871581,0.009741073,0.01459912,0.0078872815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033301853,0.0002597346,0.00035963173,0.0020557775,0.0011668386,0.0067286594,0.0015891697,0.0013891509,0.0056252433],"category_scores_gemma":[0.22724766,0.00030730857,0.00026157408,0.001161307,0.0022307308,0.0076669804,0.0032066933,0.0009818648,0.00085819256],"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":[0.00042227158,0.0033642692,0.17681934,0.0007187786,0.000051337323,0.0014121596,0.05586551,0.0016092177,0.0032669199,0.029590081,0.012235007,0.7146452],"study_design_scores_gemma":[0.0004984447,0.0040587164,0.31535175,0.006357336,0.0003319883,0.005376136,0.2348783,0.04325372,0.021954913,0.12736739,0.24019957,0.00037168764],"about_ca_topic_score_codex":0.0018748973,"about_ca_topic_score_gemma":0.0029458152,"teacher_disagreement_score":0.033301853,"about_ca_system_score_codex":0.0030227148,"about_ca_system_score_gemma":0.0041987575,"threshold_uncertainty_score":0.17611909},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2829556,0.026000988,0.19181272,0.061300803,0.0012302382,0.0011761355,0.00048425377,0.0005298336,0.4345094],"genre_scores_gemma":[0.863215,0.008518436,0.09265352,0.0021817375,0.00016405953,0.00087697577,0.00017000473,0.00014278325,0.032077365],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95267045,0.030430958,0.0013708611,0.0024686563,0.01141507,0.0016440029],"domain_scores_gemma":[0.9294297,0.039216053,0.00447969,0.003601352,0.019527843,0.0037453135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0436194,0.0008584854,0.0010523169,0.004518913,0.0045638406,0.017200617,0.0020806952,0.0018914399,0.010002912],"category_scores_gemma":[0.060306784,0.00046761034,0.00068946334,0.005590792,0.01151191,0.011512956,0.007905276,0.003749118,0.0012491988],"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":[0.00035062432,0.0004116455,0.022924036,0.0032537284,0.0001896167,0.00021263704,0.12635612,0.0023322173,0.003546451,0.2733065,0.007570702,0.5595457],"study_design_scores_gemma":[0.00010804348,0.001056124,0.08460571,0.009813035,0.0003015153,0.0003775183,0.22315985,0.006483311,0.008200036,0.19865659,0.46682805,0.00041016834],"about_ca_topic_score_codex":0.11069127,"about_ca_topic_score_gemma":0.1540004,"teacher_disagreement_score":0.11069127,"about_ca_system_score_codex":0.027574936,"about_ca_system_score_gemma":0.04251695,"threshold_uncertainty_score":0.23068422},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036241613,0.0042230734,0.16701408,0.063808665,0.0018335668,0.0006210695,0.00037069275,0.00025292143,0.7256343],"genre_scores_gemma":[0.8294635,0.0028666388,0.11784061,0.01264751,0.0010097409,0.0014453391,0.0006351149,0.00014583142,0.03394575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9531887,0.02694686,0.0037853909,0.0040074615,0.009319039,0.0027524733],"domain_scores_gemma":[0.96561176,0.012700869,0.00545478,0.003067989,0.0096202595,0.0035443276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018603602,0.0010441979,0.00071433734,0.0061283954,0.0050152405,0.013029507,0.0021354528,0.0040169437,0.007075889],"category_scores_gemma":[0.036830448,0.0003967775,0.0008376948,0.005136055,0.030061586,0.012791217,0.007778979,0.0036026428,0.002188723],"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":[0.000010773654,0.000032371507,0.0021729565,0.00014475288,0.000012265976,0.000068974834,0.0057070847,0.00025055293,0.00015610093,0.95835274,0.0060772873,0.027014157],"study_design_scores_gemma":[0.0000195176,0.00009634543,0.0050526094,0.0010334464,0.000029660368,0.0004445533,0.017472746,0.0009842372,0.00061256567,0.70985895,0.26435187,0.000043423348],"about_ca_topic_score_codex":0.009987275,"about_ca_topic_score_gemma":0.011297268,"teacher_disagreement_score":0.018603602,"about_ca_system_score_codex":0.008959684,"about_ca_system_score_gemma":0.018545836,"threshold_uncertainty_score":0.09838647},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008903499,0.13542256,0.01697098,0.5382464,0.08147032,0.0009965922,0.018948095,0.0070794644,0.19997524],"genre_scores_gemma":[0.004897037,0.07867632,0.031446833,0.06426192,0.0073222225,0.0013000988,0.0074016214,0.0023878454,0.80230606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951454,0.0007872047,0.00027947596,0.00032655484,0.0032059087,0.0002554929],"domain_scores_gemma":[0.97916806,0.0029827086,0.001045949,0.00048266063,0.010835932,0.0054847067],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011173757,0.0015913715,0.00063653965,0.0038467883,0.0018740712,0.0041330084,0.0021308032,0.0042150756,0.16725017],"category_scores_gemma":[0.022021601,0.0010773513,0.0006745369,0.0034271588,0.0011556636,0.0035310844,0.0026409356,0.004196372,0.13854198],"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":[0.00001194936,0.000005425452,0.00009130836,0.00010151388,0.0000011783419,0.000009474797,0.000029908248,0.000014805656,0.000050172945,0.00030661435,0.9378603,0.06151725],"study_design_scores_gemma":[0.000008644584,0.000007962997,0.0004319241,0.00042158013,0.000004064596,0.000021946653,0.000077877055,0.000022926575,0.00011424316,0.00042744508,0.99845195,0.000009341445],"about_ca_topic_score_codex":0.06999886,"about_ca_topic_score_gemma":0.15860508,"teacher_disagreement_score":0.9888262,"about_ca_system_score_codex":0.0030280177,"about_ca_system_score_gemma":0.017639449,"threshold_uncertainty_score":0.55950755},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007842953,0.016246477,0.0011833385,0.21429773,0.7669029,0.000099391305,0.00005764459,0.00009121816,0.0010428331],"genre_scores_gemma":[0.0010773117,0.009387195,0.001894681,0.111444205,0.873961,0.00013430713,0.000032121123,0.00017531979,0.0018939521],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9087495,0.0316225,0.012694346,0.0065130037,0.03802751,0.0023930166],"domain_scores_gemma":[0.49903625,0.29873914,0.01925959,0.010945633,0.15441252,0.017606838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12292809,0.0025450096,0.005485345,0.0052248673,0.0054639573,0.020090038,0.0073146196,0.02691394,0.008769533],"category_scores_gemma":[0.2946037,0.00212583,0.0032883813,0.0036604602,0.01200705,0.008745343,0.004196772,0.031892892,0.0036120622],"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":[0.000039934108,0.000022152739,0.00011294186,0.0006875075,0.000057367462,0.000061840954,0.00009766895,0.000036204987,0.000080206315,0.0013531165,0.98409283,0.013358182],"study_design_scores_gemma":[0.0001400146,0.00008734692,0.0010070322,0.002912715,0.00021295952,0.00034183162,0.000318332,0.00042822346,0.00017893799,0.006300075,0.98796356,0.000108977256],"about_ca_topic_score_codex":0.012920886,"about_ca_topic_score_gemma":0.041684102,"teacher_disagreement_score":0.12292809,"about_ca_system_score_codex":0.010355727,"about_ca_system_score_gemma":0.025404897,"threshold_uncertainty_score":0.65011364},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020396993,0.0017852524,0.97177863,0.0039041778,0.0001629227,0.0047393953,0.00012467985,0.00021795751,0.015247401],"genre_scores_gemma":[0.031682856,0.00065217377,0.9562964,0.00050469284,0.000031639953,0.01025004,0.00006903068,0.00004545741,0.00046765304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6399879,0.3372259,0.0059431875,0.0048534856,0.010517171,0.0014723432],"domain_scores_gemma":[0.77880776,0.18787012,0.007107993,0.011097559,0.01263642,0.0024801139],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25620294,0.003911136,0.0038656525,0.01681483,0.005539017,0.011738182,0.0067721335,0.0035671992,0.0053625177],"category_scores_gemma":[0.13023478,0.0018186026,0.0038535914,0.009489679,0.017960364,0.011483061,0.015366119,0.0066445647,0.0008934342],"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":[0.0001381883,0.00049368135,0.0029264973,0.0041031833,0.0006732785,0.0003419166,0.015771423,0.013624636,0.00080458797,0.78875774,0.0031237572,0.16924126],"study_design_scores_gemma":[0.00037237702,0.00080899097,0.0020809572,0.009689638,0.0004963742,0.0004139103,0.0127745345,0.04184717,0.0019371836,0.84041935,0.088914976,0.00024448603],"about_ca_topic_score_codex":0.008438845,"about_ca_topic_score_gemma":0.011913169,"teacher_disagreement_score":0.74379706,"about_ca_system_score_codex":0.020356998,"about_ca_system_score_gemma":0.033986434,"threshold_uncertainty_score":0.9172342},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003978204,0.0017636449,0.0004042488,0.9600205,0.033410925,0.000044632063,0.00004274487,0.00011051958,0.003804894],"genre_scores_gemma":[0.02162351,0.003202568,0.00419405,0.8126089,0.09185922,0.0002982872,0.0001677648,0.0005589697,0.065486684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92756456,0.031060925,0.0042261956,0.004297043,0.026467048,0.0063842866],"domain_scores_gemma":[0.69146454,0.12074201,0.014399981,0.010878506,0.054258842,0.10825617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11211543,0.0013196216,0.0014742371,0.0017386598,0.0114345895,0.018143425,0.0046445653,0.050908454,0.0376939],"category_scores_gemma":[0.18878216,0.0015736034,0.001572284,0.0017557782,0.010999307,0.013238454,0.014138603,0.052163202,0.008478743],"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":[0.00003436398,0.000040949395,0.0001506988,0.000060135262,0.0000060031975,0.00009537433,0.00034863182,0.000017892453,0.00013633148,0.0020523702,0.9898588,0.0071986145],"study_design_scores_gemma":[0.00011479528,0.00010292705,0.002382658,0.00044108467,0.000027440708,0.0001963544,0.0019593148,0.00021409676,0.00036026884,0.0037301534,0.99036306,0.00010782517],"about_ca_topic_score_codex":0.021626716,"about_ca_topic_score_gemma":0.08004971,"teacher_disagreement_score":0.11211543,"about_ca_system_score_codex":0.013858122,"about_ca_system_score_gemma":0.050319947,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003668238,0.024507333,0.10120983,0.837681,0.008103297,0.0022643271,0.00014286631,0.0002627323,0.0221603],"genre_scores_gemma":[0.43202198,0.022971928,0.3616355,0.14442822,0.014012262,0.019068683,0.00039305986,0.00060280523,0.004865485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.14688133,0.7120867,0.051667508,0.017896187,0.06354578,0.007922497],"domain_scores_gemma":[0.069992006,0.7406292,0.031439826,0.08126597,0.06182,0.0148530025],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7865131,0.0036218727,0.012850843,0.014916464,0.01424954,0.070398875,0.014389252,0.040378205,0.006229771],"category_scores_gemma":[0.80092883,0.0034665337,0.005040885,0.013212405,0.12992148,0.078801736,0.035935905,0.051214084,0.0024994714],"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":[0.0005223802,0.00024441056,0.0017834472,0.010053272,0.00040572314,0.00024458102,0.024373462,0.0010272724,0.0006674174,0.88050437,0.0140885515,0.06608507],"study_design_scores_gemma":[0.00031025684,0.0002670562,0.00083511067,0.015565645,0.00019200733,0.000147795,0.008807108,0.0014793624,0.00052767457,0.92830634,0.04339633,0.00016527365],"about_ca_topic_score_codex":0.0048343744,"about_ca_topic_score_gemma":0.0029058093,"teacher_disagreement_score":0.21348691,"about_ca_system_score_codex":0.03871651,"about_ca_system_score_gemma":0.13148166,"threshold_uncertainty_score":0.28090924},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008856327,0.0036429209,0.44191256,0.074589334,0.0017396358,0.0010016174,0.00020102662,0.0003096023,0.46774697],"genre_scores_gemma":[0.48802346,0.0033697144,0.41713855,0.007769977,0.0009746273,0.0029074168,0.0004111139,0.00033021864,0.07907485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.961096,0.028823975,0.0011616618,0.002579465,0.0050405166,0.0012985073],"domain_scores_gemma":[0.9799872,0.012555263,0.00090918195,0.0017099616,0.0037567117,0.0010816884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02481075,0.00221316,0.00095087674,0.007354974,0.00865188,0.022509463,0.0048090452,0.007339442,0.02192659],"category_scores_gemma":[0.023240864,0.0007010511,0.0013964196,0.0038093622,0.037429724,0.015758313,0.012974043,0.010450524,0.002987728],"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":[0.000012376261,0.00004298846,0.000064289336,0.00010913543,0.000007479699,0.000030192557,0.0039836294,0.00077528734,0.000104252525,0.9816071,0.0034336187,0.009829718],"study_design_scores_gemma":[0.000031654363,0.000042818916,0.000071532864,0.0002713061,0.000008140375,0.000056960576,0.0073954025,0.0046730554,0.0004201913,0.8464357,0.14057365,0.000019598861],"about_ca_topic_score_codex":0.0040877163,"about_ca_topic_score_gemma":0.0047785956,"teacher_disagreement_score":0.02481075,"about_ca_system_score_codex":0.016287489,"about_ca_system_score_gemma":0.012356444,"threshold_uncertainty_score":0.1312133},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01685533,0.0005046035,0.9194721,0.0009869759,0.00039786642,0.05299942,0.00031073517,0.0005042297,0.007968735],"genre_scores_gemma":[0.049909364,0.00015900357,0.86078966,0.00035244538,0.000058107333,0.088068165,0.000052109688,0.00008615302,0.0005249538],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.56395006,0.40186912,0.012215284,0.006889679,0.013544904,0.001530958],"domain_scores_gemma":[0.40144613,0.5039963,0.020258319,0.040161807,0.03206198,0.0020754107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3439459,0.0023610182,0.0016518498,0.005315552,0.0031630653,0.0064110584,0.003314161,0.0022144585,0.010545314],"category_scores_gemma":[0.3652214,0.0017624383,0.0023461895,0.0042698216,0.0042243986,0.004202136,0.0066154934,0.0035777723,0.0012648285],"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":[0.0038915144,0.003993023,0.0092036715,0.01362773,0.0019242818,0.00033290824,0.03379385,0.015008214,0.009283867,0.25384766,0.008146124,0.64694726],"study_design_scores_gemma":[0.009236819,0.019813739,0.015197306,0.013833036,0.0030396162,0.0003500601,0.020655507,0.11908554,0.051010516,0.5806853,0.16629821,0.00079427846],"about_ca_topic_score_codex":0.00118483,"about_ca_topic_score_gemma":0.0032704477,"teacher_disagreement_score":0.3439459,"about_ca_system_score_codex":0.0047495887,"about_ca_system_score_gemma":0.009516982,"threshold_uncertainty_score":0.80903155},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001636564,0.9974252,0.00041808048,0.0006841548,0.00022032669,0.00027354437,0.00005906477,0.0000069256603,0.0007490254],"genre_scores_gemma":[0.0024355846,0.9954862,0.0011223007,0.00029184468,0.00008922917,0.0003934645,0.00006424178,0.0000054612856,0.00011161042],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.96728945,0.015608556,0.00874076,0.0012276775,0.006420019,0.0007135548],"domain_scores_gemma":[0.82148767,0.15186913,0.008413147,0.0022783468,0.014996804,0.0009548794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04347343,0.0018438121,0.005640654,0.021249069,0.0018406494,0.0060383426,0.0022751887,0.004038296,0.004305978],"category_scores_gemma":[0.13154307,0.0012337974,0.0040572365,0.022363743,0.0027528573,0.0049837497,0.0031215746,0.002668713,0.0007271854],"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":[0.000089204215,0.000061355306,0.000521265,0.59323853,0.000985701,0.00012607459,0.0009777187,0.00030271045,0.00021887501,0.0038951284,0.007629241,0.39195415],"study_design_scores_gemma":[0.000018949822,0.00004808012,0.00069526903,0.9300252,0.0016492566,0.00013984516,0.0005111393,0.00007670647,0.00014037415,0.0012412231,0.06543471,0.000019133726],"about_ca_topic_score_codex":0.013668313,"about_ca_topic_score_gemma":0.024093473,"teacher_disagreement_score":0.9565266,"about_ca_system_score_codex":0.00900725,"about_ca_system_score_gemma":0.041748215,"threshold_uncertainty_score":0.22991228},"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":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028767066,0.005786742,0.18878993,0.040769562,0.0007513907,0.0015782836,0.00080849044,0.00054541527,0.7322031],"genre_scores_gemma":[0.39006752,0.015662076,0.4834742,0.008874816,0.00033569933,0.002306262,0.001627446,0.0003948329,0.09725719],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97282976,0.009040367,0.001757728,0.0011835203,0.014457947,0.00073069107],"domain_scores_gemma":[0.9338102,0.0480097,0.0030258372,0.0026001805,0.011250307,0.0013038139],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02156771,0.0009335566,0.0010406297,0.0054978193,0.0022440038,0.016566735,0.002259957,0.0037545306,0.016679846],"category_scores_gemma":[0.045081913,0.0006743004,0.0006229993,0.004389366,0.005211103,0.016319387,0.008548455,0.0035431397,0.0050543696],"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":[0.000036605958,0.00025835272,0.005371025,0.0019408322,0.000035992307,0.0003238812,0.01573801,0.0016092459,0.0014984537,0.43326667,0.019514212,0.52040666],"study_design_scores_gemma":[0.000020842306,0.00026874343,0.011849994,0.007903544,0.00006080437,0.0010123408,0.040751684,0.0055941488,0.0035796936,0.59121424,0.33763945,0.00010442842],"about_ca_topic_score_codex":0.0030249031,"about_ca_topic_score_gemma":0.003930427,"teacher_disagreement_score":0.9784323,"about_ca_system_score_codex":0.007236281,"about_ca_system_score_gemma":0.023203857,"threshold_uncertainty_score":0.11406237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969247,0.0001248717,0.00041463127,0.00015991344,0.00001777572,0.0015084454,0.000081236656,0.000016368,0.00075201486],"genre_scores_gemma":[0.995093,0.0001527009,0.0013261104,0.00013976028,0.000015852575,0.0027871907,0.000116909025,0.0000044793674,0.00036394052],"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.98091424,0.012527162,0.0013737392,0.0010154843,0.0015865747,0.002582747],"domain_scores_gemma":[0.9542056,0.023284651,0.006720874,0.003985736,0.0056006536,0.0062025758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031100173,0.00079910335,0.0010212624,0.00161181,0.0059407875,0.0027680567,0.0018689033,0.0019057955,0.0024940914],"category_scores_gemma":[0.048021704,0.0009119744,0.0010730767,0.0013272421,0.0029709549,0.0026028955,0.0038710143,0.0035581647,0.000585365],"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":[0.011139191,0.3235585,0.30452085,0.0014257844,0.0003819055,0.0007584411,0.13930482,0.00101938,0.0019240463,0.0009359394,0.0024815493,0.21254963],"study_design_scores_gemma":[0.006963534,0.19969928,0.6343685,0.001190382,0.0008135351,0.00041866532,0.14042033,0.0017831704,0.0052013863,0.0010539092,0.007659087,0.0004283287],"about_ca_topic_score_codex":0.013042748,"about_ca_topic_score_gemma":0.020897334,"teacher_disagreement_score":0.031100173,"about_ca_system_score_codex":0.004959971,"about_ca_system_score_gemma":0.012944913,"threshold_uncertainty_score":0.16447538},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993701,0.00037510818,0.00017511557,0.0007669152,0.000020025915,0.000043786404,0.000043861968,0.000006134587,0.0048681013],"genre_scores_gemma":[0.99828774,0.00032897075,0.00015442548,0.0002051164,0.000004085814,0.000018138482,0.000035148118,0.0000050011913,0.0009614222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9895929,0.0030734986,0.00036472117,0.00054729905,0.00397883,0.0024426186],"domain_scores_gemma":[0.95334864,0.010221671,0.004758782,0.0006765996,0.021841373,0.009153019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014325121,0.00024465442,0.00040379475,0.003884672,0.00781746,0.003987478,0.00095716264,0.00071747025,0.0017333861],"category_scores_gemma":[0.030617243,0.00034995668,0.0002844477,0.0039693993,0.003795539,0.0008623715,0.0027047999,0.0012558176,0.00014831725],"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":[0.00037758244,0.0002535763,0.5302114,0.00020496524,0.000038008595,0.00034468767,0.42179635,0.000116264266,0.0009492318,0.0017448966,0.0031610024,0.040802013],"study_design_scores_gemma":[0.00002364115,0.00017148638,0.5544269,0.0002936497,0.000024223838,0.00020601379,0.4262628,0.00042401842,0.00042960964,0.00023053492,0.017440509,0.000066689136],"about_ca_topic_score_codex":0.88273835,"about_ca_topic_score_gemma":0.93252593,"teacher_disagreement_score":0.9686126,"about_ca_system_score_codex":0.031387374,"about_ca_system_score_gemma":0.058348566,"threshold_uncertainty_score":0.2359044},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5191848,0.0014976254,0.33064595,0.046942037,0.002260854,0.022187835,0.0005469877,0.00995639,0.06677752],"genre_scores_gemma":[0.5187558,0.0005725155,0.43612963,0.0042320234,0.0004331083,0.0056669298,0.0005178242,0.00064100284,0.03305116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96951586,0.015701579,0.0018166194,0.0031769995,0.0070296684,0.0027592934],"domain_scores_gemma":[0.8967494,0.014977719,0.006231676,0.010212709,0.040526506,0.031301923],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0737377,0.00059333595,0.0004988772,0.003873961,0.005547617,0.0076371557,0.0045897355,0.0014077238,0.010477042],"category_scores_gemma":[0.0500954,0.00077897584,0.00061105605,0.0014193126,0.0021518809,0.0041714543,0.009152085,0.0043833144,0.0027238864],"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":[0.00037746542,0.0068078,0.028182182,0.00058702554,0.00006347825,0.00028569068,0.013567914,0.003974351,0.009234049,0.009222301,0.036312807,0.89138496],"study_design_scores_gemma":[0.000980981,0.01314783,0.18131946,0.0025968817,0.00024417244,0.0012259813,0.029384607,0.023504626,0.04056834,0.015448923,0.69097406,0.00060420576],"about_ca_topic_score_codex":0.008737567,"about_ca_topic_score_gemma":0.02247573,"teacher_disagreement_score":0.98168814,"about_ca_system_score_codex":0.018311886,"about_ca_system_score_gemma":0.07774902,"threshold_uncertainty_score":0.3899669},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008354899,0.9611531,0.011222515,0.015691767,0.0014031737,0.00217628,0.00013464373,0.00005066287,0.0073324004],"genre_scores_gemma":[0.04621537,0.8915777,0.043893963,0.005986796,0.0005086952,0.010601684,0.00021777143,0.000056776193,0.00094127294],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83248645,0.12718831,0.0175445,0.0039025422,0.016976159,0.0019021132],"domain_scores_gemma":[0.69217324,0.26130185,0.011134206,0.0064564934,0.027097903,0.0018363147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16624753,0.0017326717,0.003680421,0.012515657,0.004137729,0.011123503,0.004376135,0.0040131207,0.0031605887],"category_scores_gemma":[0.26714042,0.0011720463,0.0036686114,0.013380834,0.0076711285,0.008020245,0.009498611,0.0066881105,0.00043176854],"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":[0.00015597868,0.00017775259,0.00060417096,0.26430026,0.0009145152,0.00020326154,0.015669534,0.0016033842,0.0002198686,0.17063639,0.023042196,0.5224727],"study_design_scores_gemma":[0.000111727924,0.00014538392,0.00080693356,0.67184067,0.001264181,0.00024235163,0.008482164,0.000696518,0.00037161112,0.024717802,0.29122934,0.000091337715],"about_ca_topic_score_codex":0.015656902,"about_ca_topic_score_gemma":0.024947809,"teacher_disagreement_score":0.16624753,"about_ca_system_score_codex":0.022207813,"about_ca_system_score_gemma":0.07400792,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0234277,0.009639557,0.91640717,0.007936486,0.00070210744,0.0037307981,0.0003967361,0.0011995932,0.03655981],"genre_scores_gemma":[0.3024221,0.0016844177,0.68803036,0.00072572514,0.00018783358,0.0054515833,0.00025827193,0.00023082101,0.001008905],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.41378182,0.5057175,0.030881489,0.006626687,0.040692985,0.0022995137],"domain_scores_gemma":[0.28042775,0.58466417,0.042339467,0.032718442,0.056292836,0.0035572785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34462368,0.0026677141,0.0028916139,0.018689714,0.0028028216,0.016476039,0.0032083536,0.003938661,0.0038658157],"category_scores_gemma":[0.60869586,0.0012993366,0.002912188,0.016911449,0.011004969,0.019446079,0.012502338,0.0051989136,0.0007705696],"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":[0.00062921195,0.000373281,0.014265,0.0057980814,0.00075792056,0.00012283163,0.010965356,0.016420633,0.0006454996,0.41317815,0.0101559125,0.5266881],"study_design_scores_gemma":[0.00042767884,0.0014161684,0.01583153,0.013277808,0.00073021115,0.00056742784,0.008677859,0.08969446,0.004579085,0.7822038,0.08202924,0.0005647986],"about_ca_topic_score_codex":0.0025479693,"about_ca_topic_score_gemma":0.0018183076,"teacher_disagreement_score":0.34462368,"about_ca_system_score_codex":0.012577402,"about_ca_system_score_gemma":0.013156359,"threshold_uncertainty_score":0.8081957},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9334589,0.00038771218,0.0053393263,0.0113770515,0.00003200043,0.00029619064,0.0000453042,0.000029029883,0.049034443],"genre_scores_gemma":[0.99797446,0.00011353646,0.00074579235,0.00030351206,0.000006481695,0.00014694293,0.00000950154,0.0000064734163,0.0006933911],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9159221,0.07088581,0.00183486,0.0016866106,0.0042706444,0.005400045],"domain_scores_gemma":[0.77367574,0.16988231,0.021975983,0.008099886,0.018091947,0.008274129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.082806796,0.00030888504,0.00046972165,0.0032946935,0.011133468,0.013180184,0.002181374,0.0023573213,0.003479148],"category_scores_gemma":[0.15446293,0.0006378003,0.00031236498,0.0049201497,0.015833646,0.010315118,0.007108046,0.005545232,0.00028522327],"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":[0.0003491015,0.0024800822,0.12890804,0.00039771106,0.00006919956,0.0005781027,0.45781988,0.004647769,0.00067741045,0.3280821,0.006954959,0.06903557],"study_design_scores_gemma":[0.00008995754,0.00038377216,0.072721966,0.0007132109,0.000033392997,0.00016735046,0.83111656,0.007592757,0.0008959815,0.035981577,0.050204996,0.0000985444],"about_ca_topic_score_codex":0.02502399,"about_ca_topic_score_gemma":0.014470901,"teacher_disagreement_score":0.082806796,"about_ca_system_score_codex":0.029809989,"about_ca_system_score_gemma":0.031401772,"threshold_uncertainty_score":0.43792945},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009688844,0.00075632293,0.97535044,0.0032374826,0.00009799449,0.0014251595,0.00005680309,0.00015539762,0.009231472],"genre_scores_gemma":[0.3177506,0.00042050632,0.67661047,0.00059805514,0.000086090586,0.003518136,0.00006437914,0.00009196995,0.000859758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44917357,0.5126122,0.009591288,0.010123137,0.017027266,0.0014725039],"domain_scores_gemma":[0.40180412,0.505156,0.022118881,0.05425432,0.014965042,0.0017016842],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30699798,0.002109745,0.0030124134,0.015556883,0.0037360715,0.010573726,0.0054505025,0.004583481,0.0066305925],"category_scores_gemma":[0.3973298,0.0018319224,0.0029305608,0.0060162917,0.02245407,0.021048546,0.012959713,0.006734715,0.00053366413],"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":[0.00032915015,0.00043352396,0.007145108,0.0030062452,0.0005993744,0.00038663458,0.038680736,0.0064115925,0.0019312436,0.7315778,0.001425371,0.20807312],"study_design_scores_gemma":[0.00033780365,0.0007142736,0.0053372663,0.0042646155,0.00041454515,0.00076016004,0.014313508,0.046744168,0.0050821276,0.89383763,0.027876573,0.00031736743],"about_ca_topic_score_codex":0.002534447,"about_ca_topic_score_gemma":0.0028379897,"teacher_disagreement_score":0.693002,"about_ca_system_score_codex":0.009500778,"about_ca_system_score_gemma":0.01402216,"threshold_uncertainty_score":0.8545949},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005092216,0.19212307,0.05912917,0.63907933,0.042915866,0.0006204325,0.004992595,0.00330384,0.05732648],"genre_scores_gemma":[0.023079036,0.2840405,0.17258584,0.2660419,0.035945974,0.0042619463,0.006766024,0.00647318,0.20080553],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9861215,0.006666121,0.0013257195,0.0007847909,0.004869958,0.00023201681],"domain_scores_gemma":[0.83733577,0.09089379,0.0064803055,0.004537676,0.056159616,0.004592868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03680838,0.0013276429,0.00108138,0.006189994,0.0030790032,0.006810031,0.0031871551,0.006569444,0.06904118],"category_scores_gemma":[0.1645279,0.0017254453,0.00084717054,0.009452313,0.0042699897,0.008041989,0.004091814,0.012095211,0.05447397],"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":[0.000028307331,0.000010095109,0.00022021281,0.00050919194,0.000012226457,0.000027052161,0.0002504639,0.00004150869,0.00007574669,0.0028371292,0.90996224,0.08602585],"study_design_scores_gemma":[0.000045716308,0.000029761364,0.0016807436,0.0034949372,0.000055865657,0.00020655466,0.0004249377,0.00022814727,0.00043991135,0.017458105,0.9758815,0.000053717897],"about_ca_topic_score_codex":0.029615778,"about_ca_topic_score_gemma":0.045454502,"teacher_disagreement_score":0.9631916,"about_ca_system_score_codex":0.0024292092,"about_ca_system_score_gemma":0.013264791,"threshold_uncertainty_score":0.23096573},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005420238,0.58308244,0.0042287596,0.20812234,0.02097374,0.0002504915,0.0011939242,0.0008523369,0.18075396],"genre_scores_gemma":[0.0036318456,0.18492082,0.0046639405,0.029953687,0.0022852034,0.00023591907,0.00048733503,0.00049169286,0.7733296],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.998256,0.00021622992,0.00007501674,0.00022141951,0.0011569357,0.00007440896],"domain_scores_gemma":[0.99655724,0.0012554293,0.00022685157,0.000086621934,0.0014283621,0.00044555336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021541817,0.0013744457,0.0008725131,0.0023196517,0.0011504972,0.0035701985,0.0012271194,0.003356781,0.080788605],"category_scores_gemma":[0.0074277427,0.00090248015,0.00039807605,0.0030715754,0.0013262616,0.00544797,0.0016957984,0.0046104034,0.056156363],"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":[0.0000047944873,0.000003166555,0.00002993162,0.00014129914,0.0000010375068,0.000014025162,0.000076644086,0.000012635974,0.000039373084,0.0005808594,0.94649607,0.05260021],"study_design_scores_gemma":[0.0000025330282,0.00000410825,0.00024404797,0.00054767815,0.0000022438091,0.00008260789,0.000120990415,0.000025289695,0.000059206577,0.00066033495,0.9982431,0.000007746994],"about_ca_topic_score_codex":0.02314527,"about_ca_topic_score_gemma":0.055942655,"teacher_disagreement_score":0.080788605,"about_ca_system_score_codex":0.0022501305,"about_ca_system_score_gemma":0.003996598,"threshold_uncertainty_score":0.2702648},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3511611,0.0076326765,0.05576306,0.30505973,0.0013090669,0.0024260457,0.0016996114,0.00088316447,0.27406558],"genre_scores_gemma":[0.931589,0.0027856622,0.034267943,0.009136696,0.00007495656,0.00047771342,0.0005409894,0.00018931727,0.020937681],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97375476,0.013233404,0.00043364533,0.0010255284,0.0050264704,0.006526142],"domain_scores_gemma":[0.9599718,0.015078317,0.00086635735,0.0026879648,0.014421068,0.0069744275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027964117,0.00070018915,0.0005890162,0.0026622354,0.029470548,0.012250884,0.0043561733,0.0027710542,0.0033879508],"category_scores_gemma":[0.03792276,0.00045961683,0.0006536109,0.005895541,0.015660604,0.005286747,0.013577986,0.0052579534,0.00035670836],"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":[0.00021589544,0.0004941731,0.048765045,0.0011227635,0.00012119822,0.0062567443,0.24409889,0.009626976,0.0015341945,0.26222414,0.11374256,0.31179747],"study_design_scores_gemma":[0.00012649193,0.00022527539,0.03532748,0.0017194594,0.00009997835,0.0005127117,0.35675493,0.0051201754,0.0015108401,0.034090694,0.56426245,0.00024944165],"about_ca_topic_score_codex":0.985884,"about_ca_topic_score_gemma":0.99448836,"teacher_disagreement_score":0.85025126,"about_ca_system_score_codex":0.14974873,"about_ca_system_score_gemma":0.38177907,"threshold_uncertainty_score":0.98617095},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024192918,0.0045793676,0.90416074,0.015024134,0.00081839855,0.024183096,0.00016050848,0.00055172964,0.026329223],"genre_scores_gemma":[0.09624141,0.0010529868,0.8811584,0.0012336143,0.00011089312,0.01927415,0.000043104243,0.00008219269,0.0008032415],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.29920912,0.66742235,0.010160154,0.004112893,0.017414428,0.0016809929],"domain_scores_gemma":[0.44491524,0.48628777,0.011250204,0.023956643,0.028333582,0.0052565546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.49723342,0.002088823,0.0029244926,0.01130184,0.008446514,0.02067388,0.0064818147,0.002823613,0.004287007],"category_scores_gemma":[0.35218593,0.0015024644,0.0024162198,0.0057667494,0.010632398,0.009730925,0.020433769,0.0054354714,0.00061973644],"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":[0.00083928474,0.0015160647,0.006560011,0.007327457,0.001259593,0.0004970864,0.09689756,0.0057140053,0.0013627606,0.08625954,0.0055263173,0.78624034],"study_design_scores_gemma":[0.0028428165,0.006052842,0.011039712,0.043845493,0.0020803371,0.0013480224,0.121461414,0.06074937,0.009496211,0.5556785,0.18425196,0.0011532715],"about_ca_topic_score_codex":0.008354929,"about_ca_topic_score_gemma":0.025437005,"teacher_disagreement_score":0.49723342,"about_ca_system_score_codex":0.015440729,"about_ca_system_score_gemma":0.031543545,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31106877,0.038408242,0.0033262465,0.07923395,0.0006089582,0.00020368911,0.0020096148,0.000043526314,0.56509703],"genre_scores_gemma":[0.97474164,0.0067292736,0.0010986316,0.0017255517,0.00006344699,0.000060936127,0.00036664965,0.00002534166,0.015188562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9712182,0.012119808,0.002451714,0.0019650029,0.009500648,0.0027445508],"domain_scores_gemma":[0.9182859,0.07033307,0.0030462518,0.0027372562,0.004578257,0.001019171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028602956,0.00027580952,0.0010222085,0.004842394,0.009032841,0.021388555,0.0022875562,0.0038188908,0.0059537385],"category_scores_gemma":[0.05264033,0.0005728752,0.00047879675,0.01242052,0.010282579,0.0068724,0.008723491,0.0041784346,0.00041306953],"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":[0.00021228283,0.00013398116,0.008776641,0.0022750257,0.000101803336,0.0015841419,0.069724455,0.0026817324,0.00031424247,0.8351753,0.019777237,0.05924319],"study_design_scores_gemma":[0.00010084255,0.000097500124,0.05002491,0.00854619,0.0002724084,0.00032244297,0.1734257,0.0015375436,0.0027841025,0.07797672,0.68470967,0.00020201187],"about_ca_topic_score_codex":0.21130659,"about_ca_topic_score_gemma":0.26063177,"teacher_disagreement_score":0.21130659,"about_ca_system_score_codex":0.04391025,"about_ca_system_score_gemma":0.03915832,"threshold_uncertainty_score":0.42015326},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007262094,0.009475016,0.00083802576,0.9455511,0.042968493,0.000025798401,0.00006202068,0.000020943091,0.0009859775],"genre_scores_gemma":[0.0033032564,0.0063295932,0.0030151247,0.87136817,0.11412356,0.0001669395,0.00002320947,0.00007987,0.0015902651],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78749263,0.12246426,0.016553868,0.016162936,0.053769372,0.0035567784],"domain_scores_gemma":[0.1539248,0.7616211,0.008466464,0.0083597265,0.06307689,0.004550988],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21781188,0.0014009264,0.0040025054,0.0033405123,0.005749134,0.011344443,0.012902654,0.05700465,0.010088854],"category_scores_gemma":[0.59043497,0.0018900576,0.0035774254,0.003457893,0.026891693,0.012816821,0.0059906025,0.063468486,0.0024808142],"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":[0.000103658545,0.000023971648,0.00024155066,0.0019211733,0.00018626306,0.0001754092,0.0015958088,0.00029763646,0.00008203367,0.05520647,0.9130136,0.02715249],"study_design_scores_gemma":[0.000256572,0.00006260117,0.00084699417,0.013613838,0.00032182966,0.00022286494,0.0011557104,0.00075847574,0.00030491615,0.07756328,0.9047142,0.0001787506],"about_ca_topic_score_codex":0.044319842,"about_ca_topic_score_gemma":0.06400092,"teacher_disagreement_score":0.7821881,"about_ca_system_score_codex":0.020379685,"about_ca_system_score_gemma":0.04121482,"threshold_uncertainty_score":0.9645772},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5727454,0.002408005,0.31574193,0.047086902,0.00068642735,0.010407563,0.00046929537,0.00026019415,0.050194323],"genre_scores_gemma":[0.802631,0.0009459355,0.17998108,0.0026239464,0.00008995556,0.009793547,0.000098665136,0.00014645018,0.0036894162],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8039903,0.1816152,0.0022303294,0.0026153617,0.00695828,0.0025904789],"domain_scores_gemma":[0.73804235,0.22943822,0.005211424,0.008048264,0.015184447,0.004075304],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16586296,0.0007211252,0.00080916344,0.0028767611,0.011312122,0.011111707,0.0036730308,0.002395501,0.0026162958],"category_scores_gemma":[0.11531574,0.0009002738,0.00060977,0.002565208,0.016685767,0.005596967,0.011134051,0.0039046544,0.0003332956],"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":[0.00012717425,0.00035414106,0.0058972426,0.0012515187,0.000049769536,0.000657661,0.87711227,0.00074780185,0.0019392667,0.032640558,0.0033090517,0.07591352],"study_design_scores_gemma":[0.000119545286,0.0005278249,0.004613999,0.0024233875,0.000084207415,0.00053476536,0.8351317,0.0026404904,0.004056085,0.053112026,0.09663723,0.000118743104],"about_ca_topic_score_codex":0.0052256603,"about_ca_topic_score_gemma":0.012696017,"teacher_disagreement_score":0.9909197,"about_ca_system_score_codex":0.009080286,"about_ca_system_score_gemma":0.024822185,"threshold_uncertainty_score":0.87717766},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001285102,0.15089096,0.29293802,0.28162262,0.04788309,0.0056143287,0.029909266,0.010465771,0.17939086],"genre_scores_gemma":[0.024253054,0.081038736,0.5821086,0.05876791,0.0056490395,0.033334102,0.008148946,0.010173582,0.19652599],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96374214,0.023686018,0.0033348207,0.0014122608,0.00746577,0.0003589588],"domain_scores_gemma":[0.7754203,0.14819075,0.008093833,0.010749797,0.053234342,0.0043109045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.064212106,0.0018527877,0.0015545365,0.0045521753,0.0039777523,0.0059816283,0.004139657,0.0069868104,0.12050431],"category_scores_gemma":[0.24886553,0.003146624,0.0019925295,0.0050711227,0.0037336107,0.004337342,0.0042192345,0.010596783,0.049189117],"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":[0.00016629283,0.000026497633,0.00020146587,0.00253724,0.00007039589,0.000056588535,0.0008114979,0.00024527244,0.00032035078,0.010373908,0.8328289,0.15236165],"study_design_scores_gemma":[0.0001726159,0.000043913176,0.0012513548,0.007385811,0.00015700364,0.00010693197,0.00040018346,0.0004948442,0.00072427554,0.017168488,0.97199124,0.000103270846],"about_ca_topic_score_codex":0.053112067,"about_ca_topic_score_gemma":0.09232956,"teacher_disagreement_score":0.12050431,"about_ca_system_score_codex":0.005626366,"about_ca_system_score_gemma":0.02139478,"threshold_uncertainty_score":0.40312713},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034060415,0.008482467,0.5360229,0.37576443,0.003132742,0.016352143,0.00012908562,0.00047822963,0.025577528],"genre_scores_gemma":[0.36192417,0.003538946,0.55107945,0.04780816,0.00063724665,0.03000616,0.00005164199,0.00060294935,0.0043513305],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.22579761,0.7454118,0.0077214665,0.0035309584,0.01370602,0.003832205],"domain_scores_gemma":[0.3465145,0.5934614,0.007567252,0.017705185,0.030029485,0.0047221393],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.60337216,0.0021957837,0.0023468481,0.0039061923,0.021917991,0.024780223,0.010689561,0.012769973,0.003941567],"category_scores_gemma":[0.39858064,0.0028236695,0.0022502225,0.0031561283,0.06661587,0.020664113,0.022728918,0.023770127,0.0013351369],"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":[0.00020248431,0.00030286683,0.0018887828,0.0030987544,0.00011983237,0.0007228326,0.78407586,0.0008981344,0.001642344,0.13454323,0.007895504,0.06460946],"study_design_scores_gemma":[0.00037666087,0.00092417415,0.0018721722,0.014285004,0.00015907553,0.001359833,0.585735,0.005899338,0.005162136,0.21364613,0.1701836,0.00039685096],"about_ca_topic_score_codex":0.01210148,"about_ca_topic_score_gemma":0.019724485,"teacher_disagreement_score":0.39662784,"about_ca_system_score_codex":0.028259909,"about_ca_system_score_gemma":0.04131182,"threshold_uncertainty_score":0.4891128},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009907967,0.0017128161,0.8585519,0.016591322,0.00034147425,0.00048366477,0.00071992,0.00029035014,0.11140054],"genre_scores_gemma":[0.67582065,0.003231082,0.29153016,0.0028019238,0.00038475817,0.0033421838,0.0008921719,0.00015990059,0.021837153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99210453,0.0050600916,0.0002965251,0.00059243606,0.0015280489,0.00041845744],"domain_scores_gemma":[0.9843253,0.0115339,0.00078113715,0.0010232287,0.0019493143,0.00038719465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0094247395,0.0013662896,0.00093863363,0.0023826612,0.001178016,0.00420648,0.0026855948,0.0031311393,0.010362248],"category_scores_gemma":[0.021869104,0.00045312743,0.001447932,0.0022316703,0.0043186005,0.0050286264,0.0022560498,0.004231288,0.0014655838],"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":[0.000008294068,0.000036034555,0.00025682137,0.00007005314,0.000015787406,0.000022671811,0.00019611527,0.014017011,0.000027095453,0.97825694,0.001968609,0.0051245946],"study_design_scores_gemma":[0.000025056339,0.000030612544,0.00012431551,0.00009358687,0.000014511815,0.000020777841,0.00011201919,0.052792028,0.00008422742,0.9344803,0.01221156,0.000011006683],"about_ca_topic_score_codex":0.004107931,"about_ca_topic_score_gemma":0.0036030996,"teacher_disagreement_score":0.010362248,"about_ca_system_score_codex":0.004854846,"about_ca_system_score_gemma":0.0039993473,"threshold_uncertainty_score":0.04984343},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020329459,0.0010300593,0.00055378483,0.0027930147,0.009665799,0.00025318257,0.014760132,0.001619078,0.9691216],"genre_scores_gemma":[0.001017269,0.0010703078,0.00044580427,0.0014335713,0.0018140222,0.00010049046,0.008861418,0.0005405339,0.98471665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906427,0.00008302603,0.00007755871,0.00018692014,0.0004742826,0.00011397576],"domain_scores_gemma":[0.99694175,0.00032388506,0.00016160581,0.0003976819,0.0012905044,0.00088455586],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009619201,0.0014082756,0.0011181802,0.0030853709,0.0016318782,0.0078991,0.0016397187,0.002184255,0.9192148],"category_scores_gemma":[0.005012177,0.00051526545,0.0007917439,0.0033112706,0.00046175218,0.0044242553,0.0022756108,0.0021833417,0.87842757],"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":[0.000012685889,0.000015630912,0.000044043863,0.00009073536,0.0000011253774,0.000013757512,0.00000824842,0.000014421023,0.000078533965,0.0009188756,0.9642045,0.034597438],"study_design_scores_gemma":[0.000004101014,0.0000057404845,0.00013616265,0.00004959982,6.8039554e-7,0.000018428698,0.000017218637,0.000013870706,0.000032131426,0.0003751416,0.99934465,0.0000021386425],"about_ca_topic_score_codex":0.0019998567,"about_ca_topic_score_gemma":0.0042119063,"teacher_disagreement_score":0.080785215,"about_ca_system_score_codex":0.001150197,"about_ca_system_score_gemma":0.0020966032,"threshold_uncertainty_score":0.11523032},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014966227,0.010823793,0.0004705299,0.12374828,0.83685,0.000045500037,0.00032834185,0.0002879217,0.027295846],"genre_scores_gemma":[0.0024065897,0.016081793,0.00059792266,0.19480902,0.5812976,0.00010895669,0.0004967674,0.0003760887,0.20382531],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972519,0.00047120271,0.00031577767,0.00048506478,0.0011849566,0.00029104901],"domain_scores_gemma":[0.9836564,0.0024842457,0.00087074126,0.00072705856,0.008794952,0.0034666231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022977316,0.0014973696,0.0012342399,0.0019265972,0.0019663798,0.0068981815,0.0026272547,0.006234847,0.25107932],"category_scores_gemma":[0.02570693,0.0005601336,0.0009970712,0.0011875203,0.0011089356,0.005912274,0.002908488,0.008066241,0.16541795],"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":[0.000008061816,0.0000062082954,0.000031317624,0.00009051095,0.000002381707,0.00007365032,0.0000118341095,0.0000074164454,0.00002957189,0.00030742204,0.9861859,0.013245747],"study_design_scores_gemma":[0.0000061376645,0.0000081615935,0.000085348576,0.00021948873,0.0000028500576,0.00026173386,0.000050466762,0.000013855324,0.00003652798,0.00045625152,0.9988525,0.0000066060943],"about_ca_topic_score_codex":0.0008415643,"about_ca_topic_score_gemma":0.0015587393,"teacher_disagreement_score":0.25107932,"about_ca_system_score_codex":0.0016747141,"about_ca_system_score_gemma":0.0028465278,"threshold_uncertainty_score":0.839944},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045889232,0.0018153532,0.8278864,0.0280431,0.0006994099,0.004502215,0.00070136535,0.000545045,0.089917846],"genre_scores_gemma":[0.3182544,0.0015077944,0.6627132,0.0019574747,0.000115677685,0.009195233,0.0004940943,0.00028939825,0.005472733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89592,0.09002013,0.0034522673,0.0030448404,0.005416941,0.0021458808],"domain_scores_gemma":[0.85951054,0.1178356,0.0044526006,0.006196111,0.00905138,0.0029537813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12064798,0.0024871104,0.001834522,0.02127189,0.011285552,0.020592354,0.0052158637,0.004287416,0.01301467],"category_scores_gemma":[0.089556396,0.0015422998,0.0034854575,0.01055484,0.036093876,0.026757658,0.024018122,0.008779719,0.0013912759],"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":[0.000078711324,0.000105817606,0.0027352644,0.0016067963,0.000067676905,0.0005625323,0.30593607,0.0012355691,0.0010186094,0.6102054,0.006267573,0.0701799],"study_design_scores_gemma":[0.00007733962,0.00012733186,0.0017395857,0.0044223336,0.000089107976,0.0005376036,0.3217271,0.005858908,0.0015510318,0.5330857,0.13061173,0.00017217488],"about_ca_topic_score_codex":0.008733611,"about_ca_topic_score_gemma":0.010280972,"teacher_disagreement_score":0.12064798,"about_ca_system_score_codex":0.02085519,"about_ca_system_score_gemma":0.030583704,"threshold_uncertainty_score":0.63805515},"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":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035900102,0.0049162367,0.0000787176,0.03279357,0.96106666,0.000023530954,0.00007265353,0.000026821244,0.0009858896],"genre_scores_gemma":[0.0006882437,0.004585586,0.000115418625,0.016888125,0.972195,0.00003909668,0.00003986601,0.000032361728,0.0054162624],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.985535,0.0023609612,0.002318219,0.0012932139,0.0076902853,0.0008022886],"domain_scores_gemma":[0.9122896,0.031073898,0.004453549,0.0017574051,0.04448656,0.0059389686],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014493244,0.004819424,0.006547197,0.0103854565,0.0054160315,0.010074443,0.0060985214,0.023872022,0.01130371],"category_scores_gemma":[0.070357844,0.0015133265,0.0038486633,0.0055925897,0.0044561895,0.003755994,0.0015997536,0.019332195,0.0059603425],"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":[0.000024499679,0.000010566192,0.000021311365,0.00012476266,0.000012861993,0.000046854544,0.0000073766723,0.000012769777,0.000014106911,0.00013140656,0.9969248,0.0026687626],"study_design_scores_gemma":[0.00014353829,0.000040431114,0.000981114,0.0011045466,0.00016629897,0.00027022502,0.00009742742,0.00025255812,0.00014420827,0.0008272076,0.99593395,0.000038524053],"about_ca_topic_score_codex":0.02286584,"about_ca_topic_score_gemma":0.042471096,"teacher_disagreement_score":0.99028134,"about_ca_system_score_codex":0.009718631,"about_ca_system_score_gemma":0.012318422,"threshold_uncertainty_score":0.07664853},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019433452,0.008602945,0.52915156,0.01575722,0.00027362144,0.002742896,0.00043077656,0.00043815994,0.42316946],"genre_scores_gemma":[0.32169363,0.009401746,0.6158659,0.0018236827,0.00016829906,0.0036231477,0.00043435727,0.00034744237,0.04664186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9794572,0.014402655,0.0005994763,0.00067888916,0.003974331,0.00088758883],"domain_scores_gemma":[0.98120314,0.014634494,0.0007803887,0.0010464897,0.001877255,0.00045825698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014066002,0.00092874764,0.0010081053,0.0031557502,0.002230959,0.010441819,0.0017406764,0.002012923,0.011475011],"category_scores_gemma":[0.022325307,0.0008963609,0.0010035005,0.0037524784,0.007547802,0.006833492,0.0031404258,0.0032164583,0.0012366486],"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":[0.000030902775,0.000127756,0.0012482624,0.0008272413,0.000032570522,0.000040645846,0.0015783999,0.0056402953,0.00035859045,0.8891216,0.0040743165,0.096919455],"study_design_scores_gemma":[0.000057531262,0.0003297546,0.0042787823,0.0023252624,0.0001257086,0.000115242125,0.0037664315,0.014756445,0.0021880097,0.81230885,0.15969491,0.000053123345],"about_ca_topic_score_codex":0.0037017355,"about_ca_topic_score_gemma":0.0037263702,"teacher_disagreement_score":0.014066002,"about_ca_system_score_codex":0.010016662,"about_ca_system_score_gemma":0.012914751,"threshold_uncertainty_score":0.07438898},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04097065,0.024329755,0.19209766,0.041909404,0.00057350774,0.00015578119,0.00021534206,0.00016486036,0.699583],"genre_scores_gemma":[0.78658116,0.025945656,0.1262262,0.0033975327,0.00029270913,0.00038665917,0.00036439844,0.00007582033,0.05672975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980988,0.0011519307,0.00006478445,0.00017553431,0.00033267098,0.000176393],"domain_scores_gemma":[0.996369,0.002985185,0.00016747255,0.00014135591,0.00018571991,0.0001511921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027114076,0.00057089573,0.0003629226,0.0008856117,0.0013540623,0.009947886,0.0009876085,0.001981749,0.00457843],"category_scores_gemma":[0.004754372,0.0003162873,0.0004666343,0.0013017575,0.008245194,0.008312775,0.0021243838,0.003509115,0.0008661943],"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":[0.000009673135,0.000028095059,0.00048479444,0.0001470015,0.000007910048,0.00011696042,0.0047708224,0.0049854475,0.00023552169,0.9445604,0.0057123126,0.038940944],"study_design_scores_gemma":[0.0000035423307,0.000010511976,0.00045225077,0.0002464895,0.000003601774,0.000052410574,0.004218791,0.0025981206,0.00020084475,0.93064964,0.061553475,0.00001027551],"about_ca_topic_score_codex":0.0049974853,"about_ca_topic_score_gemma":0.008140667,"teacher_disagreement_score":0.009947886,"about_ca_system_score_codex":0.0029708194,"about_ca_system_score_gemma":0.0034136225,"threshold_uncertainty_score":0.021554887},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98312646,0.00039783004,0.00022098456,0.0020716474,0.00004435813,0.000041416803,0.00093115953,0.000019357112,0.013146779],"genre_scores_gemma":[0.9984555,0.0001132645,0.00011544305,0.000114176255,0.000013476306,0.000015665173,0.00029252184,0.000005658312,0.0008742542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98050267,0.0038162586,0.00091116,0.0017972931,0.009994327,0.002978275],"domain_scores_gemma":[0.9444676,0.012231547,0.02772715,0.0026650496,0.008271548,0.004637047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009933637,0.00023531748,0.0006712344,0.0017677122,0.001886031,0.0031045706,0.0016787307,0.0010575665,0.0025904397],"category_scores_gemma":[0.057498783,0.00042405145,0.0006445137,0.003182597,0.002541273,0.0014728198,0.0013068819,0.0011610311,0.0005362595],"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":[0.00006566437,0.00006753255,0.989433,0.000023057331,0.000065490196,0.000024833178,0.002319836,0.00005068065,0.000080025755,0.000117843796,0.00054251275,0.0072095236],"study_design_scores_gemma":[0.0000018750798,0.000016069189,0.99884087,0.000005249562,0.000006431578,0.000003909605,0.00076455117,0.000016696296,0.000019744131,0.000015095649,0.00030718025,0.0000022241315],"about_ca_topic_score_codex":0.72643834,"about_ca_topic_score_gemma":0.8990402,"teacher_disagreement_score":0.98855233,"about_ca_system_score_codex":0.011447684,"about_ca_system_score_gemma":0.014711359,"threshold_uncertainty_score":0.5503454},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023060679,0.06168627,0.011952974,0.6586597,0.042820096,0.0014058219,0.0039196345,0.00074794336,0.21650149],"genre_scores_gemma":[0.075125046,0.07726471,0.049825072,0.14907362,0.015737973,0.0016711762,0.009641533,0.0020667447,0.6195941],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.904609,0.017633073,0.0065642893,0.0025472168,0.06000881,0.008637574],"domain_scores_gemma":[0.83367586,0.018532906,0.004577049,0.005965551,0.1145053,0.022743378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12508534,0.002200286,0.002950222,0.009027495,0.011851999,0.029311532,0.0067828577,0.019766515,0.026683474],"category_scores_gemma":[0.115095824,0.001803854,0.002806869,0.009114055,0.01272187,0.00687449,0.007977991,0.014371895,0.009610791],"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":[0.000032711483,0.00004401924,0.0004173278,0.0003006222,0.000024141289,0.000030430032,0.00029955216,0.00028686968,0.00018063953,0.020603584,0.95313275,0.02464744],"study_design_scores_gemma":[0.0000161723,0.000014140049,0.001878767,0.0013578492,0.000025494213,0.000023704099,0.0005737602,0.00030073704,0.00030199823,0.008771777,0.98663735,0.00009824561],"about_ca_topic_score_codex":0.81071144,"about_ca_topic_score_gemma":0.8918662,"teacher_disagreement_score":0.9013859,"about_ca_system_score_codex":0.098614104,"about_ca_system_score_gemma":0.42592585,"threshold_uncertainty_score":0.71549875},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022133365,0.00959212,0.7196039,0.017152375,0.0021907382,0.00042701172,0.0002718495,0.0007074019,0.24784133],"genre_scores_gemma":[0.1910935,0.013383909,0.7095768,0.0075767543,0.0043251836,0.002520806,0.00042631256,0.0015889397,0.06950787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98500973,0.010770526,0.0005472218,0.0008154067,0.0026390683,0.00021809086],"domain_scores_gemma":[0.9341165,0.057423625,0.0009800436,0.003487869,0.0035502966,0.00044166483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018195476,0.0014820887,0.0009795574,0.0069692614,0.0025335178,0.01280394,0.0026019597,0.0025456243,0.012251022],"category_scores_gemma":[0.052925315,0.0006431175,0.00089885783,0.0038831409,0.023055952,0.015910154,0.004670351,0.005929012,0.0024711124],"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":[0.000012183509,0.000014371217,0.00009917548,0.00023493412,0.00001208056,0.000023294862,0.0026549888,0.0004522945,0.00016077104,0.92930543,0.013741775,0.053288706],"study_design_scores_gemma":[0.000005980024,0.000006600995,0.000088144894,0.00028488087,0.000008205957,0.000034480003,0.0005699321,0.0014898595,0.00030205568,0.9464265,0.05076748,0.000015717369],"about_ca_topic_score_codex":0.0025412235,"about_ca_topic_score_gemma":0.0025577925,"teacher_disagreement_score":0.018195476,"about_ca_system_score_codex":0.0057218145,"about_ca_system_score_gemma":0.0043081436,"threshold_uncertainty_score":0.09622806},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06526771,0.118819684,0.058744766,0.27602607,0.007259519,0.0059034307,0.0015308092,0.0005318793,0.46591622],"genre_scores_gemma":[0.57092655,0.11855994,0.20125705,0.06072788,0.003013661,0.008988481,0.0030484814,0.00065533957,0.032822628],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.74113894,0.17888539,0.012809951,0.008608584,0.053399134,0.005157981],"domain_scores_gemma":[0.48246193,0.39641726,0.011005748,0.026151206,0.07038755,0.013576321],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30282643,0.0012413415,0.0019855297,0.01993482,0.0056742136,0.021152029,0.003515216,0.0044367444,0.016846588],"category_scores_gemma":[0.2883409,0.001119357,0.0015674462,0.013305515,0.012106617,0.019091086,0.029827304,0.0070572468,0.0025216243],"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":[0.0006652478,0.0010672262,0.020389628,0.009294953,0.0005414772,0.0008572984,0.023042196,0.0011322998,0.0021667103,0.14399472,0.046575222,0.75027305],"study_design_scores_gemma":[0.00032937835,0.0021931634,0.027889974,0.050047323,0.00080512493,0.0013166253,0.0778359,0.0013702959,0.0062301117,0.20963682,0.6221195,0.0002258023],"about_ca_topic_score_codex":0.0033431659,"about_ca_topic_score_gemma":0.008191842,"teacher_disagreement_score":0.6971736,"about_ca_system_score_codex":0.012060766,"about_ca_system_score_gemma":0.03625763,"threshold_uncertainty_score":0.8597391},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011897888,0.0015820452,0.00023342078,0.40086737,0.58807343,0.000043609303,0.00019388724,0.00009267516,0.008794662],"genre_scores_gemma":[0.002193362,0.0017013061,0.0009470481,0.65913826,0.24689148,0.00015369711,0.000106309875,0.00012987998,0.08873866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9873685,0.0014800098,0.0014747783,0.0022530865,0.0061911624,0.0012323081],"domain_scores_gemma":[0.9445143,0.013884876,0.0026758935,0.0024198927,0.031901047,0.004603958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017997473,0.0016073197,0.0016713899,0.0027022194,0.0052690534,0.009770556,0.0048116865,0.02684346,0.029474195],"category_scores_gemma":[0.11128567,0.0009277208,0.0026465405,0.0020119739,0.0028396675,0.00531524,0.002526529,0.02588743,0.02050659],"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":[0.000009433921,0.0000066073594,0.000040091698,0.00003038658,0.000004916264,0.00006124931,0.000021218633,0.00002037385,0.000022278604,0.00096960226,0.9968168,0.0019971358],"study_design_scores_gemma":[0.000020086227,0.000008063595,0.00022630952,0.00010875321,0.000013580098,0.00005461721,0.00006521164,0.00006445314,0.00010183141,0.0009291888,0.99838984,0.000018203938],"about_ca_topic_score_codex":0.013315754,"about_ca_topic_score_gemma":0.020156292,"teacher_disagreement_score":0.029474195,"about_ca_system_score_codex":0.0060965447,"about_ca_system_score_gemma":0.011268729,"threshold_uncertainty_score":0.09860104},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4483801,0.0017742615,0.07982293,0.0399858,0.0005829861,0.04730724,0.0013344914,0.00035662268,0.38045558],"genre_scores_gemma":[0.77429175,0.0012050571,0.123811245,0.0024124426,0.000070662405,0.014213732,0.00045356603,0.00009080357,0.08345068],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9570929,0.02866407,0.0006588728,0.002527408,0.0074007045,0.0036560316],"domain_scores_gemma":[0.9570358,0.01638668,0.0016154675,0.004283789,0.014256287,0.0064219926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06339272,0.00047912137,0.00047625502,0.0014083949,0.01939678,0.0058565782,0.0019755834,0.0011425524,0.005519284],"category_scores_gemma":[0.03474455,0.00047267237,0.00035561045,0.0019700103,0.0079889465,0.0015646867,0.0053193327,0.0016873281,0.00043712955],"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":[0.0010807709,0.0016313255,0.033849046,0.0013096647,0.00011756402,0.0024960777,0.3817787,0.0072923205,0.008804507,0.16142066,0.057848234,0.34237117],"study_design_scores_gemma":[0.0005737072,0.0007987302,0.046884198,0.001404898,0.00007863665,0.00018325221,0.22863813,0.0055456115,0.0038664704,0.026769994,0.68506604,0.0001902723],"about_ca_topic_score_codex":0.8760608,"about_ca_topic_score_gemma":0.9598154,"teacher_disagreement_score":0.9366073,"about_ca_system_score_codex":0.077080615,"about_ca_system_score_gemma":0.2784859,"threshold_uncertainty_score":0.5592616},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4483801,0.0017742615,0.07982293,0.0399858,0.0005829861,0.04730724,0.0013344914,0.00035662268,0.38045558],"genre_scores_gemma":[0.77429175,0.0012050571,0.123811245,0.0024124426,0.000070662405,0.014213732,0.00045356603,0.00009080357,0.08345068],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9570929,0.02866407,0.0006588728,0.002527408,0.0074007045,0.0036560316],"domain_scores_gemma":[0.9570358,0.01638668,0.0016154675,0.004283789,0.014256287,0.0064219926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06339272,0.00047912137,0.00047625502,0.0014083949,0.01939678,0.0058565782,0.0019755834,0.0011425524,0.005519284],"category_scores_gemma":[0.03474455,0.00047267237,0.00035561045,0.0019700103,0.0079889465,0.0015646867,0.0053193327,0.0016873281,0.00043712955],"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":[0.0010807709,0.0016313255,0.033849046,0.0013096647,0.00011756402,0.0024960777,0.3817787,0.0072923205,0.008804507,0.16142066,0.057848234,0.34237117],"study_design_scores_gemma":[0.0005737072,0.0007987302,0.046884198,0.001404898,0.00007863665,0.00018325221,0.22863813,0.0055456115,0.0038664704,0.026769994,0.68506604,0.0001902723],"about_ca_topic_score_codex":0.8760608,"about_ca_topic_score_gemma":0.9598154,"teacher_disagreement_score":0.9366073,"about_ca_system_score_codex":0.077080615,"about_ca_system_score_gemma":0.2784859,"threshold_uncertainty_score":0.5592616},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012925565,0.005401289,0.10478373,0.07775172,0.0025923145,0.0008868565,0.0009396525,0.001735615,0.79298323],"genre_scores_gemma":[0.23563671,0.0122524975,0.22074477,0.006366859,0.0014205767,0.0012851135,0.0017097971,0.0023885858,0.51819503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99237484,0.004675444,0.00034305707,0.00041932098,0.001850279,0.00033703062],"domain_scores_gemma":[0.9868803,0.008864181,0.0006602473,0.00096240285,0.0014616542,0.0011712675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010170743,0.0006586384,0.00037051708,0.0028976116,0.0031488158,0.013349224,0.0012809474,0.002337113,0.04158948],"category_scores_gemma":[0.013851931,0.0005655193,0.0004215327,0.0024529696,0.0046459963,0.011660225,0.0066315974,0.0028266662,0.0045593996],"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":[0.00012675716,0.00011921483,0.0021947676,0.0008827545,0.000027777116,0.0009056002,0.027545583,0.0011670715,0.0021970123,0.45035666,0.21811292,0.2963639],"study_design_scores_gemma":[0.000009249629,0.000033874938,0.0005967114,0.00043216252,0.000008220274,0.00037010998,0.0063323667,0.00077836344,0.0013078074,0.046441596,0.94367117,0.000018320712],"about_ca_topic_score_codex":0.0018861467,"about_ca_topic_score_gemma":0.00428331,"teacher_disagreement_score":0.04158948,"about_ca_system_score_codex":0.0023822598,"about_ca_system_score_gemma":0.0031537632,"threshold_uncertainty_score":0.13913065},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034699647,0.00009962781,0.000105352054,0.00024136055,0.000021317195,0.000032982538,0.99759704,0.00007563291,0.0014795981],"genre_scores_gemma":[0.002351251,0.0001660522,0.0007700498,0.00016891699,0.00001274214,0.00035686698,0.9950282,0.000046579127,0.0010993592],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99260145,0.0024809863,0.0014210697,0.0009596938,0.0018182772,0.0007183491],"domain_scores_gemma":[0.9587648,0.019416437,0.0056684464,0.0061031254,0.008337943,0.0017093074],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072127166,0.0012263271,0.0011598422,0.009374697,0.0009029408,0.0028443483,0.0025216257,0.0016374438,0.032760493],"category_scores_gemma":[0.05154345,0.0005898395,0.0012428784,0.021244686,0.00048731355,0.001495441,0.0026677574,0.0025017194,0.015223616],"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":[0.0001221215,0.00003340183,0.006413094,0.0011731639,0.00009236677,0.000012095635,0.00005860974,0.00040625205,0.000038952207,0.0018230557,0.9836427,0.0061842096],"study_design_scores_gemma":[0.0003152433,0.000024358567,0.03836378,0.0014247897,0.0001319692,0.000046272427,0.00025790802,0.0006377136,0.00028287698,0.0021340926,0.95632976,0.000051384864],"about_ca_topic_score_codex":0.09522522,"about_ca_topic_score_gemma":0.134958,"teacher_disagreement_score":0.9927873,"about_ca_system_score_codex":0.004510711,"about_ca_system_score_gemma":0.008684409,"threshold_uncertainty_score":0.1893419},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11668039,0.029562984,0.026033515,0.64124566,0.0033011185,0.0050255964,0.00016417277,0.0004043184,0.17758219],"genre_scores_gemma":[0.8563464,0.014493084,0.04843249,0.04792348,0.0007756723,0.0066779926,0.00014939274,0.00048651444,0.02471493],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79897374,0.16161866,0.009412055,0.0028400728,0.018061459,0.009094099],"domain_scores_gemma":[0.7042134,0.19576369,0.006761682,0.01287222,0.07081874,0.009570265],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23149009,0.0009680847,0.00120529,0.0036298526,0.015509086,0.021129847,0.0054038214,0.005331295,0.006625647],"category_scores_gemma":[0.20416863,0.0009880979,0.0013229816,0.0032334712,0.019369679,0.017070565,0.01839954,0.0137090115,0.000797773],"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":[0.00039945042,0.0006061498,0.00597787,0.005902341,0.00018975849,0.0018008042,0.31203008,0.0014005404,0.0016717524,0.15959087,0.07133732,0.4390931],"study_design_scores_gemma":[0.00039103717,0.00095712015,0.0139993075,0.018325534,0.00021099117,0.0011177091,0.27616063,0.0022258656,0.0028089613,0.077704,0.6056922,0.00040671864],"about_ca_topic_score_codex":0.07866545,"about_ca_topic_score_gemma":0.13644795,"teacher_disagreement_score":0.7685099,"about_ca_system_score_codex":0.05708936,"about_ca_system_score_gemma":0.0903508,"threshold_uncertainty_score":0.94770956},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39853817,0.0012174704,0.00074433896,0.0008344967,0.00013007817,0.0010845226,0.52476513,0.00015499891,0.07253078],"genre_scores_gemma":[0.73490584,0.0037294354,0.0021611094,0.0006594463,0.00007955794,0.001001218,0.17820847,0.00009744102,0.07915744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993771,0.000029364175,0.0000332086,0.00006992255,0.00026713,0.00022330236],"domain_scores_gemma":[0.99787784,0.000052687155,0.00022597182,0.000049870643,0.0013840828,0.00040952308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028721147,0.00034791286,0.00035573743,0.0020138342,0.0028569212,0.0011355673,0.00088019355,0.00020181842,0.007653711],"category_scores_gemma":[0.0016759689,0.00031203934,0.00035138417,0.0060415403,0.00036859806,0.00042360846,0.0006648939,0.0005661324,0.0019758316],"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":[0.00015007946,0.00014802504,0.8261803,0.00033400135,0.00006348985,0.0003381891,0.0024582532,0.00048286648,0.00054087327,0.0005340931,0.14218,0.026589872],"study_design_scores_gemma":[0.000018107507,0.000032054948,0.96836644,0.00014088409,0.000021072972,0.000099242476,0.0034175597,0.00014261455,0.00019119075,0.000031920572,0.02752482,0.000014012989],"about_ca_topic_score_codex":0.9922389,"about_ca_topic_score_gemma":0.9967182,"teacher_disagreement_score":0.011899779,"about_ca_system_score_codex":0.011899779,"about_ca_system_score_gemma":0.0413243,"threshold_uncertainty_score":0.086339355},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012974933,0.004069326,0.00035544045,0.042907972,0.92431563,0.00006831587,0.00038154476,0.000366652,0.027405454],"genre_scores_gemma":[0.0027456968,0.0070669423,0.0005745986,0.050281532,0.7531663,0.00010652956,0.0008677148,0.00044188928,0.18474884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956448,0.00050686457,0.00038973067,0.0008083198,0.0022384354,0.00041188073],"domain_scores_gemma":[0.9761084,0.0023833143,0.0011924774,0.0015616717,0.014605225,0.0041490137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033994692,0.001630797,0.0012952887,0.002476604,0.0023290927,0.0070841457,0.002668624,0.0056202947,0.21168314],"category_scores_gemma":[0.025419928,0.0005463252,0.0013695596,0.00096213236,0.0014506888,0.0039535705,0.0018070396,0.006910354,0.14783226],"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":[0.000011899169,0.0000054582842,0.000029472165,0.00006666836,0.0000024578821,0.0000611031,0.000009290824,0.000008436664,0.000040825318,0.00031438205,0.99042904,0.009020917],"study_design_scores_gemma":[0.000008303782,0.0000097290895,0.000092591545,0.00013121539,0.0000035885105,0.00016417308,0.000032157277,0.000021999973,0.000069390524,0.00043432083,0.9990276,0.00000487995],"about_ca_topic_score_codex":0.0010310689,"about_ca_topic_score_gemma":0.0017100004,"teacher_disagreement_score":0.21168314,"about_ca_system_score_codex":0.002148983,"about_ca_system_score_gemma":0.0033762031,"threshold_uncertainty_score":0},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004641695,0.0015648662,0.03312978,0.017349934,0.0050708433,0.010103059,0.010670107,0.0021585291,0.9153113],"genre_scores_gemma":[0.037990768,0.002875533,0.03939591,0.010298223,0.0019681766,0.018665573,0.013697345,0.0020499602,0.8730585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9729274,0.0093983775,0.0016834185,0.0037347598,0.0098226415,0.0024335454],"domain_scores_gemma":[0.93125683,0.010459717,0.0022181273,0.012196951,0.029838623,0.01402969],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03386076,0.00083338714,0.0008975335,0.0050567416,0.004933112,0.00961041,0.0043602823,0.0023591106,0.33900663],"category_scores_gemma":[0.07035032,0.0004990363,0.00082004414,0.006516168,0.0019845956,0.006114815,0.0085430825,0.0034993126,0.19230223],"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":[0.0002715999,0.00041104102,0.0016233253,0.0007446186,0.00001196554,0.00015737701,0.0025973516,0.00025805092,0.00074992643,0.14256641,0.5882243,0.26238403],"study_design_scores_gemma":[0.000027582233,0.00007700746,0.0008238277,0.0003526086,0.000003699712,0.00008198653,0.0010775698,0.0000933216,0.00025977386,0.0064455583,0.9907458,0.000011337617],"about_ca_topic_score_codex":0.0037065449,"about_ca_topic_score_gemma":0.004082036,"teacher_disagreement_score":0.33900663,"about_ca_system_score_codex":0.008344991,"about_ca_system_score_gemma":0.035310138,"threshold_uncertainty_score":0.9428268},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050453786,0.0048363693,0.6097273,0.07798723,0.0026840358,0.09517651,0.0010867572,0.002389382,0.20106702],"genre_scores_gemma":[0.028394036,0.0028802808,0.8865543,0.0044233557,0.00028315888,0.052577317,0.0009998729,0.00047655051,0.023411091],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7813758,0.17594545,0.010166298,0.0034528873,0.024011439,0.0050481725],"domain_scores_gemma":[0.75095135,0.109420575,0.009600819,0.017599674,0.0913053,0.021122318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18714656,0.0023443387,0.0015809287,0.0076117557,0.009463544,0.013135313,0.0064269393,0.0066717872,0.036263872],"category_scores_gemma":[0.23700802,0.0016473652,0.0020859197,0.006857105,0.005060877,0.011946364,0.01481273,0.01021183,0.011912131],"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":[0.00016673282,0.00094585604,0.0012511022,0.0029609562,0.00007784449,0.0007993412,0.008530861,0.010675406,0.00063890475,0.13860334,0.27878612,0.55656356],"study_design_scores_gemma":[0.00033865223,0.00052098476,0.001663537,0.007570773,0.00006353058,0.00041942263,0.012530033,0.0070279604,0.0010262257,0.17505515,0.79352754,0.000256186],"about_ca_topic_score_codex":0.01629358,"about_ca_topic_score_gemma":0.031974178,"teacher_disagreement_score":0.18714656,"about_ca_system_score_codex":0.016554939,"about_ca_system_score_gemma":0.1151069,"threshold_uncertainty_score":0.98973745},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024932746,0.009258758,0.010023759,0.38893002,0.0019263261,0.0005197885,0.00017058275,0.00019164762,0.56404626],"genre_scores_gemma":[0.83900654,0.008800572,0.030994393,0.039449263,0.00072911836,0.0006740104,0.00023962941,0.0001711488,0.07993527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.96019715,0.015828028,0.0008726762,0.0013901918,0.01605411,0.0056577814],"domain_scores_gemma":[0.9588587,0.023409411,0.0025828246,0.0015245605,0.009696036,0.003928522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032221004,0.000340169,0.00046815758,0.0020918965,0.016065454,0.024988864,0.0014869416,0.0064490708,0.009925373],"category_scores_gemma":[0.08678775,0.00029152675,0.0005329306,0.003126875,0.009919747,0.005123904,0.004301926,0.010281783,0.00072523305],"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":[0.000069293,0.00015625458,0.0070664263,0.00040143178,0.000032972086,0.00025495054,0.009260957,0.0031016327,0.00046751904,0.64485157,0.12054727,0.21378964],"study_design_scores_gemma":[0.000071145056,0.0001304446,0.048814815,0.0023340303,0.00006330802,0.0001871461,0.016667072,0.0036527563,0.0010109257,0.16242178,0.76444143,0.00020519017],"about_ca_topic_score_codex":0.5686458,"about_ca_topic_score_gemma":0.7312748,"teacher_disagreement_score":0.43135422,"about_ca_system_score_codex":0.07038483,"about_ca_system_score_gemma":0.20241772,"threshold_uncertainty_score":0.8677891},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44507766,0.002054304,0.16539194,0.05303535,0.00018202415,0.0007472561,0.00024435908,0.00017143198,0.33309573],"genre_scores_gemma":[0.9891137,0.00028096235,0.008618399,0.00032309626,0.000012653578,0.00012051426,0.000018822948,0.000013432233,0.0014983802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.989707,0.007834267,0.00026896733,0.00048411812,0.0007624692,0.00094305776],"domain_scores_gemma":[0.98216003,0.011271821,0.0018735342,0.00080246304,0.0027144707,0.0011777543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013705152,0.0005717632,0.0006970367,0.0044994773,0.0025569312,0.008355443,0.0014390456,0.002255423,0.006061675],"category_scores_gemma":[0.018609801,0.0004556183,0.0007784709,0.0035982274,0.009911849,0.007859071,0.0071410607,0.0036638703,0.00037099337],"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":[0.00017847634,0.00013551424,0.020137979,0.00025807382,0.00005347095,0.0004979606,0.009577863,0.01848175,0.00026527367,0.9190927,0.0020286054,0.029292375],"study_design_scores_gemma":[0.00008122264,0.00015518394,0.012365206,0.00079562643,0.00013473231,0.00023574114,0.03740447,0.087779865,0.0009805954,0.8431431,0.016841,0.000083257175],"about_ca_topic_score_codex":0.01335714,"about_ca_topic_score_gemma":0.016074296,"teacher_disagreement_score":0.01645492,"about_ca_system_score_codex":0.01645492,"about_ca_system_score_gemma":0.013354401,"threshold_uncertainty_score":0.119389355},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012451637,0.06721769,0.0036289783,0.13622537,0.0030601437,0.00013130672,0.0010013978,0.00038769003,0.7758958],"genre_scores_gemma":[0.16724212,0.063444465,0.0068702428,0.01513794,0.0005838628,0.00011396565,0.000632599,0.00042353428,0.74555135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99261767,0.0007265134,0.00016447232,0.0005485412,0.004365329,0.001577472],"domain_scores_gemma":[0.9906927,0.002106738,0.00018500454,0.00027001873,0.0051943436,0.0015510825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004206564,0.0006342321,0.0006769668,0.0033518027,0.024373388,0.016315857,0.001694755,0.0035680942,0.014925939],"category_scores_gemma":[0.010070797,0.0006162698,0.00044768568,0.01038681,0.010460257,0.0029320675,0.0027980278,0.0045836093,0.0023221127],"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":[0.000027979071,0.000029465085,0.0010731567,0.00034314807,0.000010990062,0.00023841117,0.013492257,0.00084211794,0.0002578019,0.42813948,0.4312541,0.1242911],"study_design_scores_gemma":[0.0000028984946,0.0000035294815,0.0014791235,0.00029770093,0.0000056842873,0.000032318563,0.0036836206,0.00038256994,0.0001097777,0.011123996,0.9828584,0.000020521273],"about_ca_topic_score_codex":0.994686,"about_ca_topic_score_gemma":0.9966853,"teacher_disagreement_score":0.6760105,"about_ca_system_score_codex":0.32398948,"about_ca_system_score_gemma":0.5603669,"threshold_uncertainty_score":0.7840764},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002215034,0.013296455,0.0020050893,0.05896068,0.008025736,0.000073402305,0.00020360459,0.00011312251,0.91710037],"genre_scores_gemma":[0.040056948,0.06347947,0.00877203,0.08949254,0.012996845,0.00073074456,0.0013969414,0.0006176266,0.7824569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98587835,0.0046129758,0.00060770434,0.0010880904,0.0067171836,0.0010957441],"domain_scores_gemma":[0.99047613,0.0043175267,0.00036689173,0.0010798706,0.0027526433,0.0010069831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0096057905,0.0012656521,0.0008521967,0.0031815746,0.00472751,0.035306267,0.0023685698,0.0075536016,0.0616773],"category_scores_gemma":[0.022468224,0.00067069975,0.0008442014,0.003940341,0.009320886,0.020831965,0.012295028,0.010952824,0.02441374],"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":[0.000009518607,0.000015093185,0.00005438448,0.00026388696,0.0000035610183,0.000029524765,0.0004023993,0.00014236082,0.00004503853,0.77188253,0.19194253,0.035209138],"study_design_scores_gemma":[0.0000020508064,0.000005133951,0.00006295407,0.00048954884,0.000002132619,0.00002847519,0.00043118664,0.00003193803,0.000030168438,0.06616623,0.9327456,0.0000046665255],"about_ca_topic_score_codex":0.004578899,"about_ca_topic_score_gemma":0.0042250105,"teacher_disagreement_score":0.0616773,"about_ca_system_score_codex":0.010819908,"about_ca_system_score_gemma":0.015604906,"threshold_uncertainty_score":0.20633113},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014956796,0.007954127,0.0003131955,0.09219376,0.8783799,0.000043841042,0.00022804695,0.00016792388,0.02056962],"genre_scores_gemma":[0.0023501324,0.013257052,0.00056776474,0.15830529,0.6727329,0.00010148211,0.00038008986,0.0002332037,0.15207206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749434,0.00039117679,0.00033982287,0.0003553337,0.0011933553,0.0002259608],"domain_scores_gemma":[0.9837802,0.0032807824,0.00085793686,0.0006077484,0.008274125,0.0031991247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022201596,0.0015527213,0.001270738,0.0021347548,0.0017995944,0.006315654,0.0024705434,0.005689642,0.17875588],"category_scores_gemma":[0.022163179,0.0005490334,0.0009972322,0.0014152081,0.0009244996,0.005203137,0.002562467,0.006342509,0.08927284],"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":[0.000009469524,0.000010117306,0.00003813457,0.00010713756,0.0000027749961,0.00007399288,0.000011692689,0.000010103557,0.000034676752,0.00022854509,0.9843891,0.015084115],"study_design_scores_gemma":[0.000007546966,0.0000115193225,0.0001341049,0.00022659347,0.0000037905377,0.00024657315,0.000055521177,0.000020200736,0.00003975931,0.00034036525,0.99890685,0.000007198241],"about_ca_topic_score_codex":0.00084313785,"about_ca_topic_score_gemma":0.0020153623,"teacher_disagreement_score":0.17875588,"about_ca_system_score_codex":0.0016085474,"about_ca_system_score_gemma":0.0025423972,"threshold_uncertainty_score":0.597998},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9369945,0.0008167783,0.0012417503,0.016338555,0.000077249744,0.00023982317,0.00031171783,0.00007736911,0.043902226],"genre_scores_gemma":[0.99553156,0.00023244617,0.000502277,0.0003343135,0.000009074583,0.00003545921,0.00005411206,0.000008277156,0.0032925792],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.97333366,0.0057839644,0.00084890105,0.0009325151,0.00945008,0.009650868],"domain_scores_gemma":[0.9308209,0.018327167,0.01042109,0.002131932,0.02458908,0.013709908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018047152,0.00021133233,0.0003313102,0.0021274602,0.011203131,0.0076691797,0.0020485714,0.0009952091,0.002211297],"category_scores_gemma":[0.05571376,0.00039367014,0.00038449655,0.0036568795,0.0054588914,0.0018220225,0.005064773,0.0019490903,0.0001211017],"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":[0.00074858696,0.00065038353,0.5750286,0.00069718633,0.0001497662,0.00069738255,0.08457495,0.010608283,0.00340879,0.069045864,0.019605432,0.23478474],"study_design_scores_gemma":[0.00006449963,0.00022029722,0.88605696,0.00025432467,0.00005042325,0.000039179773,0.042734217,0.0028704447,0.0017383515,0.0033196472,0.062555216,0.00009627379],"about_ca_topic_score_codex":0.9668834,"about_ca_topic_score_gemma":0.9820833,"teacher_disagreement_score":0.70072293,"about_ca_system_score_codex":0.29927704,"about_ca_system_score_gemma":0.31003937,"threshold_uncertainty_score":0.8127393},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059033632,0.047476858,0.22593632,0.46175918,0.003510112,0.005903832,0.00026704872,0.00014569948,0.19596739],"genre_scores_gemma":[0.6808108,0.009554195,0.25371742,0.042190447,0.002127985,0.006799338,0.000074796604,0.00010107441,0.0046239793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.2890046,0.6096316,0.035837226,0.005029302,0.056338347,0.0041590054],"domain_scores_gemma":[0.25162134,0.68111634,0.01999979,0.012390896,0.031631183,0.003240306],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.52892303,0.0009011449,0.0021077422,0.0037950792,0.0078002554,0.014359593,0.003619016,0.01207793,0.0021760985],"category_scores_gemma":[0.5799772,0.0008570174,0.0015951693,0.0037268642,0.031337105,0.011413996,0.007057069,0.01158108,0.00042622047],"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":[0.00037497137,0.000332185,0.008279344,0.0019838028,0.00025962276,0.0007179378,0.027278142,0.004787749,0.0008260608,0.7719745,0.012816525,0.17036918],"study_design_scores_gemma":[0.0003796253,0.00092429394,0.008667532,0.0110279005,0.00032653825,0.0010814281,0.019067932,0.008023757,0.0037451168,0.82719994,0.119232416,0.00032354167],"about_ca_topic_score_codex":0.004536248,"about_ca_topic_score_gemma":0.0077285725,"teacher_disagreement_score":0.52892303,"about_ca_system_score_codex":0.010501213,"about_ca_system_score_gemma":0.036662698,"threshold_uncertainty_score":0.58092177},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025330853,0.14605317,0.18035251,0.5525723,0.021743797,0.0037986173,0.002169247,0.0003960678,0.067583434],"genre_scores_gemma":[0.4892408,0.09652549,0.25503498,0.08775464,0.005010006,0.021050211,0.0013538941,0.001403364,0.042626638],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.53740597,0.40521285,0.01379135,0.0077733835,0.032006856,0.0038096483],"domain_scores_gemma":[0.5097044,0.3604919,0.012353688,0.022885282,0.09037933,0.0041854507],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25163284,0.0015710951,0.0027414476,0.0072123753,0.010590401,0.01704074,0.0029503186,0.0071131834,0.008859078],"category_scores_gemma":[0.32008845,0.0014606112,0.0017875955,0.011350707,0.025932936,0.01901543,0.010885132,0.011595361,0.0015800784],"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":[0.00036575488,0.00007861595,0.0019344576,0.018646458,0.0002298314,0.0008024549,0.38795808,0.0006310325,0.003306713,0.33346078,0.08345997,0.16912588],"study_design_scores_gemma":[0.000071366354,0.000112960246,0.0025517456,0.026380789,0.00016093043,0.00061364926,0.12664065,0.00096722314,0.001893563,0.082706764,0.7577179,0.0001824983],"about_ca_topic_score_codex":0.036874596,"about_ca_topic_score_gemma":0.04127343,"teacher_disagreement_score":0.25163284,"about_ca_system_score_codex":0.032412052,"about_ca_system_score_gemma":0.061225545,"threshold_uncertainty_score":0.9228699},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040735462,0.016326223,0.0029309136,0.96691304,0.005098335,0.00006450907,0.000033402168,0.000038254344,0.008188029],"genre_scores_gemma":[0.13662148,0.093078524,0.04006104,0.6585394,0.02217619,0.0007860909,0.00028508308,0.0010136534,0.0474386],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8870658,0.0656303,0.0041923723,0.0036889357,0.0287239,0.010698596],"domain_scores_gemma":[0.68249506,0.15830207,0.006366019,0.009179888,0.099242784,0.044414222],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27387992,0.0010121786,0.001993513,0.0034992408,0.014033121,0.029212024,0.0045058234,0.018723808,0.018372575],"category_scores_gemma":[0.22516407,0.00075844885,0.0013339511,0.0033246123,0.04036844,0.024230627,0.014372902,0.024698999,0.002048356],"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":[0.00008463023,0.00011984905,0.00091408764,0.00068888825,0.000058839192,0.00012795637,0.0037765517,0.00046841337,0.00027993164,0.2094543,0.64984566,0.1341809],"study_design_scores_gemma":[0.000035992023,0.000053182408,0.001269766,0.0036391967,0.000026408325,0.00005541267,0.0067103966,0.00029331195,0.00021727278,0.117784865,0.86982554,0.00008865194],"about_ca_topic_score_codex":0.16840418,"about_ca_topic_score_gemma":0.32235196,"teacher_disagreement_score":0.27387992,"about_ca_system_score_codex":0.0473558,"about_ca_system_score_gemma":0.18615468,"threshold_uncertainty_score":0.89543533},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009934859,0.00301481,0.00021689467,0.15160197,0.8315672,0.000059617654,0.00030029129,0.00008976536,0.013050088],"genre_scores_gemma":[0.00284713,0.004210832,0.0011525358,0.31178123,0.46873,0.00016032755,0.00033711398,0.00016039163,0.2106205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99343747,0.0008682173,0.0006638069,0.00079972256,0.0036053762,0.00062536984],"domain_scores_gemma":[0.9732171,0.006282153,0.0021705034,0.0018235788,0.013740078,0.0027665775],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0072997636,0.0013344378,0.0017398696,0.00257294,0.0025031131,0.0047568227,0.0044717817,0.012160909,0.09518548],"category_scores_gemma":[0.052755028,0.0007844376,0.0018172044,0.0016092467,0.0013053102,0.0024912946,0.002005491,0.011092013,0.051634096],"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":[0.0000124726175,0.0000056582744,0.0000203563,0.000049510058,0.0000032764513,0.000063406274,0.0000075468733,0.000008066747,0.00003533172,0.00026637208,0.9958527,0.0036753402],"study_design_scores_gemma":[0.000024669707,0.000009483757,0.00020331888,0.00014083272,0.000013986241,0.00013548104,0.000034114917,0.0000461028,0.0001328876,0.00048538524,0.99876237,0.00001123045],"about_ca_topic_score_codex":0.0047309618,"about_ca_topic_score_gemma":0.011823394,"teacher_disagreement_score":0.90481454,"about_ca_system_score_codex":0.0028651566,"about_ca_system_score_gemma":0.0050600753,"threshold_uncertainty_score":0.3184272},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26071492,0.022461006,0.029838782,0.099670164,0.0006399256,0.00046664034,0.0013573043,0.0005304193,0.58432084],"genre_scores_gemma":[0.94200677,0.009113013,0.010280905,0.0026880365,0.00014725172,0.00015275613,0.00029667132,0.00030596668,0.03500855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9551311,0.010022822,0.0011119297,0.0034520873,0.023205118,0.0070769605],"domain_scores_gemma":[0.9527124,0.024093494,0.0026416006,0.0034172612,0.012941585,0.004193703],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.022501275,0.000613557,0.001170999,0.010691044,0.026074287,0.028975002,0.0043628276,0.0017381262,0.0068473793],"category_scores_gemma":[0.0678405,0.0009749078,0.0006734957,0.036189023,0.031279862,0.010279041,0.008190287,0.005496198,0.0006215382],"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":[0.00014076989,0.000070602866,0.026362084,0.00053828873,0.00006408595,0.00026277505,0.14037536,0.0011748262,0.0005520996,0.59231853,0.02690425,0.21123628],"study_design_scores_gemma":[0.000056645255,0.00007102488,0.1418565,0.0018460643,0.000103952145,0.0003983126,0.22373717,0.0061222753,0.0013067961,0.16570137,0.45850953,0.0002903695],"about_ca_topic_score_codex":0.97794527,"about_ca_topic_score_gemma":0.984766,"teacher_disagreement_score":0.9739257,"about_ca_system_score_codex":0.19031233,"about_ca_system_score_gemma":0.2501411,"threshold_uncertainty_score":0.9391229},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006576053,0.023981016,0.0017453878,0.83514464,0.11251157,0.00014394074,0.0007011086,0.00015465917,0.02496014],"genre_scores_gemma":[0.068594694,0.04009298,0.01723581,0.34519377,0.06714757,0.00075634837,0.0026974361,0.0017408351,0.45654058],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8900195,0.01659459,0.004296491,0.002769207,0.07441147,0.011908786],"domain_scores_gemma":[0.7863357,0.028426303,0.0048251287,0.0056554107,0.14141461,0.03334289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.087604,0.0020365694,0.0022364599,0.005884655,0.014373721,0.022091243,0.005809788,0.019061765,0.025255809],"category_scores_gemma":[0.11918898,0.0015433076,0.0027426095,0.0069550727,0.018587481,0.0070577613,0.008861302,0.023111755,0.007989321],"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":[0.000023284816,0.000012513747,0.00017717169,0.00013855293,0.000011688927,0.000034056917,0.00023590933,0.00006269112,0.000091390495,0.006090797,0.98190504,0.01121691],"study_design_scores_gemma":[0.000014177829,0.000009424478,0.0021708473,0.0003065621,0.000018160787,0.000029064811,0.0009867613,0.00009237404,0.00019958349,0.0027849595,0.99332446,0.00006358839],"about_ca_topic_score_codex":0.851636,"about_ca_topic_score_gemma":0.9492937,"teacher_disagreement_score":0.9065655,"about_ca_system_score_codex":0.09343453,"about_ca_system_score_gemma":0.27545196,"threshold_uncertainty_score":0.6779181},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9040694,0.0005510647,0.0034734341,0.007826094,0.0002652842,0.0061457627,0.00020948275,0.00013299225,0.07732647],"genre_scores_gemma":[0.97829986,0.0005307031,0.00989272,0.0006380064,0.000041118663,0.0019136987,0.00021189653,0.000028899405,0.008443136],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96928656,0.020120488,0.0008425986,0.00061647856,0.006708201,0.0024257016],"domain_scores_gemma":[0.9861566,0.0067349668,0.0006662831,0.00047713929,0.004190901,0.0017741481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019590572,0.00039256256,0.00031522015,0.0013825063,0.0054844376,0.0025861484,0.0015175185,0.0011857615,0.0034792935],"category_scores_gemma":[0.027713796,0.00021735037,0.00033488686,0.0009256984,0.002090223,0.0014118273,0.0025862702,0.0017042202,0.00029299827],"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":[0.0021886178,0.019876726,0.031827323,0.0020016036,0.000114158545,0.0027660998,0.07067092,0.010601695,0.005148177,0.04928201,0.023141475,0.7823812],"study_design_scores_gemma":[0.0027843628,0.054672647,0.1462955,0.0032556255,0.0004828982,0.0016665368,0.366809,0.02575426,0.047094263,0.016223745,0.33454198,0.0004190856],"about_ca_topic_score_codex":0.033717666,"about_ca_topic_score_gemma":0.040309507,"teacher_disagreement_score":0.9662823,"about_ca_system_score_codex":0.013369349,"about_ca_system_score_gemma":0.026777923,"threshold_uncertainty_score":0.103606105},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044954508,0.0010617063,0.9555759,0.0035221553,0.00036726243,0.0063881963,0.00054903305,0.002312003,0.025728332],"genre_scores_gemma":[0.060960572,0.00054980384,0.9281792,0.00034958695,0.00012824479,0.008108224,0.00028937365,0.00031920918,0.0011158743],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.57975996,0.34770653,0.028310927,0.0057741944,0.036660146,0.0017881923],"domain_scores_gemma":[0.33747485,0.5555155,0.022209913,0.035019938,0.04672412,0.003055727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.37963408,0.0036938235,0.0037270857,0.027491584,0.004755317,0.013061464,0.0032286996,0.0035037997,0.010195148],"category_scores_gemma":[0.5303242,0.0014460792,0.0039296993,0.014002976,0.007301831,0.017505916,0.011603938,0.006069284,0.0014251556],"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":[0.00047461633,0.0006815336,0.00576243,0.0061724293,0.0007461093,0.00023649269,0.010514852,0.010772445,0.0012306385,0.19065608,0.016303523,0.75644875],"study_design_scores_gemma":[0.000716824,0.0021405742,0.01161693,0.01246665,0.0012255049,0.0006295101,0.0075276457,0.052888196,0.005996759,0.6773503,0.22658709,0.0008540774],"about_ca_topic_score_codex":0.0030443957,"about_ca_topic_score_gemma":0.0028333676,"teacher_disagreement_score":0.37963408,"about_ca_system_score_codex":0.008520317,"about_ca_system_score_gemma":0.016434336,"threshold_uncertainty_score":0.7650216},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31075272,0.0018048446,0.0010361662,0.48820075,0.00040468722,0.00027144887,0.0008080371,0.000034396668,0.19668697],"genre_scores_gemma":[0.90299904,0.001940902,0.00087828387,0.017349139,0.000250712,0.000067475194,0.00011001632,0.00003350429,0.07637103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99291164,0.0011468405,0.00016273335,0.00036395263,0.0026158981,0.0027990278],"domain_scores_gemma":[0.9857897,0.0062534036,0.0011066741,0.00028214874,0.0037049695,0.0028631233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067336555,0.00020327342,0.00040953857,0.0006261139,0.011018054,0.009481059,0.0011696673,0.0053523188,0.00724698],"category_scores_gemma":[0.026524574,0.00043883087,0.00045258368,0.001532674,0.0061798645,0.0021794755,0.0020906865,0.004506078,0.0003812799],"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":[0.00054942,0.00022339441,0.050666984,0.00032678279,0.00012378897,0.0006253399,0.015143447,0.0067603188,0.001313453,0.65507644,0.22033533,0.048855294],"study_design_scores_gemma":[0.0007145903,0.00020192114,0.26897803,0.0006267045,0.0004440283,0.00010479957,0.035921253,0.008056279,0.0032071162,0.08575088,0.5957138,0.00028060816],"about_ca_topic_score_codex":0.97157234,"about_ca_topic_score_gemma":0.99163985,"teacher_disagreement_score":0.87754387,"about_ca_system_score_codex":0.122456126,"about_ca_system_score_gemma":0.267304,"threshold_uncertainty_score":0.88848555},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89572215,0.0016986643,0.011650913,0.0073575918,0.00036743132,0.05612152,0.0012986896,0.0003070873,0.025476072],"genre_scores_gemma":[0.88490814,0.0017738105,0.09451172,0.0009377861,0.00010023697,0.013834232,0.00079989847,0.000042253472,0.0030918696],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9495376,0.032559957,0.0032275775,0.0014984185,0.008878458,0.0042980122],"domain_scores_gemma":[0.96705705,0.007927748,0.0039372435,0.0023123391,0.012417623,0.0063479925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043922745,0.0008591518,0.00061331905,0.0013461758,0.0045675836,0.0031219532,0.003751261,0.0013199389,0.0023830521],"category_scores_gemma":[0.03522488,0.0005527346,0.0011417555,0.0012494373,0.0018199049,0.0012695035,0.005537853,0.0023206705,0.0002828268],"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":[0.009492135,0.06535651,0.04331565,0.00708781,0.0011937439,0.0007708856,0.017922916,0.009332113,0.005644114,0.0046295063,0.009547998,0.82570666],"study_design_scores_gemma":[0.035906214,0.24352036,0.47328657,0.015609311,0.004643927,0.00092773273,0.045333922,0.019502135,0.05054964,0.0040051574,0.10615519,0.00055979943],"about_ca_topic_score_codex":0.22051907,"about_ca_topic_score_gemma":0.42324272,"teacher_disagreement_score":0.22051907,"about_ca_system_score_codex":0.037463862,"about_ca_system_score_gemma":0.11542552,"threshold_uncertainty_score":0.43847102},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020673744,0.4490082,0.103915416,0.114481404,0.2587665,0.0035665832,0.002371146,0.0013151977,0.06636885],"genre_scores_gemma":[0.0071426425,0.4477082,0.16377698,0.06290632,0.15878071,0.010753447,0.002978164,0.0013379072,0.1446156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97502655,0.012295821,0.0042755124,0.0013086536,0.006716889,0.00037652883],"domain_scores_gemma":[0.88067436,0.083290756,0.0040856693,0.004845448,0.024654407,0.0024494291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024238305,0.0028595794,0.0028733653,0.01196864,0.0016817662,0.0043323636,0.0034192854,0.0053418116,0.06747572],"category_scores_gemma":[0.10093076,0.0019734087,0.0028444768,0.0072225304,0.004810912,0.0056686853,0.0034688178,0.009656545,0.051429797],"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":[0.0000911203,0.000052464846,0.000059548176,0.0095825335,0.00007042816,0.00014829506,0.0002164261,0.0003812806,0.0004609474,0.019624336,0.7422973,0.22701526],"study_design_scores_gemma":[0.000030030642,0.00008343134,0.00029490257,0.007989681,0.000026698013,0.00029554588,0.000096082564,0.00021812918,0.00014631182,0.043283027,0.9474753,0.000060788076],"about_ca_topic_score_codex":0.0016397218,"about_ca_topic_score_gemma":0.002484839,"teacher_disagreement_score":0.9757617,"about_ca_system_score_codex":0.0041156653,"about_ca_system_score_gemma":0.007676154,"threshold_uncertainty_score":0.22572875},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007259439,0.00058181334,0.00522488,0.013615707,0.010178403,0.00072815607,0.011109039,0.0011071429,0.95672894],"genre_scores_gemma":[0.0068917684,0.0011830393,0.0032618148,0.0058102314,0.003088925,0.0006392276,0.00927147,0.00078070804,0.9690729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99313617,0.0013385107,0.00065819215,0.0004520652,0.00402553,0.00038956114],"domain_scores_gemma":[0.97620344,0.008743526,0.0011366934,0.0027226978,0.009739134,0.0014544852],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007217741,0.0010102036,0.000977424,0.006389304,0.0025575322,0.010938256,0.0020133436,0.0060756044,0.5578128],"category_scores_gemma":[0.03584341,0.00061348506,0.00076960796,0.005647087,0.0009213533,0.01032594,0.0045787604,0.0034838908,0.40969166],"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":[0.000032568518,0.000032831595,0.00011410932,0.0002826208,0.0000023070838,0.00006744377,0.00018249267,0.00006894762,0.0002943363,0.014264592,0.9308539,0.05380379],"study_design_scores_gemma":[0.0000042983766,0.0000086453965,0.0001386379,0.00007434628,0.0000017094629,0.000028879589,0.00007255905,0.00006076943,0.00011195878,0.0015725883,0.9979213,0.00000433724],"about_ca_topic_score_codex":0.0015805846,"about_ca_topic_score_gemma":0.0025572171,"teacher_disagreement_score":0.4421872,"about_ca_system_score_codex":0.0016707098,"about_ca_system_score_gemma":0.0047284276,"threshold_uncertainty_score":0.63072634},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07328189,0.07617807,0.5668975,0.096645236,0.008472991,0.015755406,0.0037509263,0.00077442185,0.15824349],"genre_scores_gemma":[0.6447381,0.019805897,0.26777306,0.026677914,0.0024565563,0.02942166,0.0035400125,0.0014861224,0.0041007353],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.1624894,0.5808335,0.08518219,0.02846259,0.13877729,0.004255024],"domain_scores_gemma":[0.02505879,0.84993935,0.028094945,0.046922594,0.049075603,0.000908732],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71747935,0.0019325248,0.0031852196,0.01068812,0.0061260373,0.017299179,0.0065842927,0.010156499,0.018771453],"category_scores_gemma":[0.9097313,0.0026780483,0.0066347145,0.013437217,0.023371527,0.01856312,0.012846405,0.010747146,0.0038690877],"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":[0.0022509485,0.0009223929,0.07374008,0.06403147,0.005087323,0.0004696216,0.042322647,0.0031543986,0.0018743634,0.35076413,0.021887667,0.43349501],"study_design_scores_gemma":[0.0016139548,0.0027601875,0.071214184,0.14250766,0.0039638644,0.0012298073,0.019016074,0.010850595,0.013765453,0.46338588,0.26899308,0.0006993184],"about_ca_topic_score_codex":0.004120864,"about_ca_topic_score_gemma":0.0035137497,"teacher_disagreement_score":0.28252065,"about_ca_system_score_codex":0.01215295,"about_ca_system_score_gemma":0.02424206,"threshold_uncertainty_score":0.34839833},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007259439,0.00058181334,0.00522488,0.013615707,0.010178403,0.00072815607,0.011109039,0.0011071429,0.95672894],"genre_scores_gemma":[0.0068917684,0.0011830393,0.0032618148,0.0058102314,0.003088925,0.0006392276,0.00927147,0.00078070804,0.9690729],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99313617,0.0013385107,0.00065819215,0.0004520652,0.00402553,0.00038956114],"domain_scores_gemma":[0.97620344,0.008743526,0.0011366934,0.0027226978,0.009739134,0.0014544852],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007217741,0.0010102036,0.000977424,0.006389304,0.0025575322,0.010938256,0.0020133436,0.0060756044,0.5578128],"category_scores_gemma":[0.03584341,0.00061348506,0.00076960796,0.005647087,0.0009213533,0.01032594,0.0045787604,0.0034838908,0.40969166],"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":[0.000032568518,0.000032831595,0.00011410932,0.0002826208,0.0000023070838,0.00006744377,0.00018249267,0.00006894762,0.0002943363,0.014264592,0.9308539,0.05380379],"study_design_scores_gemma":[0.0000042983766,0.0000086453965,0.0001386379,0.00007434628,0.0000017094629,0.000028879589,0.00007255905,0.00006076943,0.00011195878,0.0015725883,0.9979213,0.00000433724],"about_ca_topic_score_codex":0.0015805846,"about_ca_topic_score_gemma":0.0025572171,"teacher_disagreement_score":0.4421872,"about_ca_system_score_codex":0.0016707098,"about_ca_system_score_gemma":0.0047284276,"threshold_uncertainty_score":0.63072634},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011183526,0.0006893316,0.00011923377,0.967313,0.030877309,0.000014190718,0.000038011443,0.000014332206,0.00082279317],"genre_scores_gemma":[0.00175677,0.00033226053,0.0003294583,0.96679795,0.02959647,0.000057922873,0.000012214169,0.000019526526,0.0010974327],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94614846,0.01738978,0.006801644,0.007658439,0.016716627,0.0052849874],"domain_scores_gemma":[0.6635491,0.24687038,0.013734276,0.0062297396,0.05752358,0.012092939],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037903544,0.0022346058,0.003515667,0.003667878,0.012763327,0.011331053,0.012622596,0.18531933,0.01013695],"category_scores_gemma":[0.29394376,0.0024736465,0.0036232257,0.004974994,0.020240936,0.010170992,0.007591005,0.1492979,0.007828983],"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":[0.00004509703,0.000014049156,0.00008137106,0.00022195737,0.000044234985,0.00012684919,0.00053047796,0.000058340916,0.00008013381,0.006620167,0.98932636,0.002850954],"study_design_scores_gemma":[0.00046891003,0.00006976515,0.0009664276,0.004228417,0.00038937843,0.0005769232,0.0020937163,0.0007245809,0.000616981,0.038295455,0.95137036,0.00019916763],"about_ca_topic_score_codex":0.0318085,"about_ca_topic_score_gemma":0.039688468,"teacher_disagreement_score":0.96209645,"about_ca_system_score_codex":0.020989256,"about_ca_system_score_gemma":0.03259691,"threshold_uncertainty_score":0.20045549},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072628413,0.003813753,0.056836188,0.026255734,0.010934251,0.057465736,0.029172543,0.0040288502,0.8042301],"genre_scores_gemma":[0.11919517,0.010053994,0.16268255,0.0210405,0.0026542176,0.12227865,0.04568302,0.0044063046,0.5120056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.909147,0.052953,0.007684626,0.0048830323,0.021326605,0.0040057264],"domain_scores_gemma":[0.7877543,0.043466117,0.0066805985,0.023928441,0.1283582,0.009812327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08676754,0.001445744,0.0017022428,0.0080176275,0.003999953,0.00905502,0.0052444977,0.0026773505,0.24098878],"category_scores_gemma":[0.21176183,0.00081978244,0.0020941463,0.0063939225,0.0018426487,0.0072484654,0.00861052,0.0039061941,0.057524472],"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":[0.0005964484,0.00034488487,0.0018450229,0.0027274485,0.000118543896,0.000071810326,0.0011266572,0.00053483364,0.00017751764,0.038139727,0.5087883,0.4455288],"study_design_scores_gemma":[0.00022807831,0.00026118202,0.0021037713,0.003671074,0.00009097627,0.000061870436,0.0010237013,0.00046077542,0.00037487384,0.008781855,0.9829024,0.00003946163],"about_ca_topic_score_codex":0.006962197,"about_ca_topic_score_gemma":0.007830504,"teacher_disagreement_score":0.24098878,"about_ca_system_score_codex":0.0125581585,"about_ca_system_score_gemma":0.053764947,"threshold_uncertainty_score":0.80618775},"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":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82342553,0.0020726926,0.04535044,0.03650125,0.001101547,0.06769474,0.0008435785,0.0002965024,0.02271386],"genre_scores_gemma":[0.879847,0.0015588393,0.06005433,0.002615389,0.00016646126,0.051181227,0.00024757377,0.00014781444,0.0041815005],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.44749027,0.49671087,0.014717138,0.005271938,0.02774137,0.008068438],"domain_scores_gemma":[0.29528072,0.56755686,0.020986794,0.015481304,0.08288383,0.017810564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4764518,0.0007828208,0.0014075716,0.006279705,0.016983025,0.012849405,0.005680615,0.0040132655,0.004381563],"category_scores_gemma":[0.535325,0.0013355401,0.0014161026,0.0051128343,0.017162256,0.009689296,0.019092761,0.0059720837,0.0008779395],"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":[0.0002912988,0.0008047944,0.0050270353,0.0027623826,0.000040331466,0.0005292674,0.89071125,0.000514923,0.001049408,0.010224625,0.0056469725,0.082397826],"study_design_scores_gemma":[0.0002852306,0.0014765675,0.007983823,0.0038865434,0.000068846064,0.0002479502,0.9206704,0.0010442559,0.0019655533,0.006132001,0.056037903,0.00020106102],"about_ca_topic_score_codex":0.006510315,"about_ca_topic_score_gemma":0.008372647,"teacher_disagreement_score":0.5235482,"about_ca_system_score_codex":0.035268232,"about_ca_system_score_gemma":0.07674821,"threshold_uncertainty_score":0.64562815},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07250604,0.002385216,0.004454074,0.50684065,0.0028198818,0.0029911408,0.0015038523,0.0022008142,0.40429842],"genre_scores_gemma":[0.67616165,0.0029092415,0.037421346,0.107869625,0.0020961645,0.0028528275,0.0023797492,0.00070592057,0.16760357],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9771229,0.011219848,0.0005630363,0.0006904208,0.006509981,0.0038938527],"domain_scores_gemma":[0.90013605,0.025401186,0.0035850138,0.0037787696,0.018025765,0.049073175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018466529,0.00069574814,0.0007195481,0.0031189572,0.012983091,0.011801614,0.00237207,0.0039456934,0.09962137],"category_scores_gemma":[0.09001434,0.00076338794,0.0005901024,0.0024062719,0.0015831083,0.0047288695,0.009958565,0.004511707,0.012502721],"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":[0.00021174247,0.0015563117,0.02081592,0.00025553614,0.000037666643,0.00017469328,0.0020334315,0.00026597313,0.0002613019,0.0041027963,0.6573041,0.31298044],"study_design_scores_gemma":[0.000497015,0.0007226859,0.072323225,0.00068604853,0.00008668054,0.00020005098,0.013318933,0.0023065761,0.00092855736,0.006565744,0.90221417,0.00015018247],"about_ca_topic_score_codex":0.15432855,"about_ca_topic_score_gemma":0.38276738,"teacher_disagreement_score":0.8456714,"about_ca_system_score_codex":0.01390763,"about_ca_system_score_gemma":0.10254284,"threshold_uncertainty_score":0.33326668},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015836138,0.004091767,0.00032621087,0.0998664,0.8760373,0.000057815225,0.00028920572,0.000119180135,0.019053716],"genre_scores_gemma":[0.0040170792,0.008237868,0.0004162398,0.111113675,0.6467272,0.00009657789,0.00040916685,0.00016089491,0.22882129],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745494,0.0004822672,0.0003299255,0.00034897943,0.0011286933,0.00025525515],"domain_scores_gemma":[0.98027843,0.0035978397,0.0010824171,0.00077604875,0.011363182,0.002902028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003002888,0.0011017628,0.0011835857,0.0015430555,0.0013220853,0.004050089,0.0025272786,0.0060746507,0.24689482],"category_scores_gemma":[0.031154638,0.0005577203,0.0009090638,0.0007589785,0.0008415627,0.002558234,0.0014969191,0.0050095473,0.1371999],"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":[0.00003993664,0.000008017328,0.000052474752,0.00016313717,0.000005665814,0.00017179216,0.000007292714,0.000015899597,0.00005819437,0.00036935954,0.9876058,0.01150234],"study_design_scores_gemma":[0.000020789206,0.000017165734,0.00012047272,0.00022378015,0.000007024448,0.0004275137,0.000025649537,0.00004004038,0.00012677361,0.00033828538,0.99864465,0.000007890422],"about_ca_topic_score_codex":0.00080850336,"about_ca_topic_score_gemma":0.0017036427,"teacher_disagreement_score":0.24689482,"about_ca_system_score_codex":0.0013625609,"about_ca_system_score_gemma":0.0021674084,"threshold_uncertainty_score":0.8259455},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025136585,0.0023299344,0.0076203947,0.009465537,0.0029024296,0.00018430252,0.0035332267,0.0028408351,0.96860987],"genre_scores_gemma":[0.004853369,0.0008274165,0.0021556031,0.001245531,0.00022294177,0.000046865156,0.0013793998,0.0005749217,0.9886938],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986953,0.00018265976,0.000066505614,0.00022426753,0.0006871246,0.00014400051],"domain_scores_gemma":[0.99704164,0.00045469071,0.0001136212,0.00028021875,0.0014372665,0.0006725477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017499228,0.000637259,0.0005955887,0.0022646247,0.0024576774,0.0051249056,0.0011592419,0.001019078,0.42149925],"category_scores_gemma":[0.0035804692,0.0006463896,0.00048042886,0.0012846182,0.00087326905,0.0034146754,0.0026224947,0.0022943725,0.3108188],"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":[0.0000849212,0.000083763676,0.000724312,0.00021910334,0.0000048824563,0.00033481352,0.00051506015,0.00015936428,0.0007097195,0.046571873,0.77855295,0.17203923],"study_design_scores_gemma":[0.0000038242842,0.000012509305,0.0002138201,0.000041378877,0.0000014347864,0.00015353589,0.00010273603,0.00006763744,0.0001779623,0.0018728884,0.9973476,0.0000047643666],"about_ca_topic_score_codex":0.006139148,"about_ca_topic_score_gemma":0.017194493,"teacher_disagreement_score":0.42149925,"about_ca_system_score_codex":0.0026633192,"about_ca_system_score_gemma":0.0042179488,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96571386,0.00042987315,0.013419888,0.0015443212,0.00016921718,0.002669058,0.00095894845,0.000063301646,0.015031467],"genre_scores_gemma":[0.9609449,0.0004855027,0.02774889,0.00045319536,0.000033787386,0.00417363,0.0010545517,0.000037883085,0.0050676637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98335856,0.007385274,0.001345345,0.0014567459,0.005362159,0.0010919017],"domain_scores_gemma":[0.9213216,0.031986408,0.0046041957,0.005004012,0.03521841,0.0018653698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037379697,0.00047660698,0.0005299389,0.0023343917,0.0026161005,0.0031861858,0.0010434908,0.0007898716,0.003821391],"category_scores_gemma":[0.067485,0.0003552982,0.001016049,0.0024303796,0.0025004393,0.0019124773,0.0038508007,0.0016747774,0.0005817963],"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":[0.00039317747,0.00067955157,0.55700946,0.0011343334,0.00023676589,0.00027758774,0.1239465,0.00080270064,0.0036918158,0.01142252,0.005933888,0.29447156],"study_design_scores_gemma":[0.000067567875,0.0007090976,0.8844812,0.0013867174,0.00016457771,0.00014523184,0.07482638,0.0019090194,0.004523958,0.0027403617,0.028948257,0.000097708275],"about_ca_topic_score_codex":0.0795882,"about_ca_topic_score_gemma":0.07987264,"teacher_disagreement_score":0.0795882,"about_ca_system_score_codex":0.007261568,"about_ca_system_score_gemma":0.02256571,"threshold_uncertainty_score":0.19768512},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002762901,0.004904704,0.0005307383,0.04629827,0.9077691,0.00010378916,0.000356908,0.00025758523,0.039502617],"genre_scores_gemma":[0.0049848417,0.008558836,0.000895791,0.031228019,0.7670146,0.00014947302,0.00065918895,0.00034646265,0.1861628],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99294853,0.0008584565,0.00053433474,0.0011085774,0.0040922267,0.00045784214],"domain_scores_gemma":[0.9478321,0.0071727936,0.0022310086,0.0027054034,0.03347062,0.0065881265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006000941,0.001355585,0.001152896,0.002944828,0.0026293746,0.0092294365,0.0020524696,0.003895431,0.11734844],"category_scores_gemma":[0.04386684,0.00044843103,0.0011230011,0.0011901135,0.0016638316,0.003055531,0.0016265312,0.0055166567,0.072267056],"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":[0.000016810192,0.000008998757,0.00006057966,0.00009858853,0.000002973736,0.000049902806,0.000017704055,0.000011748562,0.000039596078,0.00069632696,0.9861356,0.012861189],"study_design_scores_gemma":[0.000009108607,0.000016779772,0.00018134325,0.00022522453,0.0000045916013,0.0001273689,0.00006869019,0.000038114336,0.00009350387,0.0007453964,0.99848396,0.0000059152535],"about_ca_topic_score_codex":0.0009900932,"about_ca_topic_score_gemma":0.0017337797,"teacher_disagreement_score":0.11734844,"about_ca_system_score_codex":0.0024918776,"about_ca_system_score_gemma":0.005088259,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019575546,0.01171589,0.00010445715,0.21205787,0.7736339,0.000010188575,0.00003289113,0.000020663774,0.0024046346],"genre_scores_gemma":[0.0014364823,0.024229495,0.00039158243,0.14865948,0.8055686,0.00004969869,0.00006369611,0.000041704825,0.01955933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99170977,0.0022547594,0.0007862711,0.0007785012,0.0036106955,0.0008600389],"domain_scores_gemma":[0.9547669,0.0151310945,0.001733587,0.0011066968,0.016348738,0.0109130535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013944134,0.0022924684,0.0025709034,0.002645032,0.00420076,0.012868065,0.002715746,0.020099767,0.020411672],"category_scores_gemma":[0.055339783,0.0010050534,0.002069608,0.0013070905,0.0048419596,0.007194398,0.003346121,0.037850406,0.0072571896],"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":[0.000007678877,0.0000043999503,0.000017081982,0.000087017346,0.00000577981,0.000041173844,0.000016530314,0.000016669976,0.000007121543,0.0009062359,0.9950878,0.0038026653],"study_design_scores_gemma":[0.000023287072,0.000008175186,0.00012952898,0.0005598943,0.000020531766,0.000085726264,0.000112744594,0.000045194905,0.000018613673,0.002052286,0.996931,0.000013053313],"about_ca_topic_score_codex":0.011557103,"about_ca_topic_score_gemma":0.03657991,"teacher_disagreement_score":0.020411672,"about_ca_system_score_codex":0.0074586947,"about_ca_system_score_gemma":0.023577759,"threshold_uncertainty_score":0.073744535},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011529949,0.012100622,0.0031747513,0.21608119,0.5034937,0.0018256273,0.0029327688,0.002943571,0.25629473],"genre_scores_gemma":[0.000930075,0.0028059275,0.0012487558,0.039264716,0.05013912,0.000645327,0.0007872943,0.0008088229,0.9033699],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977191,0.00036176862,0.00013306833,0.00016891678,0.0014556894,0.00016144628],"domain_scores_gemma":[0.98397046,0.005683617,0.00093911344,0.0006513121,0.0052581714,0.00349738],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041292277,0.0013092826,0.0020770817,0.0028455995,0.0020694071,0.006217408,0.0014548302,0.005761282,0.4111562],"category_scores_gemma":[0.016440433,0.001038171,0.0008384547,0.0025261755,0.0009249094,0.004140538,0.0023719752,0.0046635796,0.39871925],"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":[0.000005196747,0.00001435113,0.000020070462,0.000033781278,7.559943e-7,0.000008364739,0.000006333848,0.000007903655,0.00007407,0.0001434145,0.9927556,0.0069301403],"study_design_scores_gemma":[0.000012833012,0.00003834227,0.00041684372,0.00008623926,0.0000019381696,0.000024459448,0.00007092638,0.00003740888,0.00006346719,0.00063104194,0.99860686,0.000009606387],"about_ca_topic_score_codex":0.0015250362,"about_ca_topic_score_gemma":0.006459562,"teacher_disagreement_score":0.4111562,"about_ca_system_score_codex":0.0016765688,"about_ca_system_score_gemma":0.0038273006,"threshold_uncertainty_score":0.8399142},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002297917,0.008953522,0.0015551324,0.110180244,0.7011521,0.00041154475,0.0039409176,0.0010378099,0.17253889],"genre_scores_gemma":[0.0028137693,0.009594838,0.0032888767,0.07299873,0.15046845,0.0006257473,0.0033802958,0.0011341843,0.7556951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904056,0.0008678977,0.0010904985,0.0013816761,0.005446929,0.0008073403],"domain_scores_gemma":[0.9544216,0.0078430325,0.0024573372,0.0038820868,0.027128045,0.00426794],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007956757,0.0014004203,0.0015255429,0.0046876697,0.0035888113,0.008597897,0.0057062022,0.0059312605,0.4067391],"category_scores_gemma":[0.06994286,0.0007954877,0.0015150027,0.004095411,0.0014007204,0.005555568,0.0035158594,0.0068893307,0.3229369],"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":[0.000007503414,0.0000063848793,0.000014726995,0.00008431599,0.0000010024454,0.000021763966,0.000025650188,0.000009565534,0.000036761685,0.00090639107,0.98743814,0.011447731],"study_design_scores_gemma":[0.000004531754,0.0000031471952,0.00003969228,0.00010963897,0.0000014415398,0.000024105464,0.000025622474,0.000008948015,0.000042582873,0.00033728417,0.9993993,0.0000036427557],"about_ca_topic_score_codex":0.003783897,"about_ca_topic_score_gemma":0.0066051446,"teacher_disagreement_score":0.4067391,"about_ca_system_score_codex":0.0036890095,"about_ca_system_score_gemma":0.009225461,"threshold_uncertainty_score":0.84621465},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023099758,0.003934077,0.012995407,0.66138333,0.009735245,0.0001758727,0.0004140009,0.00035725866,0.28790507],"genre_scores_gemma":[0.34060615,0.005932076,0.00772808,0.1867207,0.0024336486,0.00044111768,0.00040904843,0.0006503291,0.45507887],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9840104,0.009128231,0.00028520296,0.0018094032,0.0029483114,0.0018185562],"domain_scores_gemma":[0.98481005,0.0063392627,0.0011114639,0.0013559104,0.004480639,0.0019027031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014375267,0.00061754574,0.0006182,0.0008168089,0.0085439915,0.008837095,0.0017789487,0.005431462,0.061446693],"category_scores_gemma":[0.04877767,0.0003434799,0.0006016596,0.001131121,0.009172794,0.010424318,0.00510807,0.008068179,0.02710398],"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":[0.00013699083,0.00011806915,0.007033999,0.0002764136,0.000046709432,0.0016783962,0.057677235,0.00017053483,0.0010844895,0.30126864,0.5354498,0.095058724],"study_design_scores_gemma":[0.0000161227,0.00003666545,0.0014036188,0.00034781237,0.000020371597,0.0008420476,0.05698332,0.0001793921,0.00052451825,0.037081808,0.90250665,0.000057796115],"about_ca_topic_score_codex":0.009682723,"about_ca_topic_score_gemma":0.014708927,"teacher_disagreement_score":0.98562473,"about_ca_system_score_codex":0.0049140956,"about_ca_system_score_gemma":0.008095461,"threshold_uncertainty_score":0.20555967},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98605716,0.00037991113,0.00010264033,0.0047225184,0.000028155897,0.000042354324,0.00022829726,0.0000044488042,0.008434427],"genre_scores_gemma":[0.9968966,0.0003614242,0.00019751975,0.00039547318,0.0000037256077,0.00003188108,0.000076497556,0.000002746428,0.002034136],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9975677,0.0010089979,0.0000955397,0.000181275,0.00035752315,0.0007890035],"domain_scores_gemma":[0.9949456,0.0011798216,0.0010740841,0.00020296537,0.00067435077,0.001923193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027091934,0.00024306848,0.00022874516,0.0013090955,0.005094112,0.0050748074,0.0009167268,0.0007370285,0.002856306],"category_scores_gemma":[0.007180171,0.0002960017,0.0003517153,0.001706417,0.005193119,0.0024246583,0.0031874066,0.001490695,0.00024045548],"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":[0.00019220685,0.00017336724,0.47596186,0.00015153755,0.0000774976,0.00012846985,0.47961757,0.00011066178,0.000639396,0.0020792526,0.0030683298,0.037799872],"study_design_scores_gemma":[0.000010201891,0.000066756336,0.30117837,0.00020274735,0.000041212825,0.00001951016,0.69163334,0.000078292374,0.00017902085,0.000402742,0.006149821,0.000037932034],"about_ca_topic_score_codex":0.83118,"about_ca_topic_score_gemma":0.9521152,"teacher_disagreement_score":0.16882002,"about_ca_system_score_codex":0.018510612,"about_ca_system_score_gemma":0.022125635,"threshold_uncertainty_score":0.33962846},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19355604,0.00462727,0.013634834,0.38025528,0.0017789257,0.0008606972,0.00018389919,0.00018349853,0.40491953],"genre_scores_gemma":[0.86565363,0.0026441233,0.02838608,0.011694874,0.00008204679,0.000489875,0.00016345095,0.00008306129,0.0908028],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9885753,0.009293342,0.00019670253,0.00032487413,0.0006894663,0.00092025014],"domain_scores_gemma":[0.9905234,0.0052651465,0.0004654301,0.00038143556,0.0014079079,0.001956728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016500978,0.00024820192,0.00016101955,0.00054665643,0.013524169,0.010116268,0.00085843663,0.0030109475,0.013806826],"category_scores_gemma":[0.015370219,0.00023280132,0.00037097197,0.0008757889,0.0042003365,0.007655579,0.0048592873,0.0031555614,0.00125282],"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":[0.00023499655,0.0010685533,0.024995878,0.00055153586,0.000052094983,0.0013827111,0.16497616,0.0016462052,0.0020420854,0.27595022,0.20520808,0.32189146],"study_design_scores_gemma":[0.000056478028,0.0003030143,0.022683147,0.0010274815,0.00004351139,0.00027741274,0.31748688,0.002337526,0.0016206338,0.035738174,0.6183143,0.00011144249],"about_ca_topic_score_codex":0.030364998,"about_ca_topic_score_gemma":0.11135541,"teacher_disagreement_score":0.969635,"about_ca_system_score_codex":0.009059766,"about_ca_system_score_gemma":0.024281597,"threshold_uncertainty_score":0.087266564},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011164646,0.004079547,0.5661544,0.0026845422,0.0027085945,0.030503146,0.12551057,0.12486441,0.13233009],"genre_scores_gemma":[0.032346774,0.0034421224,0.7240251,0.00094261544,0.0014874847,0.03507071,0.09111567,0.01765986,0.09390968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97172576,0.011478075,0.0045736814,0.0013878891,0.010314551,0.00052017235],"domain_scores_gemma":[0.7822858,0.14269605,0.00961997,0.02427067,0.036486506,0.0046409625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015056575,0.001971645,0.002316694,0.017277809,0.0013524875,0.009063599,0.0021525424,0.0021862513,0.19471626],"category_scores_gemma":[0.19111304,0.0015685689,0.0014929781,0.019575818,0.00083498727,0.0055144285,0.0025828,0.002075561,0.14753374],"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":[0.00038358843,0.00084503496,0.0043375827,0.0023903241,0.00018307808,0.00005966773,0.00021559418,0.0008605533,0.0016658826,0.00626492,0.38841373,0.59438014],"study_design_scores_gemma":[0.0015670815,0.0010737769,0.05276467,0.0048084897,0.00058386417,0.00076867046,0.0013161937,0.04265641,0.012386926,0.07401645,0.8073584,0.0006989992],"about_ca_topic_score_codex":0.002957928,"about_ca_topic_score_gemma":0.0032729171,"teacher_disagreement_score":0.19471626,"about_ca_system_score_codex":0.0013214584,"about_ca_system_score_gemma":0.0024389103,"threshold_uncertainty_score":0.6513908},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023739256,0.061182376,0.17778413,0.21677789,0.12996088,0.0076967212,0.009066847,0.0019092973,0.37188262],"genre_scores_gemma":[0.035238076,0.017623877,0.05260313,0.005437163,0.0020043033,0.0028251675,0.0031755066,0.00060020864,0.8804926],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98821694,0.0051369807,0.0003940818,0.0009241849,0.00411844,0.0012094342],"domain_scores_gemma":[0.9806502,0.0030349034,0.00031815813,0.00083220296,0.012351952,0.002812588],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.040726677,0.001194965,0.001412339,0.0019094325,0.0069101704,0.007659794,0.002817453,0.0030626145,0.09293634],"category_scores_gemma":[0.02112892,0.0010721051,0.001227263,0.001608824,0.004292223,0.0018759541,0.005891881,0.005809286,0.015710512],"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":[0.00044007372,0.00016941244,0.0014796539,0.0011298828,0.000055983255,0.00031409468,0.005309771,0.0005763207,0.0035026614,0.008820222,0.7921642,0.18603767],"study_design_scores_gemma":[0.000030318439,0.00003832668,0.0015941431,0.0006980234,0.000019069026,0.00004684835,0.002193713,0.00022664982,0.0007558309,0.0018331264,0.9925282,0.000035754358],"about_ca_topic_score_codex":0.42289817,"about_ca_topic_score_gemma":0.77506775,"teacher_disagreement_score":0.95927334,"about_ca_system_score_codex":0.021096492,"about_ca_system_score_gemma":0.05793863,"threshold_uncertainty_score":0.84087324},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024417058,0.0034304806,0.1966564,0.012411517,0.0058675483,0.049988274,0.044359658,0.003570961,0.65929806],"genre_scores_gemma":[0.14933285,0.0071937717,0.28297243,0.0065557,0.002013067,0.06808179,0.054769233,0.0042924504,0.42478877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9704366,0.0130615635,0.0028545896,0.0045010815,0.008275941,0.0008701105],"domain_scores_gemma":[0.9458089,0.02171076,0.001956439,0.006279306,0.023380956,0.0008636879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022528846,0.0012825424,0.0015260363,0.011990346,0.004066065,0.008889704,0.003028399,0.0014320873,0.11574788],"category_scores_gemma":[0.066213824,0.00063032814,0.0012191747,0.013354822,0.0024529044,0.006468651,0.0054421034,0.0027248815,0.042610206],"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":[0.00030546237,0.00018645759,0.0014540643,0.0040965294,0.000052853684,0.00021619127,0.0386445,0.0009247259,0.002735721,0.09966587,0.28577852,0.56593907],"study_design_scores_gemma":[0.00003571592,0.00006502296,0.0011989593,0.0018353869,0.000023217377,0.00009485576,0.012174268,0.00079777406,0.0013755684,0.01445513,0.967905,0.000039177292],"about_ca_topic_score_codex":0.0026882538,"about_ca_topic_score_gemma":0.0019926196,"teacher_disagreement_score":0.11574788,"about_ca_system_score_codex":0.00895716,"about_ca_system_score_gemma":0.01147719,"threshold_uncertainty_score":0.3872152},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7517629,0.0021800296,0.12403412,0.039760828,0.0018251259,0.0069288732,0.00022713114,0.0020569444,0.07122412],"genre_scores_gemma":[0.702462,0.0016916129,0.25559348,0.0049975836,0.00051756593,0.0031877358,0.00037998275,0.00017358726,0.030996379],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99033153,0.005128705,0.00044016173,0.0005206383,0.0024869554,0.0010920024],"domain_scores_gemma":[0.9688007,0.006285043,0.0028342812,0.0025370074,0.0069226753,0.012620259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025296053,0.0006404701,0.00043154552,0.001363358,0.0022004084,0.0047920053,0.0020017761,0.0010101749,0.006848943],"category_scores_gemma":[0.037500866,0.00042564777,0.00040414385,0.0006286501,0.0016119151,0.002348985,0.0074396175,0.0030416343,0.0014248976],"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":[0.00021092335,0.011259505,0.02775116,0.0007609181,0.00002692054,0.0001964807,0.01825947,0.0013932321,0.0060208673,0.011649316,0.0585375,0.8639338],"study_design_scores_gemma":[0.0006426382,0.010420941,0.15937883,0.0049984343,0.00016011593,0.001991035,0.057197113,0.013380407,0.02706899,0.062202282,0.6622773,0.00028198888],"about_ca_topic_score_codex":0.0008666207,"about_ca_topic_score_gemma":0.004100472,"teacher_disagreement_score":0.025296053,"about_ca_system_score_codex":0.004264003,"about_ca_system_score_gemma":0.01811005,"threshold_uncertainty_score":0.13377988},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94398856,0.0025475791,0.0023037507,0.0036135027,0.0001916166,0.0059760786,0.028250283,0.00044881672,0.01267978],"genre_scores_gemma":[0.969027,0.001059641,0.0075202994,0.0008964482,0.00006000172,0.0016753735,0.012274953,0.000066577624,0.0074197813],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98893774,0.0017302246,0.000533886,0.0008878024,0.0057545314,0.0021558432],"domain_scores_gemma":[0.9661518,0.0012206017,0.0026651837,0.0010281501,0.023770863,0.0051635127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010035395,0.00075762067,0.001032468,0.0018079128,0.0045732823,0.0020761222,0.0026082515,0.0009750563,0.0020083839],"category_scores_gemma":[0.014187491,0.00049362733,0.0012446464,0.004719762,0.0010884233,0.0008875436,0.0024882073,0.0008979578,0.00050046487],"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":[0.0021889834,0.0020887367,0.8908787,0.00046944764,0.0002940481,0.00011606145,0.0021902153,0.0017755862,0.00091210473,0.00051711564,0.026510531,0.07205854],"study_design_scores_gemma":[0.00057508604,0.000939459,0.98776734,0.00009854901,0.0001688265,0.000052733536,0.0015313718,0.001433773,0.0005021268,0.00006227131,0.006831416,0.000037040914],"about_ca_topic_score_codex":0.9917891,"about_ca_topic_score_gemma":0.9941666,"teacher_disagreement_score":0.10698161,"about_ca_system_score_codex":0.10698161,"about_ca_system_score_gemma":0.25415686,"threshold_uncertainty_score":0.7762096},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069563445,0.003019863,0.94191635,0.015058799,0.0009417218,0.0042107548,0.00021799603,0.0003393871,0.027338872],"genre_scores_gemma":[0.15122378,0.0015985065,0.8307283,0.0034740865,0.0005071603,0.01045201,0.0001464833,0.00029295878,0.0015767209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.58288205,0.35183477,0.014538721,0.0106566455,0.038598623,0.0014890837],"domain_scores_gemma":[0.47171745,0.42405608,0.012154513,0.059906572,0.03010868,0.0020567693],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.32107967,0.0015092359,0.0028913538,0.008040011,0.0050774347,0.016812213,0.0034365538,0.0037482595,0.0055054035],"category_scores_gemma":[0.4671532,0.0019998194,0.002229953,0.0067254673,0.028310617,0.015001827,0.016987173,0.008531458,0.0014192234],"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":[0.00012920494,0.00027739085,0.0058096587,0.0034646303,0.00036825074,0.00013244212,0.022054693,0.0011669172,0.0014179545,0.7810817,0.004807819,0.17928948],"study_design_scores_gemma":[0.00023264838,0.000472295,0.0048414664,0.005288868,0.00022918114,0.00039952062,0.004033988,0.0057335845,0.0023644124,0.90156376,0.07464991,0.00019048897],"about_ca_topic_score_codex":0.0017934231,"about_ca_topic_score_gemma":0.00235414,"teacher_disagreement_score":0.32107967,"about_ca_system_score_codex":0.006945614,"about_ca_system_score_gemma":0.018185657,"threshold_uncertainty_score":0.8372296},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019063944,0.7442288,0.05633634,0.041800752,0.03295985,0.03163073,0.006802,0.00056655554,0.06661112],"genre_scores_gemma":[0.24834168,0.49749416,0.13099016,0.017889177,0.015716232,0.03346044,0.0075832387,0.0007268979,0.047798],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.81502223,0.10767648,0.035905175,0.0030214617,0.03714199,0.0012326152],"domain_scores_gemma":[0.5275482,0.35834706,0.026607394,0.019602366,0.06390206,0.0039930143],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11714226,0.002066935,0.004900048,0.008249192,0.0014287382,0.0061933864,0.0029884172,0.005058923,0.03578279],"category_scores_gemma":[0.54317755,0.001152392,0.006834226,0.0042656795,0.0027099547,0.004198584,0.0025472208,0.003555868,0.007969893],"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":[0.007010826,0.0014537268,0.0039447504,0.16436172,0.007280369,0.00023674924,0.00041376892,0.0021546143,0.0030719268,0.0065929494,0.070350215,0.73312837],"study_design_scores_gemma":[0.0039814,0.018069867,0.050355073,0.41101637,0.052446626,0.0019994576,0.0011248903,0.004870533,0.03069145,0.0647045,0.36018515,0.0005547339],"about_ca_topic_score_codex":0.0012992481,"about_ca_topic_score_gemma":0.0027395138,"teacher_disagreement_score":0.88285774,"about_ca_system_score_codex":0.0058843177,"about_ca_system_score_gemma":0.012851553,"threshold_uncertainty_score":0.6195149},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03295048,0.02654757,0.036677714,0.5757101,0.0041305195,0.00033993303,0.00006873453,0.00022227001,0.32335255],"genre_scores_gemma":[0.85791844,0.013237586,0.022700844,0.076549925,0.0012928293,0.000529784,0.000064788845,0.0003700332,0.027335847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9330107,0.053759985,0.001164911,0.0020815064,0.0064236424,0.00355926],"domain_scores_gemma":[0.9221698,0.046421338,0.002365655,0.004274462,0.0181699,0.0065988954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07960362,0.0007965986,0.0009749449,0.0046113315,0.011597591,0.030188499,0.0030476088,0.005101815,0.007617096],"category_scores_gemma":[0.0564114,0.00039395885,0.0005254105,0.0049727377,0.05768797,0.016750962,0.014039773,0.010644323,0.000680843],"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":[0.000050424398,0.00011070144,0.004580064,0.0010135534,0.00003952406,0.0003619223,0.16299577,0.0007027575,0.00034125173,0.69193333,0.06097136,0.07689934],"study_design_scores_gemma":[0.000024746301,0.000099153,0.0029722338,0.0030038028,0.000039938062,0.00026010087,0.29622838,0.0010384958,0.00070925313,0.2376444,0.45792985,0.00004964598],"about_ca_topic_score_codex":0.024720902,"about_ca_topic_score_gemma":0.03947703,"teacher_disagreement_score":0.07960362,"about_ca_system_score_codex":0.023797248,"about_ca_system_score_gemma":0.049744587,"threshold_uncertainty_score":0.42098922},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001146831,0.00054918235,0.00041829247,0.0020575956,0.006045516,0.0002926902,0.026246617,0.0013800788,0.9628953],"genre_scores_gemma":[0.0004070469,0.000453581,0.00032422418,0.00066535483,0.00071783125,0.00009453295,0.01034456,0.00034821665,0.98664457],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870205,0.00009379484,0.00007119765,0.00014738053,0.0008325616,0.00015302778],"domain_scores_gemma":[0.99520147,0.0005448972,0.0002294907,0.0004384623,0.002468265,0.0011174654],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011592988,0.0017377472,0.0013236816,0.00542718,0.0021652335,0.0098492615,0.0020910555,0.002915466,0.9245241],"category_scores_gemma":[0.0068394393,0.00079703185,0.0010855715,0.0058473623,0.000641134,0.0038291428,0.002246916,0.002257409,0.8840906],"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":[0.000009014626,0.00001399109,0.000023773015,0.00007724569,7.2453315e-7,0.0000072328594,0.0000038028732,0.0000229487,0.00003376752,0.00054817914,0.9818897,0.017369635],"study_design_scores_gemma":[0.000010638585,0.000006777242,0.00019978009,0.000070149,0.0000011420454,0.000008665761,0.000013176159,0.000032279513,0.000030569354,0.00046483366,0.9991584,0.0000035100836],"about_ca_topic_score_codex":0.015913634,"about_ca_topic_score_gemma":0.03715463,"teacher_disagreement_score":0.07547587,"about_ca_system_score_codex":0.002403858,"about_ca_system_score_gemma":0.00615756,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008474604,0.009866889,0.88304216,0.0052891443,0.014672004,0.05190519,0.005585616,0.0033184765,0.017845893],"genre_scores_gemma":[0.06388796,0.002298459,0.8390742,0.0018317112,0.00112156,0.08229548,0.0006834481,0.0013610246,0.007446237],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78595024,0.1552332,0.021195851,0.012461055,0.023320891,0.0018386772],"domain_scores_gemma":[0.64466226,0.28536373,0.01115591,0.033069573,0.024195077,0.0015534987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.085725404,0.002608677,0.0063491506,0.010517895,0.0034886356,0.0032924067,0.006280952,0.0042626527,0.0629891],"category_scores_gemma":[0.46487406,0.0022882016,0.009700718,0.008793279,0.003734494,0.00384942,0.004376513,0.008740483,0.009806996],"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":[0.0066774874,0.0007902455,0.0017164029,0.031858563,0.004577,0.00026577516,0.00128971,0.0015731278,0.0026900498,0.020796057,0.035566818,0.89219874],"study_design_scores_gemma":[0.01569809,0.01261393,0.023624722,0.042880796,0.03583621,0.0020230704,0.0034788458,0.044673905,0.03108097,0.27180326,0.51507014,0.0012160686],"about_ca_topic_score_codex":0.0015452654,"about_ca_topic_score_gemma":0.0027521844,"teacher_disagreement_score":0.085725404,"about_ca_system_score_codex":0.0032060118,"about_ca_system_score_gemma":0.006124859,"threshold_uncertainty_score":0.45336467},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045889232,0.0018153532,0.8278864,0.0280431,0.0006994099,0.004502215,0.00070136535,0.000545045,0.089917846],"genre_scores_gemma":[0.3182544,0.0015077944,0.6627132,0.0019574747,0.000115677685,0.009195233,0.0004940943,0.00028939825,0.005472733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89592,0.09002013,0.0034522673,0.0030448404,0.005416941,0.0021458808],"domain_scores_gemma":[0.85951054,0.1178356,0.0044526006,0.006196111,0.00905138,0.0029537813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12064798,0.0024871104,0.001834522,0.02127189,0.011285552,0.020592354,0.0052158637,0.004287416,0.01301467],"category_scores_gemma":[0.089556396,0.0015422998,0.0034854575,0.01055484,0.036093876,0.026757658,0.024018122,0.008779719,0.0013912759],"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":[0.000078711324,0.000105817606,0.0027352644,0.0016067963,0.000067676905,0.0005625323,0.30593607,0.0012355691,0.0010186094,0.6102054,0.006267573,0.0701799],"study_design_scores_gemma":[0.00007733962,0.00012733186,0.0017395857,0.0044223336,0.000089107976,0.0005376036,0.3217271,0.005858908,0.0015510318,0.5330857,0.13061173,0.00017217488],"about_ca_topic_score_codex":0.008733611,"about_ca_topic_score_gemma":0.010280972,"teacher_disagreement_score":0.12064798,"about_ca_system_score_codex":0.02085519,"about_ca_system_score_gemma":0.030583704,"threshold_uncertainty_score":0.63805515},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21676373,0.014233059,0.011392524,0.62781006,0.0023531707,0.0059281397,0.010125447,0.00076609344,0.110627756],"genre_scores_gemma":[0.83792007,0.013074931,0.07668847,0.049018465,0.0008637491,0.0020163157,0.0044801696,0.00015270771,0.01578503],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96713233,0.009179777,0.0045918734,0.00090574916,0.013740504,0.004449807],"domain_scores_gemma":[0.8983269,0.026896166,0.007433043,0.00080518,0.0531243,0.0134143885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033915035,0.000754931,0.0009888489,0.0058097322,0.004743491,0.010052849,0.004581961,0.004837642,0.0058251573],"category_scores_gemma":[0.11129164,0.00085128244,0.0015556242,0.0052353884,0.0017885026,0.0024408288,0.0026756732,0.004171617,0.00059502415],"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":[0.0006744578,0.00082801876,0.24579018,0.0027840163,0.0006647632,0.0014874818,0.005986119,0.019397432,0.00095085765,0.028394205,0.44798452,0.24505791],"study_design_scores_gemma":[0.0012330413,0.00045319094,0.6576049,0.008368272,0.0009518105,0.00033750825,0.013440114,0.04440274,0.0013284014,0.0070412764,0.26444778,0.00039104366],"about_ca_topic_score_codex":0.96176296,"about_ca_topic_score_gemma":0.97941077,"teacher_disagreement_score":0.862859,"about_ca_system_score_codex":0.137141,"about_ca_system_score_gemma":0.3983701,"threshold_uncertainty_score":0.9950323},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068151637,0.0004933074,0.001476562,0.0016652556,0.0005907093,0.00006994399,0.00021308805,0.00013587097,0.99467367],"genre_scores_gemma":[0.04485919,0.0021668535,0.0024601552,0.0028767353,0.00076730055,0.00016432448,0.0010269447,0.0003218253,0.94535667],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960692,0.00041766642,0.000088840614,0.00035806355,0.0026351756,0.00043097264],"domain_scores_gemma":[0.99682295,0.00047750215,0.00013615651,0.00050125853,0.0015609446,0.000501173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022779536,0.0010699715,0.0004920794,0.002799023,0.0019730437,0.0070155477,0.0015729804,0.0015842151,0.3301619],"category_scores_gemma":[0.009352201,0.00026292904,0.0007474804,0.0017452319,0.0012878991,0.0042451313,0.0042163064,0.0019753869,0.11100143],"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":[0.000121460005,0.00012858218,0.0011000728,0.00037186936,0.000019353554,0.00015392982,0.0003643995,0.00049012987,0.0012958471,0.25687462,0.3358969,0.4031828],"study_design_scores_gemma":[0.000011194057,0.000032096923,0.0009493775,0.00021253721,0.000013946608,0.00016113977,0.00033569554,0.00019013161,0.00082894985,0.036699615,0.96055305,0.000012182118],"about_ca_topic_score_codex":0.003699466,"about_ca_topic_score_gemma":0.0043318067,"teacher_disagreement_score":0.3301619,"about_ca_system_score_codex":0.0028844832,"about_ca_system_score_gemma":0.004316776,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000316762,0.0025162254,0.00007327604,0.023356369,0.97092867,0.000029802566,0.000061021798,0.000046926543,0.0029560917],"genre_scores_gemma":[0.00052293215,0.002624857,0.00011865174,0.01980377,0.9526048,0.000047791276,0.00007044648,0.000051065163,0.024155812],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99273336,0.0012982549,0.00085364934,0.0008640971,0.0036401972,0.0006104112],"domain_scores_gemma":[0.9706796,0.0072668404,0.002802155,0.0013159935,0.012704712,0.0052307327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007336872,0.0030636205,0.00390248,0.0041468246,0.0028929985,0.009539992,0.0035053836,0.013815185,0.047600504],"category_scores_gemma":[0.044403907,0.0010538182,0.002556643,0.0015486836,0.00196143,0.0032355154,0.0025335383,0.012467706,0.033790674],"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":[0.00002266631,0.0000089852365,0.000019762385,0.00011178165,0.000011777318,0.00012075856,0.0000054755305,0.000012988972,0.000023463375,0.00012352622,0.9947076,0.0048312526],"study_design_scores_gemma":[0.0000788522,0.000020786867,0.0001561503,0.00039451793,0.00004007213,0.0002607209,0.000025234858,0.00007850158,0.0000782282,0.0008326126,0.9980202,0.000014243289],"about_ca_topic_score_codex":0.0011573326,"about_ca_topic_score_gemma":0.0033159144,"teacher_disagreement_score":0.047600504,"about_ca_system_score_codex":0.0032905529,"about_ca_system_score_gemma":0.003992815,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040034554,0.15313332,0.04710249,0.34143245,0.008604947,0.00013587112,0.00025471195,0.00023923865,0.44509345],"genre_scores_gemma":[0.44427323,0.23124684,0.07818647,0.07695339,0.0115787145,0.0006069266,0.00037954788,0.000715803,0.15605907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98792446,0.0066573597,0.0002867344,0.0008124278,0.0035989499,0.0007199983],"domain_scores_gemma":[0.989869,0.006781633,0.00021805616,0.00060308294,0.0020379794,0.0004902913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019641452,0.0011036703,0.00080745167,0.0028890178,0.004507186,0.01615322,0.0026221967,0.004497265,0.010015007],"category_scores_gemma":[0.011152256,0.00034106604,0.0007353254,0.0037613572,0.03242727,0.016537365,0.0046885535,0.008272681,0.0021839826],"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":[0.000015216316,0.000023954748,0.0004016598,0.00047538342,0.000007979637,0.000057741214,0.0066865175,0.0003139503,0.00017379691,0.8768688,0.030174747,0.08480036],"study_design_scores_gemma":[0.00000445374,0.000030705232,0.0006890619,0.0022300219,0.000010659064,0.00011202581,0.008883283,0.00048947317,0.0004950354,0.45111874,0.5359033,0.000033273205],"about_ca_topic_score_codex":0.022223294,"about_ca_topic_score_gemma":0.024651943,"teacher_disagreement_score":0.022223294,"about_ca_system_score_codex":0.019154686,"about_ca_system_score_gemma":0.01745303,"threshold_uncertainty_score":0.13897759},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015814114,0.012339575,0.119894914,0.019585986,0.01036709,0.100793295,0.019633133,0.0027462575,0.69882566],"genre_scores_gemma":[0.1976913,0.026018813,0.22123115,0.012167859,0.0031720002,0.17589815,0.026044838,0.0026024887,0.33517334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87897927,0.07890467,0.010425511,0.0041594543,0.024502056,0.0030290268],"domain_scores_gemma":[0.8364303,0.06633713,0.006701276,0.020397106,0.06485965,0.005274612],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09751738,0.0012898453,0.0018557204,0.0065331375,0.002656984,0.006199638,0.003276019,0.0019124208,0.116552226],"category_scores_gemma":[0.25190485,0.0005641381,0.0018709743,0.0050175777,0.0017317455,0.004713309,0.0069955764,0.0023823539,0.022338383],"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":[0.0010331555,0.0004153204,0.0022451219,0.0051616877,0.00013995165,0.00008910863,0.002262453,0.0009518904,0.00024800908,0.037136544,0.16935106,0.7809657],"study_design_scores_gemma":[0.00029520594,0.0007177717,0.0032768818,0.009760429,0.00016246496,0.00013054103,0.0019365064,0.0007169233,0.00097394414,0.011223551,0.9707484,0.000057337216],"about_ca_topic_score_codex":0.0030246726,"about_ca_topic_score_gemma":0.0032073641,"teacher_disagreement_score":0.88344777,"about_ca_system_score_codex":0.008323541,"about_ca_system_score_gemma":0.0318275,"threshold_uncertainty_score":0.51572734},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006674039,0.0005116722,0.0014372113,0.0019799718,0.0006657628,0.000068747606,0.00021518825,0.00012452739,0.9943295],"genre_scores_gemma":[0.04666315,0.0023036685,0.0024612697,0.003397796,0.0009029972,0.00017854339,0.0010741872,0.00034283794,0.9426756],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99556243,0.00049743516,0.00010574586,0.0004145153,0.002923395,0.0004964868],"domain_scores_gemma":[0.99612254,0.0005973885,0.00016253104,0.00061438157,0.0018997327,0.00060345116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026176663,0.0010794973,0.00050128537,0.0027749094,0.0021122692,0.007682161,0.0016529812,0.0017111908,0.32727966],"category_scores_gemma":[0.01119702,0.00026750195,0.0007749603,0.0017466064,0.0014531056,0.0046986933,0.0045273355,0.002211641,0.11178347],"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":[0.000118492055,0.00012848827,0.0011179231,0.0003749778,0.00001916957,0.00015642367,0.00041599883,0.00042829182,0.0011200098,0.28698146,0.3372361,0.3719026],"study_design_scores_gemma":[0.000011229099,0.000030166348,0.0009294676,0.000234952,0.0000139036,0.00016166457,0.00037938714,0.00016615386,0.0007243424,0.040424086,0.95691264,0.0000119931765],"about_ca_topic_score_codex":0.0037159296,"about_ca_topic_score_gemma":0.004337291,"teacher_disagreement_score":0.6727203,"about_ca_system_score_codex":0.0030763317,"about_ca_system_score_gemma":0.004761136,"threshold_uncertainty_score":0},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000773313,0.0076339855,0.22044224,0.0042948495,0.00091027725,0.0005470432,0.00027693046,0.00045356792,0.7646679],"genre_scores_gemma":[0.072013155,0.018198906,0.25131246,0.0043804133,0.0016228395,0.0020403233,0.0011261285,0.0006504098,0.64865535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98714393,0.0051898584,0.00060522644,0.0011227962,0.005551106,0.00038698455],"domain_scores_gemma":[0.9921136,0.004236409,0.00028083017,0.0010178379,0.002149858,0.00020143852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010376909,0.0015318131,0.0009929276,0.004937266,0.0014911494,0.007838163,0.002507175,0.0020461504,0.0436516],"category_scores_gemma":[0.018592918,0.0005342191,0.00081090524,0.0031906536,0.0030018373,0.005665753,0.0033019749,0.002426703,0.015798138],"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":[0.000011910273,0.000036116562,0.00010134561,0.00034401767,0.00001672409,0.000025680329,0.00026574743,0.001075467,0.00016808652,0.7354834,0.03959493,0.2228766],"study_design_scores_gemma":[0.00000951509,0.00002014606,0.00020826103,0.0006919584,0.000017898978,0.00009984295,0.00028329183,0.002187465,0.0005637266,0.4905792,0.5053218,0.000017017019],"about_ca_topic_score_codex":0.0023126185,"about_ca_topic_score_gemma":0.0028765614,"teacher_disagreement_score":0.0436516,"about_ca_system_score_codex":0.004872219,"about_ca_system_score_gemma":0.0053141657,"threshold_uncertainty_score":0.14602917},"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":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000704468,0.00017364345,0.0012003747,0.00056904636,0.00030144752,0.00016094613,0.99127215,0.0018826299,0.0037352995],"genre_scores_gemma":[0.0038417417,0.00010825218,0.0044652554,0.00044237048,0.00006482609,0.0005229863,0.98620504,0.00043143533,0.0039180666],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938286,0.00218658,0.0007971046,0.0015381249,0.001097319,0.00055231014],"domain_scores_gemma":[0.9720266,0.011904226,0.0016778117,0.007666633,0.0054080193,0.0013167424],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010956818,0.0020485187,0.0015545787,0.0032651066,0.0011569385,0.0047695534,0.004076165,0.0035169905,0.100961134],"category_scores_gemma":[0.065836474,0.0010445919,0.002289258,0.0043641427,0.0007728825,0.0023563674,0.0027500757,0.0026841394,0.10672419],"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":[0.00016020428,0.00004569938,0.0027757704,0.00049334083,0.000050242434,0.000010125135,0.000025965943,0.0004277436,0.00007419793,0.00061621255,0.9894499,0.005870638],"study_design_scores_gemma":[0.0011628747,0.00006123891,0.006502075,0.0006464282,0.00012815291,0.0000586072,0.00011014639,0.004471599,0.0008189461,0.005164442,0.9808142,0.00006130506],"about_ca_topic_score_codex":0.023868747,"about_ca_topic_score_gemma":0.10052321,"teacher_disagreement_score":0.9890432,"about_ca_system_score_codex":0.0024350188,"about_ca_system_score_gemma":0.005944785,"threshold_uncertainty_score":0.33774865},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1595341,0.18392926,0.13289766,0.15524651,0.0021923047,0.0007762665,0.00020523409,0.00055948144,0.36465922],"genre_scores_gemma":[0.93904173,0.027122516,0.018831942,0.0058700093,0.0011378446,0.00047061773,0.00007755538,0.00019091701,0.007256825],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.808502,0.16211714,0.0060052397,0.0034037302,0.017250285,0.0027216575],"domain_scores_gemma":[0.7666105,0.19420685,0.011380457,0.0074842996,0.01619479,0.004123156],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09693822,0.00075353665,0.001177777,0.008504337,0.0068959016,0.024007443,0.0019687833,0.0032027725,0.009947439],"category_scores_gemma":[0.11724655,0.00059038395,0.0012173263,0.0058774846,0.018954953,0.02124636,0.01581479,0.0036907936,0.0012314152],"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":[0.0003159866,0.0002762011,0.025020724,0.0063862777,0.00045596767,0.0007212414,0.1284071,0.0010830141,0.0009901344,0.23805316,0.01606547,0.5822247],"study_design_scores_gemma":[0.000102487196,0.00054909865,0.038241398,0.025862979,0.00050502963,0.002129945,0.17167749,0.002453585,0.0031272932,0.23340401,0.5215883,0.00035844732],"about_ca_topic_score_codex":0.0038704465,"about_ca_topic_score_gemma":0.0047256546,"teacher_disagreement_score":0.90306175,"about_ca_system_score_codex":0.007844324,"about_ca_system_score_gemma":0.010328922,"threshold_uncertainty_score":0.51266444},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002629204,0.0026428446,0.00009265289,0.04650024,0.9482551,0.000017785233,0.00006515005,0.000070174916,0.002329669],"genre_scores_gemma":[0.00040929296,0.004029338,0.00011404677,0.0726267,0.9028635,0.00003716513,0.000075133845,0.00006717411,0.019777501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964838,0.00055591215,0.0004508298,0.00049337867,0.0017273629,0.0002887648],"domain_scores_gemma":[0.98397416,0.0035809118,0.0009379426,0.00052535423,0.007832,0.0031496189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004434986,0.0027746945,0.002507423,0.0021831694,0.0023810354,0.008049878,0.0033734976,0.011293456,0.053257577],"category_scores_gemma":[0.027482128,0.0009809827,0.0018826006,0.0011558677,0.0013320543,0.0055067562,0.0017992998,0.017927466,0.043445054],"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":[0.000014658788,0.000008616685,0.000020462956,0.00008632597,0.0000053631306,0.000045317385,0.000004443597,0.0000122479,0.00001731319,0.00012040404,0.99440986,0.005254959],"study_design_scores_gemma":[0.000037329843,0.00002070199,0.00016236825,0.00039659024,0.0000177317,0.00019286596,0.000028133069,0.00006113199,0.000055818342,0.00056433346,0.99844813,0.000014829582],"about_ca_topic_score_codex":0.0013666144,"about_ca_topic_score_gemma":0.0035661992,"teacher_disagreement_score":0.053257577,"about_ca_system_score_codex":0.002389502,"about_ca_system_score_gemma":0.0034991563,"threshold_uncertainty_score":0.17816436},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009934859,0.00301481,0.00021689467,0.15160197,0.8315672,0.000059617654,0.00030029129,0.00008976536,0.013050088],"genre_scores_gemma":[0.00284713,0.004210832,0.0011525358,0.31178123,0.46873,0.00016032755,0.00033711398,0.00016039163,0.2106205],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99343747,0.0008682173,0.0006638069,0.00079972256,0.0036053762,0.00062536984],"domain_scores_gemma":[0.9732171,0.006282153,0.0021705034,0.0018235788,0.013740078,0.0027665775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072997636,0.0013344378,0.0017398696,0.00257294,0.0025031131,0.0047568227,0.0044717817,0.012160909,0.09518548],"category_scores_gemma":[0.052755028,0.0007844376,0.0018172044,0.0016092467,0.0013053102,0.0024912946,0.002005491,0.011092013,0.051634096],"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":[0.0000124726175,0.0000056582744,0.0000203563,0.000049510058,0.0000032764513,0.000063406274,0.0000075468733,0.000008066747,0.00003533172,0.00026637208,0.9958527,0.0036753402],"study_design_scores_gemma":[0.000024669707,0.000009483757,0.00020331888,0.00014083272,0.000013986241,0.00013548104,0.000034114917,0.0000461028,0.0001328876,0.00048538524,0.99876237,0.00001123045],"about_ca_topic_score_codex":0.0047309618,"about_ca_topic_score_gemma":0.011823394,"teacher_disagreement_score":0.09518548,"about_ca_system_score_codex":0.0028651566,"about_ca_system_score_gemma":0.0050600753,"threshold_uncertainty_score":0.3184272},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000307139,0.0010773869,0.00029110245,0.10983632,0.8682527,0.00005512384,0.0011596136,0.00015855626,0.018862097],"genre_scores_gemma":[0.0072144247,0.005486106,0.001633904,0.18193175,0.09957079,0.00021600704,0.002226394,0.00090891466,0.7008117],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923499,0.0006212679,0.000993624,0.0007345616,0.004605238,0.0006954693],"domain_scores_gemma":[0.97102374,0.004759273,0.0010029058,0.0010905373,0.020742904,0.00138058],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030867895,0.0011925646,0.0012553153,0.0029348973,0.009612462,0.0059354957,0.0027800235,0.0074935216,0.061733894],"category_scores_gemma":[0.051541883,0.000665298,0.00130957,0.0029555962,0.00295205,0.0021950293,0.0027019074,0.009508126,0.03064669],"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":[0.000006380159,0.0000028473462,0.000035233126,0.000028497709,0.000001348149,0.000073417505,0.000058734055,0.000009599526,0.000010402503,0.0005076629,0.9974132,0.0018527197],"study_design_scores_gemma":[0.000006173472,0.000006501231,0.00033654284,0.00015077827,0.000007892332,0.00007670882,0.0002890508,0.00002853689,0.00005700086,0.0002721009,0.9987531,0.000015555224],"about_ca_topic_score_codex":0.40626037,"about_ca_topic_score_gemma":0.46548232,"teacher_disagreement_score":0.9382661,"about_ca_system_score_codex":0.016999017,"about_ca_system_score_gemma":0.027049705,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028313804,0.0034766626,0.65360147,0.05951067,0.0021057792,0.0021097332,0.0001174562,0.0015191005,0.24924539],"genre_scores_gemma":[0.5129797,0.003763126,0.45671237,0.0075897137,0.00039395687,0.0028197377,0.00014763059,0.0004602777,0.015133477],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92755634,0.057084266,0.002116016,0.0041842656,0.0076766685,0.0013823743],"domain_scores_gemma":[0.85859174,0.10687182,0.0058919545,0.01307802,0.0117282,0.0038381822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054961734,0.0009720641,0.0007081257,0.0031004206,0.003116722,0.0122743035,0.002898102,0.003951586,0.00977844],"category_scores_gemma":[0.12147464,0.000919863,0.0012694873,0.0016519955,0.018919373,0.011043763,0.0081890905,0.006088558,0.0029464175],"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":[0.00018709201,0.00064470083,0.004220283,0.0030607814,0.00017414462,0.00037801752,0.0851341,0.0018272256,0.0016338106,0.43498582,0.028426562,0.43932745],"study_design_scores_gemma":[0.0003919639,0.00064762984,0.0052020485,0.01095725,0.00026203247,0.0008067043,0.03716541,0.009487821,0.005186212,0.63246506,0.29720438,0.0002234892],"about_ca_topic_score_codex":0.0029188653,"about_ca_topic_score_gemma":0.002584362,"teacher_disagreement_score":0.054961734,"about_ca_system_score_codex":0.0055876616,"about_ca_system_score_gemma":0.016577514,"threshold_uncertainty_score":0.29066885},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004127555,0.0010819625,0.08208874,0.0044813803,0.000571326,0.0011108824,0.0013082399,0.00038336025,0.90484643],"genre_scores_gemma":[0.37280005,0.003690448,0.19067217,0.0066269375,0.0018602656,0.0052849264,0.006416604,0.0017900666,0.41085857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9490925,0.016853672,0.0031419925,0.006814062,0.02257441,0.0015234126],"domain_scores_gemma":[0.90984577,0.040753312,0.0031197865,0.018653436,0.026690995,0.00093666953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033582434,0.0015998572,0.0013930877,0.009050626,0.0035424833,0.010522556,0.0026471056,0.0022199475,0.07847872],"category_scores_gemma":[0.15008827,0.00095334864,0.0023291903,0.004276137,0.008603309,0.009898185,0.0075363447,0.0034524144,0.03016193],"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":[0.00010881331,0.000078440265,0.0036549708,0.0006083241,0.000085732936,0.000060164264,0.0017393949,0.00080966664,0.00061723206,0.69279313,0.040489353,0.25895485],"study_design_scores_gemma":[0.000065088825,0.00008289709,0.004797573,0.0014115531,0.00014009757,0.00044599667,0.0017632404,0.0029424597,0.0033464506,0.6447486,0.34018767,0.00006825571],"about_ca_topic_score_codex":0.0066837976,"about_ca_topic_score_gemma":0.0045288056,"teacher_disagreement_score":0.07847872,"about_ca_system_score_codex":0.005912941,"about_ca_system_score_gemma":0.014507641,"threshold_uncertainty_score":0},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30450392,0.0436714,0.058859594,0.10996749,0.0132391,0.008503371,0.1484446,0.0021613482,0.31064913],"genre_scores_gemma":[0.8663146,0.015620229,0.03102688,0.021114778,0.006614065,0.005263972,0.04353595,0.00014074377,0.010368743],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.67632747,0.19941199,0.040624928,0.008961018,0.06842876,0.006245814],"domain_scores_gemma":[0.23242311,0.5130174,0.13274114,0.048417315,0.068253025,0.005148057],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17857316,0.001448254,0.0018366718,0.013427574,0.0009201527,0.0053902552,0.0035652504,0.004035564,0.008862408],"category_scores_gemma":[0.53618014,0.0005988277,0.0032363217,0.011079122,0.0016438649,0.004626915,0.004802302,0.0042910916,0.0013191848],"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":[0.0027193646,0.0013572712,0.2962819,0.011048858,0.0044609355,0.00027444435,0.0018332732,0.00786246,0.0008614597,0.023994694,0.16777928,0.48152596],"study_design_scores_gemma":[0.001580771,0.0053155906,0.5928195,0.015242667,0.009615001,0.0008205826,0.0037584652,0.024338754,0.019248921,0.057849538,0.26891556,0.0004947144],"about_ca_topic_score_codex":0.01202584,"about_ca_topic_score_gemma":0.0077993292,"teacher_disagreement_score":0.82142687,"about_ca_system_score_codex":0.007455924,"about_ca_system_score_gemma":0.012171495,"threshold_uncertainty_score":0.94439644},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079382426,0.014172226,0.0035672917,0.0051484746,0.007915722,0.00021445114,0.0049643484,0.0017117399,0.9615119],"genre_scores_gemma":[0.0019542298,0.0074970387,0.0033390566,0.0022600535,0.0009745121,0.00009122464,0.004889821,0.0005287144,0.9784653],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944466,0.000031181986,0.000032856657,0.000077505705,0.0003785204,0.000035293873],"domain_scores_gemma":[0.9988053,0.00021613998,0.00005854797,0.00012539752,0.0006089579,0.0001856671],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002725683,0.0006762401,0.00083179766,0.0023114372,0.0014784758,0.005761844,0.0014715035,0.0011334561,0.48226565],"category_scores_gemma":[0.0030500104,0.00041846963,0.00058318593,0.0030802637,0.00047666987,0.0031397764,0.0014650653,0.0018430918,0.35667652],"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":[0.000009702333,0.000027356551,0.000050792685,0.000226946,0.0000024064134,0.000066536835,0.00007195726,0.0000893581,0.00015595881,0.0062098694,0.90348345,0.08960571],"study_design_scores_gemma":[0.0000022637375,0.000005138893,0.00013163303,0.00013158056,9.652443e-7,0.000076862256,0.000044321976,0.000031158037,0.00004147962,0.0018467924,0.99768424,0.0000034515472],"about_ca_topic_score_codex":0.001755398,"about_ca_topic_score_gemma":0.0040988196,"teacher_disagreement_score":0.51773435,"about_ca_system_score_codex":0.0010270351,"about_ca_system_score_gemma":0.0017938414,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82091236,0.0027050334,0.0067553003,0.11091245,0.0011074191,0.00065882807,0.00007745359,0.000103050734,0.056768153],"genre_scores_gemma":[0.9858212,0.0007802983,0.0018252506,0.0072335266,0.000121174584,0.00024575499,0.00002088511,0.000059886428,0.0038921544],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8221505,0.14848506,0.0029595536,0.002982477,0.009256777,0.014165692],"domain_scores_gemma":[0.8331199,0.12592398,0.004062996,0.0036820224,0.021003122,0.0122079495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11073343,0.0010428792,0.001148029,0.0024252695,0.057654507,0.0222533,0.003915999,0.0071264673,0.0022297874],"category_scores_gemma":[0.09065994,0.0011643952,0.0009061568,0.003547899,0.024556948,0.009066041,0.02219671,0.018725565,0.0003392151],"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":[0.000054478136,0.000105323685,0.0015443828,0.00010658197,0.0000123937625,0.001551718,0.9799541,0.00011235677,0.00036092135,0.006625353,0.0024976304,0.007074794],"study_design_scores_gemma":[0.000006370946,0.00003475767,0.00082551397,0.0001608807,0.000009398108,0.00019223413,0.98445016,0.000106821084,0.00028980573,0.00050568016,0.013382826,0.00003553757],"about_ca_topic_score_codex":0.124419875,"about_ca_topic_score_gemma":0.1903097,"teacher_disagreement_score":0.124419875,"about_ca_system_score_codex":0.049728498,"about_ca_system_score_gemma":0.046653282,"threshold_uncertainty_score":0.58562136},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023146078,0.11328704,0.0021002854,0.18656226,0.039669495,0.0002920576,0.008385653,0.0009841076,0.64640445],"genre_scores_gemma":[0.001920253,0.010092972,0.00026970886,0.001894051,0.00039407721,0.000020255055,0.00036902147,0.00008226079,0.98495746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99853945,0.000108281514,0.00008612151,0.00025154414,0.0008297945,0.00018484256],"domain_scores_gemma":[0.9962322,0.00033200893,0.00015657092,0.00006770815,0.0024070416,0.0008045332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020095787,0.0007577333,0.00066737644,0.001563109,0.0029833834,0.0054216776,0.0010094123,0.0025487137,0.15683512],"category_scores_gemma":[0.0040834886,0.0007444772,0.00020861479,0.002517763,0.0009381531,0.0026151203,0.0014114737,0.003742157,0.110626504],"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":[0.000006999385,0.0000030282333,0.00010157523,0.000032480908,5.455914e-7,0.000017153377,0.000083775,0.000011599308,0.000032764518,0.000736506,0.98308057,0.015892956],"study_design_scores_gemma":[0.0000021257797,0.0000031866084,0.0005350768,0.00007197832,0.000001023588,0.000026384465,0.00013330528,0.000009599663,0.000045125133,0.00012493145,0.999041,0.0000062863437],"about_ca_topic_score_codex":0.31823075,"about_ca_topic_score_gemma":0.5537018,"teacher_disagreement_score":0.68176925,"about_ca_system_score_codex":0.007016518,"about_ca_system_score_gemma":0.012759356,"threshold_uncertainty_score":0.6327569},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070572976,0.002730723,0.012492853,0.014415365,0.0018266374,0.000028361046,0.00009839916,0.00010586704,0.9675962],"genre_scores_gemma":[0.050262928,0.0028670037,0.0068136025,0.014105751,0.0014881828,0.0001426229,0.00018609906,0.00018756153,0.92394626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782854,0.0006052023,0.00007862638,0.0005176828,0.00077408977,0.00019585293],"domain_scores_gemma":[0.99874276,0.00046314587,0.000060478207,0.00029831709,0.0003507642,0.000084570005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019960238,0.00074838696,0.0006176832,0.0008111715,0.0025381928,0.0065744813,0.0011509412,0.0030815175,0.04459406],"category_scores_gemma":[0.005924918,0.00030435086,0.00033164013,0.00073999277,0.008249246,0.007052858,0.0025930516,0.00523486,0.029970601],"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":[0.000006068443,0.00000802593,0.000046839683,0.00005365589,0.0000032604005,0.000021399559,0.0003688517,0.00012206592,0.000096874035,0.89870435,0.07777934,0.022789128],"study_design_scores_gemma":[0.0000031777738,0.0000064134665,0.00009621443,0.00010359807,0.0000025470845,0.00004840356,0.0002793918,0.00014063535,0.00017007858,0.42052504,0.578617,0.0000075110343],"about_ca_topic_score_codex":0.0031596317,"about_ca_topic_score_gemma":0.0055366373,"teacher_disagreement_score":0.04459406,"about_ca_system_score_codex":0.0026884775,"about_ca_system_score_gemma":0.0026050815,"threshold_uncertainty_score":0.14918196},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017265926,0.009772368,0.00068811834,0.115492836,0.8064581,0.000067364475,0.00053441175,0.00041856867,0.0663955],"genre_scores_gemma":[0.0030029905,0.014837015,0.00093780295,0.16702485,0.38190973,0.0001448694,0.00096998474,0.00058483006,0.43058792],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963309,0.0006082075,0.00039231393,0.00062779716,0.001662689,0.00037812607],"domain_scores_gemma":[0.98298806,0.0025492813,0.0008039906,0.0009828121,0.009260032,0.00341586],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029064447,0.0015272822,0.0011534677,0.0018121524,0.0024728419,0.0091984775,0.0029987097,0.006101762,0.31667987],"category_scores_gemma":[0.028732125,0.0005462403,0.00097076746,0.0012373385,0.001129989,0.0057728495,0.0034534629,0.008306857,0.23466586],"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":[0.000007299489,0.00000604936,0.000026514526,0.00006522849,0.0000016900696,0.000053241194,0.000015678312,0.0000065435624,0.000024756646,0.0004886299,0.9852386,0.014065875],"study_design_scores_gemma":[0.0000032814985,0.0000054397146,0.000051560935,0.00011480682,0.0000017706021,0.00014829659,0.00004090219,0.000009199961,0.000023408385,0.00035123914,0.99924624,0.000003935324],"about_ca_topic_score_codex":0.0010025029,"about_ca_topic_score_gemma":0.0019168896,"teacher_disagreement_score":0.31667987,"about_ca_system_score_codex":0.001826874,"about_ca_system_score_gemma":0.0040228968,"threshold_uncertainty_score":0.9746733},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0154886,0.0010440822,0.014178353,0.007091479,0.00073587755,0.00034844218,0.00013904017,0.00014388593,0.9608301],"genre_scores_gemma":[0.3032663,0.0015061436,0.017334968,0.003968711,0.0001644207,0.0005794484,0.000257049,0.00017855273,0.6727444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941227,0.0020626392,0.00021920947,0.0007473759,0.0020500757,0.0007979863],"domain_scores_gemma":[0.99495536,0.0016665423,0.000285576,0.00082586927,0.0012404106,0.0010262326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005480389,0.0008274675,0.0003873696,0.0014195213,0.006608922,0.007557695,0.0017201998,0.0017758218,0.08098319],"category_scores_gemma":[0.011145737,0.00024283337,0.0006348009,0.0012601856,0.0066539124,0.0038291297,0.00811627,0.0029671479,0.011305714],"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":[0.000104514926,0.00022248448,0.00216059,0.00029816706,0.000015295414,0.00032520352,0.055292055,0.00045876662,0.000771476,0.66123325,0.04577054,0.2333476],"study_design_scores_gemma":[0.000019341265,0.00006264897,0.0012361795,0.00050872983,0.000011080009,0.00020950293,0.023414833,0.00049063965,0.000653413,0.08811939,0.88525164,0.000022596538],"about_ca_topic_score_codex":0.03127622,"about_ca_topic_score_gemma":0.06545865,"teacher_disagreement_score":0.08098319,"about_ca_system_score_codex":0.011583481,"about_ca_system_score_gemma":0.012280462,"threshold_uncertainty_score":0.27091575},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10841964,0.028769672,0.7147638,0.018554365,0.0011207681,0.009697355,0.0051017012,0.0011933405,0.11237924],"genre_scores_gemma":[0.5006114,0.0068712593,0.478494,0.0010947039,0.0002688214,0.008737413,0.0015387882,0.00020776039,0.0021758708],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84990066,0.09806392,0.017260712,0.007054936,0.025493369,0.0022263774],"domain_scores_gemma":[0.7280528,0.20854878,0.019189263,0.015900297,0.025412953,0.0028959452],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.109452255,0.0032146045,0.004170999,0.062619336,0.0038784586,0.026517222,0.0038224782,0.0025461318,0.007273381],"category_scores_gemma":[0.17963435,0.0013031643,0.006971971,0.041465852,0.012062101,0.018060463,0.015895842,0.0046863793,0.00082501495],"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":[0.0005231656,0.00061407336,0.0426362,0.016386447,0.0045711547,0.00036166914,0.03582549,0.014846871,0.0022949756,0.3176623,0.007082377,0.5571952],"study_design_scores_gemma":[0.0003504148,0.0016834113,0.05961732,0.013878779,0.0035551728,0.000723408,0.06056109,0.054100487,0.0026254081,0.7127058,0.0893709,0.0008277972],"about_ca_topic_score_codex":0.0039997385,"about_ca_topic_score_gemma":0.0048312624,"teacher_disagreement_score":0.89054775,"about_ca_system_score_codex":0.01655712,"about_ca_system_score_gemma":0.0125744,"threshold_uncertainty_score":0.57884574},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007735916,0.04560262,0.2866306,0.41965517,0.1409604,0.0013654912,0.0008483457,0.0011073423,0.096094094],"genre_scores_gemma":[0.32221586,0.048459124,0.23693874,0.138262,0.13507822,0.006183249,0.0012206896,0.001850321,0.10979187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9796808,0.013337895,0.0011155941,0.0018278884,0.0034929106,0.0005450025],"domain_scores_gemma":[0.95814323,0.030041298,0.0013034642,0.0019035016,0.0073072575,0.0013011999],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03390663,0.00082870666,0.000853867,0.0016823587,0.0047922484,0.00906915,0.0024084602,0.005038142,0.018594624],"category_scores_gemma":[0.059866205,0.00065851887,0.0011929725,0.0016020813,0.0121386405,0.008194507,0.0057592005,0.010357936,0.003534378],"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":[0.00010225694,0.000082248,0.0004915777,0.0015415937,0.000037592585,0.0002534988,0.031745106,0.00043799033,0.0027376327,0.556896,0.32461256,0.08106198],"study_design_scores_gemma":[0.000016692908,0.00014935745,0.00050411705,0.0016611875,0.000021469283,0.0004041391,0.0074575357,0.0005953294,0.0008911328,0.17236914,0.8158796,0.000050234536],"about_ca_topic_score_codex":0.0012381268,"about_ca_topic_score_gemma":0.0010647988,"teacher_disagreement_score":0.96609336,"about_ca_system_score_codex":0.0036337953,"about_ca_system_score_gemma":0.004362326,"threshold_uncertainty_score":0.17931753},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068151637,0.0004933074,0.001476562,0.0016652556,0.0005907093,0.00006994399,0.00021308805,0.00013587097,0.99467367],"genre_scores_gemma":[0.04485919,0.0021668535,0.0024601552,0.0028767353,0.00076730055,0.00016432448,0.0010269447,0.0003218253,0.94535667],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960692,0.00041766642,0.000088840614,0.00035806355,0.0026351756,0.00043097264],"domain_scores_gemma":[0.99682295,0.00047750215,0.00013615651,0.00050125853,0.0015609446,0.000501173],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022779536,0.0010699715,0.0004920794,0.002799023,0.0019730437,0.0070155477,0.0015729804,0.0015842151,0.3301619],"category_scores_gemma":[0.009352201,0.00026292904,0.0007474804,0.0017452319,0.0012878991,0.0042451313,0.0042163064,0.0019753869,0.11100143],"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":[0.000121460005,0.00012858218,0.0011000728,0.00037186936,0.000019353554,0.00015392982,0.0003643995,0.00049012987,0.0012958471,0.25687462,0.3358969,0.4031828],"study_design_scores_gemma":[0.000011194057,0.000032096923,0.0009493775,0.00021253721,0.000013946608,0.00016113977,0.00033569554,0.00019013161,0.00082894985,0.036699615,0.96055305,0.000012182118],"about_ca_topic_score_codex":0.003699466,"about_ca_topic_score_gemma":0.0043318067,"teacher_disagreement_score":0.6698381,"about_ca_system_score_codex":0.0028844832,"about_ca_system_score_gemma":0.004316776,"threshold_uncertainty_score":0},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007231858,0.122343354,0.0045922413,0.1729249,0.003842767,0.00009636055,0.00088832603,0.00028063185,0.68779945],"genre_scores_gemma":[0.12778977,0.07260505,0.0053683305,0.012390267,0.00079921435,0.00007487756,0.0003893966,0.00033516678,0.7802478],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927765,0.0009803305,0.0002158758,0.00047398361,0.0037610563,0.0017922071],"domain_scores_gemma":[0.9917675,0.0024279007,0.0001827648,0.00023407718,0.0038895567,0.0014980948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049229846,0.0011131719,0.0011531498,0.004204232,0.017118044,0.019512564,0.0022024664,0.005822573,0.020570353],"category_scores_gemma":[0.014096592,0.0011410502,0.0006280916,0.013400135,0.010299655,0.0035778128,0.0025957082,0.006034515,0.002158803],"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":[0.000025148094,0.000029870649,0.00081353734,0.00023020203,0.000017207472,0.00012244689,0.0025572334,0.001474331,0.00008882564,0.44318667,0.44945806,0.10199645],"study_design_scores_gemma":[0.0000069342664,0.0000057717257,0.0020505094,0.0004368885,0.000012895822,0.000027806907,0.0025761751,0.0010787633,0.000090300135,0.0465642,0.94710857,0.00004118956],"about_ca_topic_score_codex":0.995193,"about_ca_topic_score_gemma":0.9972301,"teacher_disagreement_score":0.73771274,"about_ca_system_score_codex":0.26228726,"about_ca_system_score_gemma":0.47716823,"threshold_uncertainty_score":0.8556422},"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":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82342553,0.0020726926,0.04535044,0.03650125,0.001101547,0.06769474,0.0008435785,0.0002965024,0.02271386],"genre_scores_gemma":[0.879847,0.0015588393,0.06005433,0.002615389,0.00016646126,0.051181227,0.00024757377,0.00014781444,0.0041815005],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.44749027,0.49671087,0.014717138,0.005271938,0.02774137,0.008068438],"domain_scores_gemma":[0.29528072,0.56755686,0.020986794,0.015481304,0.08288383,0.017810564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4764518,0.0007828208,0.0014075716,0.006279705,0.016983025,0.012849405,0.005680615,0.0040132655,0.004381563],"category_scores_gemma":[0.535325,0.0013355401,0.0014161026,0.0051128343,0.017162256,0.009689296,0.019092761,0.0059720837,0.0008779395],"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":[0.0002912988,0.0008047944,0.0050270353,0.0027623826,0.000040331466,0.0005292674,0.89071125,0.000514923,0.001049408,0.010224625,0.0056469725,0.082397826],"study_design_scores_gemma":[0.0002852306,0.0014765675,0.007983823,0.0038865434,0.000068846064,0.0002479502,0.9206704,0.0010442559,0.0019655533,0.006132001,0.056037903,0.00020106102],"about_ca_topic_score_codex":0.006510315,"about_ca_topic_score_gemma":0.008372647,"teacher_disagreement_score":0.5235482,"about_ca_system_score_codex":0.035268232,"about_ca_system_score_gemma":0.07674821,"threshold_uncertainty_score":0.64562815},"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":"other","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017570002,0.002821864,0.15797701,0.050202817,0.017191932,0.09256175,0.026534833,0.013205128,0.6219346],"genre_scores_gemma":[0.03279763,0.0012060987,0.08514455,0.009249305,0.0036882127,0.039208937,0.013288359,0.0022820928,0.81313485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97872204,0.009397648,0.0013894386,0.0015226889,0.007300412,0.0016676738],"domain_scores_gemma":[0.97234255,0.0032147486,0.0010105841,0.0024809854,0.015018011,0.005933072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036722235,0.0010801192,0.0007898186,0.0025934672,0.0027474784,0.0063783857,0.0022401593,0.003501252,0.13280465],"category_scores_gemma":[0.021279292,0.0010115317,0.00074521184,0.0013221835,0.0017227622,0.0022803522,0.0055356342,0.0038986688,0.067148134],"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":[0.0006643312,0.0010807111,0.0014001515,0.001068257,0.000014920818,0.00011764674,0.00060416723,0.00039240217,0.0031465772,0.02378706,0.73247355,0.23525025],"study_design_scores_gemma":[0.00024318039,0.000608652,0.003968357,0.00039321897,0.000010004952,0.000096673946,0.0003354873,0.00035091556,0.0024619538,0.0045774025,0.9869103,0.00004384678],"about_ca_topic_score_codex":0.001990349,"about_ca_topic_score_gemma":0.0042395573,"teacher_disagreement_score":0.13280465,"about_ca_system_score_codex":0.002989628,"about_ca_system_score_gemma":0.01573683,"threshold_uncertainty_score":0.4442758},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001488737,0.143501,0.0144290505,0.09204927,0.017942272,0.0015064795,0.0017054931,0.00033912878,0.7270386],"genre_scores_gemma":[0.027419683,0.20767574,0.07069766,0.020983396,0.0032988873,0.0017708583,0.002749061,0.0002980059,0.6651067],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986681,0.0005442954,0.00011794349,0.000096721866,0.0004993859,0.0000735307],"domain_scores_gemma":[0.9976828,0.0010650308,0.00016129714,0.00006290038,0.00076404534,0.00026391385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003465669,0.00064195093,0.0004354728,0.0015537062,0.0010324185,0.004415472,0.0007469737,0.0023547502,0.01638331],"category_scores_gemma":[0.004915849,0.00040961528,0.00020835001,0.0019508185,0.00088199304,0.002520182,0.0016610024,0.003474582,0.0066615692],"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":[0.0000129686905,0.000047112575,0.00019926559,0.0012864947,0.0000043710206,0.00007055384,0.0005186433,0.00063300686,0.0002439684,0.09008561,0.71666425,0.19023374],"study_design_scores_gemma":[0.0000042503757,0.000015708862,0.00041167563,0.0026184581,0.000002665096,0.00007947396,0.00023882637,0.0002581137,0.00015663302,0.012706335,0.98349935,0.000008546724],"about_ca_topic_score_codex":0.007001886,"about_ca_topic_score_gemma":0.014347485,"teacher_disagreement_score":0.01638331,"about_ca_system_score_codex":0.004098763,"about_ca_system_score_gemma":0.012740106,"threshold_uncertainty_score":0.054807663},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004598427,0.0011328664,0.07972357,0.004908723,0.0006129421,0.0011847765,0.0014539289,0.0003728557,0.90601194],"genre_scores_gemma":[0.4183108,0.0038294813,0.18563335,0.0070371963,0.002009769,0.005953996,0.007053462,0.0018256176,0.3683463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.942685,0.01925157,0.0036452145,0.0076311314,0.025108727,0.001678388],"domain_scores_gemma":[0.8907772,0.05077046,0.0037747866,0.022187054,0.031406123,0.001084393],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03819046,0.0016247319,0.0014307036,0.009223042,0.0036148846,0.010960689,0.0026864405,0.0022530004,0.07776229],"category_scores_gemma":[0.17589273,0.0009620022,0.0024424188,0.0044636037,0.008994566,0.010549274,0.007767883,0.0035845407,0.028463472],"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":[0.000114959184,0.00008451705,0.0043607154,0.0006639766,0.00009741109,0.000058903344,0.0019419042,0.0008094783,0.0005505935,0.69888127,0.040340062,0.25209624],"study_design_scores_gemma":[0.0000726344,0.000090189526,0.00570646,0.0016076664,0.0001615695,0.00042823885,0.002009123,0.0029585874,0.0030797876,0.66312873,0.32068497,0.0000719575],"about_ca_topic_score_codex":0.006655347,"about_ca_topic_score_gemma":0.004541412,"teacher_disagreement_score":0.9222377,"about_ca_system_score_codex":0.0061916374,"about_ca_system_score_gemma":0.015302696,"threshold_uncertainty_score":0},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025166166,0.026012428,0.052531052,0.88628185,0.008720283,0.001158994,0.00019197508,0.00022505052,0.02236178],"genre_scores_gemma":[0.17076883,0.06416796,0.5668944,0.13079198,0.009841235,0.01747661,0.00090579473,0.0008632939,0.03828987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55262125,0.3772954,0.020621095,0.008447121,0.03428713,0.0067280577],"domain_scores_gemma":[0.26747134,0.4864927,0.016418902,0.03246061,0.17525262,0.021903869],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4192978,0.0019411867,0.0037850365,0.007529147,0.01595522,0.026140345,0.007178228,0.01943042,0.026574662],"category_scores_gemma":[0.4979838,0.0016675243,0.0042244885,0.0065349205,0.029245446,0.05522487,0.017809527,0.01882329,0.008563567],"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":[0.0007282373,0.0003572092,0.001961726,0.009231037,0.00018723267,0.0007547845,0.08073786,0.0013341206,0.0024037797,0.4228041,0.18201853,0.29748145],"study_design_scores_gemma":[0.00022265765,0.00023202729,0.0013449633,0.013475144,0.00019348171,0.00048251444,0.11316793,0.001067521,0.0011581954,0.23559387,0.63280547,0.00025616642],"about_ca_topic_score_codex":0.027616888,"about_ca_topic_score_gemma":0.02539855,"teacher_disagreement_score":0.5807022,"about_ca_system_score_codex":0.02010819,"about_ca_system_score_gemma":0.09134881,"threshold_uncertainty_score":0.71610916},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9858774,0.00054013345,0.00019961777,0.001299507,0.000011288611,0.000048758124,0.00015091166,0.00000505747,0.011867279],"genre_scores_gemma":[0.9987472,0.00021983575,0.0001041516,0.00010187933,0.0000014538294,0.000008237613,0.000041368083,0.000002344189,0.00077358575],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99416614,0.0010688842,0.00022472179,0.00043094458,0.0016455454,0.0024637342],"domain_scores_gemma":[0.9858068,0.0035879884,0.0019598715,0.0005731689,0.004783004,0.0032892185],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0038171497,0.00015939602,0.00046349075,0.0020979713,0.01520095,0.0044032936,0.0011838964,0.0006298384,0.0017049408],"category_scores_gemma":[0.014500445,0.00027913027,0.00028171373,0.007129346,0.007188252,0.0011156566,0.0033725246,0.0012981324,0.000065496984],"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":true,"study_design_scores_codex":[0.00033623053,0.00017285907,0.44910517,0.00029971343,0.00006963753,0.0011450322,0.46442255,0.0012363965,0.0012147183,0.028896758,0.0033126932,0.049788214],"study_design_scores_gemma":[0.000019250487,0.000056789966,0.59319043,0.0002217253,0.00004093917,0.00014572906,0.38201213,0.0008554744,0.00035224707,0.0011534374,0.021884808,0.00006709929],"about_ca_topic_score_codex":0.9967032,"about_ca_topic_score_gemma":0.99872154,"teacher_disagreement_score":0.984799,"about_ca_system_score_codex":0.15282546,"about_ca_system_score_gemma":0.20149714,"threshold_uncertainty_score":0.98260236},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3370207,0.0010674872,0.00070628466,0.00076296856,0.0001333035,0.0011069481,0.5830452,0.00015667286,0.07600042],"genre_scores_gemma":[0.70134467,0.0036349294,0.002202858,0.00062267465,0.00008356567,0.0010306388,0.21078263,0.00010188263,0.08019617],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993705,0.00003148133,0.000034643337,0.00007025429,0.000267376,0.0002257989],"domain_scores_gemma":[0.99782556,0.000052191117,0.00022777064,0.000052304524,0.0014239834,0.00041822976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028827728,0.000353411,0.0003612264,0.0020713056,0.0027697878,0.001083791,0.0009201374,0.00020726303,0.008234065],"category_scores_gemma":[0.0017400675,0.00031336898,0.00035502258,0.005773736,0.00035708383,0.00043902776,0.0006477889,0.0005815795,0.0022660044],"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":[0.00015623061,0.00016049902,0.80511117,0.00035125818,0.000066210145,0.000329639,0.002070988,0.00051897694,0.00053485186,0.0005194295,0.16378224,0.026398499],"study_design_scores_gemma":[0.000019080446,0.00003496503,0.96792674,0.00014339296,0.000021370144,0.00009222755,0.0029649327,0.00015192997,0.00019793099,0.000033336637,0.028399656,0.000014365857],"about_ca_topic_score_codex":0.9914614,"about_ca_topic_score_gemma":0.9961104,"teacher_disagreement_score":0.011381683,"about_ca_system_score_codex":0.011381683,"about_ca_system_score_gemma":0.03894324,"threshold_uncertainty_score":0.08258027},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14498842,0.012413984,0.31282339,0.12870573,0.0005786783,0.00065535767,0.00004573797,0.00015132569,0.39963743],"genre_scores_gemma":[0.9542293,0.0024303573,0.036226917,0.0024492883,0.00006750049,0.00029409764,0.000010356592,0.00004629045,0.0042459997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9534067,0.039169002,0.0011096464,0.0014065214,0.0032365255,0.0016715461],"domain_scores_gemma":[0.96173704,0.026747296,0.0030330871,0.0024203474,0.0049030473,0.0011592051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.063421294,0.00069144496,0.00063578604,0.005040349,0.008657922,0.017203609,0.0019135097,0.002848372,0.0031394898],"category_scores_gemma":[0.039438255,0.0005077822,0.00046138393,0.0033179575,0.048504166,0.017228635,0.015462501,0.0062043993,0.00028870825],"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":[0.00002049405,0.000031069732,0.00079346116,0.00016358202,0.000007773087,0.000086374064,0.04340147,0.00032908618,0.00017367507,0.93450207,0.0008001955,0.019690793],"study_design_scores_gemma":[0.000048211292,0.00008828009,0.001706736,0.0030178244,0.000048672802,0.0003855015,0.137583,0.0045519318,0.0017334064,0.7534108,0.09737368,0.00005194541],"about_ca_topic_score_codex":0.00528395,"about_ca_topic_score_gemma":0.0063741803,"teacher_disagreement_score":0.063421294,"about_ca_system_score_codex":0.014795622,"about_ca_system_score_gemma":0.015916165,"threshold_uncertainty_score":0.33540785},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010231397,0.00028075124,0.00004453426,0.00022750592,0.00001706716,0.000023131759,0.99743986,0.00006075987,0.00088320865],"genre_scores_gemma":[0.00968037,0.0006978256,0.00040961558,0.00017180592,0.000017675835,0.00020418811,0.98574847,0.000050762057,0.0030192344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975363,0.00033709285,0.000315415,0.00039937612,0.00087353715,0.00053833803],"domain_scores_gemma":[0.9864038,0.0027300634,0.0013644453,0.0014517243,0.006949138,0.0011007177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020843092,0.0013287334,0.0015591623,0.0056350054,0.0012808522,0.0026110155,0.0031070448,0.0017283594,0.022293517],"category_scores_gemma":[0.018758893,0.000683151,0.002034396,0.02365393,0.0005879312,0.0006857102,0.0014515981,0.002152112,0.0063508805],"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":[0.00022147967,0.00004441497,0.010850411,0.0009223323,0.00018950125,0.00003543016,0.00006779822,0.0024976062,0.000027692473,0.0013011815,0.97767067,0.006171362],"study_design_scores_gemma":[0.0011070698,0.000047684527,0.15888564,0.0021605247,0.00046040997,0.00006291981,0.000519417,0.0048804856,0.00044690372,0.0023143264,0.82899225,0.00012234147],"about_ca_topic_score_codex":0.97992146,"about_ca_topic_score_gemma":0.9818081,"teacher_disagreement_score":0.9729628,"about_ca_system_score_codex":0.027037194,"about_ca_system_score_gemma":0.071969844,"threshold_uncertainty_score":0.1961695},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008178888,0.00485936,0.63678515,0.10540906,0.0012160559,0.0045510754,0.0006681165,0.0012803501,0.23705196],"genre_scores_gemma":[0.1787495,0.0039056835,0.7803867,0.004043834,0.00067484257,0.0064637456,0.000549307,0.0006285787,0.024597852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.7488233,0.20820351,0.009970479,0.01278932,0.016906433,0.0033070662],"domain_scores_gemma":[0.62813497,0.29335636,0.014703629,0.026830507,0.025226569,0.011747959],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2112489,0.0022516467,0.0018522808,0.0347003,0.011804668,0.040230926,0.008829455,0.008136002,0.032766912],"category_scores_gemma":[0.2555482,0.002288241,0.0027403086,0.023283081,0.018451769,0.04634819,0.032165885,0.008175342,0.004426579],"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":[0.00020194553,0.0002127227,0.004220537,0.0019971724,0.00044191108,0.00090878137,0.037793785,0.0033924563,0.0013742659,0.67787564,0.02269349,0.24888736],"study_design_scores_gemma":[0.0001079357,0.00020079802,0.001185733,0.0031490598,0.00025703455,0.00035299934,0.019437533,0.0075689848,0.0008447074,0.6243613,0.34240022,0.00013367055],"about_ca_topic_score_codex":0.006803635,"about_ca_topic_score_gemma":0.013319814,"teacher_disagreement_score":0.7887511,"about_ca_system_score_codex":0.023017654,"about_ca_system_score_gemma":0.038249735,"threshold_uncertainty_score":0.9726705},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8175352,0.0015692109,0.07589044,0.02933972,0.00078909314,0.04609401,0.0005537929,0.00075653597,0.027472002],"genre_scores_gemma":[0.8285161,0.0006091969,0.14905633,0.0018405366,0.000113135255,0.016516855,0.0003372776,0.00020866367,0.0028019515],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.62522286,0.32045275,0.012627042,0.004041854,0.02732638,0.010329126],"domain_scores_gemma":[0.55107707,0.28068474,0.010555962,0.028001856,0.10875308,0.020927235],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34144175,0.0013776887,0.0015722585,0.0015572425,0.007664184,0.011489511,0.00998159,0.0042579314,0.0048885085],"category_scores_gemma":[0.37289605,0.0015077752,0.0012852884,0.0016257694,0.005457147,0.008984932,0.007464928,0.0067562503,0.0009883911],"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":[0.00563074,0.052957352,0.058272112,0.008224814,0.0005451003,0.005344516,0.17943949,0.026687177,0.0120648155,0.022489639,0.02612405,0.6022203],"study_design_scores_gemma":[0.009465878,0.13207628,0.077771336,0.015643131,0.0007363808,0.003296119,0.46426755,0.049483504,0.031352226,0.02088416,0.19373907,0.0012843811],"about_ca_topic_score_codex":0.020185366,"about_ca_topic_score_gemma":0.032229457,"teacher_disagreement_score":0.34144175,"about_ca_system_score_codex":0.024011713,"about_ca_system_score_gemma":0.053463686,"threshold_uncertainty_score":0.8121196},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018662872,0.0032047124,0.033522673,0.019199727,0.0021974933,0.00044301667,0.00021187421,0.0004940846,0.93886024],"genre_scores_gemma":[0.14171393,0.00752722,0.053403303,0.015022022,0.001654657,0.0016127285,0.0008397512,0.0006832011,0.7775432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9735206,0.0133325495,0.0014143838,0.004268776,0.0056502316,0.0018134686],"domain_scores_gemma":[0.9858095,0.004437879,0.00091381633,0.0039044826,0.0025867436,0.0023475618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010300879,0.0010585932,0.00084060576,0.0020467658,0.0076659727,0.020361504,0.004073311,0.0058198413,0.10258191],"category_scores_gemma":[0.023679977,0.0005738323,0.00095758535,0.0028709138,0.011763206,0.0150269745,0.021515738,0.0055463677,0.04641755],"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":[0.00003185559,0.000066203764,0.00056920736,0.00040310752,0.000025453939,0.00024104938,0.012990941,0.00035336855,0.00026060807,0.68473583,0.17468414,0.12563823],"study_design_scores_gemma":[0.000006748688,0.000016284974,0.00013212742,0.0002941532,0.0000038404046,0.00014510639,0.0021229314,0.00014657874,0.00007134751,0.06004641,0.9370043,0.000010114396],"about_ca_topic_score_codex":0.002757119,"about_ca_topic_score_gemma":0.003295162,"teacher_disagreement_score":0.10258191,"about_ca_system_score_codex":0.0059840446,"about_ca_system_score_gemma":0.013514071,"threshold_uncertainty_score":0.3431707},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029175982,0.39338177,0.009939451,0.4534696,0.030516382,0.003297828,0.0021062254,0.00021856408,0.07789421],"genre_scores_gemma":[0.18194294,0.5715484,0.044343635,0.0307902,0.020057552,0.0036205687,0.0030101507,0.00027544633,0.14441106],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918168,0.0032582039,0.00049263507,0.00024525909,0.003667899,0.00051921996],"domain_scores_gemma":[0.9784666,0.005253486,0.0010979397,0.0003048014,0.010774561,0.004102625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026967965,0.00072415674,0.0014568043,0.0022680676,0.001680572,0.005515822,0.0009942439,0.0018723105,0.016479919],"category_scores_gemma":[0.024590762,0.0004906509,0.00047927734,0.0022772136,0.0016391886,0.0013756664,0.0021982295,0.00256245,0.0024436205],"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":[0.0006283141,0.00057092507,0.0051727374,0.003911868,0.00007720285,0.00012578961,0.0022355968,0.00025283924,0.0012774827,0.0024067294,0.45980474,0.5235358],"study_design_scores_gemma":[0.0007544753,0.0011257898,0.18172736,0.0153312655,0.0003089977,0.00030112115,0.006027077,0.0006957924,0.0023105566,0.008519829,0.7826591,0.00023857746],"about_ca_topic_score_codex":0.11290673,"about_ca_topic_score_gemma":0.46895322,"teacher_disagreement_score":0.88709325,"about_ca_system_score_codex":0.012069711,"about_ca_system_score_gemma":0.034883574,"threshold_uncertainty_score":0.22449905},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008635695,0.008661931,0.24691781,0.005153025,0.0010594522,0.00060747325,0.0003627115,0.00052764354,0.7358463],"genre_scores_gemma":[0.08435329,0.020260282,0.28108275,0.0049986863,0.0020200792,0.0024020856,0.0014924421,0.00081940216,0.60257095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98432344,0.0067435503,0.0007675614,0.0013543244,0.006340555,0.00047050972],"domain_scores_gemma":[0.98906577,0.006063579,0.0003780869,0.0014081266,0.0028176194,0.00026684403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0129902605,0.0016800531,0.0010727476,0.0053256466,0.0015594065,0.008669307,0.002676448,0.0022320237,0.04523471],"category_scores_gemma":[0.024253067,0.00056636747,0.000918264,0.0035038881,0.003129589,0.0062369187,0.0035854385,0.002618489,0.0166822],"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":[0.000013643451,0.000039662416,0.00011648808,0.00040148644,0.00002064708,0.000025954652,0.0002683444,0.0011221129,0.0001628476,0.74264425,0.039448485,0.21573609],"study_design_scores_gemma":[0.000010981487,0.000022186854,0.00023299648,0.00079735613,0.000022021753,0.00009941325,0.00029547044,0.0023930424,0.0005795403,0.52214384,0.47338462,0.00001850199],"about_ca_topic_score_codex":0.0022254887,"about_ca_topic_score_gemma":0.0026432967,"teacher_disagreement_score":0.04523471,"about_ca_system_score_codex":0.0051605143,"about_ca_system_score_gemma":0.005637066,"threshold_uncertainty_score":0.15132517},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043801633,0.0030704646,0.010680102,0.017560415,0.0020288,0.0001953505,0.00041067065,0.00030797053,0.96136606],"genre_scores_gemma":[0.1251278,0.0077097765,0.014548877,0.01275038,0.0008994308,0.000556962,0.0011698208,0.00043394323,0.8368031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947212,0.0016806372,0.00024133749,0.00076960225,0.0020601773,0.00052704936],"domain_scores_gemma":[0.9964574,0.00079147,0.00024154808,0.00051145145,0.001291177,0.00070693396],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003297781,0.0006201161,0.00042955476,0.0012880297,0.0026936324,0.007712514,0.0011663118,0.0021160024,0.12681068],"category_scores_gemma":[0.008576029,0.00029811502,0.000589497,0.0011715887,0.0034762167,0.005669494,0.0060264827,0.0027405887,0.037056595],"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":[0.00009261588,0.00011875726,0.0019814465,0.00051492394,0.000019567302,0.00023922948,0.0066792783,0.00017909287,0.0011147126,0.44059834,0.23313713,0.315325],"study_design_scores_gemma":[0.0000083811265,0.00002315697,0.0009590182,0.0002783344,0.0000039207894,0.00015396143,0.0011814133,0.00005831002,0.000261842,0.019630233,0.97743076,0.000010589948],"about_ca_topic_score_codex":0.0038174812,"about_ca_topic_score_gemma":0.005504597,"teacher_disagreement_score":0.87318933,"about_ca_system_score_codex":0.0038120775,"about_ca_system_score_gemma":0.006434239,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027110237,0.023873983,0.0073804497,0.24056669,0.011153455,0.0001304425,0.00010307018,0.00015691301,0.713924],"genre_scores_gemma":[0.122872755,0.027419027,0.016127113,0.13226849,0.0054301233,0.00047995106,0.00015832798,0.00076389086,0.6944804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99538463,0.0025333283,0.000127223,0.00042596474,0.0011524587,0.00037645138],"domain_scores_gemma":[0.99615675,0.0026014415,0.00011947086,0.000207808,0.0005637027,0.0003508488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005183338,0.0006961072,0.0006014451,0.0009461038,0.005449693,0.013676962,0.0013989107,0.004719946,0.01625913],"category_scores_gemma":[0.012902758,0.00040447645,0.0003810036,0.0009121139,0.0188577,0.017863264,0.0057797064,0.012806707,0.005229571],"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":[0.000012115454,0.000018542862,0.00025432822,0.00008769722,0.000003409531,0.00014090442,0.01478756,0.0001002278,0.000099397665,0.6918249,0.2536241,0.039046813],"study_design_scores_gemma":[0.0000037125951,0.000011934142,0.00015642428,0.00036839113,0.0000027771684,0.000092812945,0.008100626,0.00008038352,0.00008729918,0.11592761,0.8751569,0.000011130518],"about_ca_topic_score_codex":0.008879236,"about_ca_topic_score_gemma":0.022073478,"teacher_disagreement_score":0.01625913,"about_ca_system_score_codex":0.0064265435,"about_ca_system_score_gemma":0.0065063126,"threshold_uncertainty_score":0.05439222},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03918187,0.00038540366,0.8470966,0.0013835746,0.00030896004,0.0013918732,0.013901546,0.010281986,0.08606821],"genre_scores_gemma":[0.21977964,0.0006804439,0.75364596,0.00013419644,0.000060277576,0.0021827554,0.010610721,0.0012663645,0.011639547],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983968,0.00061787106,0.000095501,0.00029438437,0.0004952134,0.0001002222],"domain_scores_gemma":[0.99603796,0.0014291707,0.00033489784,0.0007956221,0.0011916652,0.00021063449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002549349,0.0011413618,0.00049065176,0.0055532237,0.00091782364,0.0032438969,0.0011840194,0.0007208923,0.011939635],"category_scores_gemma":[0.008821264,0.00041087577,0.0008257035,0.004709253,0.0008547853,0.0040093833,0.0029320843,0.0010803354,0.002592736],"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":[0.0005570503,0.0005446316,0.023851002,0.0021189095,0.0002045626,0.0004598368,0.014036318,0.02291471,0.007067762,0.06967193,0.050021116,0.8085522],"study_design_scores_gemma":[0.00030874927,0.000689237,0.05123836,0.0016800202,0.00039186465,0.0008028954,0.018294105,0.103041425,0.024676388,0.23243682,0.56596696,0.00047321347],"about_ca_topic_score_codex":0.006920676,"about_ca_topic_score_gemma":0.007750133,"teacher_disagreement_score":0.011939635,"about_ca_system_score_codex":0.0006819701,"about_ca_system_score_gemma":0.0022499487,"threshold_uncertainty_score":0.039942086},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031016325,0.0013201217,0.0027487264,0.0006579709,0.0002135422,0.9909067,0.0028815444,0.00007347293,0.00088775635],"genre_scores_gemma":[0.00025490831,0.001130381,0.0063350974,0.00015051273,0.000020209254,0.9914076,0.00038729145,0.0000069827,0.0003069464],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9076813,0.04338465,0.033091098,0.0043456424,0.008516509,0.00298088],"domain_scores_gemma":[0.8833157,0.052504487,0.01446072,0.010145436,0.035542462,0.0040311143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18117648,0.004332586,0.010310597,0.02355461,0.007913302,0.009747425,0.005959699,0.010073963,0.057539713],"category_scores_gemma":[0.15321366,0.006392414,0.012019909,0.022734607,0.0071882564,0.009378097,0.009791682,0.0098739145,0.016536007],"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":[0.004234589,0.0008310309,0.0013012287,0.7257163,0.0011791433,0.001894025,0.015879255,0.002508862,0.0037782886,0.025118755,0.084445156,0.1331134],"study_design_scores_gemma":[0.008046078,0.001204413,0.0037925674,0.6127471,0.0022753635,0.0007504913,0.0091005955,0.001251302,0.002324653,0.01744713,0.3405068,0.00055347994],"about_ca_topic_score_codex":0.008312924,"about_ca_topic_score_gemma":0.018203437,"teacher_disagreement_score":0.18117648,"about_ca_system_score_codex":0.01844828,"about_ca_system_score_gemma":0.132062,"threshold_uncertainty_score":0.9581643},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045750577,0.061484855,0.23486108,0.42774796,0.017129524,0.004512075,0.00489161,0.00067771,0.20294465],"genre_scores_gemma":[0.700106,0.0134334285,0.13249852,0.1296525,0.006752565,0.0065773693,0.003972421,0.00042802963,0.0065790885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.4905263,0.3318523,0.05485462,0.023570735,0.09243135,0.0067646797],"domain_scores_gemma":[0.1253491,0.73616666,0.037905414,0.039130095,0.05931368,0.0021350263],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50058985,0.000942678,0.00214436,0.0061812764,0.002724393,0.012249054,0.0059123356,0.008595277,0.015168819],"category_scores_gemma":[0.79728585,0.00086069526,0.00602988,0.0055248644,0.014981984,0.009435291,0.007352349,0.011014501,0.0040836534],"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":[0.003476276,0.0007998012,0.04788291,0.029666841,0.0058971033,0.00028346697,0.010604921,0.0015424029,0.001216498,0.34858093,0.07703574,0.47301307],"study_design_scores_gemma":[0.001981385,0.0019171314,0.0631168,0.065781526,0.0076336768,0.0010674861,0.009015598,0.0075382977,0.013649523,0.49633986,0.33121043,0.0007483833],"about_ca_topic_score_codex":0.0035857158,"about_ca_topic_score_gemma":0.00330117,"teacher_disagreement_score":0.49941015,"about_ca_system_score_codex":0.0058805225,"about_ca_system_score_gemma":0.014200775,"threshold_uncertainty_score":0.61586165},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04515564,0.011378516,0.010115138,0.5697102,0.0011704188,0.00014669249,0.00057375967,0.00018760162,0.36156204],"genre_scores_gemma":[0.9089336,0.006069394,0.012945262,0.043822795,0.0004377142,0.0002684419,0.00024448324,0.00020844738,0.027069792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8842535,0.034587074,0.003224847,0.005504261,0.06300018,0.009430151],"domain_scores_gemma":[0.7817686,0.119859055,0.005481971,0.009664777,0.07307294,0.010152627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08652501,0.0007029277,0.0012344097,0.008019046,0.036799047,0.038859356,0.0056860363,0.0068001044,0.0065851533],"category_scores_gemma":[0.12351967,0.0009895477,0.0008000081,0.009976282,0.087189116,0.008967477,0.012310662,0.0129338885,0.00048035264],"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":[0.00003584979,0.000028803148,0.0031512785,0.00015306642,0.000025633568,0.000101717036,0.026775995,0.0007513016,0.00019179376,0.8771076,0.05201838,0.039658625],"study_design_scores_gemma":[0.000034836925,0.000034678054,0.017261945,0.0022263413,0.000093892115,0.000090400965,0.082761995,0.0021970088,0.0009939675,0.21421744,0.67970526,0.0003821965],"about_ca_topic_score_codex":0.98376554,"about_ca_topic_score_gemma":0.9871317,"teacher_disagreement_score":0.2567796,"about_ca_system_score_codex":0.2567796,"about_ca_system_score_gemma":0.379628,"threshold_uncertainty_score":0.8620303},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26334918,0.01865458,0.3143885,0.07275997,0.0008916095,0.017629987,0.011764825,0.0009249247,0.29963642],"genre_scores_gemma":[0.74067247,0.0044831135,0.23819108,0.002834,0.000093011055,0.0072939033,0.0019159662,0.00018018372,0.004336367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.7460214,0.16829829,0.01541625,0.0075898124,0.053129032,0.009545248],"domain_scores_gemma":[0.68916,0.15754199,0.01049699,0.015316501,0.11884077,0.008643713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1989412,0.0009543302,0.0023753457,0.026179714,0.022922114,0.023743311,0.0047915983,0.0020213884,0.0019389032],"category_scores_gemma":[0.24973334,0.0010835712,0.0015163912,0.044759,0.015202013,0.0069809337,0.015068205,0.005042157,0.0002140283],"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":[0.0002577995,0.0004882005,0.10647863,0.0032182555,0.0011316009,0.0006263171,0.09151389,0.012060745,0.0012567558,0.4354192,0.018761842,0.32878676],"study_design_scores_gemma":[0.00022775317,0.00070689514,0.43774304,0.012673162,0.0010756282,0.00028449064,0.13384676,0.041853394,0.003697585,0.18636234,0.1805659,0.000963154],"about_ca_topic_score_codex":0.9867335,"about_ca_topic_score_gemma":0.98811483,"teacher_disagreement_score":0.25571454,"about_ca_system_score_codex":0.25571454,"about_ca_system_score_gemma":0.44786495,"threshold_uncertainty_score":0.9878481},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21378636,0.002669601,0.017838301,0.11782036,0.0008285416,0.00025840482,0.00010071951,0.00022046274,0.64647716],"genre_scores_gemma":[0.96040404,0.0007330792,0.0026646026,0.007095189,0.00016338547,0.000110458976,0.000030106648,0.00004656521,0.028752511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99228656,0.0029493514,0.00014623103,0.0004027619,0.0017359097,0.0024792214],"domain_scores_gemma":[0.9870502,0.0026281865,0.0010247319,0.0010813029,0.002222266,0.005993291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008103053,0.00048797944,0.0005325995,0.0033350745,0.011339674,0.011841822,0.0013823312,0.0022357067,0.022844367],"category_scores_gemma":[0.023789307,0.0002782638,0.00031763685,0.0020721368,0.013316869,0.009391268,0.026359538,0.0036175684,0.0015902907],"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":[0.0001736745,0.00037971782,0.0334511,0.00030411224,0.00011891524,0.00056155113,0.04019183,0.0008634804,0.0015006942,0.61311305,0.056939863,0.25240216],"study_design_scores_gemma":[0.000118847034,0.000664958,0.032951795,0.0019425481,0.000107040745,0.00035219023,0.101605505,0.0019316633,0.0015414639,0.27476037,0.58394253,0.000080987054],"about_ca_topic_score_codex":0.049150202,"about_ca_topic_score_gemma":0.101656616,"teacher_disagreement_score":0.049150202,"about_ca_system_score_codex":0.007730712,"about_ca_system_score_gemma":0.021099491,"threshold_uncertainty_score":0.09772825},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082047775,0.65375954,0.033182632,0.14875449,0.005188043,0.0011298778,0.0015312913,0.0002688488,0.07413758],"genre_scores_gemma":[0.7557341,0.18671602,0.035177674,0.01707415,0.00090707064,0.0006457539,0.0009493602,0.00014473598,0.002651299],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8235202,0.09412472,0.01029701,0.005631123,0.062428813,0.003998201],"domain_scores_gemma":[0.46050492,0.17010182,0.023880359,0.015580055,0.323037,0.0068958895],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28593263,0.00094832934,0.0019017914,0.008847986,0.005133261,0.014955303,0.0053443713,0.0017703031,0.0014285967],"category_scores_gemma":[0.39598992,0.0005872801,0.0013422646,0.014285035,0.0110757835,0.011108799,0.0036321331,0.004448496,0.0002161214],"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":[0.0005819401,0.0001422932,0.03654034,0.019878872,0.0007397314,0.00015515745,0.020855982,0.0018674787,0.0005083969,0.066204496,0.035625283,0.8169],"study_design_scores_gemma":[0.00022119262,0.0008431479,0.22554709,0.11907173,0.002482689,0.00047230977,0.053809702,0.005243242,0.0035947321,0.038476307,0.54952246,0.0007152671],"about_ca_topic_score_codex":0.85931563,"about_ca_topic_score_gemma":0.894629,"teacher_disagreement_score":0.8969035,"about_ca_system_score_codex":0.10309649,"about_ca_system_score_gemma":0.18519226,"threshold_uncertainty_score":0.8805722},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8932101,0.0017903093,0.07577762,0.0005673794,0.0002272597,0.008597882,0.0036981818,0.0005220706,0.015609148],"genre_scores_gemma":[0.85807806,0.0008987692,0.10163294,0.00015308947,0.000061102866,0.016235493,0.0021454545,0.00016346315,0.020631667],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98134446,0.009363897,0.0020316083,0.003063173,0.0031707394,0.0010261724],"domain_scores_gemma":[0.94230074,0.035393503,0.005700867,0.0038576722,0.011771369,0.00097578805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013543516,0.0012660115,0.0016623038,0.0050409185,0.002109481,0.003801405,0.0024530853,0.0013229122,0.011042496],"category_scores_gemma":[0.06164107,0.00096906483,0.0021773218,0.006378216,0.0013297251,0.001982412,0.0027089033,0.0014987455,0.001315414],"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":[0.0032348072,0.0011562817,0.38097957,0.0045649493,0.0017390882,0.00031469998,0.074333765,0.0028423767,0.0034178495,0.006614815,0.0050504836,0.5157513],"study_design_scores_gemma":[0.0003933941,0.0022118755,0.85475504,0.0019465842,0.0018634564,0.0003413339,0.053678017,0.020437649,0.00915576,0.0046414593,0.050204776,0.00037060442],"about_ca_topic_score_codex":0.066978544,"about_ca_topic_score_gemma":0.06714602,"teacher_disagreement_score":0.9330214,"about_ca_system_score_codex":0.004439985,"about_ca_system_score_gemma":0.0063291914,"threshold_uncertainty_score":0.1331774},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017044173,0.90463805,0.072788514,0.0112871425,0.0019267264,0.0025491067,0.0002459666,0.00013012133,0.004729948],"genre_scores_gemma":[0.07767176,0.6624297,0.22235522,0.013664448,0.0025955902,0.019232852,0.00034730186,0.00028847193,0.0014147329],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.68141145,0.2268192,0.045781728,0.012404413,0.031866405,0.001716809],"domain_scores_gemma":[0.36428505,0.5834084,0.017306287,0.015382691,0.018962655,0.00065493665],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31354782,0.0027575083,0.008457394,0.021788672,0.002190928,0.014063726,0.005445831,0.007766219,0.004465335],"category_scores_gemma":[0.41414395,0.0023392888,0.008687621,0.019639045,0.014662731,0.013745345,0.009690449,0.008648461,0.0012345185],"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":[0.00045752304,0.00024946866,0.0016481671,0.25601575,0.003050225,0.000121550474,0.0060348143,0.0023824032,0.0007605938,0.14387514,0.0052955374,0.58010876],"study_design_scores_gemma":[0.00051578775,0.00144765,0.0063287043,0.59021586,0.009094467,0.00070191163,0.0035058132,0.002908319,0.0031768854,0.20386752,0.17795931,0.00027768675],"about_ca_topic_score_codex":0.0046517616,"about_ca_topic_score_gemma":0.0038065242,"teacher_disagreement_score":0.68645215,"about_ca_system_score_codex":0.0134280715,"about_ca_system_score_gemma":0.016491268,"threshold_uncertainty_score":0.84651774},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9576769,0.012799961,0.0027587484,0.008369997,0.0000708013,0.00009936907,0.00026285765,0.00004112228,0.0179203],"genre_scores_gemma":[0.99448836,0.002250825,0.0009345092,0.00028357632,0.000013303172,0.00003152859,0.00007013746,0.000011416045,0.0019163733],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.99429446,0.0022060405,0.00020524343,0.0005452377,0.0014738871,0.0012750814],"domain_scores_gemma":[0.9662846,0.01181399,0.004352811,0.0008339506,0.013943813,0.0027708893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008322367,0.000479758,0.00050191075,0.0017589343,0.003688405,0.0059073656,0.0013071968,0.0009531929,0.0037610948],"category_scores_gemma":[0.01850468,0.00034563144,0.0005020959,0.0025023369,0.0038479213,0.0023465757,0.0020042001,0.0010824575,0.00024654012],"study_design_candidate":"systematic_review","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":[0.00023343971,0.00022372883,0.77155113,0.0012001038,0.0002327739,0.0007468461,0.070684515,0.0017826582,0.002236285,0.009183355,0.0045111557,0.13741398],"study_design_scores_gemma":[0.000009721423,0.00008167362,0.9307864,0.0008885144,0.0000980635,0.000115328614,0.04800364,0.0017675603,0.0005485099,0.0009875573,0.016618874,0.00009413979],"about_ca_topic_score_codex":0.9352498,"about_ca_topic_score_gemma":0.95979047,"teacher_disagreement_score":0.95878,"about_ca_system_score_codex":0.041220035,"about_ca_system_score_gemma":0.055575725,"threshold_uncertainty_score":0.2990737},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017808074,0.06431564,0.13979338,0.58545136,0.00496011,0.00039299,0.00019025653,0.00024928513,0.18683891],"genre_scores_gemma":[0.7490227,0.044160843,0.10805988,0.05167035,0.0050796373,0.0020118281,0.00019684607,0.00044730425,0.039350595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73184055,0.21277726,0.008688674,0.011446306,0.03049834,0.0047488837],"domain_scores_gemma":[0.5500481,0.38030604,0.011569224,0.030483712,0.022652855,0.0049399715],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.18682541,0.0011575017,0.0027165262,0.0061065443,0.008457163,0.03188436,0.0037163836,0.013566271,0.007246952],"category_scores_gemma":[0.16967072,0.0013263526,0.0017538213,0.0068798084,0.09040347,0.034369387,0.015653793,0.017164849,0.0017993837],"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":[0.00001753251,0.000022063461,0.0002914551,0.00040892506,0.000023673845,0.000049125767,0.008574651,0.00025568824,0.00010560597,0.9752364,0.0021568863,0.0128580155],"study_design_scores_gemma":[0.0000417326,0.00007945828,0.0005506172,0.0026774916,0.000037395093,0.00012369998,0.00754401,0.00055899034,0.00057550386,0.80706507,0.18069448,0.000051463787],"about_ca_topic_score_codex":0.0061670244,"about_ca_topic_score_gemma":0.006074343,"teacher_disagreement_score":0.9915428,"about_ca_system_score_codex":0.018913321,"about_ca_system_score_gemma":0.05736748,"threshold_uncertainty_score":0.988039},"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":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41590375,0.002294385,0.19683497,0.025712032,0.00027129133,0.005327203,0.00089390966,0.0010042357,0.35175824],"genre_scores_gemma":[0.9515278,0.00049810717,0.044411093,0.000523174,0.00002472434,0.00069037505,0.00016626412,0.00008095558,0.002077501],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9397642,0.042013198,0.0029914868,0.002299668,0.008800509,0.0041308333],"domain_scores_gemma":[0.95369124,0.01931803,0.006561822,0.008965218,0.008499528,0.0029643006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06738751,0.0006010729,0.0005600124,0.0036212916,0.0025377704,0.011359069,0.0010302769,0.0009945314,0.004794255],"category_scores_gemma":[0.081123084,0.00029403003,0.00044279234,0.004796644,0.006285251,0.007815812,0.01125059,0.0018620896,0.00045614823],"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":[0.00014102078,0.0009123277,0.11466324,0.0014258847,0.00016782044,0.00021374272,0.020739617,0.0074364725,0.0019316069,0.337837,0.0065421276,0.50798917],"study_design_scores_gemma":[0.00017964457,0.0021672507,0.20709133,0.004497338,0.00042148514,0.00036428627,0.07869259,0.015489976,0.01364534,0.5582273,0.119007014,0.00021650309],"about_ca_topic_score_codex":0.0033071716,"about_ca_topic_score_gemma":0.0059989505,"teacher_disagreement_score":0.06738751,"about_ca_system_score_codex":0.0077349776,"about_ca_system_score_gemma":0.023968074,"threshold_uncertainty_score":0.35638344},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026378623,0.010082566,0.0007066574,0.14193681,0.8052143,0.00006001256,0.00049781305,0.00039852495,0.040839605],"genre_scores_gemma":[0.0054351017,0.017805325,0.0008864428,0.2181384,0.49030536,0.00011798379,0.0008159517,0.00051345857,0.26598203],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731255,0.000461534,0.00028308228,0.00049763883,0.0011416847,0.00030356334],"domain_scores_gemma":[0.9858109,0.0022742164,0.0008412925,0.0007274408,0.0075387373,0.0028073266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022487233,0.001152246,0.00093518617,0.0014614459,0.0017631642,0.0055367714,0.0026165869,0.005309563,0.2250267],"category_scores_gemma":[0.026993167,0.0005131241,0.0008771335,0.00083506317,0.0010533489,0.004125833,0.0023359768,0.0073862006,0.13295299],"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":[0.000012303801,0.000006936833,0.000053618183,0.000091311515,0.000002699234,0.00010209264,0.000015534753,0.000011446856,0.000039239538,0.0004826808,0.98454976,0.014632398],"study_design_scores_gemma":[0.0000063313655,0.000008602932,0.000112348214,0.00019016772,0.0000028922404,0.00035850512,0.000044752025,0.000019549685,0.000056113415,0.00045070084,0.99874383,0.000006128493],"about_ca_topic_score_codex":0.001138533,"about_ca_topic_score_gemma":0.0020718942,"teacher_disagreement_score":0.2250267,"about_ca_system_score_codex":0.0016533611,"about_ca_system_score_gemma":0.0035412093,"threshold_uncertainty_score":0.75278926},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26235154,0.009350975,0.3505993,0.044605255,0.00047509573,0.00017371296,0.0004331813,0.00014319229,0.33186778],"genre_scores_gemma":[0.9791464,0.00082714605,0.017486844,0.00021353422,0.00010513706,0.00010771965,0.00006866381,0.000053923217,0.0019905334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9595663,0.029537035,0.0013246363,0.0029570856,0.0050175716,0.0015974059],"domain_scores_gemma":[0.87386805,0.105012864,0.004321902,0.011192076,0.003964242,0.0016408737],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.027433377,0.0007098649,0.0013365021,0.010646401,0.004787339,0.025614481,0.0023653475,0.003838259,0.007128769],"category_scores_gemma":[0.05775483,0.0008938633,0.0010344919,0.0071803653,0.061049644,0.03187626,0.017237293,0.0048400555,0.0004309096],"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":[0.000021501544,0.000013205924,0.00074999186,0.000079446356,0.000022450735,0.00006767842,0.015539955,0.0002624941,0.00015407159,0.97837454,0.00018634115,0.004528293],"study_design_scores_gemma":[0.000011141989,0.000007140304,0.0005879585,0.00009627642,0.000011691534,0.00006781642,0.0070288195,0.0008778579,0.0002052806,0.9862623,0.00483115,0.000012508293],"about_ca_topic_score_codex":0.0043003354,"about_ca_topic_score_gemma":0.002923714,"teacher_disagreement_score":0.9952127,"about_ca_system_score_codex":0.007743114,"about_ca_system_score_gemma":0.006065511,"threshold_uncertainty_score":0.14508331},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022309965,0.021824246,0.00541079,0.16822581,0.04988988,0.0014905033,0.02309294,0.0013605099,0.72647434],"genre_scores_gemma":[0.023520421,0.016479475,0.008966274,0.012730167,0.0019844521,0.00074349926,0.015975844,0.00072839763,0.91887134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9805932,0.0023027307,0.00081988785,0.0013707962,0.011819539,0.003093838],"domain_scores_gemma":[0.93805337,0.0030777827,0.0007627752,0.0017339586,0.03654817,0.01982387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017917763,0.0010759855,0.0014814989,0.0029332722,0.009308706,0.013755349,0.0031891873,0.00502823,0.24793014],"category_scores_gemma":[0.033446714,0.00073403755,0.0007837214,0.003462341,0.0035526578,0.0027008846,0.0058004917,0.0054647895,0.06963216],"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":[0.000023747745,0.000019318402,0.00020295689,0.00008745857,0.0000044463354,0.000020357671,0.000094126626,0.000033977,0.0000433364,0.0029419905,0.97659916,0.01992909],"study_design_scores_gemma":[0.0000075509083,0.0000060194716,0.0010007813,0.00020944714,0.0000026396297,0.000007513971,0.0002846664,0.000033191376,0.00003621724,0.00051142974,0.9978867,0.000013812244],"about_ca_topic_score_codex":0.8192017,"about_ca_topic_score_gemma":0.9281184,"teacher_disagreement_score":0.9510951,"about_ca_system_score_codex":0.048904885,"about_ca_system_score_gemma":0.26625738,"threshold_uncertainty_score":0.82940894},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005704941,0.0011369833,0.0006613094,0.08651991,0.9083347,0.00005214897,0.0015228083,0.00034139393,0.0013736634],"genre_scores_gemma":[0.010024197,0.016386945,0.009443055,0.2860609,0.554646,0.0011196684,0.0045671426,0.003095997,0.11465609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96839106,0.0063397856,0.00733549,0.0026290538,0.013714724,0.0015898529],"domain_scores_gemma":[0.7845106,0.0654675,0.01021786,0.009838732,0.12513858,0.004826755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022421898,0.004050064,0.0038039251,0.008462711,0.0065439073,0.009333818,0.0068599856,0.013010213,0.06592686],"category_scores_gemma":[0.31080016,0.0021820113,0.0037740022,0.0077481465,0.0061967326,0.005633029,0.0052021747,0.02019071,0.03838665],"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":[0.00002039061,0.0000029338166,0.000029935749,0.00027560658,0.000012748915,0.000084356325,0.00003601304,0.000019001027,0.000013238202,0.0005083596,0.9966145,0.0023829879],"study_design_scores_gemma":[0.00010426671,0.000021510024,0.00046138486,0.0031189313,0.0001123932,0.0005141613,0.00018626981,0.00024858784,0.0002333025,0.0034020857,0.9915168,0.000080299906],"about_ca_topic_score_codex":0.040638868,"about_ca_topic_score_gemma":0.043977022,"teacher_disagreement_score":0.06592686,"about_ca_system_score_codex":0.009495574,"about_ca_system_score_gemma":0.022904646,"threshold_uncertainty_score":0.22054726},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018105254,0.025959333,0.4362297,0.035126247,0.012550486,0.15328284,0.013317461,0.0015309356,0.30389783],"genre_scores_gemma":[0.056796253,0.010680864,0.5538328,0.019049572,0.003229988,0.27534366,0.0060436274,0.0015802524,0.073442936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87618643,0.079281874,0.012078203,0.0078204125,0.022246445,0.002386613],"domain_scores_gemma":[0.8359521,0.06622966,0.005581518,0.03171482,0.058153998,0.0023679726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13369663,0.0016524525,0.0016871555,0.0060441266,0.0035919196,0.0067050667,0.004216727,0.0026641896,0.052032713],"category_scores_gemma":[0.27557907,0.0011438961,0.0015996074,0.0072578937,0.0029964822,0.0036883294,0.0049535153,0.0040732143,0.018016577],"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":[0.0014409819,0.0006396624,0.0068039587,0.011750643,0.00018804839,0.0003219917,0.02291592,0.0012682183,0.0016367317,0.19994873,0.12616943,0.62691563],"study_design_scores_gemma":[0.00022813669,0.0004490392,0.004488163,0.009777033,0.0001430666,0.00037498915,0.005443867,0.00090913044,0.0018221869,0.066912815,0.9093886,0.00006289479],"about_ca_topic_score_codex":0.004112694,"about_ca_topic_score_gemma":0.007345921,"teacher_disagreement_score":0.13369663,"about_ca_system_score_codex":0.006938217,"about_ca_system_score_gemma":0.018705035,"threshold_uncertainty_score":0.7070638},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89835334,0.0022886419,0.009629618,0.01784039,0.00029637726,0.0034468677,0.00035680475,0.00021165822,0.06757636],"genre_scores_gemma":[0.97126836,0.0011440697,0.012676632,0.0013342323,0.000027752612,0.00085829326,0.00021004316,0.00008627103,0.012394373],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95848686,0.026566872,0.0010320758,0.0016357962,0.005429682,0.0068486757],"domain_scores_gemma":[0.92325765,0.020393508,0.0019055539,0.0024580352,0.027249498,0.024735697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0447906,0.0008547609,0.00070898194,0.0016618433,0.020272298,0.00824701,0.0037423933,0.0019128954,0.0028373853],"category_scores_gemma":[0.054007404,0.00059660734,0.0004573506,0.0022174339,0.009909487,0.002088322,0.010109976,0.0034177892,0.00044203323],"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":[0.00089479913,0.0033927928,0.04172449,0.0015779352,0.00012591349,0.0053466787,0.54722065,0.0073546846,0.0037139417,0.0143029345,0.043450255,0.33089495],"study_design_scores_gemma":[0.00021606527,0.0011777839,0.04538173,0.0021054498,0.00006219061,0.0005606953,0.7178961,0.0037893231,0.0032426734,0.005868316,0.21941096,0.00028874385],"about_ca_topic_score_codex":0.7509953,"about_ca_topic_score_gemma":0.91592836,"teacher_disagreement_score":0.9552094,"about_ca_system_score_codex":0.104441196,"about_ca_system_score_gemma":0.20447402,"threshold_uncertainty_score":0.75777745},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002358512,0.054994494,0.09853532,0.1163112,0.0032719444,0.00032327272,0.000115604846,0.00032015314,0.7237694],"genre_scores_gemma":[0.47267476,0.11858543,0.1885558,0.036868718,0.008392261,0.0020107215,0.0003067242,0.0008929738,0.1717127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9336898,0.046755865,0.0011754051,0.0023784959,0.01462597,0.0013745129],"domain_scores_gemma":[0.9209824,0.0687855,0.00096179335,0.0038614,0.0045456192,0.0008633007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06163639,0.0013889173,0.0015020309,0.0051740743,0.0049824305,0.024452908,0.003310303,0.00503307,0.0065988083],"category_scores_gemma":[0.042981014,0.00062806584,0.0007942928,0.003907267,0.050058495,0.02111799,0.009872693,0.008484754,0.0017567797],"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":[0.0000069628195,0.000010983363,0.00003995866,0.00012539848,0.0000055425257,0.00002346684,0.0013104972,0.00026647683,0.000041730804,0.9712796,0.005247446,0.021641865],"study_design_scores_gemma":[0.0000129732325,0.000016933813,0.0000920956,0.0007667943,0.0000073388296,0.00006625753,0.0013052415,0.0005762868,0.00020576752,0.7485729,0.2483593,0.000018136272],"about_ca_topic_score_codex":0.011644134,"about_ca_topic_score_gemma":0.010685403,"teacher_disagreement_score":0.06163639,"about_ca_system_score_codex":0.019857427,"about_ca_system_score_gemma":0.021508675,"threshold_uncertainty_score":0.32596827},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027932617,0.00030999453,0.00028972758,0.0031877742,0.0005006163,0.0001105151,0.0004700465,0.0005444584,0.99430746],"genre_scores_gemma":[0.000551028,0.00015550034,0.00017570508,0.0014547077,0.00015289387,0.00006712593,0.00016372002,0.000077309465,0.99720216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989513,0.000094897,0.00009423424,0.00023087575,0.00039334237,0.00023534677],"domain_scores_gemma":[0.9971944,0.0009786951,0.00018669276,0.00023392546,0.0006808999,0.000725404],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016539342,0.0018790074,0.0017322412,0.00184448,0.0021609797,0.003490189,0.0023533728,0.012164853,0.969635],"category_scores_gemma":[0.0035198892,0.000788014,0.0009486096,0.0018519132,0.0018891889,0.0040087244,0.0026264938,0.004629955,0.9786405],"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":[0.00033485677,0.00018652789,0.00067963224,0.0003268058,0.000020359355,0.00026165514,0.000056340054,0.00024790122,0.0009784106,0.00481659,0.68327045,0.3088204],"study_design_scores_gemma":[0.000058269834,0.000064468324,0.0005626447,0.00026233145,0.0000063923662,0.0001711075,0.00007402306,0.00019284866,0.00011676478,0.00080470095,0.9976713,0.000015254297],"about_ca_topic_score_codex":0.006036345,"about_ca_topic_score_gemma":0.007208542,"teacher_disagreement_score":0.03036499,"about_ca_system_score_codex":0.0017053192,"about_ca_system_score_gemma":0.0018411295,"threshold_uncertainty_score":0.043311894},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014609961,0.009529864,0.00044328885,0.13238367,0.8164213,0.00005736707,0.00045088967,0.00025699497,0.040310442],"genre_scores_gemma":[0.002776121,0.014714826,0.000701467,0.1882669,0.48361757,0.00011360151,0.0007852489,0.00035643583,0.3086678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972451,0.0003887878,0.000254352,0.000517291,0.0012967172,0.0002977013],"domain_scores_gemma":[0.98747766,0.0020726575,0.00055207015,0.0005574512,0.0066294367,0.0027106577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025695893,0.0015085313,0.0009780178,0.00191722,0.0022692375,0.0063301814,0.0026603509,0.006110548,0.20083548],"category_scores_gemma":[0.023110365,0.0005660901,0.00090668065,0.0010370787,0.0012154742,0.0046291053,0.002316599,0.007855845,0.12751725],"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":[0.000009275629,0.0000051946777,0.00003373149,0.000054483728,0.0000014907107,0.00004732017,0.0000109913135,0.000007527374,0.00002750061,0.00037823513,0.98857063,0.0108536165],"study_design_scores_gemma":[0.0000036674558,0.000004389525,0.0000753728,0.00008212621,0.0000018051807,0.0001150072,0.000022791164,0.0000098391,0.000024475612,0.00022171326,0.9994355,0.0000033995202],"about_ca_topic_score_codex":0.0024836916,"about_ca_topic_score_gemma":0.0056197303,"teacher_disagreement_score":0.20083548,"about_ca_system_score_codex":0.0020176012,"about_ca_system_score_gemma":0.004669225,"threshold_uncertainty_score":0.67186165},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019645171,0.001964277,0.9154845,0.0052250926,0.000114500486,0.0009306752,0.00037965117,0.00082679396,0.05542937],"genre_scores_gemma":[0.49933183,0.002142487,0.47741136,0.00067372125,0.000075730924,0.0015623177,0.0005582741,0.0004270793,0.017817212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9729628,0.016581586,0.0012224087,0.0026827978,0.0058287196,0.00072163256],"domain_scores_gemma":[0.9684377,0.017366152,0.0018705338,0.005860017,0.005890273,0.00057529414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026486257,0.0011404902,0.0008122409,0.005227093,0.00258858,0.012355601,0.003163557,0.0024641014,0.007519782],"category_scores_gemma":[0.04944223,0.0007338798,0.0015233271,0.0049800905,0.014938487,0.011763039,0.0037721791,0.0031891314,0.0009969154],"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":[0.000099177836,0.000096911426,0.0039722677,0.00097098906,0.000099619276,0.00012146563,0.019774806,0.013322966,0.0016839822,0.80893433,0.0026442604,0.14827913],"study_design_scores_gemma":[0.00011047629,0.0005078487,0.0076949815,0.0030173867,0.00028257666,0.00029655267,0.013200605,0.06683463,0.011017576,0.6584222,0.23834823,0.000267006],"about_ca_topic_score_codex":0.08898241,"about_ca_topic_score_gemma":0.067197956,"teacher_disagreement_score":0.9110176,"about_ca_system_score_codex":0.020884318,"about_ca_system_score_gemma":0.021740038,"threshold_uncertainty_score":0.17692894},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9985423,0.00013065318,0.00048797438,0.00011156255,0.000003970659,0.00008552166,0.0001763642,0.0000024272106,0.00045922425],"genre_scores_gemma":[0.9963683,0.00015633329,0.001829625,0.00010138216,0.0000071912204,0.0003191505,0.00046668047,0.0000063055263,0.0007449656],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9928243,0.0046527716,0.00040671095,0.0005454987,0.000780231,0.0007905492],"domain_scores_gemma":[0.9837006,0.011283001,0.0017574469,0.00077984744,0.0019829024,0.00049627735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009171052,0.0002559625,0.00054298557,0.0025087413,0.0025180553,0.0027521045,0.0011076201,0.0006394254,0.0009774808],"category_scores_gemma":[0.018228527,0.00035030115,0.0004673064,0.003258755,0.0016749629,0.0013344567,0.0025017716,0.0011553701,0.00008338631],"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":[0.00037805893,0.0011418036,0.8163532,0.00024655418,0.00037011356,0.00024089604,0.11443122,0.0008978706,0.0010085995,0.0028316819,0.0018297564,0.060270198],"study_design_scores_gemma":[0.000023017485,0.00037657164,0.83928967,0.00016523573,0.00012311405,0.000029674049,0.15211056,0.0037112066,0.00053471216,0.0006844792,0.0029182131,0.000033623182],"about_ca_topic_score_codex":0.30772156,"about_ca_topic_score_gemma":0.48219404,"teacher_disagreement_score":0.30772156,"about_ca_system_score_codex":0.008771071,"about_ca_system_score_gemma":0.008921463,"threshold_uncertainty_score":0.6118609},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004683529,0.0062412014,0.027834171,0.9123735,0.0024211572,0.0006969701,0.00003898644,0.00018764369,0.045523],"genre_scores_gemma":[0.608847,0.01369932,0.11471592,0.24271898,0.0033014724,0.004469274,0.00016513046,0.0006058203,0.011477045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2811696,0.61683714,0.02221506,0.011054202,0.049435716,0.019288305],"domain_scores_gemma":[0.14881612,0.7270937,0.014474628,0.025516802,0.062980525,0.021118132],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6139299,0.0016591247,0.0034656462,0.007433902,0.023528885,0.06750646,0.008175779,0.028363211,0.010009714],"category_scores_gemma":[0.63208205,0.0023608676,0.0023581223,0.006064767,0.069425605,0.078748,0.024977138,0.040613487,0.0020099883],"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":[0.00022666328,0.000620101,0.0044051283,0.0032921243,0.00013596113,0.0002627535,0.03435894,0.0015706543,0.00048529715,0.637095,0.06867458,0.24887274],"study_design_scores_gemma":[0.00038182526,0.0006357049,0.00533867,0.029126802,0.00023740358,0.0002660223,0.090626396,0.002505256,0.0021639003,0.5402797,0.32814124,0.00029711242],"about_ca_topic_score_codex":0.01588233,"about_ca_topic_score_gemma":0.01142473,"teacher_disagreement_score":0.6139299,"about_ca_system_score_codex":0.05244821,"about_ca_system_score_gemma":0.24724607,"threshold_uncertainty_score":0.47609317},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004698798,0.00289528,0.6263652,0.09924519,0.007857364,0.0029023862,0.017911814,0.00634427,0.23177972],"genre_scores_gemma":[0.082609944,0.0077421176,0.7601672,0.035161227,0.0033982836,0.0055537946,0.04847849,0.008578463,0.048310548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6819557,0.13176067,0.04837339,0.017961474,0.113050655,0.00689812],"domain_scores_gemma":[0.49556288,0.20282471,0.017843109,0.14284824,0.13366124,0.0072598476],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19074053,0.001661371,0.0022650969,0.02528002,0.0069525307,0.04564032,0.008647121,0.012612829,0.015242552],"category_scores_gemma":[0.39411286,0.0026669938,0.0038334485,0.03426449,0.014656615,0.042609606,0.015666876,0.019830031,0.013622136],"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":[0.000055536526,0.000114370654,0.0027701387,0.00060504756,0.00006032154,0.00015934998,0.0016063057,0.002152681,0.0004152942,0.8718089,0.07664323,0.04360887],"study_design_scores_gemma":[0.000026340387,0.000034401484,0.0015184229,0.0017548337,0.000044494125,0.00023635216,0.0012256657,0.002231803,0.0016190881,0.24666224,0.74448305,0.00016326172],"about_ca_topic_score_codex":0.03253715,"about_ca_topic_score_gemma":0.011603185,"teacher_disagreement_score":0.19074053,"about_ca_system_score_codex":0.01767229,"about_ca_system_score_gemma":0.043985914,"threshold_uncertainty_score":0.997961},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04210839,0.006534972,0.0290812,0.8643603,0.0012279042,0.00023310563,0.000048413942,0.00010037841,0.05630531],"genre_scores_gemma":[0.9332558,0.0033745526,0.016501335,0.042115144,0.0007701886,0.00046696325,0.000020938529,0.00013896055,0.003356156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5570383,0.34633166,0.015618885,0.012045066,0.04723276,0.021733332],"domain_scores_gemma":[0.49149403,0.38936788,0.027400434,0.019795338,0.040072624,0.03186965],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38081008,0.0010514004,0.0018569398,0.0057754694,0.020191068,0.078218766,0.005830144,0.020951532,0.0026045376],"category_scores_gemma":[0.3941568,0.001651853,0.0013920459,0.0054558893,0.0972186,0.041355975,0.054148618,0.025671352,0.00046690993],"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":[0.00012934617,0.00007156559,0.0043903315,0.0005868739,0.000107945656,0.0003825612,0.09546013,0.0005306567,0.00041339648,0.8636025,0.010038084,0.0242867],"study_design_scores_gemma":[0.00019023399,0.00011751729,0.0019621616,0.0027752786,0.00013506641,0.0003044117,0.102410026,0.0017238879,0.0010154608,0.6990015,0.190129,0.0002354787],"about_ca_topic_score_codex":0.012277177,"about_ca_topic_score_gemma":0.009779281,"teacher_disagreement_score":0.6191899,"about_ca_system_score_codex":0.042871144,"about_ca_system_score_gemma":0.072017886,"threshold_uncertainty_score":0.7635714},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25404167,0.003077981,0.008602497,0.054163445,0.0010320963,0.0039244704,0.25694484,0.0015369284,0.41667613],"genre_scores_gemma":[0.38840508,0.003970643,0.025486102,0.0037636538,0.00009729732,0.0023442416,0.08450113,0.0005295365,0.49090233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968663,0.00042294772,0.00014165418,0.00016825156,0.0018502848,0.0005506092],"domain_scores_gemma":[0.98502016,0.001766377,0.00028845464,0.0005390296,0.010667404,0.0017184223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054351287,0.00069158635,0.00043022662,0.00402252,0.0031317424,0.0041997405,0.0011934038,0.0014637023,0.010190087],"category_scores_gemma":[0.01064818,0.0004067617,0.0003106662,0.0039245323,0.00084108615,0.0017566754,0.0032092212,0.0015745028,0.0017172121],"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":[0.0002716151,0.00062345894,0.08853988,0.00037546194,0.00010736554,0.0005166473,0.0032809158,0.0046755876,0.0010444348,0.011397981,0.7366421,0.15252458],"study_design_scores_gemma":[0.00018268892,0.00019422076,0.4181594,0.00077255047,0.00020552454,0.00013673805,0.031172967,0.0116345035,0.0052248607,0.008782752,0.52326286,0.00027093326],"about_ca_topic_score_codex":0.9800965,"about_ca_topic_score_gemma":0.9889571,"teacher_disagreement_score":0.031870373,"about_ca_system_score_codex":0.031870373,"about_ca_system_score_gemma":0.16314866,"threshold_uncertainty_score":0.23123682},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027229956,0.0004911887,0.9461671,0.0101529425,0.0003539405,0.0049441746,0.0011228919,0.009601247,0.024443477],"genre_scores_gemma":[0.013287151,0.00021926036,0.9807513,0.00044853543,0.000048197824,0.002782401,0.00071671384,0.00041654104,0.0013299511],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88656807,0.086413935,0.009166544,0.0042009344,0.011458521,0.0021920041],"domain_scores_gemma":[0.8409037,0.09369279,0.013283555,0.02484757,0.023406258,0.0038660967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14389588,0.002147873,0.0015346513,0.009724921,0.0034913518,0.01608092,0.004284018,0.0032716652,0.015094346],"category_scores_gemma":[0.17501597,0.0018903455,0.0025820336,0.009707629,0.0059672883,0.019705717,0.0097273,0.00638583,0.004864935],"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":[0.00028996085,0.0007149361,0.006459674,0.0029998533,0.00032832185,0.00044453965,0.008115071,0.025361462,0.0016609016,0.2701336,0.08533202,0.5981597],"study_design_scores_gemma":[0.0006024931,0.0008160687,0.005553193,0.0059354366,0.0004224588,0.0005069225,0.008489368,0.06770624,0.0067275455,0.38034385,0.5223274,0.0005689214],"about_ca_topic_score_codex":0.005870735,"about_ca_topic_score_gemma":0.00741897,"teacher_disagreement_score":0.14389588,"about_ca_system_score_codex":0.0083886,"about_ca_system_score_gemma":0.030385869,"threshold_uncertainty_score":0.76100326},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054166983,0.018499728,0.06287368,0.5993544,0.018884782,0.0016702347,0.00027961846,0.00078041595,0.29224053],"genre_scores_gemma":[0.4534409,0.035343736,0.11229428,0.22567256,0.021373486,0.007420811,0.00091735163,0.0017852365,0.14175159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86545485,0.11182428,0.0059640706,0.0020813288,0.011592125,0.003083335],"domain_scores_gemma":[0.7992376,0.14365707,0.009038854,0.007351214,0.027348606,0.01336657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1025639,0.0010125702,0.0010720973,0.0020645768,0.0067715114,0.036527857,0.0027865309,0.013509202,0.03091013],"category_scores_gemma":[0.096833415,0.00044753935,0.0012926747,0.0027103852,0.031578016,0.015042333,0.01245235,0.012060755,0.008188108],"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":[0.00014569775,0.00013580316,0.0007268226,0.0029805324,0.000033310476,0.0007440626,0.019059855,0.001004019,0.000865573,0.59083873,0.27422845,0.10923719],"study_design_scores_gemma":[0.00005076278,0.0002041063,0.001251593,0.005754962,0.000028934635,0.000658944,0.033454955,0.0010287731,0.0010889247,0.16253607,0.79384524,0.00009674707],"about_ca_topic_score_codex":0.0054390607,"about_ca_topic_score_gemma":0.0068964437,"teacher_disagreement_score":0.1025639,"about_ca_system_score_codex":0.014255302,"about_ca_system_score_gemma":0.028236227,"threshold_uncertainty_score":0.5424162},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77620274,0.03317812,0.009533816,0.006193387,0.0001729167,0.0009816763,0.0025202131,0.00019527283,0.17102179],"genre_scores_gemma":[0.98349804,0.008350135,0.0048690992,0.000536459,0.000022393378,0.00037057544,0.0008402946,0.000053489086,0.0014595934],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95297563,0.028307876,0.004317521,0.0011776449,0.0095958095,0.0036254583],"domain_scores_gemma":[0.90777797,0.051237166,0.008692373,0.0037396834,0.025369642,0.0031831465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060691584,0.00043999977,0.0007176286,0.0149658155,0.0030412814,0.008537906,0.00093357527,0.0010431658,0.0019457374],"category_scores_gemma":[0.07755077,0.00034252324,0.00087630644,0.02573604,0.0035295344,0.0030042944,0.0043397504,0.0008654935,0.00019817929],"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":[0.0013562362,0.0004506272,0.30202496,0.004139394,0.000572248,0.0016839457,0.040316053,0.013733569,0.00071039225,0.24215306,0.012700324,0.38015917],"study_design_scores_gemma":[0.00019429461,0.00053595094,0.6363848,0.008424406,0.00053334725,0.0010349486,0.1030452,0.0027244026,0.0014852902,0.015172234,0.23026824,0.00019682012],"about_ca_topic_score_codex":0.073327065,"about_ca_topic_score_gemma":0.035055563,"teacher_disagreement_score":0.073327065,"about_ca_system_score_codex":0.026559124,"about_ca_system_score_gemma":0.024504427,"threshold_uncertainty_score":0.3209716},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021726198,0.6805923,0.14756364,0.008285848,0.005132098,0.112530015,0.018868402,0.0009722363,0.0043293303],"genre_scores_gemma":[0.31462884,0.1529508,0.25748783,0.007965996,0.002739883,0.25292477,0.0075553805,0.0006502126,0.0030962422],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.82483256,0.12934893,0.029213978,0.006395426,0.009151102,0.0010580594],"domain_scores_gemma":[0.7892403,0.16773525,0.018446837,0.012469527,0.010675446,0.0014326479],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13420364,0.004453639,0.013553814,0.010562422,0.0013461162,0.005673084,0.0032804983,0.0049108574,0.009305571],"category_scores_gemma":[0.35386768,0.0019801313,0.029801263,0.007890626,0.0015424187,0.0036061052,0.003536639,0.003343228,0.0013472178],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013750912,0.00022415613,0.0042186272,0.46108156,0.4595396,0.0002262225,0.00044272665,0.0013067065,0.0009892766,0.0028466827,0.0057690265,0.049604557],"study_design_scores_gemma":[0.011727548,0.002794801,0.0052838377,0.0729431,0.8701597,0.00040516086,0.00026627793,0.0015107212,0.0017076823,0.012845483,0.020166513,0.00018919371],"about_ca_topic_score_codex":0.0019702588,"about_ca_topic_score_gemma":0.005216933,"teacher_disagreement_score":0.8657963,"about_ca_system_score_codex":0.004876822,"about_ca_system_score_gemma":0.0068685575,"threshold_uncertainty_score":0.70974517},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02473869,0.13494937,0.12212537,0.53792554,0.015136214,0.00096162304,0.00054259837,0.00072547595,0.16289516],"genre_scores_gemma":[0.69384277,0.059833515,0.1463913,0.072189,0.0090528065,0.004284693,0.00072967116,0.0014953152,0.012180901],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5896783,0.30808654,0.023697745,0.010902799,0.06038935,0.0072451876],"domain_scores_gemma":[0.43528152,0.40802088,0.028551128,0.032593954,0.085471146,0.0100813955],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26628807,0.0015879681,0.0046540564,0.013011394,0.009632797,0.047504153,0.0046335696,0.010852691,0.006979817],"category_scores_gemma":[0.45423314,0.0008861683,0.0021598232,0.01427594,0.033274382,0.04506547,0.013445568,0.008825563,0.0021418394],"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":[0.00036538485,0.00031764535,0.009911872,0.013173835,0.00033695067,0.00026062547,0.041256435,0.0010912169,0.0011460935,0.47922635,0.05279433,0.40011922],"study_design_scores_gemma":[0.00012496002,0.00046719247,0.013949345,0.033963062,0.00025730004,0.0005726477,0.052679196,0.0016553542,0.002189586,0.3977734,0.4960017,0.00036614202],"about_ca_topic_score_codex":0.003546421,"about_ca_topic_score_gemma":0.0031781679,"teacher_disagreement_score":0.73371196,"about_ca_system_score_codex":0.022075,"about_ca_system_score_gemma":0.026529448,"threshold_uncertainty_score":0.90479743},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038462235,0.0529277,0.06420878,0.8506198,0.008279943,0.0011823145,0.00022853969,0.0002841614,0.018422635],"genre_scores_gemma":[0.4933589,0.03730814,0.2587756,0.17362255,0.019562619,0.011553156,0.0005774248,0.00061433145,0.004627289],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23370636,0.6154556,0.049095146,0.017139541,0.07591995,0.008683329],"domain_scores_gemma":[0.080984466,0.7773591,0.02682156,0.0458779,0.052190136,0.016766908],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73637164,0.004289102,0.014792015,0.021880196,0.015491266,0.07563818,0.0153456805,0.048537057,0.010208982],"category_scores_gemma":[0.7622879,0.0052821785,0.005469184,0.0155208325,0.101244085,0.08416465,0.04548036,0.04958318,0.0030242025],"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":[0.00084837654,0.0004349939,0.002956302,0.018664509,0.0009350084,0.00020581871,0.013422327,0.0010024497,0.0004456581,0.8015244,0.026612297,0.13294774],"study_design_scores_gemma":[0.0003766443,0.00026011743,0.0010309126,0.015409573,0.0003223941,0.0001120359,0.0060266512,0.0015526692,0.00038137022,0.952759,0.02161623,0.00015247958],"about_ca_topic_score_codex":0.0035234,"about_ca_topic_score_gemma":0.0035605207,"teacher_disagreement_score":0.26362836,"about_ca_system_score_codex":0.041638,"about_ca_system_score_gemma":0.13230024,"threshold_uncertainty_score":0.32510078},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12615173,0.053973436,0.24094997,0.22000208,0.0026956738,0.0016262141,0.00022997896,0.0004708877,0.35390002],"genre_scores_gemma":[0.9521937,0.005548889,0.02727951,0.0045103454,0.0003780251,0.0014092579,0.000073533585,0.00016221209,0.008444653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.70070887,0.26629224,0.0049203834,0.005069174,0.019686913,0.003322314],"domain_scores_gemma":[0.4831694,0.48666865,0.008187356,0.0064507187,0.01191223,0.0036117055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11335555,0.00081084576,0.0010727731,0.0047529754,0.0047627883,0.015426784,0.0019525589,0.0055026757,0.008029207],"category_scores_gemma":[0.29854962,0.0007649587,0.0009060558,0.0033113663,0.032985978,0.019967182,0.013090003,0.010357912,0.0007057307],"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":[0.00033628923,0.00036055694,0.0049208817,0.003220277,0.0001350291,0.00031729465,0.22441936,0.0009760281,0.0009699193,0.58562785,0.008176444,0.17054003],"study_design_scores_gemma":[0.00021533584,0.0005541812,0.009819974,0.0065860255,0.00014298446,0.00057098246,0.12635729,0.003221653,0.0033996657,0.7002129,0.14869419,0.00022493325],"about_ca_topic_score_codex":0.0038705196,"about_ca_topic_score_gemma":0.0028438426,"teacher_disagreement_score":0.11335555,"about_ca_system_score_codex":0.015717298,"about_ca_system_score_gemma":0.01677697,"threshold_uncertainty_score":0.5994886},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013090725,0.045961518,0.012600686,0.27083123,0.008902143,0.0007877461,0.0017201182,0.00042009074,0.65746737],"genre_scores_gemma":[0.30363247,0.07829533,0.040607125,0.088215426,0.016449023,0.003135332,0.0031166011,0.0011573446,0.46539134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8959458,0.055874966,0.004147432,0.0076519786,0.028676892,0.0077029],"domain_scores_gemma":[0.8560357,0.07917864,0.0056388592,0.012189046,0.039085582,0.007872197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059416097,0.00097066106,0.0023254978,0.008219063,0.013705062,0.040381428,0.0043732873,0.015408101,0.041533343],"category_scores_gemma":[0.13388455,0.001185426,0.0010375438,0.018824048,0.037081614,0.012770988,0.009196509,0.011338946,0.0070092496],"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":[0.000008756619,0.0000069074754,0.00020872193,0.00022611849,0.000008074941,0.000045557183,0.0012779782,0.0002739206,0.000013968756,0.86273795,0.122651584,0.012540497],"study_design_scores_gemma":[0.000007314512,0.000003204064,0.00037807415,0.0011629423,0.000004752867,0.00001779405,0.001776449,0.00024781577,0.000025112042,0.11177988,0.884574,0.000022664024],"about_ca_topic_score_codex":0.37068412,"about_ca_topic_score_gemma":0.25210533,"teacher_disagreement_score":0.37068412,"about_ca_system_score_codex":0.09023777,"about_ca_system_score_gemma":0.17660598,"threshold_uncertainty_score":0.737053},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10843852,0.07799121,0.1348572,0.31155694,0.004726667,0.00033179732,0.00041574778,0.0002653452,0.36141664],"genre_scores_gemma":[0.9010651,0.01565133,0.029682461,0.012619515,0.003038652,0.00070552435,0.00013926027,0.00029825754,0.0367998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.95296425,0.030981883,0.0028541577,0.0030657283,0.008812808,0.0013211488],"domain_scores_gemma":[0.90762955,0.071187235,0.0046401713,0.0036742012,0.011429979,0.0014388234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031104043,0.0010049791,0.0012661513,0.003376375,0.004130993,0.021663487,0.0018907278,0.0055853548,0.0063552335],"category_scores_gemma":[0.065119065,0.00035876242,0.0008765779,0.0030542195,0.027294373,0.016478142,0.0054838313,0.005646627,0.0011141235],"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":[0.00019894769,0.00011104006,0.0037747321,0.0011558563,0.000073985,0.00017999447,0.06557851,0.00054536917,0.0009560032,0.79491675,0.012606054,0.11990272],"study_design_scores_gemma":[0.00006432558,0.00027906528,0.01463914,0.0040145507,0.000092647475,0.00051527715,0.06622818,0.002143346,0.0032267433,0.49707347,0.4115407,0.00018247365],"about_ca_topic_score_codex":0.007562822,"about_ca_topic_score_gemma":0.006183515,"teacher_disagreement_score":0.031104043,"about_ca_system_score_codex":0.008852893,"about_ca_system_score_gemma":0.0066599036,"threshold_uncertainty_score":0.16449589},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032263994,0.073189326,0.022790503,0.114519656,0.0038287954,0.00045553638,0.0006826347,0.00030657116,0.7810006],"genre_scores_gemma":[0.3303794,0.13172543,0.06498126,0.030137066,0.003563305,0.0009843344,0.0010910208,0.000825118,0.43631306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9523497,0.016203033,0.0016282155,0.0023140947,0.022296095,0.0052088164],"domain_scores_gemma":[0.9455807,0.032064132,0.0013685246,0.0025835775,0.015548947,0.002854038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032296624,0.00079662516,0.0013605608,0.006353662,0.015584737,0.030607844,0.0029052787,0.005480083,0.009905379],"category_scores_gemma":[0.064155586,0.00082793675,0.00053427764,0.014496466,0.03519248,0.0078845285,0.005606141,0.008074975,0.0019653833],"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":[0.0000054338147,0.0000066959556,0.00022822354,0.00019687538,0.000005643439,0.000045841454,0.004778703,0.00042875207,0.000031146523,0.9054555,0.060824618,0.02799248],"study_design_scores_gemma":[0.00000513024,0.000003340935,0.0007068559,0.00088143727,0.000006564506,0.000027788143,0.0049596997,0.00033131219,0.00007454641,0.13008489,0.86288536,0.000033100976],"about_ca_topic_score_codex":0.8530069,"about_ca_topic_score_gemma":0.88451177,"teacher_disagreement_score":0.8530069,"about_ca_system_score_codex":0.15452519,"about_ca_system_score_gemma":0.27379465,"threshold_uncertainty_score":0.98063093},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024243311,0.24256623,0.0031974525,0.032863535,0.0061684432,0.00002789559,0.00011577397,0.00010491905,0.7125313],"genre_scores_gemma":[0.058920015,0.101487085,0.0015248689,0.0075455536,0.0055355043,0.000048119902,0.00011650032,0.00010618162,0.82471627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989254,0.00042694094,0.00004147992,0.00018433455,0.00030870875,0.000113242284],"domain_scores_gemma":[0.99898535,0.00062326103,0.00008144743,0.00009109388,0.00010875987,0.000110086614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012053383,0.0008428158,0.0007866773,0.0015279338,0.0021897305,0.009915335,0.00046201676,0.0029753267,0.031489737],"category_scores_gemma":[0.002742977,0.00032846056,0.00032523545,0.0027688055,0.009075384,0.007908496,0.0027818454,0.0035349305,0.0066700117],"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":[0.00003795951,0.000024556302,0.00019473962,0.0005368602,0.00001030257,0.00007307243,0.0027492878,0.00034873412,0.00019308692,0.6831808,0.16747834,0.1451722],"study_design_scores_gemma":[0.0000054429624,0.00001616828,0.00033024416,0.000561339,0.0000041060957,0.00006224716,0.00060920196,0.00008646672,0.000067797155,0.08832539,0.90992373,0.0000078149515],"about_ca_topic_score_codex":0.0039823307,"about_ca_topic_score_gemma":0.008570818,"teacher_disagreement_score":0.031489737,"about_ca_system_score_codex":0.004531399,"about_ca_system_score_gemma":0.002857595,"threshold_uncertainty_score":0.10534364},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053289337,0.08367216,0.00040383032,0.8107546,0.022452576,0.00006149745,0.0010267753,0.0001477173,0.07615198],"genre_scores_gemma":[0.23562428,0.13751614,0.002521157,0.38237166,0.015861081,0.000174494,0.001392754,0.00041959935,0.22411883],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9812758,0.0014426645,0.00060956104,0.0021359632,0.009108329,0.0054277224],"domain_scores_gemma":[0.94796365,0.0068760454,0.0015884693,0.000764271,0.022597551,0.02021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007948993,0.000661735,0.0009192104,0.005601148,0.02742366,0.01910486,0.0026928051,0.0094454,0.018863216],"category_scores_gemma":[0.024000172,0.00071526755,0.0006036547,0.01152859,0.012857077,0.0042542596,0.005001271,0.0103716655,0.0022567606],"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":[0.00003656572,0.000028970315,0.0028084875,0.00055105996,0.000016212378,0.00041312832,0.0079078665,0.00022312897,0.00021470078,0.07814191,0.8639444,0.045713592],"study_design_scores_gemma":[0.000008157151,0.000005942298,0.0056702616,0.0006229726,0.000007867641,0.00006276033,0.0031161066,0.00011179951,0.000057599533,0.0029730254,0.98732114,0.00004249242],"about_ca_topic_score_codex":0.990871,"about_ca_topic_score_gemma":0.9917658,"teacher_disagreement_score":0.6886732,"about_ca_system_score_codex":0.3113268,"about_ca_system_score_gemma":0.6245542,"threshold_uncertainty_score":0.7987633},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6298715,0.008514109,0.026987705,0.010867261,0.0007466662,0.00028582418,0.00008963425,0.00015850406,0.3224788],"genre_scores_gemma":[0.985521,0.002132124,0.0035692044,0.0003221478,0.00011568921,0.00009563087,0.00002095703,0.000023470806,0.008199773],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9779048,0.016892802,0.00077079004,0.0004985425,0.003142858,0.00079019275],"domain_scores_gemma":[0.98291576,0.011665912,0.0024587717,0.0007665485,0.0010089421,0.0011840784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009053214,0.00030521417,0.00025543055,0.00077241973,0.003366531,0.00567765,0.00082050543,0.0008839252,0.0031919593],"category_scores_gemma":[0.02286361,0.00027280409,0.0002941792,0.0009425773,0.0037963903,0.003302796,0.004441507,0.0013361069,0.0005667296],"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":[0.00070189696,0.0006478585,0.053268537,0.0010640443,0.00013297504,0.0015514122,0.15929228,0.004436961,0.004307344,0.13622007,0.01505602,0.62332064],"study_design_scores_gemma":[0.00018164744,0.0017367031,0.12853086,0.0034180023,0.00023521433,0.0036428473,0.2661042,0.0088359,0.012044858,0.23454405,0.34029406,0.00043157538],"about_ca_topic_score_codex":0.0013291485,"about_ca_topic_score_gemma":0.0017522783,"teacher_disagreement_score":0.009053214,"about_ca_system_score_codex":0.0019715596,"about_ca_system_score_gemma":0.0018683278,"threshold_uncertainty_score":0.047878563},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09188345,0.0008959731,0.8600191,0.004506871,0.00012752702,0.00037853772,0.00019955423,0.00027927477,0.041709717],"genre_scores_gemma":[0.7247012,0.0015559813,0.26071903,0.00037438763,0.00010903502,0.0005772839,0.0002252363,0.00012273618,0.011615128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9937356,0.0028247146,0.00025576315,0.0010986319,0.0017130784,0.00037221055],"domain_scores_gemma":[0.95669895,0.035128042,0.0020816445,0.0019822805,0.0037228158,0.00038627535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011065808,0.0013991266,0.001009106,0.0030760586,0.0013630248,0.004191389,0.0019759792,0.0020605763,0.014461017],"category_scores_gemma":[0.04433897,0.0009950475,0.0030740192,0.0025556523,0.00456813,0.006740423,0.002983385,0.003386151,0.0008506082],"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":[0.00016398996,0.00026133558,0.013463505,0.00069830695,0.00027218316,0.00030026058,0.0055848653,0.24628872,0.0021688303,0.60565245,0.0018815111,0.123264015],"study_design_scores_gemma":[0.00007517265,0.0004251342,0.008794502,0.0004731836,0.00019544008,0.0002794274,0.00438978,0.42078882,0.0034883602,0.5419738,0.01898387,0.00013247578],"about_ca_topic_score_codex":0.020667346,"about_ca_topic_score_gemma":0.018013414,"teacher_disagreement_score":0.020667346,"about_ca_system_score_codex":0.005266218,"about_ca_system_score_gemma":0.0043105376,"threshold_uncertainty_score":0.058522284},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06307703,0.054697208,0.51815045,0.069125764,0.001967052,0.0010861767,0.00016497623,0.00043786012,0.2912935],"genre_scores_gemma":[0.73629266,0.020033149,0.19406281,0.0068745892,0.000989141,0.0016916309,0.0000930139,0.000431378,0.03953166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7928675,0.16948244,0.0053512934,0.0060363803,0.02387029,0.0023921009],"domain_scores_gemma":[0.7106881,0.23294643,0.010717615,0.01461718,0.028629312,0.002401377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13143857,0.0012779988,0.0016887175,0.0062560225,0.005943311,0.02111382,0.0030067249,0.005622454,0.006523027],"category_scores_gemma":[0.1551071,0.00094294787,0.0014610883,0.0074912626,0.021397715,0.014229601,0.0064889276,0.00737582,0.0015249294],"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":[0.00018898972,0.00021852888,0.0027353952,0.0028814746,0.00013925717,0.00013816424,0.042699646,0.003451597,0.0014242617,0.7266816,0.004105527,0.21533556],"study_design_scores_gemma":[0.00013305283,0.0013047879,0.009805912,0.0089504905,0.00023991251,0.0007579369,0.032686144,0.009341939,0.009239338,0.4603677,0.46685773,0.00031503232],"about_ca_topic_score_codex":0.009678494,"about_ca_topic_score_gemma":0.012165167,"teacher_disagreement_score":0.13143857,"about_ca_system_score_codex":0.017074736,"about_ca_system_score_gemma":0.020487119,"threshold_uncertainty_score":0.6951219},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4779156,0.007916909,0.29197562,0.077513866,0.00083004765,0.001180304,0.000047763802,0.00023919021,0.14238071],"genre_scores_gemma":[0.971032,0.00082520547,0.025523175,0.0008461921,0.000053144304,0.0002721306,0.000012526356,0.000034794535,0.0014008811],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.812741,0.16149811,0.004195446,0.0047478606,0.013482093,0.0033354182],"domain_scores_gemma":[0.80163574,0.16135207,0.012032743,0.013635137,0.007880537,0.003463756],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.12212381,0.0008077841,0.0010208256,0.006284313,0.012699429,0.017609768,0.0038390374,0.0052497843,0.0018800193],"category_scores_gemma":[0.1394252,0.00083570677,0.0010572523,0.0024105485,0.091313116,0.02167926,0.024996132,0.006892284,0.00033715088],"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":[0.000079314246,0.00014747644,0.0057496545,0.000522425,0.00004472993,0.00057618564,0.6574932,0.00055799197,0.0013466523,0.24806546,0.0011894845,0.08422742],"study_design_scores_gemma":[0.00007884154,0.0002484734,0.007256369,0.002421101,0.00008732716,0.0011133776,0.33569157,0.004322353,0.0045093,0.55154246,0.092558555,0.00017024836],"about_ca_topic_score_codex":0.005394094,"about_ca_topic_score_gemma":0.0072165965,"teacher_disagreement_score":0.9873006,"about_ca_system_score_codex":0.010630347,"about_ca_system_score_gemma":0.015425943,"threshold_uncertainty_score":0.64586014},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9154833,0.0022385723,0.06953761,0.0007515048,0.0002267457,0.002303574,0.0013610116,0.0002887989,0.007808886],"genre_scores_gemma":[0.9315402,0.0008037407,0.06301666,0.00021941322,0.00008680837,0.0021148256,0.0013734642,0.00006647703,0.00077844923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95276725,0.028500607,0.0076740137,0.0012496929,0.009159772,0.0006486083],"domain_scores_gemma":[0.86656463,0.08119084,0.021526858,0.0054667587,0.024205137,0.0010457454],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.043752946,0.00067760254,0.00093082455,0.0058860555,0.00038565678,0.0012909091,0.0008023897,0.00056946697,0.0015328651],"category_scores_gemma":[0.106476374,0.0002457237,0.0010574405,0.0032577685,0.0008993992,0.0012548687,0.0014556595,0.00067497516,0.00046430685],"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":[0.0005017166,0.0003833106,0.82703876,0.00085600204,0.00069446285,0.00008594381,0.002912152,0.0013246102,0.002712278,0.00042765096,0.0022658417,0.16079728],"study_design_scores_gemma":[0.00016333963,0.004353157,0.96653706,0.0009468698,0.0004082784,0.0009507317,0.0041073547,0.007645294,0.0057136538,0.0011136208,0.007856398,0.00020423725],"about_ca_topic_score_codex":0.0011562565,"about_ca_topic_score_gemma":0.001859708,"teacher_disagreement_score":0.95624703,"about_ca_system_score_codex":0.00085397693,"about_ca_system_score_gemma":0.0014730274,"threshold_uncertainty_score":0.23139048},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102407396,0.028628424,0.35582656,0.060670994,0.0018883622,0.0029372037,0.00036056835,0.0004942911,0.44678617],"genre_scores_gemma":[0.7400816,0.012952005,0.15255652,0.0049783103,0.0007527964,0.0055690394,0.00034954408,0.0005071848,0.082253024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78101593,0.1735254,0.0072181295,0.008226317,0.027171817,0.0028423415],"domain_scores_gemma":[0.7720695,0.179132,0.00753914,0.014310534,0.023106847,0.0038420071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13038962,0.001110312,0.0013658368,0.006126563,0.0052809333,0.01811812,0.0020679012,0.0047560195,0.006939893],"category_scores_gemma":[0.14876433,0.00082569843,0.0012710043,0.006997484,0.022033919,0.013470271,0.012741048,0.0077476846,0.0013516311],"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":[0.00032780186,0.00033164694,0.0029669926,0.0020337044,0.000077092904,0.00022244838,0.1015719,0.0012693779,0.0017235728,0.5819767,0.007066624,0.30043224],"study_design_scores_gemma":[0.00019053764,0.0009781962,0.016229382,0.0062522455,0.00014950152,0.00075254467,0.066967025,0.0041911514,0.009677777,0.21203585,0.68234396,0.00023184992],"about_ca_topic_score_codex":0.006404458,"about_ca_topic_score_gemma":0.008159552,"teacher_disagreement_score":0.13038962,"about_ca_system_score_codex":0.016493635,"about_ca_system_score_gemma":0.021990886,"threshold_uncertainty_score":0.6895745},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033278372,0.0029057276,0.68002737,0.045306616,0.00076216296,0.0041830307,0.00018178107,0.00082630484,0.23252875],"genre_scores_gemma":[0.62912756,0.0023205727,0.3456323,0.0020595575,0.00031774616,0.004916455,0.00010541953,0.00017026793,0.0153500335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9471076,0.04506038,0.0008922555,0.0015815299,0.004453847,0.000904388],"domain_scores_gemma":[0.93396145,0.05089005,0.0026869716,0.004109122,0.006140198,0.0022122057],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.054029882,0.0010840363,0.00084428914,0.004682916,0.0033549948,0.014121511,0.002712882,0.002227034,0.012050565],"category_scores_gemma":[0.06847987,0.0004205648,0.0006863853,0.0022123673,0.01050897,0.00869123,0.008839326,0.0040946407,0.0010105511],"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":[0.00008437846,0.0007113752,0.0026676804,0.00060734653,0.000066379595,0.000088908,0.004925201,0.008581184,0.00047748958,0.7849323,0.0056559197,0.1912018],"study_design_scores_gemma":[0.0001226274,0.00040548114,0.0011751127,0.0009621033,0.00005025866,0.00005471569,0.008569771,0.024794511,0.0016457309,0.91211486,0.050051004,0.000053936485],"about_ca_topic_score_codex":0.0022946782,"about_ca_topic_score_gemma":0.0042838794,"teacher_disagreement_score":0.9459701,"about_ca_system_score_codex":0.011844702,"about_ca_system_score_gemma":0.016298264,"threshold_uncertainty_score":0.28574073},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012451637,0.06721769,0.0036289783,0.13622537,0.0030601437,0.00013130672,0.0010013978,0.00038769003,0.7758958],"genre_scores_gemma":[0.16724212,0.063444465,0.0068702428,0.01513794,0.0005838628,0.00011396565,0.000632599,0.00042353428,0.74555135],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99261767,0.0007265134,0.00016447232,0.0005485412,0.004365329,0.001577472],"domain_scores_gemma":[0.9906927,0.002106738,0.00018500454,0.00027001873,0.0051943436,0.0015510825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004206564,0.0006342321,0.0006769668,0.0033518027,0.024373388,0.016315857,0.001694755,0.0035680942,0.014925939],"category_scores_gemma":[0.010070797,0.0006162698,0.00044768568,0.01038681,0.010460257,0.0029320675,0.0027980278,0.0045836093,0.0023221127],"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":[0.000027979071,0.000029465085,0.0010731567,0.00034314807,0.000010990062,0.00023841117,0.013492257,0.00084211794,0.0002578019,0.42813948,0.4312541,0.1242911],"study_design_scores_gemma":[0.0000028984946,0.0000035294815,0.0014791235,0.00029770093,0.0000056842873,0.000032318563,0.0036836206,0.00038256994,0.0001097777,0.011123996,0.9828584,0.000020521273],"about_ca_topic_score_codex":0.994686,"about_ca_topic_score_gemma":0.9966853,"teacher_disagreement_score":0.6760105,"about_ca_system_score_codex":0.32398948,"about_ca_system_score_gemma":0.5603669,"threshold_uncertainty_score":0.7840764},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015725836,0.012718708,0.23684382,0.10564464,0.0031749206,0.0027307868,0.0004005528,0.001176977,0.6215838],"genre_scores_gemma":[0.48175842,0.022896804,0.3542706,0.029803853,0.0025609548,0.005180781,0.0010079172,0.0010744839,0.10144614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78788304,0.15521736,0.012346767,0.014905999,0.02484987,0.0047969655],"domain_scores_gemma":[0.7832322,0.12919778,0.007829775,0.048275925,0.024926778,0.0065375497],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14408962,0.0016325387,0.0017256308,0.007647828,0.011879813,0.029611222,0.008001783,0.0104912,0.020294832],"category_scores_gemma":[0.1481168,0.0017021456,0.0021973148,0.0064601805,0.04816262,0.033539698,0.026345676,0.010866285,0.0061727525],"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":[0.000031229836,0.000083617146,0.0009850719,0.0008402503,0.000027402955,0.00052537693,0.13594843,0.0005670403,0.0006388984,0.75208706,0.014850379,0.093415275],"study_design_scores_gemma":[0.000021502869,0.00007720298,0.00037463833,0.0033331404,0.000023936744,0.00035972966,0.02987463,0.00039434267,0.0003906149,0.26538303,0.6997222,0.000045061188],"about_ca_topic_score_codex":0.0030026496,"about_ca_topic_score_gemma":0.0025668337,"teacher_disagreement_score":0.85591036,"about_ca_system_score_codex":0.015361763,"about_ca_system_score_gemma":0.02517853,"threshold_uncertainty_score":0.76202786},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007858613,0.12732232,0.015745526,0.79815507,0.010020619,0.0017246191,0.0008142864,0.00013078128,0.038228117],"genre_scores_gemma":[0.41659877,0.19484876,0.188646,0.17975968,0.0098903505,0.0041329265,0.0015804411,0.00017951996,0.0043635857],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6919678,0.22241709,0.03636318,0.0053093117,0.038823023,0.005119592],"domain_scores_gemma":[0.20969045,0.68066305,0.02779415,0.011634214,0.058689997,0.0115281865],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.29175028,0.002811899,0.004846115,0.03165326,0.0047949827,0.030052466,0.00733324,0.017434731,0.0122685],"category_scores_gemma":[0.61713976,0.001703951,0.0033832416,0.010392747,0.009499284,0.021159988,0.011975696,0.020118957,0.0019732942],"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":[0.0012378857,0.0018159993,0.025726326,0.063610025,0.006575631,0.0011316938,0.006555163,0.0045088693,0.00076720497,0.13031627,0.13835911,0.6193958],"study_design_scores_gemma":[0.001647167,0.00070676144,0.007647364,0.3234506,0.004727447,0.0004068045,0.013810873,0.005979947,0.0017205935,0.41312984,0.22623734,0.0005352972],"about_ca_topic_score_codex":0.014446169,"about_ca_topic_score_gemma":0.031810224,"teacher_disagreement_score":0.29175028,"about_ca_system_score_codex":0.017729463,"about_ca_system_score_gemma":0.104076974,"threshold_uncertainty_score":0.873398},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081037,0.0023854224,0.0015561177,0.02090406,0.00007543377,0.00092351,0.0006683416,0.000021513553,0.06536195],"genre_scores_gemma":[0.9899103,0.001274759,0.0020835844,0.0005004634,0.000016286194,0.0003749858,0.00017069696,0.000014677766,0.0056543034],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98453146,0.006385856,0.0010039605,0.00073768693,0.0046486612,0.0026924727],"domain_scores_gemma":[0.9368415,0.04938803,0.0035182917,0.0012435074,0.0073955767,0.0016131233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02600291,0.0005948305,0.00069272757,0.0058837454,0.02962751,0.011749854,0.001994928,0.00230086,0.001966271],"category_scores_gemma":[0.047040027,0.0005934168,0.00037419423,0.0114466,0.02325103,0.004818971,0.0066259583,0.0028938623,0.00009428263],"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":[0.000055151762,0.000028392158,0.005253592,0.00023671542,0.0000076035612,0.00039227784,0.95349175,0.0002178139,0.00036149877,0.029295143,0.0012901356,0.00936999],"study_design_scores_gemma":[0.000016132988,0.0000208199,0.012759878,0.00044912586,0.000023301573,0.000035362107,0.9296388,0.0003240079,0.0005475406,0.0032499793,0.052902643,0.00003232707],"about_ca_topic_score_codex":0.9545992,"about_ca_topic_score_gemma":0.96155524,"teacher_disagreement_score":0.34416184,"about_ca_system_score_codex":0.34416184,"about_ca_system_score_gemma":0.30224124,"threshold_uncertainty_score":0.7606793},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081037,0.0023854224,0.0015561177,0.02090406,0.00007543377,0.00092351,0.0006683416,0.000021513553,0.06536195],"genre_scores_gemma":[0.9899103,0.001274759,0.0020835844,0.0005004634,0.000016286194,0.0003749858,0.00017069696,0.000014677766,0.0056543034],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98453146,0.006385856,0.0010039605,0.00073768693,0.0046486612,0.0026924727],"domain_scores_gemma":[0.9368415,0.04938803,0.0035182917,0.0012435074,0.0073955767,0.0016131233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02600291,0.0005948305,0.00069272757,0.0058837454,0.02962751,0.011749854,0.001994928,0.00230086,0.001966271],"category_scores_gemma":[0.047040027,0.0005934168,0.00037419423,0.0114466,0.02325103,0.004818971,0.0066259583,0.0028938623,0.00009428263],"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":[0.000055151762,0.000028392158,0.005253592,0.00023671542,0.0000076035612,0.00039227784,0.95349175,0.0002178139,0.00036149877,0.029295143,0.0012901356,0.00936999],"study_design_scores_gemma":[0.000016132988,0.0000208199,0.012759878,0.00044912586,0.000023301573,0.000035362107,0.9296388,0.0003240079,0.0005475406,0.0032499793,0.052902643,0.00003232707],"about_ca_topic_score_codex":0.9545992,"about_ca_topic_score_gemma":0.96155524,"teacher_disagreement_score":0.34416184,"about_ca_system_score_codex":0.34416184,"about_ca_system_score_gemma":0.30224124,"threshold_uncertainty_score":0.7606793},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8283756,0.0003779038,0.090064265,0.0027799571,0.00014305988,0.008817081,0.00351618,0.0003537548,0.06557234],"genre_scores_gemma":[0.89527696,0.0001793942,0.09083704,0.00015352744,0.000023627868,0.00706307,0.0011524259,0.00007325861,0.005240695],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9671698,0.02472067,0.0010392185,0.002204213,0.0031534715,0.0017125827],"domain_scores_gemma":[0.94166714,0.026985368,0.004555967,0.011633814,0.011099973,0.0040577487],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.04012872,0.0005834439,0.00043608987,0.0056840796,0.009465243,0.0070280624,0.002538328,0.0016611931,0.00668984],"category_scores_gemma":[0.054615103,0.0006654794,0.00046633146,0.006241392,0.004248866,0.0097757075,0.015477047,0.001980154,0.0008000729],"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":[0.0006302679,0.0016305203,0.19708529,0.00095447875,0.00012617493,0.0013568251,0.45802426,0.003785315,0.0012851383,0.078987345,0.010623121,0.24551134],"study_design_scores_gemma":[0.00020605985,0.0003639536,0.06451338,0.00068465475,0.00010151113,0.00047487873,0.7686617,0.0171606,0.0017746649,0.05563434,0.09030033,0.00012391325],"about_ca_topic_score_codex":0.04034949,"about_ca_topic_score_gemma":0.07600769,"teacher_disagreement_score":0.9905348,"about_ca_system_score_codex":0.0071288636,"about_ca_system_score_gemma":0.023409046,"threshold_uncertainty_score":0.21222353},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29407215,0.0068185288,0.14481401,0.19171377,0.00091888406,0.00058240484,0.000056199322,0.00037364094,0.3606505],"genre_scores_gemma":[0.9713679,0.0006625893,0.0077812984,0.0034782332,0.000056484896,0.00013794232,0.000008960072,0.000109369415,0.016397186],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7739963,0.20351614,0.002787008,0.0044667823,0.008900447,0.006333375],"domain_scores_gemma":[0.9092591,0.06736936,0.004076526,0.005910384,0.008814386,0.0045702714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12272829,0.0005840787,0.000990733,0.0032032249,0.034517594,0.030400183,0.0028067878,0.005050606,0.0060369032],"category_scores_gemma":[0.09185512,0.0006062889,0.00070257,0.0020383117,0.09518934,0.021604078,0.020985292,0.009117198,0.0008051072],"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":[0.00003401524,0.000049663184,0.0010690906,0.00007399299,0.000010272874,0.00037991337,0.569746,0.00031083927,0.00038338196,0.4056766,0.00392617,0.018339962],"study_design_scores_gemma":[0.0000201081,0.00008138898,0.0010287839,0.00069550757,0.000027839485,0.0003548729,0.6105668,0.0013007007,0.0018192456,0.17244008,0.2115526,0.000112170885],"about_ca_topic_score_codex":0.030774968,"about_ca_topic_score_gemma":0.036658224,"teacher_disagreement_score":0.12272829,"about_ca_system_score_codex":0.02690808,"about_ca_system_score_gemma":0.020760996,"threshold_uncertainty_score":0.649057},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91610503,0.001149373,0.010227865,0.019547835,0.00015903832,0.00052420225,0.000052966207,0.0000877645,0.052145917],"genre_scores_gemma":[0.99319094,0.00030006867,0.002787734,0.0007850827,0.000021293166,0.00021450853,0.000017345465,0.000035755653,0.0026472865],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8439943,0.13799137,0.001546973,0.0017750778,0.0057793865,0.008912901],"domain_scores_gemma":[0.9398753,0.03917284,0.0031794098,0.002081067,0.006805184,0.008886165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08169101,0.00075850234,0.00093043974,0.002959014,0.028528858,0.02238078,0.0030161378,0.0025117132,0.004734807],"category_scores_gemma":[0.04712327,0.00078900123,0.00060441723,0.00231095,0.029749839,0.009665422,0.03120348,0.0051259603,0.00052471436],"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":[0.000058575148,0.00027450462,0.0095499195,0.00012709967,0.0000128208285,0.0005546886,0.956522,0.00011601852,0.00032873853,0.008712699,0.0018396745,0.021903211],"study_design_scores_gemma":[0.00000962957,0.00007105233,0.0023012483,0.0001782731,0.000007670768,0.000102135,0.9834442,0.00018389962,0.0003896439,0.0018801264,0.011418088,0.000013943653],"about_ca_topic_score_codex":0.027504515,"about_ca_topic_score_gemma":0.0675269,"teacher_disagreement_score":0.08169101,"about_ca_system_score_codex":0.026170045,"about_ca_system_score_gemma":0.027590847,"threshold_uncertainty_score":0.43202853},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09154124,0.07447821,0.05341464,0.059377044,0.0011433895,0.027544864,0.2736365,0.004726834,0.4141373],"genre_scores_gemma":[0.37606606,0.11433101,0.29003227,0.00362851,0.00041121955,0.042942435,0.11192725,0.0011706285,0.059490707],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98961544,0.0052909576,0.0014947946,0.00029594367,0.0023896627,0.000913159],"domain_scores_gemma":[0.9638738,0.01495928,0.0032562364,0.0011356564,0.015058337,0.0017166632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018755915,0.00081835454,0.000978454,0.01922486,0.0016383086,0.009750025,0.0012308283,0.00095908594,0.018743133],"category_scores_gemma":[0.041629974,0.0007885153,0.0009208807,0.027197529,0.0008105337,0.0055915103,0.0039027338,0.0013812871,0.0020141073],"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":[0.00036114475,0.0004338083,0.013151836,0.013764536,0.00024984794,0.00056784926,0.003944353,0.01507324,0.00059757143,0.05408087,0.43883908,0.45893577],"study_design_scores_gemma":[0.00017504004,0.00025976117,0.047147118,0.011300568,0.00018767492,0.00034738806,0.007240075,0.0044136094,0.00057616073,0.008065937,0.9201104,0.00017635588],"about_ca_topic_score_codex":0.05273892,"about_ca_topic_score_gemma":0.04735861,"teacher_disagreement_score":0.05273892,"about_ca_system_score_codex":0.009462198,"about_ca_system_score_gemma":0.02334304,"threshold_uncertainty_score":0.10486388},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038264995,0.3291274,0.085370734,0.030802378,0.007729588,0.0016862878,0.26301193,0.008475166,0.26997006],"genre_scores_gemma":[0.052052133,0.34442163,0.22277874,0.008329964,0.0031643133,0.0056889346,0.16515182,0.0040074303,0.19440514],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936925,0.0013850082,0.0007659523,0.00030627326,0.0035208294,0.000329431],"domain_scores_gemma":[0.9778516,0.009483063,0.0015239618,0.001519236,0.00910585,0.0005162295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010546369,0.0017437091,0.0015561173,0.008680834,0.0010872083,0.0043684547,0.002492952,0.0013753807,0.04861079],"category_scores_gemma":[0.033164386,0.0014741212,0.0010013779,0.018782813,0.0017123038,0.003991624,0.0019027601,0.003038306,0.013393827],"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":[0.000017816477,0.000041519987,0.002275136,0.0006509822,0.000022210892,0.000016626338,0.00018513214,0.00038473576,0.00007902227,0.007603173,0.7657196,0.22300407],"study_design_scores_gemma":[0.00001381474,0.000027024536,0.017871402,0.0026248468,0.00003406819,0.000099129946,0.00055127684,0.00043384734,0.00038023302,0.0094231665,0.96848863,0.00005249816],"about_ca_topic_score_codex":0.320482,"about_ca_topic_score_gemma":0.30775672,"teacher_disagreement_score":0.320482,"about_ca_system_score_codex":0.0073786452,"about_ca_system_score_gemma":0.024541812,"threshold_uncertainty_score":0.63723314},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005378189,0.0065781465,0.001481575,0.058085445,0.9322024,0.00048100587,0.00004964401,0.00019669314,0.00087124715],"genre_scores_gemma":[0.0016470471,0.009637,0.004921958,0.062196102,0.9139353,0.0014816724,0.00007363929,0.0002371551,0.0058701094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.87273633,0.057263896,0.017303908,0.006775432,0.043022472,0.00289792],"domain_scores_gemma":[0.48535338,0.264628,0.028617747,0.018898545,0.1877559,0.014746456],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09495841,0.00393216,0.0037836453,0.008567208,0.0047057075,0.01810101,0.006511351,0.017871933,0.018043295],"category_scores_gemma":[0.4261923,0.0018331243,0.0049252626,0.0024241796,0.010394881,0.012029572,0.006059911,0.028279921,0.0139478585],"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":[0.000072873285,0.000021489861,0.000043153435,0.002493132,0.000065860215,0.00011329055,0.0003401763,0.00005773863,0.000109824236,0.0020351869,0.9749452,0.019701997],"study_design_scores_gemma":[0.00012556605,0.000121304765,0.00024063187,0.007861089,0.00012366331,0.00030711992,0.00037537864,0.00034665188,0.00031271204,0.009552193,0.980531,0.00010265894],"about_ca_topic_score_codex":0.0010775205,"about_ca_topic_score_gemma":0.0015670551,"teacher_disagreement_score":0.9050416,"about_ca_system_score_codex":0.0055659935,"about_ca_system_score_gemma":0.018560557,"threshold_uncertainty_score":0.50219405},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11158539,0.0034532459,0.18352169,0.1361236,0.0012698809,0.002544516,0.00006645256,0.00036497536,0.5610702],"genre_scores_gemma":[0.90859747,0.00078801485,0.067852065,0.007635951,0.00011598328,0.0013219742,0.000020736948,0.00010500444,0.013562756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8275636,0.15516579,0.0030584275,0.0038483846,0.006802672,0.0035611838],"domain_scores_gemma":[0.9082321,0.054903567,0.004435304,0.013059732,0.012198948,0.0071703386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09680399,0.0005294603,0.0004667593,0.0034455177,0.015992623,0.017319951,0.003574328,0.003629949,0.0064625926],"category_scores_gemma":[0.08525659,0.00053445133,0.0006180168,0.0026189112,0.042901345,0.008441208,0.01650203,0.0071415617,0.00058769056],"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":[0.00004444038,0.00018462952,0.005011303,0.00029516438,0.000050701514,0.00088328804,0.2213152,0.001100539,0.0006444945,0.69507277,0.0060288776,0.06936868],"study_design_scores_gemma":[0.000044424145,0.00014554702,0.0051067504,0.0018944019,0.000042651285,0.0008004617,0.22673602,0.0023468737,0.0012842832,0.51357377,0.2478995,0.00012540286],"about_ca_topic_score_codex":0.016632134,"about_ca_topic_score_gemma":0.03296918,"teacher_disagreement_score":0.09680399,"about_ca_system_score_codex":0.026828244,"about_ca_system_score_gemma":0.039510015,"threshold_uncertainty_score":0.51195455},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18729222,0.024430817,0.09873801,0.39828047,0.0024603307,0.0051364005,0.0009597505,0.0018305983,0.28087142],"genre_scores_gemma":[0.8279826,0.015545726,0.12333617,0.015847439,0.00043141175,0.0028335194,0.0004383328,0.00028715687,0.013297597],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9376193,0.035107866,0.002705589,0.0017288773,0.011085035,0.011753326],"domain_scores_gemma":[0.90093446,0.03797434,0.009153232,0.0062758746,0.020948999,0.024713077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1259933,0.00164321,0.0018025305,0.007909753,0.0053948974,0.041527968,0.004680902,0.0062515927,0.009612548],"category_scores_gemma":[0.13346064,0.00080867053,0.0011755163,0.0070377365,0.008441056,0.026620017,0.020923575,0.0043395874,0.003193846],"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":[0.00037228002,0.0012010037,0.02889837,0.004926151,0.00038948085,0.0004535511,0.01795262,0.008184468,0.0016999977,0.38495046,0.04085178,0.5101198],"study_design_scores_gemma":[0.00035513254,0.0014606775,0.030461647,0.008016762,0.0002748311,0.00033423075,0.12012088,0.005452604,0.004217026,0.35463303,0.4741726,0.00050068443],"about_ca_topic_score_codex":0.009513513,"about_ca_topic_score_gemma":0.013537732,"teacher_disagreement_score":0.8740067,"about_ca_system_score_codex":0.02650582,"about_ca_system_score_gemma":0.10396853,"threshold_uncertainty_score":0.6663242},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020319147,0.0159932,0.5780887,0.06420456,0.0013515025,0.0002481892,0.00017501354,0.0002345892,0.31938508],"genre_scores_gemma":[0.7898621,0.0071630403,0.18123253,0.0053120083,0.0012920244,0.0006996945,0.00013877642,0.00023634326,0.014063465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9437994,0.042561617,0.0027202137,0.0021180965,0.0073976927,0.0014028912],"domain_scores_gemma":[0.8075626,0.16914997,0.006196782,0.0065644723,0.009326984,0.0011991822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045290153,0.001200285,0.0014273179,0.008151231,0.0036381448,0.016693452,0.0023002876,0.006999048,0.008240356],"category_scores_gemma":[0.1462071,0.00063403905,0.0015961248,0.007707749,0.042673238,0.026309943,0.0070290505,0.0067029805,0.001376958],"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":[0.0000055256796,0.000004903461,0.00007485044,0.000045943874,0.000003478335,0.00001494075,0.00032865483,0.00062546984,0.000019272193,0.99564517,0.00029643645,0.0029355106],"study_design_scores_gemma":[0.0000051096176,0.0000037437062,0.000035548743,0.00007675285,0.000002651937,0.00001125526,0.00010616862,0.0010236471,0.000039029554,0.9949197,0.0037716064,0.0000047760736],"about_ca_topic_score_codex":0.0025775626,"about_ca_topic_score_gemma":0.0014085814,"teacher_disagreement_score":0.045290153,"about_ca_system_score_codex":0.0081354445,"about_ca_system_score_gemma":0.0041068587,"threshold_uncertainty_score":0.23952013},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019465675,0.000014699027,0.00001250412,0.00004707934,0.000012919191,0.000007791874,0.9992976,0.00005763195,0.0005302298],"genre_scores_gemma":[0.00024264553,0.00005184394,0.00013927743,0.00007856218,0.000008170751,0.00008516977,0.99751496,0.00006700792,0.0018124434],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640393,0.0003769882,0.0003622599,0.00050472823,0.0015755672,0.00077644084],"domain_scores_gemma":[0.97913796,0.004018617,0.0013219721,0.0030293507,0.01034437,0.0021476562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028871833,0.0025065767,0.0023063011,0.009263413,0.002455024,0.005786059,0.0032972095,0.0031282683,0.15050963],"category_scores_gemma":[0.018315168,0.0014953605,0.0019464197,0.020498442,0.0009838692,0.0015744794,0.0024170636,0.0032100056,0.13600996],"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":[0.000015775982,0.000007571477,0.0002294445,0.00012911756,0.0000069118014,0.00000397179,0.0000063785114,0.00010041398,0.000008992123,0.00023131949,0.998604,0.0006561563],"study_design_scores_gemma":[0.00018403861,0.000007410704,0.0046820994,0.00034431007,0.000019617777,0.000010958892,0.00006800292,0.00029089925,0.0001052025,0.00086799776,0.99338704,0.0000324285],"about_ca_topic_score_codex":0.75008804,"about_ca_topic_score_gemma":0.7981817,"teacher_disagreement_score":0.98756397,"about_ca_system_score_codex":0.012436006,"about_ca_system_score_gemma":0.034665592,"threshold_uncertainty_score":0.5035049},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29695863,0.005188555,0.020138077,0.2766451,0.000727015,0.00016837085,0.000044148434,0.00019204347,0.39993805],"genre_scores_gemma":[0.98452723,0.00045641267,0.0024544054,0.0032266472,0.00005306877,0.000055223223,0.000012412298,0.0000244337,0.009190249],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97138286,0.021182979,0.00045038998,0.0009381327,0.004551342,0.0014943805],"domain_scores_gemma":[0.9631212,0.027514175,0.002566008,0.0012375986,0.0027926203,0.0027685082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024341235,0.00017870155,0.00019411318,0.0013382877,0.009895293,0.014126483,0.0012828661,0.0025249429,0.0030620862],"category_scores_gemma":[0.045009673,0.00026359296,0.00018072697,0.0013144109,0.042384617,0.005105628,0.007391649,0.0069978987,0.00027245472],"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":[0.00002183803,0.00013739627,0.009007137,0.000071515635,0.000008590035,0.00014825368,0.33947673,0.0002714988,0.00047888554,0.55816245,0.011770044,0.08044565],"study_design_scores_gemma":[0.00004219928,0.00012875805,0.015345628,0.0005165857,0.000017067605,0.00008682297,0.4990391,0.0010178856,0.0016077813,0.22812025,0.25402802,0.000049813512],"about_ca_topic_score_codex":0.034578543,"about_ca_topic_score_gemma":0.06960223,"teacher_disagreement_score":0.034578543,"about_ca_system_score_codex":0.027398603,"about_ca_system_score_gemma":0.03675288,"threshold_uncertainty_score":0.19879168},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066893484,0.00359227,0.0012969447,0.0035484384,0.001403076,0.00007561159,0.002258983,0.00030479842,0.9868509],"genre_scores_gemma":[0.004340678,0.0017821956,0.00069771986,0.00062644953,0.00013046907,0.000019007186,0.000765803,0.000093370894,0.99154425],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927706,0.000035263398,0.00001429621,0.00011273101,0.00042333297,0.00013725624],"domain_scores_gemma":[0.99927324,0.00003767563,0.000014073575,0.00004376831,0.0005186136,0.00011255172],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040721445,0.00074001146,0.00047204536,0.0014994736,0.0043529505,0.006880571,0.0013271935,0.0017078365,0.25992265],"category_scores_gemma":[0.0010489788,0.000275517,0.00038987267,0.0023078246,0.001402127,0.0015258393,0.0015820249,0.0018621172,0.091622196],"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":[0.0000138179485,0.000017348242,0.00034237426,0.00011752504,0.0000018037261,0.000116032395,0.0009394941,0.00024282024,0.0003105111,0.09286831,0.80088675,0.10414319],"study_design_scores_gemma":[5.298913e-7,0.0000015222153,0.0001995961,0.00004918049,5.155467e-7,0.000024609284,0.000116313844,0.00001906203,0.00003537031,0.00092344865,0.99862766,0.000002193048],"about_ca_topic_score_codex":0.63116544,"about_ca_topic_score_gemma":0.7618775,"teacher_disagreement_score":0.7400774,"about_ca_system_score_codex":0.019979512,"about_ca_system_score_gemma":0.01864127,"threshold_uncertainty_score":0.86952794},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081045836,0.026089638,0.169626,0.32294187,0.006473825,0.00036463796,0.0011186091,0.00057279365,0.39176682],"genre_scores_gemma":[0.86672515,0.009901161,0.060003005,0.011099831,0.0021613846,0.00056767894,0.00029417613,0.00044109215,0.048806503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94801134,0.030179828,0.0032984745,0.0035235132,0.0137683,0.0012185625],"domain_scores_gemma":[0.8232472,0.13793461,0.007459761,0.007671684,0.022353556,0.001333271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03681528,0.0006487611,0.0007508268,0.0058295247,0.0038104607,0.014148727,0.0024344549,0.003383862,0.009534384],"category_scores_gemma":[0.12663458,0.00038591344,0.00079551496,0.0052324245,0.01808762,0.011015908,0.0046035224,0.0049849083,0.0017163712],"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":[0.00009230003,0.00004565812,0.005027641,0.000653298,0.00003057904,0.00020398639,0.041396793,0.0005256004,0.00053500105,0.845092,0.017122267,0.08927482],"study_design_scores_gemma":[0.000042248277,0.00022350617,0.019404367,0.0039331215,0.000062439685,0.00065152405,0.051562604,0.0024945585,0.004043727,0.3360719,0.58132243,0.00018752774],"about_ca_topic_score_codex":0.011898865,"about_ca_topic_score_gemma":0.012300143,"teacher_disagreement_score":0.03681528,"about_ca_system_score_codex":0.009071495,"about_ca_system_score_gemma":0.007926827,"threshold_uncertainty_score":0.19470006},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002999649,0.0075905384,0.0006009909,0.024708798,0.9659008,0.000028679711,0.00003512019,0.000051713258,0.0010534466],"genre_scores_gemma":[0.0004250679,0.009792714,0.0008561145,0.026011538,0.9579534,0.000058347898,0.000046200585,0.000112903326,0.004743884],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9803832,0.0039529586,0.0029294454,0.0016315924,0.010266619,0.0008361165],"domain_scores_gemma":[0.87564296,0.05876055,0.0058490676,0.002835764,0.047957562,0.008954033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025063826,0.002813615,0.003826299,0.007081228,0.0034719757,0.014696886,0.0037085179,0.010363167,0.021686435],"category_scores_gemma":[0.07473735,0.0013889273,0.004203984,0.0033300428,0.0042752805,0.0067534987,0.0034565758,0.02200237,0.014368189],"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":[0.000021575588,0.000018200137,0.00005577825,0.00036741293,0.000015300686,0.000045551984,0.000036819176,0.000039319155,0.0000930006,0.00093567383,0.9784873,0.019884074],"study_design_scores_gemma":[0.000021203059,0.00004990083,0.00031146975,0.001199907,0.00002985193,0.00028525185,0.000074486445,0.00016732079,0.000110422814,0.0023295172,0.9953844,0.00003622599],"about_ca_topic_score_codex":0.0011359022,"about_ca_topic_score_gemma":0.003312322,"teacher_disagreement_score":0.025063826,"about_ca_system_score_codex":0.0030435128,"about_ca_system_score_gemma":0.007408801,"threshold_uncertainty_score":0.13255179},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7442185,0.0027010518,0.010527209,0.057677735,0.00017369597,0.0009092889,0.00015012448,0.00017543732,0.18346694],"genre_scores_gemma":[0.97734344,0.0014761476,0.0069763428,0.0022346247,0.000028581473,0.00010875791,0.00006733171,0.000046627305,0.011718292],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9487652,0.021452995,0.0015245861,0.0022966948,0.01798227,0.007978284],"domain_scores_gemma":[0.85146886,0.07187047,0.0057352097,0.0030766418,0.045029875,0.02281892],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04955318,0.00046678152,0.00048914395,0.003942867,0.026235146,0.018958764,0.003302292,0.0042847134,0.004555677],"category_scores_gemma":[0.10231987,0.00042396417,0.0003173354,0.0047385925,0.008907944,0.0058319517,0.007129336,0.0042080246,0.00051258487],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015684278,0.0012576504,0.07884949,0.00072477246,0.00006709826,0.0011170125,0.5833698,0.0019133675,0.0020893693,0.021002611,0.025232246,0.28421974],"study_design_scores_gemma":[0.000053740085,0.00035336718,0.056237232,0.0012140351,0.000058838446,0.00026116963,0.7881239,0.0027714996,0.0014707214,0.008203382,0.14110066,0.00015146579],"about_ca_topic_score_codex":0.777486,"about_ca_topic_score_gemma":0.8944908,"teacher_disagreement_score":0.95044684,"about_ca_system_score_codex":0.08646534,"about_ca_system_score_gemma":0.2790519,"threshold_uncertainty_score":0.62735283},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001389528,0.234825,0.108137205,0.42446473,0.010945527,0.0005889403,0.00033783118,0.0004054821,0.21890576],"genre_scores_gemma":[0.14092739,0.29456857,0.26687828,0.14490795,0.013084448,0.008302457,0.0005609233,0.00080624764,0.12996379],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8329523,0.1428109,0.002434078,0.0027071605,0.01766894,0.0014265578],"domain_scores_gemma":[0.52863646,0.44195768,0.0027118772,0.0127743725,0.010877125,0.0030425522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17098577,0.0016050556,0.0032164077,0.005585964,0.0060312375,0.021725401,0.005225472,0.009666066,0.019804692],"category_scores_gemma":[0.13583604,0.0015891712,0.0012156715,0.005143877,0.08753412,0.041285828,0.012832813,0.011584742,0.004813246],"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":[0.000029541305,0.00005171811,0.0001156161,0.0026133938,0.000015882326,0.000057743997,0.012040876,0.0002029656,0.00014534169,0.8330432,0.04755935,0.104124315],"study_design_scores_gemma":[0.00002801117,0.00002157829,0.000087715714,0.0037794982,0.0000071650047,0.00010235747,0.0070284894,0.0003056439,0.000118260636,0.7823578,0.20613667,0.000026890775],"about_ca_topic_score_codex":0.004709852,"about_ca_topic_score_gemma":0.0063291946,"teacher_disagreement_score":0.82901424,"about_ca_system_score_codex":0.014338365,"about_ca_system_score_gemma":0.027995586,"threshold_uncertainty_score":0.90427},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062805777,0.9670913,0.004769043,0.015600752,0.0004985606,0.00028214758,0.00014187054,0.000021444694,0.005314355],"genre_scores_gemma":[0.069871455,0.9132697,0.011479808,0.0037878943,0.0004968773,0.0005810567,0.0001709838,0.000025496138,0.00031676443],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9819375,0.009753063,0.0035608145,0.00087572174,0.0033408226,0.00053201575],"domain_scores_gemma":[0.71480715,0.24809591,0.0131496675,0.0033895727,0.018817935,0.0017397049],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04974335,0.0006450059,0.0023898953,0.013381621,0.0016264321,0.0088867005,0.0014972357,0.0019474067,0.002536958],"category_scores_gemma":[0.12700666,0.00063126505,0.0019279777,0.016620146,0.0027827015,0.01144428,0.0045151734,0.0028159395,0.00033315105],"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":[0.00014267431,0.00017463761,0.0057379846,0.22205646,0.0016696848,0.00032810163,0.014725041,0.0010014664,0.00072975055,0.042176202,0.011917158,0.69934076],"study_design_scores_gemma":[0.00005888685,0.0002745704,0.016572917,0.6067102,0.0056442977,0.0007676105,0.034327753,0.0010451541,0.0010406952,0.03230424,0.3010931,0.00016055725],"about_ca_topic_score_codex":0.0038509727,"about_ca_topic_score_gemma":0.010647668,"teacher_disagreement_score":0.95025665,"about_ca_system_score_codex":0.0050107194,"about_ca_system_score_gemma":0.029490652,"threshold_uncertainty_score":0.26307112},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028761065,0.0010183193,0.10320225,0.0045342515,0.0024028898,0.015273682,0.047177933,0.0019148724,0.7957147],"genre_scores_gemma":[0.16766854,0.0022147142,0.20758557,0.002229165,0.0009032325,0.040841296,0.052958168,0.004602487,0.5209968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98919314,0.0041801664,0.0008215935,0.0016209139,0.0035587791,0.0006254513],"domain_scores_gemma":[0.98134434,0.006767327,0.00058969215,0.0023291903,0.008598777,0.00037066496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010875483,0.0008457828,0.0009828322,0.011852009,0.0034342732,0.0059900377,0.0020436086,0.00084812037,0.12649581],"category_scores_gemma":[0.03714573,0.00044123252,0.0011555897,0.014487722,0.0022130348,0.003760323,0.004208578,0.001548217,0.029166784],"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":[0.00025260207,0.000106913576,0.0019554165,0.0040499596,0.00005757075,0.00021724237,0.07503199,0.0003740087,0.0027627293,0.2041567,0.2870355,0.42399928],"study_design_scores_gemma":[0.000029687451,0.000040596206,0.0022795475,0.0011468211,0.000048798305,0.00012482185,0.03929539,0.0006826207,0.0014670315,0.034833804,0.92002416,0.000026803604],"about_ca_topic_score_codex":0.0050096214,"about_ca_topic_score_gemma":0.0060281996,"teacher_disagreement_score":0.12649581,"about_ca_system_score_codex":0.004179671,"about_ca_system_score_gemma":0.009557264,"threshold_uncertainty_score":0.42317063},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004691823,0.0023582822,0.0066221394,0.02632441,0.006935133,0.00026032518,0.005398311,0.0008665821,0.9465428],"genre_scores_gemma":[0.09290859,0.0030490886,0.006650606,0.03480615,0.0022739107,0.00044544175,0.00954121,0.0013778043,0.8489472],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99690175,0.0005086559,0.00010302253,0.00075996626,0.0012616958,0.00046494365],"domain_scores_gemma":[0.9944781,0.0011384416,0.00022637784,0.000733195,0.0027347794,0.00068905414],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00342321,0.0008601016,0.000473508,0.0012616604,0.0017224008,0.005997492,0.001917658,0.002169032,0.44709998],"category_scores_gemma":[0.01632434,0.00021565375,0.0010781356,0.0010058997,0.001083566,0.0033583543,0.0021904223,0.0019777855,0.17257571],"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":[0.0006527413,0.00013014326,0.003954742,0.0009253476,0.00006678928,0.00024125188,0.0008751228,0.00062317215,0.001535818,0.10002879,0.64103353,0.24993245],"study_design_scores_gemma":[0.00004717391,0.000041658393,0.0039091655,0.00053204485,0.000039863164,0.00012814396,0.001828009,0.0002062719,0.0012545374,0.025705894,0.96629137,0.000015958964],"about_ca_topic_score_codex":0.009310883,"about_ca_topic_score_gemma":0.008078172,"teacher_disagreement_score":0.44709998,"about_ca_system_score_codex":0.0033188865,"about_ca_system_score_gemma":0.0042522587,"threshold_uncertainty_score":0.7886448},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48802778,0.0067803124,0.06251783,0.28361994,0.00089359866,0.0018329178,0.00048277155,0.0005820861,0.15526277],"genre_scores_gemma":[0.97040963,0.0011963552,0.02201591,0.003499558,0.00009954117,0.0005969199,0.0001134556,0.000079739395,0.0019889218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7110819,0.21283136,0.013724812,0.009230595,0.036780056,0.016351264],"domain_scores_gemma":[0.51682985,0.30833933,0.04067477,0.0274892,0.09412217,0.01254469],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25782382,0.0005690552,0.0009778845,0.009021072,0.011053453,0.031750426,0.003604721,0.0052469564,0.0020156663],"category_scores_gemma":[0.40749115,0.0010126126,0.000568925,0.010895831,0.022958657,0.013119882,0.008649492,0.0047079925,0.0004134769],"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":[0.0003055224,0.001015883,0.08301634,0.001534473,0.00014870388,0.0005971419,0.17420341,0.012957432,0.0018600817,0.36329037,0.025169527,0.33590117],"study_design_scores_gemma":[0.00021656923,0.00064201,0.15733258,0.007399133,0.0001211,0.00017463288,0.33914143,0.0148997065,0.0049966504,0.21280825,0.2618394,0.00042850434],"about_ca_topic_score_codex":0.24196346,"about_ca_topic_score_gemma":0.19838312,"teacher_disagreement_score":0.25782382,"about_ca_system_score_codex":0.16499034,"about_ca_system_score_gemma":0.24592866,"threshold_uncertainty_score":0.96849287},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015057789,0.0017464741,0.9627115,0.0009909525,0.00017808462,0.012756572,0.00036491296,0.0002122394,0.0059813345],"genre_scores_gemma":[0.12074955,0.0006307988,0.83449614,0.00040621808,0.00005544361,0.042477395,0.00016928844,0.000052862903,0.0009623272],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.53442067,0.44825324,0.003781645,0.0045824377,0.008060665,0.000901321],"domain_scores_gemma":[0.73138,0.2456425,0.007985099,0.009658653,0.0043834923,0.0009501767],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20641674,0.002461385,0.0033527361,0.004445846,0.001664784,0.0048428145,0.0029007748,0.0024927633,0.005544041],"category_scores_gemma":[0.22863796,0.0011016761,0.003943981,0.0028827786,0.0036094736,0.0029367986,0.008344995,0.003407054,0.00046371925],"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":[0.0046347464,0.0016906706,0.01414279,0.0059538204,0.005549044,0.00021911184,0.00649524,0.086611666,0.0011024615,0.308026,0.0034164048,0.5621581],"study_design_scores_gemma":[0.0037661786,0.009337188,0.013669757,0.005063819,0.0021073145,0.00030508856,0.0032393436,0.5145229,0.0042341338,0.40759698,0.035625488,0.0005319276],"about_ca_topic_score_codex":0.0033932906,"about_ca_topic_score_gemma":0.00424471,"teacher_disagreement_score":0.20641674,"about_ca_system_score_codex":0.006051854,"about_ca_system_score_gemma":0.0055156187,"threshold_uncertainty_score":0.97862947},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2812076,0.016880158,0.007843901,0.28230634,0.0011962774,0.0007270792,0.0006156099,0.00020442269,0.40901864],"genre_scores_gemma":[0.89570355,0.015877364,0.012424325,0.017358882,0.00008938653,0.0001969363,0.000275585,0.000110383946,0.057963558],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98985857,0.0040636687,0.00025061992,0.00054426567,0.0022719577,0.003010827],"domain_scores_gemma":[0.9781837,0.0080467295,0.00052855775,0.00064116745,0.008453953,0.0041457983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009990581,0.0007255483,0.00040943534,0.001652989,0.022256527,0.015427884,0.0033507706,0.0030176612,0.006098371],"category_scores_gemma":[0.013712675,0.00043276616,0.00050739566,0.004024739,0.010417724,0.0045950413,0.006383822,0.0053743953,0.0006027271],"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":[0.00021525193,0.00037780288,0.035899807,0.0014755513,0.00012761656,0.010972495,0.30080026,0.0065892343,0.0030369952,0.19888675,0.13009545,0.3115228],"study_design_scores_gemma":[0.00004242241,0.00010675647,0.018329179,0.0012705114,0.000062181665,0.0006447253,0.45589426,0.0013148771,0.0013204664,0.012409443,0.5084383,0.00016693016],"about_ca_topic_score_codex":0.9897984,"about_ca_topic_score_gemma":0.9966151,"teacher_disagreement_score":0.18452583,"about_ca_system_score_codex":0.18452583,"about_ca_system_score_gemma":0.40004373,"threshold_uncertainty_score":0.94583446},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25450456,0.011235306,0.04041796,0.46671918,0.015467656,0.00078288344,0.00012041167,0.00034048458,0.21041152],"genre_scores_gemma":[0.9095602,0.0064299065,0.012543683,0.029856158,0.001321168,0.00037263072,0.00002990231,0.00040370933,0.039482538],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9452253,0.04456087,0.00072811206,0.0017334566,0.0042063366,0.003545928],"domain_scores_gemma":[0.9556104,0.0317087,0.0017249839,0.0019915013,0.0037541334,0.0052102474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04269386,0.00092436053,0.00092275895,0.0012285396,0.023612954,0.012757812,0.0039379783,0.005924862,0.0055740387],"category_scores_gemma":[0.06161285,0.0006182607,0.0010592898,0.0009214433,0.03562654,0.009444637,0.011714946,0.0243219,0.0008950317],"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":[0.000048392434,0.00016498295,0.00036156172,0.00016283564,0.00001278367,0.0010638526,0.92925674,0.00011039036,0.00078610354,0.02669873,0.020397002,0.020936543],"study_design_scores_gemma":[0.000015299724,0.0001226816,0.0005961592,0.0008309427,0.000014020026,0.00084759586,0.7004475,0.00025183073,0.00077740505,0.0054743206,0.29056394,0.00005836371],"about_ca_topic_score_codex":0.01753066,"about_ca_topic_score_gemma":0.026063573,"teacher_disagreement_score":0.04269386,"about_ca_system_score_codex":0.011523337,"about_ca_system_score_gemma":0.014343062,"threshold_uncertainty_score":0.22578943},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906194,0.00008876873,0.0016493748,0.0002458751,0.0000115770445,0.00020366469,0.00008130796,0.000006011845,0.0070941267],"genre_scores_gemma":[0.9977508,0.00005233768,0.0016843274,0.000017621005,0.000002886305,0.00013935182,0.000049277904,0.0000014030674,0.0003019504],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9927856,0.0042525963,0.0007405482,0.00027648316,0.0014223884,0.00052241154],"domain_scores_gemma":[0.9659792,0.011704934,0.010717527,0.0017636957,0.0072160023,0.0026185873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011911682,0.00024557894,0.00027454496,0.0019684106,0.0025268414,0.002260701,0.000703185,0.00050947233,0.0016900791],"category_scores_gemma":[0.03842799,0.00024789284,0.00050801074,0.0013574641,0.0013856179,0.0016861222,0.0040115183,0.0010329477,0.00018177566],"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":[0.00018008654,0.00028487487,0.8912671,0.00020526067,0.0001400106,0.00019150086,0.048780847,0.00035758072,0.0006464208,0.001487221,0.00094506657,0.055514053],"study_design_scores_gemma":[0.00002403598,0.0005771929,0.86197174,0.0003181468,0.0001516939,0.00032997402,0.12605357,0.0036441537,0.0010815831,0.0013763446,0.004411695,0.000059867925],"about_ca_topic_score_codex":0.015041872,"about_ca_topic_score_gemma":0.025968265,"teacher_disagreement_score":0.015041872,"about_ca_system_score_codex":0.0031673638,"about_ca_system_score_gemma":0.002836832,"threshold_uncertainty_score":0.06299573},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028417677,0.0056547117,0.5400279,0.34603798,0.0026737049,0.0015963117,0.00077627663,0.001592773,0.07322272],"genre_scores_gemma":[0.36508223,0.0038721443,0.61307174,0.008830765,0.000567477,0.0014048152,0.00047779156,0.00045653037,0.006236479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.73767203,0.20519689,0.018934967,0.007146046,0.026622055,0.0044280346],"domain_scores_gemma":[0.47869483,0.31990692,0.03143166,0.028960083,0.13294497,0.008061513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21514508,0.0017004091,0.0012516155,0.014613384,0.0076881493,0.03237232,0.0055171223,0.006088333,0.0070284787],"category_scores_gemma":[0.40965113,0.0014118038,0.0012788379,0.0100530945,0.018953532,0.035644446,0.015096148,0.013791551,0.0019367298],"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":[0.0001713302,0.0002896315,0.009670857,0.0020677636,0.000058266265,0.00056207186,0.08756912,0.0039182925,0.0009795655,0.5447936,0.058749504,0.29117],"study_design_scores_gemma":[0.00009692136,0.00034188514,0.0063145123,0.01018832,0.000118090546,0.0007232474,0.09194895,0.017313108,0.0043115616,0.44885007,0.41932312,0.00047018912],"about_ca_topic_score_codex":0.032885216,"about_ca_topic_score_gemma":0.051173907,"teacher_disagreement_score":0.21514508,"about_ca_system_score_codex":0.031090688,"about_ca_system_score_gemma":0.05603034,"threshold_uncertainty_score":0.9678658},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42376813,0.02578278,0.049046215,0.36098865,0.0042798873,0.0019266373,0.00028062676,0.0003139436,0.13361317],"genre_scores_gemma":[0.9598207,0.004107917,0.010128149,0.020171365,0.00065411616,0.000840558,0.00006910486,0.00013992608,0.0040681325],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.492577,0.46455333,0.010069376,0.003951197,0.01735891,0.011490099],"domain_scores_gemma":[0.5950233,0.29609773,0.014801503,0.0057957955,0.070101336,0.018180419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.29959643,0.00088340987,0.0010227141,0.0039020737,0.015487281,0.022357067,0.0029392052,0.0057388623,0.0038399345],"category_scores_gemma":[0.25221506,0.0010483769,0.0011924999,0.0027038725,0.017773554,0.011211184,0.014991565,0.010798178,0.00041707596],"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":[0.0003479548,0.0005221674,0.018957067,0.0016772532,0.00017651418,0.0016440406,0.8356609,0.0006000423,0.0012838606,0.03584149,0.023092512,0.08019618],"study_design_scores_gemma":[0.00015474191,0.00042638462,0.005188383,0.0055592135,0.00016383252,0.0009783965,0.7858433,0.0010783413,0.0022698317,0.010701312,0.18745238,0.00018387013],"about_ca_topic_score_codex":0.009097512,"about_ca_topic_score_gemma":0.011684966,"teacher_disagreement_score":0.29959643,"about_ca_system_score_codex":0.015847964,"about_ca_system_score_gemma":0.031947765,"threshold_uncertainty_score":0.8637223},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86027545,0.0029712773,0.000874621,0.048745785,0.00021214166,0.00015888813,0.0011183713,0.00008354287,0.085559815],"genre_scores_gemma":[0.99198055,0.00078117097,0.00041374852,0.0019373058,0.00003321216,0.00002451145,0.00018122724,0.000022102095,0.004626176],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900113,0.0014671413,0.00030362798,0.0005761495,0.005260954,0.0023808377],"domain_scores_gemma":[0.9410085,0.014973904,0.004874495,0.00081491825,0.025511168,0.012816938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010714911,0.00015468664,0.00036627412,0.0022855818,0.007997318,0.007713725,0.0010880154,0.0012102391,0.009675387],"category_scores_gemma":[0.032771967,0.00027648616,0.00019839482,0.0034474798,0.003048048,0.002147174,0.0016913016,0.0012276846,0.0005628845],"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":[0.0008505937,0.0006516309,0.50987977,0.0008646896,0.000044604505,0.00129449,0.064703256,0.00067568896,0.0037228288,0.028222863,0.09375943,0.2953302],"study_design_scores_gemma":[0.000055294833,0.00010790601,0.7702861,0.0007078501,0.000023271059,0.00019325948,0.12116214,0.0014521801,0.0010159633,0.0019127033,0.102957,0.00012631092],"about_ca_topic_score_codex":0.93597054,"about_ca_topic_score_gemma":0.9755755,"teacher_disagreement_score":0.9892851,"about_ca_system_score_codex":0.07861433,"about_ca_system_score_gemma":0.11532085,"threshold_uncertainty_score":0.57038957},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22160962,0.002065096,0.4251997,0.25635687,0.0019963174,0.0058737006,0.00013318488,0.0015220705,0.08524345],"genre_scores_gemma":[0.8264133,0.0005141149,0.15459691,0.008673601,0.00022253396,0.0027435964,0.00006904057,0.0002511172,0.006515843],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6699256,0.23952326,0.01902771,0.011496938,0.047883764,0.012142832],"domain_scores_gemma":[0.5513486,0.21414846,0.039967675,0.04669974,0.114501595,0.03333395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.31407213,0.0010889014,0.0014829922,0.0061252913,0.020612443,0.043774217,0.004462949,0.0062998817,0.003180353],"category_scores_gemma":[0.27446193,0.0019475428,0.00096492865,0.0036986787,0.02637524,0.020893652,0.030881096,0.018456882,0.0009678855],"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":[0.00045440852,0.0024230222,0.026439613,0.0018002723,0.000254824,0.0009450161,0.28488368,0.0065611294,0.008436377,0.298672,0.024240116,0.34488955],"study_design_scores_gemma":[0.00044569987,0.001710303,0.02950138,0.006275257,0.00022528907,0.00092343055,0.25049323,0.023047693,0.015921121,0.29782814,0.37270838,0.0009200879],"about_ca_topic_score_codex":0.009505465,"about_ca_topic_score_gemma":0.010282103,"teacher_disagreement_score":0.31407213,"about_ca_system_score_codex":0.047410045,"about_ca_system_score_gemma":0.124786414,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93094206,0.00037672993,0.040484123,0.001494688,0.00021517031,0.0124791935,0.0029427973,0.00015025206,0.010914868],"genre_scores_gemma":[0.90135634,0.00039884806,0.07042037,0.0007427758,0.000049151116,0.019713104,0.0027000976,0.00006583793,0.004553518],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98066425,0.011527486,0.0021707346,0.0006569808,0.003969007,0.0010116094],"domain_scores_gemma":[0.9358846,0.03631314,0.003652011,0.002888772,0.019198973,0.0020624911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035627726,0.00036452644,0.0005132826,0.0019098213,0.0007236655,0.0010082028,0.0007943211,0.00072569493,0.003430222],"category_scores_gemma":[0.051910568,0.0003610197,0.000611135,0.001095617,0.00096605264,0.000987045,0.0016947963,0.0011975168,0.00073690765],"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":[0.0011280465,0.0031869202,0.5417677,0.0020504785,0.00020187868,0.00038293295,0.025982393,0.0045946985,0.011636427,0.007983506,0.012896581,0.38818845],"study_design_scores_gemma":[0.00043061477,0.0026481694,0.87183625,0.0010724672,0.00009705723,0.00040486592,0.014458646,0.008348764,0.0133104045,0.0025132045,0.08473009,0.0001494863],"about_ca_topic_score_codex":0.005040775,"about_ca_topic_score_gemma":0.004032225,"teacher_disagreement_score":0.035627726,"about_ca_system_score_codex":0.00205503,"about_ca_system_score_gemma":0.00615756,"threshold_uncertainty_score":0.18841964},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98013055,0.00013127681,0.0017387896,0.0030698953,0.00002006946,0.0002198565,0.000033788965,0.00002204058,0.014633685],"genre_scores_gemma":[0.9962919,0.00007097566,0.0023027088,0.00020874238,0.0000033559265,0.00011423117,0.000032626096,0.0000040498003,0.000971574],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9845168,0.010263787,0.0005244907,0.0004208427,0.001688623,0.0025853985],"domain_scores_gemma":[0.901722,0.05444694,0.007897887,0.0024165055,0.01637676,0.017139917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024176976,0.0002538026,0.00022461457,0.0013497318,0.0029271008,0.0033405947,0.0013599714,0.0013179956,0.0041938634],"category_scores_gemma":[0.0898463,0.00037719464,0.0002168085,0.0005825293,0.0022935485,0.0026595274,0.0036754888,0.00224172,0.00048581458],"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":[0.00075096334,0.007532374,0.58531433,0.00087938545,0.00010313135,0.0015487513,0.10892703,0.0061731483,0.0038995615,0.02611704,0.01088734,0.24786703],"study_design_scores_gemma":[0.0001490804,0.0017062292,0.64313567,0.0019469588,0.000058648977,0.00068793533,0.29152817,0.014246576,0.0070630247,0.016524548,0.022795461,0.00015767428],"about_ca_topic_score_codex":0.013771823,"about_ca_topic_score_gemma":0.034857385,"teacher_disagreement_score":0.024176976,"about_ca_system_score_codex":0.0058894353,"about_ca_system_score_gemma":0.026294218,"threshold_uncertainty_score":0.12786156},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006544546,0.024168313,0.0036342314,0.014308359,0.0031174175,0.00017280139,0.000110900546,0.00018252543,0.9477609],"genre_scores_gemma":[0.024092805,0.015143806,0.0049096006,0.0055855336,0.00061303383,0.00014510406,0.0001648523,0.000088817986,0.9492565],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996667,0.00005244763,0.000009233019,0.00003949414,0.00016790349,0.00006433898],"domain_scores_gemma":[0.9997471,0.00006728967,0.000014274877,0.000008779823,0.00005424572,0.00010826845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043408517,0.0004362479,0.00019616768,0.00047072835,0.0011950925,0.0022382853,0.0004655256,0.0009489992,0.021605931],"category_scores_gemma":[0.00062271993,0.00013460792,0.00017544822,0.0005318933,0.0008052384,0.0017270049,0.0019208796,0.0014467693,0.005837185],"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":[0.000012497841,0.00022702695,0.0005657829,0.00027282533,0.0000017898054,0.00013057013,0.0046311086,0.00033369605,0.0006903459,0.07980523,0.54962677,0.3637023],"study_design_scores_gemma":[0.0000021501091,0.00003189738,0.0010868147,0.0003241949,8.264017e-7,0.0001397668,0.0017945709,0.00011315001,0.00014806898,0.00572719,0.99062645,0.0000049249356],"about_ca_topic_score_codex":0.0043773046,"about_ca_topic_score_gemma":0.017167471,"teacher_disagreement_score":0.021605931,"about_ca_system_score_codex":0.0018179069,"about_ca_system_score_gemma":0.0037446767,"threshold_uncertainty_score":0.072279036},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91974735,0.002433259,0.0020440884,0.030774193,0.00035157823,0.00013049672,0.00008613823,0.000028428898,0.044404436],"genre_scores_gemma":[0.9830126,0.000993618,0.00063319,0.0013754863,0.000031827538,0.0000678836,0.00003382794,0.00001660318,0.013834844],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9934227,0.0034100818,0.000115973504,0.00045367182,0.0010860849,0.0015115422],"domain_scores_gemma":[0.99007064,0.002584563,0.0012280566,0.00037025934,0.0029794828,0.0027670895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076363827,0.00043963254,0.00045702155,0.0010523871,0.023496836,0.0071397903,0.0017871003,0.002338332,0.009180741],"category_scores_gemma":[0.013294583,0.0003671056,0.00043342588,0.0012065937,0.016609207,0.0043234583,0.007042396,0.00464386,0.00070899713],"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":[0.000026794485,0.00004922572,0.009820787,0.000087142944,0.000009906532,0.00038533588,0.9691776,0.00004791612,0.00036433185,0.005585002,0.0023203837,0.012125583],"study_design_scores_gemma":[0.000005169762,0.00004408864,0.017526252,0.000257345,0.000010689504,0.00008985628,0.9482954,0.00007374182,0.00015793084,0.0010795265,0.032434635,0.00002541813],"about_ca_topic_score_codex":0.62184185,"about_ca_topic_score_gemma":0.7678047,"teacher_disagreement_score":0.62184185,"about_ca_system_score_codex":0.02516569,"about_ca_system_score_gemma":0.04702827,"threshold_uncertainty_score":0.7607704},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004590031,0.74248576,0.025337264,0.2072214,0.0034005987,0.0005779366,0.000075508775,0.000063951775,0.01624745],"genre_scores_gemma":[0.053866606,0.8338661,0.056146726,0.046299443,0.0018532289,0.00124339,0.00007884944,0.00013083246,0.0065148235],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.91331565,0.07024828,0.0034435063,0.001659991,0.010449536,0.00088297046],"domain_scores_gemma":[0.5471089,0.39997897,0.0058987276,0.005355562,0.037526093,0.0041318266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13422269,0.000864373,0.001895237,0.004419971,0.0024792089,0.01027971,0.0023791748,0.0035254348,0.0025994428],"category_scores_gemma":[0.23262598,0.0008236035,0.0010821291,0.0045001716,0.004878542,0.012937986,0.008448322,0.010569093,0.0007731237],"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":[0.00013012996,0.00033496268,0.0016008784,0.0149875255,0.00039754272,0.00019303973,0.019842496,0.0006757933,0.0003459436,0.040162947,0.075954355,0.8453744],"study_design_scores_gemma":[0.00014691356,0.0004935483,0.003466646,0.089744695,0.0006503331,0.00066760235,0.017918175,0.0006645152,0.0012873956,0.06733125,0.8173823,0.0002467553],"about_ca_topic_score_codex":0.0058664205,"about_ca_topic_score_gemma":0.031155974,"teacher_disagreement_score":0.8657773,"about_ca_system_score_codex":0.0053264094,"about_ca_system_score_gemma":0.019959789,"threshold_uncertainty_score":0.7098459},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025811592,0.014529074,0.0033147996,0.8750576,0.015801227,0.00054568605,0.0003264225,0.00022138117,0.06439228],"genre_scores_gemma":[0.62373006,0.044061624,0.022638818,0.16705179,0.0091835335,0.0018175412,0.00081467454,0.00020596944,0.130496],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.98009,0.011149362,0.0007744901,0.0011185546,0.004175229,0.0026923518],"domain_scores_gemma":[0.9786824,0.0049325833,0.00057242025,0.0007827998,0.0051630633,0.009866809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023445424,0.0008381571,0.000716118,0.001361658,0.0054557836,0.0098686805,0.0030465152,0.005376861,0.01272692],"category_scores_gemma":[0.033919316,0.00044237298,0.00077993964,0.0011175921,0.00505578,0.010019187,0.005491613,0.010312694,0.0029509105],"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":[0.00017660172,0.0011105405,0.003854808,0.0010259014,0.000029375375,0.0011021504,0.015732698,0.001189329,0.00018743411,0.032495353,0.54254305,0.40055272],"study_design_scores_gemma":[0.00012283199,0.00063047756,0.0035771457,0.0028896148,0.000017212833,0.0007797605,0.043927483,0.0007067219,0.00027285432,0.032144394,0.91484237,0.00008922099],"about_ca_topic_score_codex":0.013301665,"about_ca_topic_score_gemma":0.041652262,"teacher_disagreement_score":0.023445424,"about_ca_system_score_codex":0.009802659,"about_ca_system_score_gemma":0.020399965,"threshold_uncertainty_score":0.12399274},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014128102,0.011970632,0.001635976,0.041103616,0.004577444,0.00010690951,0.0006271212,0.0002543229,0.93831116],"genre_scores_gemma":[0.015385584,0.009759016,0.0018155812,0.012854131,0.0004614412,0.000081223334,0.0005758732,0.00016018741,0.9589068],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986651,0.00018179904,0.00003631517,0.0001234396,0.00072333735,0.0002700688],"domain_scores_gemma":[0.99896085,0.00018067099,0.000024037465,0.00005057603,0.00058611925,0.00019767767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014341288,0.0008112183,0.0003605218,0.00081703626,0.004671395,0.009515499,0.0012836735,0.0032167945,0.05603709],"category_scores_gemma":[0.0028600593,0.00025874397,0.00052365486,0.0011521708,0.0025894064,0.0026952995,0.0026160306,0.004002036,0.012108191],"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":[0.000016702463,0.000013188288,0.00015308248,0.00011541131,0.0000026022483,0.00011322451,0.0007724633,0.0001707174,0.0001520908,0.07471812,0.87814975,0.04562276],"study_design_scores_gemma":[0.0000018631381,0.0000039921047,0.00023254717,0.00012144838,0.0000012135655,0.000051834326,0.0005749933,0.00009250634,0.000068895766,0.003859498,0.99498534,0.000005797625],"about_ca_topic_score_codex":0.4042495,"about_ca_topic_score_gemma":0.6165376,"teacher_disagreement_score":0.4042495,"about_ca_system_score_codex":0.0296478,"about_ca_system_score_gemma":0.034105185,"threshold_uncertainty_score":0.803793},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031627223,0.019140322,0.004906314,0.88944036,0.005404009,0.0002569874,0.00008732722,0.00008996045,0.07751209],"genre_scores_gemma":[0.44833758,0.045130167,0.029882828,0.39780915,0.008125753,0.001965432,0.0003247833,0.00046307617,0.06796116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.63513166,0.28986064,0.011849205,0.007543125,0.037842214,0.017773228],"domain_scores_gemma":[0.59233993,0.2930607,0.008524034,0.012985677,0.071658626,0.021430971],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27536014,0.0009145461,0.0019162035,0.003571322,0.015292914,0.03646138,0.0034622257,0.019156106,0.013461157],"category_scores_gemma":[0.34000117,0.0010589865,0.0015100259,0.004453427,0.03626701,0.02985197,0.023448152,0.023185102,0.0016390356],"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":[0.00011693364,0.00010050859,0.0009689143,0.0013850629,0.0000472941,0.00029800023,0.008585927,0.0019475729,0.0001386594,0.68095595,0.2233123,0.082142815],"study_design_scores_gemma":[0.00006321874,0.00012639354,0.0012197772,0.006882342,0.000030531777,0.000107161235,0.01606732,0.0012649447,0.00043639448,0.24380769,0.72989523,0.00009894447],"about_ca_topic_score_codex":0.025215367,"about_ca_topic_score_gemma":0.02231356,"teacher_disagreement_score":0.27536014,"about_ca_system_score_codex":0.06193214,"about_ca_system_score_gemma":0.13793238,"threshold_uncertainty_score":0.89360994},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98301,0.000066724315,0.0039787646,0.00050246174,0.000010066201,0.00014863332,0.00022237728,0.000020287003,0.012040683],"genre_scores_gemma":[0.9984699,0.00002102637,0.000983613,0.000026375896,0.0000037264408,0.00004935661,0.00009223597,0.0000024509034,0.00035123466],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9621056,0.020236013,0.002268371,0.002043657,0.009885849,0.003460476],"domain_scores_gemma":[0.7864046,0.09469271,0.05006804,0.010185218,0.050373342,0.008276048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037546035,0.0001728179,0.0004930226,0.0026771203,0.0029311616,0.00332649,0.0010236045,0.0007239298,0.0016437748],"category_scores_gemma":[0.11105478,0.00018335924,0.00029484832,0.005820865,0.0037839115,0.0020180072,0.0034547215,0.0012560185,0.00023179734],"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":[0.000109399385,0.00016715619,0.9448517,0.00009377436,0.0001047796,0.00006997769,0.0155585185,0.0059607467,0.00035996083,0.00599931,0.0009468906,0.025777785],"study_design_scores_gemma":[0.000014738993,0.00011930158,0.9542572,0.00012941101,0.000045355762,0.000022251123,0.02694446,0.008265001,0.00072141027,0.00468796,0.0047452836,0.00004772771],"about_ca_topic_score_codex":0.3765536,"about_ca_topic_score_gemma":0.42995784,"teacher_disagreement_score":0.3765536,"about_ca_system_score_codex":0.019484729,"about_ca_system_score_gemma":0.0177285,"threshold_uncertainty_score":0.7487236},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05891688,0.1162986,0.3212693,0.17695148,0.011544159,0.00926178,0.000990833,0.0086638145,0.29610324],"genre_scores_gemma":[0.54781944,0.02651846,0.3593555,0.030854598,0.0026873902,0.014637376,0.0005973458,0.003372197,0.0141577395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.4164625,0.5075652,0.032381155,0.0058689048,0.03491038,0.0028119353],"domain_scores_gemma":[0.38493362,0.46130875,0.03900493,0.039691497,0.06492374,0.010137455],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35717767,0.0009227009,0.0017941932,0.010159478,0.0056220246,0.013448093,0.003577252,0.004390885,0.007957288],"category_scores_gemma":[0.51570445,0.0011819145,0.0015005349,0.011307009,0.00890169,0.011890738,0.018887524,0.0054540783,0.0018685253],"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":[0.00030782208,0.00036146306,0.009191794,0.0063283266,0.00012300952,0.00037993919,0.04809537,0.0005233936,0.0005570988,0.05390541,0.056492854,0.8237335],"study_design_scores_gemma":[0.00019371505,0.0010195724,0.020821938,0.04955776,0.00021392954,0.0015619332,0.035216764,0.0032244474,0.0036183645,0.05909328,0.82509774,0.00038041148],"about_ca_topic_score_codex":0.004012225,"about_ca_topic_score_gemma":0.005665732,"teacher_disagreement_score":0.35717767,"about_ca_system_score_codex":0.017252332,"about_ca_system_score_gemma":0.027372327,"threshold_uncertainty_score":0.79271436},"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":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008475715,0.0884043,0.056913335,0.29009882,0.004354017,0.0002297769,0.00012675983,0.00030879964,0.5510885],"genre_scores_gemma":[0.668813,0.073311575,0.10333294,0.05162924,0.0059310077,0.0015208977,0.00025294555,0.000909847,0.09429861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91500086,0.062404074,0.0031062264,0.0031239274,0.013874368,0.002490604],"domain_scores_gemma":[0.91242975,0.06801354,0.0027653878,0.0071176575,0.0077423416,0.0019313472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05733912,0.0013577079,0.0019926832,0.008019679,0.008705025,0.041312054,0.00280929,0.0057247425,0.0038138325],"category_scores_gemma":[0.061411243,0.0008284707,0.00088240206,0.011837392,0.10272769,0.049916644,0.012525401,0.00697315,0.0015767583],"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":[0.0000054803577,0.000007942839,0.00023414056,0.00018940477,0.000006024917,0.000031060634,0.00935766,0.00012307258,0.000047344787,0.9596318,0.0071239504,0.023242086],"study_design_scores_gemma":[0.0000051173865,0.000015770283,0.00025535558,0.001177786,0.000008891086,0.000102988866,0.0084255375,0.00033632168,0.00015457407,0.8510698,0.1384273,0.000020592508],"about_ca_topic_score_codex":0.006764341,"about_ca_topic_score_gemma":0.005228762,"teacher_disagreement_score":0.94266087,"about_ca_system_score_codex":0.021367962,"about_ca_system_score_gemma":0.020890681,"threshold_uncertainty_score":0.30324185},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004690913,0.0013410755,0.00048261893,0.07368864,0.92099047,0.00003291263,0.00041360423,0.0001925021,0.0028112938],"genre_scores_gemma":[0.0049613127,0.009886948,0.0029764557,0.3001441,0.42323622,0.00043346488,0.0018302923,0.0010634337,0.2554678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910033,0.0019404574,0.0013067507,0.0010099395,0.004006257,0.0007333661],"domain_scores_gemma":[0.946841,0.014780654,0.0018793768,0.0017224614,0.032641143,0.0021353946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005849852,0.003121578,0.0029806048,0.0047780923,0.0068129306,0.006409245,0.0049909335,0.012273252,0.07009551],"category_scores_gemma":[0.07625013,0.0015516048,0.0037968517,0.0032302835,0.0043771695,0.0037933218,0.0046960963,0.015806193,0.048221637],"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":[0.000006801877,0.0000043581485,0.000021730832,0.00006273708,0.0000058024557,0.00007600518,0.000025775895,0.0000153966,0.000012091879,0.000325143,0.9976546,0.0017895056],"study_design_scores_gemma":[0.000026423457,0.000019053314,0.00078003044,0.0005108449,0.000042922686,0.00030299078,0.00018408928,0.0002524367,0.00015110573,0.001800713,0.9958691,0.000060164602],"about_ca_topic_score_codex":0.08941009,"about_ca_topic_score_gemma":0.13663158,"teacher_disagreement_score":0.08941009,"about_ca_system_score_codex":0.009068623,"about_ca_system_score_gemma":0.010014284,"threshold_uncertainty_score":0.23449284},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92416316,0.0025621313,0.0038811231,0.032298736,0.00018905532,0.00031136352,0.000046031884,0.000019006144,0.036529314],"genre_scores_gemma":[0.9961571,0.00072784506,0.001139933,0.0010100653,0.00001925573,0.000085821695,0.000008752284,0.000012235931,0.00083901465],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95986426,0.034915518,0.00074662274,0.0004884483,0.0015049248,0.0024802648],"domain_scores_gemma":[0.9752891,0.016066154,0.0015763635,0.0005920887,0.003129593,0.0033465826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035040468,0.00031871797,0.0005115306,0.0006750119,0.006131114,0.0071241907,0.0010263474,0.0014282512,0.0021296772],"category_scores_gemma":[0.03249695,0.0003150387,0.0003965088,0.0009931391,0.0069712317,0.004882221,0.004570507,0.0024661887,0.0001418688],"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":[0.00019902275,0.00057655637,0.026659558,0.00088576745,0.000053116706,0.0034172395,0.9001906,0.000859536,0.0012989825,0.012690223,0.0034954506,0.049673975],"study_design_scores_gemma":[0.000032928492,0.00039362485,0.008940425,0.0011478424,0.00003162272,0.0005353032,0.9383713,0.00058698107,0.001095991,0.0049102446,0.043898303,0.00005532711],"about_ca_topic_score_codex":0.018253077,"about_ca_topic_score_gemma":0.027869068,"teacher_disagreement_score":0.035040468,"about_ca_system_score_codex":0.010900559,"about_ca_system_score_gemma":0.010444766,"threshold_uncertainty_score":0.18531394},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7643308,0.0011517223,0.1592634,0.009308417,0.00014249606,0.0035748067,0.0000735819,0.00020187307,0.061952736],"genre_scores_gemma":[0.92904496,0.0005305442,0.06648713,0.00039366545,0.000015537464,0.0012536633,0.000019141904,0.000029222874,0.0022261476],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9201823,0.07485538,0.0008560639,0.0011905084,0.0011880018,0.0017278361],"domain_scores_gemma":[0.9605624,0.030851096,0.0016160712,0.0030513054,0.0024657967,0.0014533368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06462844,0.000652411,0.0003330228,0.001508624,0.009012381,0.007949079,0.0021410577,0.001320484,0.001596932],"category_scores_gemma":[0.03420126,0.00043095887,0.00036330303,0.0012396082,0.011988567,0.0061671184,0.009520335,0.0018539397,0.00022735143],"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":[0.0000822176,0.0005562636,0.014982777,0.0006673101,0.000028974247,0.0015354669,0.763102,0.0011996699,0.0029132513,0.02300763,0.0010711652,0.19085328],"study_design_scores_gemma":[0.00009808463,0.0013344312,0.015424347,0.0018308305,0.000085043655,0.0008812594,0.8452724,0.0028164056,0.004868464,0.028077243,0.099180244,0.00013112825],"about_ca_topic_score_codex":0.008519766,"about_ca_topic_score_gemma":0.028872745,"teacher_disagreement_score":0.06462844,"about_ca_system_score_codex":0.006679522,"about_ca_system_score_gemma":0.011419205,"threshold_uncertainty_score":0.34179193},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060264138,0.0068747476,0.9279911,0.016352162,0.000733753,0.00056226505,0.00011636128,0.00030804414,0.04103513],"genre_scores_gemma":[0.15673883,0.0028278695,0.83084655,0.00341723,0.0005160713,0.0015498291,0.00009630544,0.000366473,0.0036409493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.653915,0.25023705,0.014963601,0.011622847,0.067123726,0.0021378004],"domain_scores_gemma":[0.46693215,0.4622339,0.010127047,0.031901423,0.026405577,0.002400011],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22645576,0.0018144923,0.0035710335,0.014334746,0.0059158397,0.018661618,0.00501718,0.0052103936,0.004983868],"category_scores_gemma":[0.43687937,0.0014712415,0.002357844,0.010465802,0.025812566,0.018924976,0.009481705,0.0071857073,0.001498435],"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":[0.00009646376,0.00004369361,0.00084954844,0.00057148666,0.00012271553,0.000045665958,0.002422386,0.0032085984,0.000081568156,0.91017395,0.004198945,0.07818496],"study_design_scores_gemma":[0.000071324386,0.000042099455,0.0004767094,0.0006988881,0.000055866298,0.000078905694,0.0007300045,0.008435436,0.00028982214,0.96703213,0.022020638,0.000068291745],"about_ca_topic_score_codex":0.006490996,"about_ca_topic_score_gemma":0.0071603684,"teacher_disagreement_score":0.22645576,"about_ca_system_score_codex":0.009366127,"about_ca_system_score_gemma":0.01538838,"threshold_uncertainty_score":0.95391774},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007059947,0.012038519,0.0043493086,0.9438353,0.034469616,0.000022426217,0.000021857173,0.00008809416,0.004468929],"genre_scores_gemma":[0.039231163,0.014417873,0.016328067,0.84916204,0.025858575,0.00013782561,0.00003892751,0.00032851435,0.054497063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718685,0.012455787,0.0017204818,0.0031636646,0.009404968,0.0013867182],"domain_scores_gemma":[0.8341937,0.055746544,0.0047925613,0.0043214536,0.058417745,0.042527888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02520031,0.001293774,0.0015350999,0.0024774498,0.009532416,0.018292336,0.0036663238,0.011882085,0.0093594],"category_scores_gemma":[0.12950365,0.0007338406,0.0009110052,0.0013210865,0.020430405,0.013495598,0.005035987,0.031758323,0.0039311554],"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":[0.00005072766,0.00010211681,0.00053569995,0.00017638516,0.000042327552,0.00047358812,0.006799443,0.00012052788,0.00022250651,0.02370593,0.9501665,0.017604308],"study_design_scores_gemma":[0.00006783365,0.00009125483,0.00045245365,0.0011828245,0.000042528274,0.001549124,0.022714058,0.0004584865,0.00049347844,0.07225844,0.9005332,0.0001562444],"about_ca_topic_score_codex":0.024166334,"about_ca_topic_score_gemma":0.036941633,"teacher_disagreement_score":0.02520031,"about_ca_system_score_codex":0.00890471,"about_ca_system_score_gemma":0.026274012,"threshold_uncertainty_score":0.13327354},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040442147,0.022949936,0.015931621,0.9202468,0.015462028,0.000055101093,0.000022488726,0.000091658716,0.021196144],"genre_scores_gemma":[0.3233591,0.08983839,0.07467245,0.39620382,0.050262343,0.00039547498,0.00006386271,0.0011017594,0.06410273],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9430804,0.03504947,0.0016499731,0.0029123381,0.01608863,0.0012192202],"domain_scores_gemma":[0.815581,0.1262437,0.0024642542,0.0055187964,0.038455334,0.0117368745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05205446,0.0005571715,0.0009011415,0.002978041,0.008112633,0.017175116,0.0019369232,0.0034821087,0.0017598228],"category_scores_gemma":[0.113227144,0.0007011607,0.000439195,0.0018585125,0.02497478,0.018960822,0.0066480716,0.016452814,0.0005679579],"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":[0.000068561356,0.0001357234,0.0016604417,0.00069618435,0.00004962858,0.00054686726,0.058345526,0.0006238467,0.0005395957,0.25498658,0.5430612,0.13928585],"study_design_scores_gemma":[0.000012733945,0.000036636477,0.00057479535,0.0010934388,0.000026162816,0.00052824523,0.020360911,0.00072643766,0.0009151699,0.12610133,0.8494915,0.00013263166],"about_ca_topic_score_codex":0.009491105,"about_ca_topic_score_gemma":0.016518189,"teacher_disagreement_score":0.05205446,"about_ca_system_score_codex":0.0072080167,"about_ca_system_score_gemma":0.01535089,"threshold_uncertainty_score":0.2752936},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037798267,0.035775628,0.0034292706,0.905927,0.0031250094,0.00008011125,0.000046683086,0.000054414708,0.04778199],"genre_scores_gemma":[0.45001948,0.09805603,0.018099695,0.33845264,0.0038547376,0.00024293043,0.000078544756,0.0005699876,0.09062596],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.92726964,0.02629374,0.0023977074,0.00435086,0.032822434,0.0068656337],"domain_scores_gemma":[0.84809166,0.066081755,0.0026111288,0.0026503126,0.058744326,0.02182082],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.04798846,0.0005893155,0.0014377129,0.005207923,0.03881333,0.03220757,0.0033533801,0.008896652,0.0033420653],"category_scores_gemma":[0.099647745,0.0011036947,0.000665161,0.006582069,0.08856794,0.011084436,0.0058703204,0.026638892,0.0004433898],"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":[0.000065583714,0.00009799252,0.0025050866,0.00032019868,0.00004066318,0.000433588,0.031551555,0.0009435705,0.00022505857,0.6097425,0.30349636,0.050577827],"study_design_scores_gemma":[0.000031554806,0.000028238026,0.0025722461,0.0016245091,0.000025162388,0.00016361233,0.022644693,0.000798192,0.00032697947,0.09543485,0.8761123,0.00023756626],"about_ca_topic_score_codex":0.9650465,"about_ca_topic_score_gemma":0.979162,"teacher_disagreement_score":0.96118665,"about_ca_system_score_codex":0.24311756,"about_ca_system_score_gemma":0.38482332,"threshold_uncertainty_score":0.87787634},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019325914,0.0015964787,0.00026613538,0.5484891,0.4429849,0.000038568945,0.00017838369,0.00020407932,0.0060490645],"genre_scores_gemma":[0.0033875913,0.0017716276,0.0010948505,0.70151347,0.2373176,0.000121738434,0.00012226013,0.00018324106,0.054487653],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9869446,0.0011456308,0.0011464745,0.0025494106,0.006962715,0.0012511433],"domain_scores_gemma":[0.947793,0.010852068,0.002420006,0.0022110492,0.031177519,0.005546324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012304888,0.0016213716,0.0018207384,0.0018592312,0.004965354,0.010235266,0.0049102586,0.02267303,0.026112597],"category_scores_gemma":[0.09679381,0.00084378006,0.002662956,0.0016011815,0.0034098965,0.005850587,0.003152073,0.026675982,0.022777406],"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":[0.000011365107,0.000006455436,0.00004870229,0.000025012692,0.0000038684757,0.00006491964,0.000029838851,0.000015401189,0.000030193058,0.00057232595,0.9966529,0.0025390866],"study_design_scores_gemma":[0.000015769709,0.000010932569,0.0002556201,0.000115325296,0.000008021646,0.000102163685,0.000109923865,0.0000707058,0.00013567081,0.0008579628,0.9982936,0.000024284685],"about_ca_topic_score_codex":0.009010021,"about_ca_topic_score_gemma":0.017166335,"teacher_disagreement_score":0.026112597,"about_ca_system_score_codex":0.005206063,"about_ca_system_score_gemma":0.011127049,"threshold_uncertainty_score":0.087355316},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018834956,0.011397459,0.8521821,0.082259566,0.001510965,0.0049364455,0.00040369114,0.00020440774,0.028270384],"genre_scores_gemma":[0.46771204,0.0059484933,0.5053768,0.0071832114,0.00069688034,0.011237845,0.00018779798,0.00014531554,0.0015116393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6325803,0.31223416,0.013725385,0.0075204694,0.031254932,0.0026847813],"domain_scores_gemma":[0.26269838,0.6934296,0.014510321,0.014462625,0.01269311,0.0022060745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35270166,0.0027991042,0.006449667,0.008008849,0.0041445624,0.015607256,0.006588077,0.006213282,0.010281088],"category_scores_gemma":[0.5485412,0.0017786167,0.0048858067,0.0053417585,0.027512131,0.030768653,0.011996455,0.0128682405,0.000506555],"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":[0.00021903109,0.00021793907,0.0038269109,0.0036659772,0.0006938029,0.00008944892,0.002413507,0.015237608,0.00017331133,0.9188044,0.001133184,0.05352477],"study_design_scores_gemma":[0.000113291826,0.00014666855,0.0006609552,0.0015568834,0.00021150606,0.000034048862,0.0007267662,0.012115889,0.00031839087,0.9811739,0.0028926716,0.000049113944],"about_ca_topic_score_codex":0.006895921,"about_ca_topic_score_gemma":0.008587788,"teacher_disagreement_score":0.35270166,"about_ca_system_score_codex":0.017400937,"about_ca_system_score_gemma":0.0256892,"threshold_uncertainty_score":0.7982341},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026547597,0.040476758,0.023306925,0.7666357,0.032792263,0.00010777303,0.00016632624,0.00041209662,0.13344744],"genre_scores_gemma":[0.23687823,0.07727305,0.041876532,0.20352432,0.041310616,0.00023253102,0.00023635151,0.0009095575,0.39775878],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.954162,0.013367827,0.0019047436,0.0032717744,0.025460107,0.0018334413],"domain_scores_gemma":[0.87990445,0.039861348,0.0034270484,0.007314583,0.054474972,0.0150174685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021584146,0.00048768157,0.0005900009,0.0034337186,0.005378391,0.010790047,0.001347239,0.0030525734,0.0083686765],"category_scores_gemma":[0.10097003,0.00065853173,0.0004567648,0.0034463513,0.008072489,0.0054047597,0.0042216415,0.011627605,0.0022430995],"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":[0.00003663243,0.00004175535,0.0012590033,0.00017993512,0.00002641128,0.00014417946,0.0023870708,0.00050262903,0.00018758193,0.10881312,0.7333803,0.1530413],"study_design_scores_gemma":[0.000004097235,0.0000096211925,0.00058862776,0.00019294095,0.000006438495,0.00020146201,0.00034779136,0.00027359376,0.00021713755,0.022048663,0.97608167,0.000027886743],"about_ca_topic_score_codex":0.05621977,"about_ca_topic_score_gemma":0.0696487,"teacher_disagreement_score":0.05621977,"about_ca_system_score_codex":0.014379768,"about_ca_system_score_gemma":0.03326118,"threshold_uncertainty_score":0.11414921},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0150910355,0.011502968,0.07013273,0.8501688,0.0050225244,0.00021749751,0.000026895688,0.00035936543,0.047478154],"genre_scores_gemma":[0.6917383,0.010009854,0.10285664,0.17993434,0.002857637,0.0007799099,0.000056885907,0.00067456765,0.0110919075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7042643,0.23050542,0.010529533,0.009733361,0.03782759,0.007139797],"domain_scores_gemma":[0.58183527,0.21066543,0.014330405,0.035275485,0.12052434,0.037369095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25932518,0.0007290085,0.0014270106,0.00461187,0.017065894,0.03547212,0.0033480166,0.0064333794,0.0033423796],"category_scores_gemma":[0.24930933,0.0014005416,0.0009999741,0.0028591824,0.04913774,0.042507578,0.023319313,0.024109675,0.0014196843],"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":[0.00009928498,0.0004712599,0.0053553698,0.0010733387,0.00018819861,0.00027753762,0.055862173,0.00085297815,0.0008748914,0.5815994,0.101972476,0.25137308],"study_design_scores_gemma":[0.000090102716,0.00031340614,0.003831166,0.006250379,0.00009389415,0.0004460206,0.08537016,0.002332917,0.001965479,0.44311392,0.4558392,0.0003533305],"about_ca_topic_score_codex":0.010759791,"about_ca_topic_score_gemma":0.0076345685,"teacher_disagreement_score":0.25932518,"about_ca_system_score_codex":0.020545831,"about_ca_system_score_gemma":0.0532133,"threshold_uncertainty_score":0.9133839},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28618127,0.0970635,0.046357065,0.3554298,0.0054979473,0.00062488765,0.00043996744,0.0005873648,0.2078182],"genre_scores_gemma":[0.88987315,0.0383862,0.035159037,0.008881591,0.0016664026,0.00025957817,0.000302564,0.00028699875,0.02518455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9532326,0.020966774,0.002240902,0.0021896032,0.018732497,0.0026376343],"domain_scores_gemma":[0.7641327,0.12694134,0.012284916,0.0067856433,0.07609986,0.013755632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048242103,0.0004457926,0.0005697689,0.012987674,0.004913827,0.018791063,0.0012895241,0.0016616746,0.0027631118],"category_scores_gemma":[0.19517563,0.0004485849,0.00029350657,0.013190955,0.0068604564,0.009898082,0.005720372,0.0031800414,0.0007054194],"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":[0.00025026198,0.00018600517,0.040514152,0.0019273543,0.0000848158,0.00065755466,0.03842974,0.0013674824,0.00150716,0.06941918,0.06137065,0.78428566],"study_design_scores_gemma":[0.000041173575,0.00035753893,0.09699975,0.008495308,0.00015462984,0.0010408739,0.073886834,0.0036456732,0.007108514,0.05512058,0.752825,0.00032407558],"about_ca_topic_score_codex":0.031375453,"about_ca_topic_score_gemma":0.052305557,"teacher_disagreement_score":0.048242103,"about_ca_system_score_codex":0.017335663,"about_ca_system_score_gemma":0.04482345,"threshold_uncertainty_score":0.25513172},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077743334,0.0055779843,0.0038925477,0.014021747,0.031974338,0.0006572913,0.0123110395,0.0053945347,0.9253931],"genre_scores_gemma":[0.0030644129,0.0035393944,0.0026028152,0.006565761,0.0033156676,0.0002867179,0.008097679,0.0019620818,0.97056544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971842,0.00036766464,0.00022742852,0.00048268653,0.0014839936,0.000254032],"domain_scores_gemma":[0.9929268,0.0007152853,0.00030364576,0.0010202107,0.0035763138,0.0014577471],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018924826,0.0015488724,0.0012999586,0.0032172028,0.0029175917,0.009669673,0.003954179,0.0038037247,0.8438274],"category_scores_gemma":[0.012478712,0.0007010274,0.0012929394,0.0029162713,0.0010354009,0.0057110847,0.00661964,0.0029635925,0.7594328],"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":[0.000058053873,0.00003831839,0.00012455789,0.00048176412,0.0000072084345,0.00013436384,0.000104093255,0.00004870919,0.00034472908,0.0032483668,0.8869196,0.10849016],"study_design_scores_gemma":[0.000007489941,0.000014210577,0.000104774284,0.00012151654,0.0000047981493,0.00011020599,0.00006012769,0.000015893705,0.00010006246,0.0008786693,0.99857616,0.000006114703],"about_ca_topic_score_codex":0.003677487,"about_ca_topic_score_gemma":0.008250557,"teacher_disagreement_score":0.15617257,"about_ca_system_score_codex":0.0022756811,"about_ca_system_score_gemma":0.006587815,"threshold_uncertainty_score":0},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001071554,0.006336146,0.005646136,0.09644614,0.5349613,0.0015375749,0.034634985,0.004543561,0.31482267],"genre_scores_gemma":[0.00614548,0.00723117,0.007139404,0.049174227,0.08665504,0.0011689056,0.029684603,0.0032406899,0.8095605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99379385,0.00082795403,0.0006313332,0.0007251661,0.003567038,0.00045464686],"domain_scores_gemma":[0.91524494,0.011205545,0.0022494104,0.0049975673,0.0587476,0.0075548366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004050314,0.001498047,0.0013930809,0.0037020713,0.0025154694,0.006505977,0.0038401058,0.0029213503,0.695728],"category_scores_gemma":[0.07181855,0.0007024803,0.001259468,0.0027851928,0.0009956226,0.0033778772,0.0038279823,0.003759144,0.4598952],"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":[0.00003847559,0.000016850392,0.000053850537,0.00017684615,0.0000031750446,0.0000563174,0.000022483637,0.00001845727,0.00008029095,0.00047111168,0.9782762,0.020785807],"study_design_scores_gemma":[0.000019740666,0.000031868316,0.00022508598,0.00017468169,0.000007039772,0.00022989782,0.000049133836,0.000030435825,0.00012969521,0.00080970157,0.99828184,0.000010971901],"about_ca_topic_score_codex":0.0043900413,"about_ca_topic_score_gemma":0.01053671,"teacher_disagreement_score":0.304272,"about_ca_system_score_codex":0.0027705596,"about_ca_system_score_gemma":0.009760666,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009075671,0.0057734293,0.8671819,0.023811683,0.0012230838,0.00045876886,0.00023345211,0.0002309247,0.09201103],"genre_scores_gemma":[0.61202246,0.004339723,0.3602875,0.0051088147,0.0025189468,0.0019501265,0.0003098307,0.00034485964,0.013117698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8767645,0.09488531,0.004196111,0.007236667,0.015021501,0.0018959396],"domain_scores_gemma":[0.6949682,0.26443443,0.007143975,0.018755876,0.013022428,0.0016750839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11056996,0.0017346184,0.0023489268,0.009452751,0.0065154363,0.009799355,0.0038133452,0.0060074185,0.013771674],"category_scores_gemma":[0.21440455,0.0011030093,0.0029813687,0.007240245,0.03506328,0.023552971,0.010232768,0.009175946,0.0014575225],"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":[0.000013042044,0.000015369336,0.0003461567,0.00010237916,0.00003473927,0.00004214836,0.00064941344,0.0008646497,0.000023831886,0.9895167,0.00094882806,0.0074427472],"study_design_scores_gemma":[0.000009288323,0.0000071265767,0.00007695397,0.00010339924,0.000014143213,0.00002990645,0.00014542286,0.0019103038,0.000076229306,0.9916781,0.005939038,0.000010132367],"about_ca_topic_score_codex":0.003129998,"about_ca_topic_score_gemma":0.0019434172,"teacher_disagreement_score":0.11056996,"about_ca_system_score_codex":0.008375866,"about_ca_system_score_gemma":0.006817175,"threshold_uncertainty_score":0.58475685},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006413299,0.084770836,0.014177744,0.80094075,0.0063625164,0.000096247706,0.00007556104,0.000105606254,0.08705747],"genre_scores_gemma":[0.6239874,0.14021821,0.03846673,0.13542154,0.004349751,0.00027835643,0.0001167691,0.00052697427,0.05663438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9214914,0.032729793,0.0025998063,0.003585993,0.034250055,0.0053429613],"domain_scores_gemma":[0.7802609,0.09609828,0.0026759943,0.005650932,0.09777786,0.017535936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07577963,0.00062545517,0.00112563,0.009455103,0.024562448,0.023422955,0.0036303885,0.0053263716,0.0031604804],"category_scores_gemma":[0.1354606,0.0008084378,0.00059317675,0.012029676,0.046059053,0.0094134435,0.0077542383,0.011377949,0.0004890829],"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":[0.000052127867,0.00006569827,0.0022898465,0.00067441136,0.00003661391,0.00023448293,0.03520521,0.0010653569,0.00017517465,0.63158286,0.20662294,0.1219952],"study_design_scores_gemma":[0.000009479981,0.00001752404,0.0022966308,0.0016664541,0.000023577802,0.0001138851,0.014632589,0.0007867453,0.00032862075,0.062251873,0.9177636,0.00010896984],"about_ca_topic_score_codex":0.922461,"about_ca_topic_score_gemma":0.9451082,"teacher_disagreement_score":0.922461,"about_ca_system_score_codex":0.20652553,"about_ca_system_score_gemma":0.3085327,"threshold_uncertainty_score":0.9203179},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023795722,0.015392708,0.12061098,0.80992424,0.0039955974,0.00038657617,0.00002810208,0.0001961588,0.02566993],"genre_scores_gemma":[0.6754308,0.014804501,0.19911996,0.09436904,0.002889481,0.0022830477,0.000038340288,0.00047314257,0.010591702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.60776675,0.32639366,0.013508838,0.011829979,0.034309193,0.006191589],"domain_scores_gemma":[0.4125699,0.4986364,0.009215788,0.013137988,0.053807136,0.012632697],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.33780456,0.00093699625,0.0017372626,0.008633319,0.017323839,0.030510938,0.008227175,0.010908685,0.0030066979],"category_scores_gemma":[0.36633798,0.0013492672,0.00129101,0.0075975955,0.08137706,0.037265696,0.019446151,0.024871489,0.0005978833],"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":[0.0001283225,0.00025074993,0.0024696307,0.0013785948,0.00006558555,0.00084838155,0.30057606,0.00073340023,0.00031774104,0.56784534,0.03407208,0.09131415],"study_design_scores_gemma":[0.000081542275,0.00014448566,0.0014987176,0.005403568,0.000042409367,0.0008790221,0.25269085,0.002116539,0.0008042387,0.49247092,0.2436549,0.00021268014],"about_ca_topic_score_codex":0.00929612,"about_ca_topic_score_gemma":0.017006373,"teacher_disagreement_score":0.33780456,"about_ca_system_score_codex":0.027135465,"about_ca_system_score_gemma":0.03437176,"threshold_uncertainty_score":0.81660485},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98329896,0.002360714,0.00035615117,0.0021396617,0.000053558648,0.00005965004,0.0006825596,0.000021671165,0.011027074],"genre_scores_gemma":[0.9942086,0.0013185336,0.0003041903,0.00019785529,0.000081812395,0.00009030417,0.00033618708,0.000008482284,0.0034541248],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9841517,0.0064156535,0.0015415831,0.0010536953,0.004820189,0.0020172007],"domain_scores_gemma":[0.8490344,0.08085505,0.027076095,0.003973174,0.018446265,0.020614946],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.015222387,0.00037387616,0.0007112382,0.005086787,0.0019582235,0.0035540268,0.00079311786,0.00077665964,0.01922463],"category_scores_gemma":[0.061235536,0.00026662857,0.00060030347,0.00834494,0.0012819311,0.0017419503,0.004031057,0.0013335027,0.0021201689],"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":[0.00014955818,0.0001920451,0.946114,0.00026613535,0.000116062874,0.00019219701,0.01255346,0.00017740107,0.00021425998,0.00078932685,0.0013968742,0.03783862],"study_design_scores_gemma":[0.000009872939,0.0001235919,0.98258495,0.00013594513,0.00002348109,0.00012035598,0.011778189,0.00009247269,0.000099034325,0.00017719768,0.0048367726,0.000018086213],"about_ca_topic_score_codex":0.020472053,"about_ca_topic_score_gemma":0.03350493,"teacher_disagreement_score":0.997594,"about_ca_system_score_codex":0.0024059755,"about_ca_system_score_gemma":0.007034252,"threshold_uncertainty_score":0.080504656},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71600276,0.0027625456,0.011792016,0.01662916,0.0005440558,0.00052563247,0.000043461565,0.00013358306,0.25156686],"genre_scores_gemma":[0.9883759,0.00036693347,0.0018362234,0.0011919126,0.00008091405,0.00021164138,0.000020690666,0.00002762071,0.007888195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98378307,0.009554886,0.00045871278,0.0010984257,0.003888494,0.0012164542],"domain_scores_gemma":[0.9513885,0.02286532,0.010396276,0.0019262729,0.0059919595,0.0074318573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017655542,0.00039719758,0.00037030256,0.0019294966,0.0034366518,0.00728657,0.0012701257,0.0024470773,0.007704442],"category_scores_gemma":[0.038095135,0.00023511877,0.0002781529,0.0011248448,0.0086071985,0.0053225253,0.004690042,0.001822163,0.0011128247],"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":[0.0005903302,0.00090454303,0.12776037,0.0013106101,0.00010754018,0.0017110785,0.2132064,0.00055599504,0.0028015398,0.4733315,0.021889238,0.15583092],"study_design_scores_gemma":[0.0002190795,0.0017696709,0.08009199,0.003994394,0.00021013628,0.0029810073,0.27581298,0.0036741225,0.00414806,0.1279521,0.49892762,0.00021875883],"about_ca_topic_score_codex":0.0010416037,"about_ca_topic_score_gemma":0.0019544202,"teacher_disagreement_score":0.017655542,"about_ca_system_score_codex":0.003027357,"about_ca_system_score_gemma":0.004661829,"threshold_uncertainty_score":0.093372524},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7745179,0.0036294668,0.042617273,0.0069766594,0.00056225376,0.026145618,0.0011652624,0.00076494523,0.14362057],"genre_scores_gemma":[0.9528899,0.0014453994,0.027693827,0.00070560863,0.00008429239,0.011109393,0.0004003369,0.000060640334,0.0056105847],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9600894,0.032331146,0.0011252966,0.00088766514,0.00414991,0.0014166504],"domain_scores_gemma":[0.96545947,0.019293062,0.004118346,0.001634225,0.0066639944,0.0028309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03573002,0.0006031253,0.0004512422,0.0014461693,0.0016690341,0.0016533863,0.001005026,0.0005830009,0.0092140315],"category_scores_gemma":[0.050861508,0.00020418699,0.00072373834,0.0008915233,0.0011993747,0.0016524501,0.003767013,0.0010744715,0.00041765685],"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":[0.0030098385,0.010184682,0.04320763,0.005573307,0.00034340733,0.00027219555,0.019626021,0.0038104516,0.0028809619,0.012976135,0.016570382,0.881545],"study_design_scores_gemma":[0.008495914,0.067204565,0.2768415,0.02915218,0.0027147331,0.0007753771,0.07028085,0.016199743,0.06468883,0.04055614,0.42269006,0.00040016318],"about_ca_topic_score_codex":0.0014423158,"about_ca_topic_score_gemma":0.00259007,"teacher_disagreement_score":0.03573002,"about_ca_system_score_codex":0.0034835385,"about_ca_system_score_gemma":0.011158941,"threshold_uncertainty_score":0.18896067},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014109411,0.18381096,0.17189576,0.058278788,0.008427248,0.0015486139,0.0002807356,0.0009469869,0.5734],"genre_scores_gemma":[0.118605174,0.28497624,0.2205394,0.03917621,0.009547839,0.0047286316,0.0016956279,0.0012846242,0.31944627],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9087755,0.05220665,0.004328078,0.0040761377,0.029206773,0.0014068825],"domain_scores_gemma":[0.9196088,0.044372834,0.002435697,0.0076959673,0.02307415,0.0028126084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04772917,0.0011562824,0.0016275684,0.0052156853,0.0029337828,0.01197696,0.0030273541,0.004122862,0.026886174],"category_scores_gemma":[0.10450359,0.0005417343,0.0010789133,0.0057459627,0.004849053,0.008650268,0.0069084526,0.0036979266,0.0144257415],"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":[0.000046643552,0.0001127475,0.0004751158,0.0017091298,0.00007839938,0.00006535725,0.0013746308,0.00071168755,0.00015301988,0.16456822,0.2352536,0.5954514],"study_design_scores_gemma":[0.000025477444,0.00007012424,0.0005077381,0.0034872242,0.000030635103,0.00021953727,0.0008618695,0.00044704782,0.00029016615,0.0834146,0.91060925,0.000036361525],"about_ca_topic_score_codex":0.0029433724,"about_ca_topic_score_gemma":0.004213857,"teacher_disagreement_score":0.04772917,"about_ca_system_score_codex":0.006595256,"about_ca_system_score_gemma":0.012749875,"threshold_uncertainty_score":0.25241905},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008354215,0.011287494,0.0037508234,0.03570923,0.009818283,0.0010574302,0.010899719,0.0010128818,0.9256288],"genre_scores_gemma":[0.011131956,0.014587946,0.0069046654,0.01836778,0.0022079933,0.0019024282,0.015316208,0.000520399,0.9290607],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97223705,0.005843385,0.0031383936,0.0019459003,0.01496139,0.0018738748],"domain_scores_gemma":[0.8946398,0.0075675873,0.0030424928,0.004702897,0.08427486,0.005772381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019947307,0.00091053837,0.0010751643,0.005382076,0.0026920957,0.007092391,0.0021566092,0.0044704485,0.23109141],"category_scores_gemma":[0.05613659,0.00062885624,0.0008024104,0.0057482156,0.0010719406,0.0033016172,0.0033214334,0.0050738854,0.13776177],"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":[0.000057386995,0.000060017923,0.0006193426,0.0001824889,0.00001056533,0.000025686597,0.00004681628,0.000035493948,0.00005196645,0.007756703,0.91470784,0.07644566],"study_design_scores_gemma":[0.000016152195,0.0000120628165,0.0010182582,0.00022598152,0.0000051168345,0.000037374975,0.000034807916,0.0000306324,0.00002976538,0.0008969178,0.9976866,0.0000062592053],"about_ca_topic_score_codex":0.021976901,"about_ca_topic_score_gemma":0.03359614,"teacher_disagreement_score":0.23109141,"about_ca_system_score_codex":0.0058434554,"about_ca_system_score_gemma":0.038369328,"threshold_uncertainty_score":0.7730778},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037263153,0.016540987,0.0006120462,0.20975552,0.71493155,0.00017901951,0.00082760816,0.00029749432,0.056483153],"genre_scores_gemma":[0.0053148237,0.026864417,0.00087294774,0.2812076,0.46937343,0.0003064487,0.000976631,0.00035121245,0.21473248],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957586,0.00089654245,0.00039621926,0.0005539966,0.0020135208,0.00038108195],"domain_scores_gemma":[0.9739706,0.004727237,0.0011054242,0.0009898981,0.014606875,0.0045999056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003925819,0.0010448194,0.0010410249,0.0014354398,0.0014422786,0.0061437264,0.0026668278,0.0054878583,0.2081267],"category_scores_gemma":[0.04135861,0.00038387394,0.0010320992,0.0008421358,0.0012853085,0.0038560338,0.0021282102,0.007063324,0.087237306],"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":[0.000022825734,0.000016181439,0.00006481496,0.00015799701,0.0000045545885,0.000064287386,0.000011174785,0.000009949559,0.00002300013,0.00057871087,0.9797554,0.019291108],"study_design_scores_gemma":[0.00001767179,0.000023502114,0.00019294122,0.00046771308,0.000007406477,0.00022920752,0.000042642918,0.00001874812,0.000064038366,0.0005858419,0.9983425,0.000007787619],"about_ca_topic_score_codex":0.0011840804,"about_ca_topic_score_gemma":0.0021623909,"teacher_disagreement_score":0.2081267,"about_ca_system_score_codex":0.0020778647,"about_ca_system_score_gemma":0.005584873,"threshold_uncertainty_score":0.6962532},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05236108,0.369868,0.16833471,0.12362511,0.0043699853,0.000952032,0.00016296034,0.0005296073,0.27979645],"genre_scores_gemma":[0.83474743,0.05263366,0.088347346,0.011847383,0.0028571207,0.0015618344,0.0001193724,0.0002777705,0.00760809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7925403,0.14698376,0.014032544,0.006481189,0.037384573,0.002577648],"domain_scores_gemma":[0.7568157,0.1918096,0.007609081,0.014760763,0.024842069,0.004162726],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.123062566,0.0006308706,0.002239551,0.013205047,0.0030140164,0.026801215,0.0021406729,0.00512289,0.0023200435],"category_scores_gemma":[0.134208,0.000998002,0.0009227682,0.010839574,0.055265427,0.02114664,0.011952315,0.0060090018,0.0007117789],"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":[0.00010542877,0.0000955439,0.004842022,0.0019204539,0.00015133347,0.0002119237,0.030281678,0.00051451044,0.00030770633,0.7832203,0.0033687826,0.1749803],"study_design_scores_gemma":[0.000094765346,0.00025169476,0.01385329,0.006699387,0.00011452575,0.0011842789,0.03246838,0.001955837,0.00059362897,0.78927094,0.15337248,0.00014081817],"about_ca_topic_score_codex":0.002903111,"about_ca_topic_score_gemma":0.0022779817,"teacher_disagreement_score":0.87693745,"about_ca_system_score_codex":0.012311549,"about_ca_system_score_gemma":0.010362009,"threshold_uncertainty_score":0.65082484},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14117575,0.00038628673,0.77547646,0.008634736,0.00017697281,0.004048949,0.0004228838,0.0008690014,0.06880899],"genre_scores_gemma":[0.24778642,0.00032202998,0.7461309,0.00036689785,0.000011956925,0.0011598066,0.00021474193,0.00012319519,0.0038841083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9813138,0.0141666,0.0005903524,0.00045157023,0.0029408908,0.00053664506],"domain_scores_gemma":[0.9606468,0.03389973,0.0006340655,0.0018777784,0.0024037466,0.00053786626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020176357,0.0008346762,0.0005711994,0.0023853658,0.004575332,0.0055410736,0.0026904356,0.0032781917,0.0054367217],"category_scores_gemma":[0.026640076,0.0005654506,0.001384138,0.0023423813,0.0040810383,0.005801058,0.0041467813,0.0037885427,0.00088112615],"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":[0.0004396576,0.0020260627,0.006152837,0.0017763994,0.00009656278,0.008121204,0.11914855,0.052957628,0.00584684,0.5145769,0.013309283,0.27554804],"study_design_scores_gemma":[0.0008050884,0.001179096,0.0021686193,0.0030556237,0.00020576915,0.0034710998,0.07692303,0.27703962,0.021672666,0.32383013,0.28927952,0.00036980477],"about_ca_topic_score_codex":0.0075833034,"about_ca_topic_score_gemma":0.013974404,"teacher_disagreement_score":0.020176357,"about_ca_system_score_codex":0.0060204417,"about_ca_system_score_gemma":0.008619748,"threshold_uncertainty_score":0.106704},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008849455,0.00056346983,0.8988245,0.012198047,0.00026887425,0.0033754858,0.00016289395,0.00034443894,0.0754129],"genre_scores_gemma":[0.11483887,0.00041635794,0.8769212,0.0009598857,0.000038435654,0.003314116,0.0001553715,0.000044186883,0.0033115807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95621955,0.035464272,0.00084864604,0.0012536693,0.0055727875,0.00064114534],"domain_scores_gemma":[0.9638103,0.025317488,0.0012239164,0.0031704467,0.0052890414,0.001188773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03994108,0.0017162355,0.0008029447,0.005711266,0.0027956339,0.004967142,0.004031329,0.0025241731,0.013548747],"category_scores_gemma":[0.033323567,0.00076350436,0.0014118805,0.002710567,0.0061662965,0.0039272048,0.005303507,0.0034649444,0.0017022751],"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":[0.00015576869,0.0011057022,0.001929952,0.0021008311,0.0001349343,0.00046101626,0.010861064,0.023973886,0.001644802,0.74967444,0.012673051,0.19528459],"study_design_scores_gemma":[0.0005790837,0.0004939245,0.001483972,0.003065926,0.000114349044,0.00041826465,0.010263829,0.07441197,0.004593095,0.71620905,0.18823676,0.00012977145],"about_ca_topic_score_codex":0.0058116857,"about_ca_topic_score_gemma":0.01102204,"teacher_disagreement_score":0.03994108,"about_ca_system_score_codex":0.013176724,"about_ca_system_score_gemma":0.029112704,"threshold_uncertainty_score":0.21123117},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7939139,0.0047317394,0.070011355,0.031430535,0.00017147866,0.0006976783,0.00008038101,0.000053735388,0.09890927],"genre_scores_gemma":[0.9942773,0.00052192126,0.004178576,0.00040706113,0.000015485943,0.00018361774,0.000013819758,0.000019547431,0.00038256013],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.81336135,0.15832564,0.0050665345,0.00291291,0.0175133,0.002820197],"domain_scores_gemma":[0.32132828,0.6346717,0.012962935,0.006425544,0.022536464,0.0020750784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15877683,0.00043520055,0.0011943261,0.006175108,0.0073646125,0.018921798,0.002082191,0.0027592897,0.003974317],"category_scores_gemma":[0.3476903,0.0007378128,0.00053318666,0.008225615,0.03621741,0.030651083,0.008654378,0.0073628384,0.0003907696],"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":[0.0001555991,0.00064484816,0.029242799,0.0010042235,0.00003916336,0.00047395236,0.5975813,0.0010752098,0.00040996863,0.30548447,0.0017544904,0.06213391],"study_design_scores_gemma":[0.000098904704,0.00037515778,0.025789592,0.004432948,0.000060020146,0.0004179041,0.7691315,0.009867581,0.0011817665,0.16889247,0.019653527,0.000098677265],"about_ca_topic_score_codex":0.00785162,"about_ca_topic_score_gemma":0.0072190505,"teacher_disagreement_score":0.15877683,"about_ca_system_score_codex":0.017216818,"about_ca_system_score_gemma":0.014890513,"threshold_uncertainty_score":0.8397022},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5736324,0.002772765,0.26936597,0.008618257,0.0005612325,0.027554879,0.0003490241,0.0031902536,0.113955304],"genre_scores_gemma":[0.7947211,0.00068198063,0.18409751,0.0008362569,0.0001471238,0.01364723,0.00021347654,0.00028056803,0.00537476],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.48478484,0.4848086,0.0072437315,0.0024914853,0.017414037,0.0032572865],"domain_scores_gemma":[0.51669514,0.3918759,0.01526204,0.024066288,0.04208059,0.010020097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.29656377,0.0017182825,0.0013610033,0.003968962,0.004446851,0.009297197,0.003804805,0.0037889404,0.006544229],"category_scores_gemma":[0.31040108,0.00082838966,0.00094605837,0.0036983148,0.0038563474,0.0064286566,0.009180677,0.002951166,0.0016303151],"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":[0.0052058017,0.012622309,0.03235882,0.0059185955,0.00031706513,0.0028657739,0.14315733,0.010941585,0.0044801384,0.03385312,0.033392973,0.7148865],"study_design_scores_gemma":[0.010058207,0.045229547,0.10258288,0.017119208,0.00082623435,0.0058531943,0.12114919,0.06267625,0.039041117,0.11122268,0.48273873,0.0015027587],"about_ca_topic_score_codex":0.0024198624,"about_ca_topic_score_gemma":0.0038289968,"teacher_disagreement_score":0.29656377,"about_ca_system_score_codex":0.0055044484,"about_ca_system_score_gemma":0.0075681787,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026389156,0.020134034,0.56177133,0.33306313,0.0017759681,0.0019427047,0.00033174973,0.00029922312,0.054292705],"genre_scores_gemma":[0.80327225,0.00681331,0.16904363,0.015713014,0.0010386427,0.0025988491,0.00008285723,0.00006435136,0.001373157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80026406,0.17981037,0.0034690297,0.0031627065,0.0118036745,0.0014902015],"domain_scores_gemma":[0.5308201,0.44149646,0.0074055027,0.008129973,0.010574037,0.0015739417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17708892,0.0012370675,0.0020828866,0.0058477484,0.0036421884,0.009686875,0.0033280854,0.009642573,0.0053707617],"category_scores_gemma":[0.31656626,0.00083587767,0.0015642756,0.0046113776,0.032734346,0.018068545,0.0043844446,0.008258863,0.00048839895],"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":[0.00022189479,0.00029411566,0.0027232985,0.0017473687,0.00019718385,0.00013890259,0.002115453,0.0079652015,0.000111610716,0.9087936,0.0068872254,0.06880413],"study_design_scores_gemma":[0.00015393355,0.000114049704,0.0006343093,0.0010774361,0.0000832559,0.000058789556,0.0012570709,0.012815644,0.0002700992,0.97865,0.004845407,0.00004001876],"about_ca_topic_score_codex":0.00710231,"about_ca_topic_score_gemma":0.0054213894,"teacher_disagreement_score":0.8229111,"about_ca_system_score_codex":0.013068398,"about_ca_system_score_gemma":0.013755019,"threshold_uncertainty_score":0.9365469},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765069,0.00014765117,0.0068526696,0.00046741616,0.000012303999,0.00050577807,0.00011054386,0.00004350846,0.015353226],"genre_scores_gemma":[0.9952034,0.00006318058,0.0042377026,0.000028669123,0.0000025682846,0.00016319579,0.000062039326,0.0000029071243,0.00023627272],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98684305,0.0067950576,0.0009310939,0.00034118365,0.0045480398,0.0005416353],"domain_scores_gemma":[0.9601855,0.013531902,0.007611511,0.0016020177,0.013687757,0.0033812467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020852624,0.0003458625,0.00036423226,0.0048078103,0.002132011,0.0033129754,0.0007061616,0.00070643926,0.0010317443],"category_scores_gemma":[0.045349576,0.0002488208,0.0006355894,0.0025906428,0.0024657182,0.0025239259,0.004165336,0.0010713827,0.00016335439],"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":[0.00009790303,0.00058338494,0.86631316,0.00028522496,0.00016367239,0.0000748021,0.018607164,0.0033669595,0.00048150602,0.0060136737,0.0009678601,0.103044786],"study_design_scores_gemma":[0.000030987387,0.0012207475,0.8695447,0.00060225243,0.00012791074,0.00025095657,0.07319398,0.024023084,0.0034844193,0.017591607,0.009777078,0.00015216047],"about_ca_topic_score_codex":0.011056899,"about_ca_topic_score_gemma":0.017946297,"teacher_disagreement_score":0.020852624,"about_ca_system_score_codex":0.005032762,"about_ca_system_score_gemma":0.0075012073,"threshold_uncertainty_score":0.110280514},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94510627,0.002057357,0.013809386,0.004489256,0.00007757907,0.011307621,0.00035186825,0.00029827972,0.02250235],"genre_scores_gemma":[0.9704077,0.00078676024,0.024291825,0.00024106783,0.00002311603,0.0012134283,0.00022784676,0.000018490691,0.0027897274],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9780189,0.009857359,0.0010728417,0.0007231081,0.008648102,0.0016796308],"domain_scores_gemma":[0.9639287,0.00971283,0.0064543015,0.0015311622,0.015054154,0.0033188174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01893004,0.00054500566,0.00042146543,0.0020729918,0.002813156,0.002279877,0.0015492995,0.0005068419,0.0016263911],"category_scores_gemma":[0.04542879,0.00047696233,0.00041767696,0.0016315705,0.0013779032,0.0013547938,0.0018134442,0.0008994841,0.00014312893],"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":[0.0023857276,0.0023092225,0.084412895,0.002428159,0.00016140245,0.0003389627,0.0071351556,0.020036057,0.0067936713,0.0022993982,0.00626992,0.8654294],"study_design_scores_gemma":[0.002245762,0.009413543,0.85757655,0.0016885925,0.0003609237,0.000288959,0.015040777,0.045011196,0.020015305,0.0024030781,0.04565539,0.00029992018],"about_ca_topic_score_codex":0.5871513,"about_ca_topic_score_gemma":0.7140253,"teacher_disagreement_score":0.4128487,"about_ca_system_score_codex":0.05604041,"about_ca_system_score_gemma":0.09482853,"threshold_uncertainty_score":0.8305601},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01926709,0.0713657,0.06995678,0.34937456,0.0035568047,0.00015386139,0.00054953515,0.0003036582,0.48547196],"genre_scores_gemma":[0.85554415,0.05017244,0.054452427,0.02642848,0.002181736,0.0004976882,0.00050189736,0.0005444985,0.009676696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.928378,0.04081659,0.00430479,0.00409946,0.018266171,0.004135046],"domain_scores_gemma":[0.8940941,0.04313762,0.0056174025,0.0077384617,0.045773845,0.0036385776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07402938,0.0014043876,0.0018745745,0.012765076,0.0058376472,0.02587156,0.0030525548,0.0027498088,0.004899557],"category_scores_gemma":[0.089371055,0.00049490057,0.0010052157,0.020451367,0.036182288,0.018051784,0.006229768,0.010067056,0.0008307671],"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":[0.00007456103,0.000066697394,0.0055800034,0.001164378,0.000119768505,0.00004467861,0.009969717,0.0012107155,0.00027758876,0.7994596,0.01996934,0.16206294],"study_design_scores_gemma":[0.00006413359,0.00024066927,0.041872486,0.016059719,0.00060542725,0.00022848036,0.060728047,0.0040859636,0.0028314355,0.588431,0.28444928,0.00040331625],"about_ca_topic_score_codex":0.22106037,"about_ca_topic_score_gemma":0.2238961,"teacher_disagreement_score":0.22106037,"about_ca_system_score_codex":0.05174086,"about_ca_system_score_gemma":0.0429977,"threshold_uncertainty_score":0.4395473},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004673389,0.016342215,0.84689665,0.10721523,0.0030014624,0.0032230576,0.00026210732,0.00059335347,0.017792586],"genre_scores_gemma":[0.122722246,0.0057902443,0.8514787,0.009589751,0.0013050366,0.008115089,0.00007763425,0.0003033314,0.0006179843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.23773749,0.7040275,0.020787634,0.005820031,0.030186782,0.0014404963],"domain_scores_gemma":[0.08340097,0.8443094,0.01327344,0.03185972,0.025330221,0.0018262742],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.66071457,0.002614674,0.0072372304,0.013751676,0.0059331614,0.032953672,0.0063835615,0.008490528,0.0057382393],"category_scores_gemma":[0.75164026,0.002133241,0.0032781654,0.010439071,0.047986675,0.03792615,0.012121111,0.025167923,0.001459647],"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":[0.00022700202,0.00056208996,0.0026077502,0.0063548773,0.00069515366,0.0001333747,0.016958302,0.004001474,0.00042310084,0.692769,0.019755151,0.2555128],"study_design_scores_gemma":[0.00032745607,0.00018993801,0.0011934523,0.010318747,0.00014800177,0.00011331618,0.00624336,0.010096753,0.0007830879,0.94180506,0.028563062,0.00021773466],"about_ca_topic_score_codex":0.003002815,"about_ca_topic_score_gemma":0.0025018954,"teacher_disagreement_score":0.66071457,"about_ca_system_score_codex":0.01191866,"about_ca_system_score_gemma":0.028044097,"threshold_uncertainty_score":0.4183994},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08665797,0.005520474,0.19331232,0.24500985,0.0010302012,0.0001621408,0.00007126332,0.00023723514,0.4679986],"genre_scores_gemma":[0.9777002,0.0008349152,0.012795431,0.002767219,0.0003087234,0.000112357135,0.00002165725,0.000048177415,0.005411368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9700228,0.019362174,0.00072375726,0.0023463303,0.004828784,0.002716112],"domain_scores_gemma":[0.95267284,0.02885438,0.0040297406,0.0070081274,0.0045875995,0.002847359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03860897,0.0004157771,0.0006170739,0.001974634,0.00559973,0.015046579,0.0018794226,0.0040171957,0.003516693],"category_scores_gemma":[0.03204595,0.00045272175,0.00069354265,0.0014421921,0.07787363,0.016274361,0.007643233,0.0073672268,0.0004635491],"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":[0.0000070119545,0.000007384857,0.00022132102,0.0000135228065,0.000004667028,0.000013391672,0.0011443467,0.0005350917,0.00003432557,0.99465203,0.0006498049,0.0027170484],"study_design_scores_gemma":[0.000022712815,0.000009750018,0.00031465926,0.00006397009,0.0000058404366,0.000010466948,0.00064124557,0.0009405048,0.00009014529,0.9817231,0.016166223,0.000011486915],"about_ca_topic_score_codex":0.008445866,"about_ca_topic_score_gemma":0.008006617,"teacher_disagreement_score":0.03860897,"about_ca_system_score_codex":0.013311012,"about_ca_system_score_gemma":0.016219862,"threshold_uncertainty_score":0.2041862},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41901508,0.20595405,0.02552005,0.0558854,0.001125393,0.0045111924,0.001041434,0.0001848884,0.28676257],"genre_scores_gemma":[0.9600518,0.023594497,0.012954673,0.0011204414,0.00012945953,0.00069260073,0.00014716081,0.000025867495,0.0012836512],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.88144964,0.0793822,0.0061763152,0.0022965702,0.027386913,0.0033083814],"domain_scores_gemma":[0.6347789,0.19941281,0.020425696,0.0094315605,0.12820175,0.0077492427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1422812,0.00069873664,0.0015592664,0.015491716,0.0060877907,0.012023352,0.0029045038,0.001009964,0.0017118892],"category_scores_gemma":[0.21346238,0.00060099154,0.0005863433,0.02040997,0.010307361,0.0043585626,0.004351165,0.0022988084,0.000093716495],"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":[0.00039102748,0.0007074377,0.108698286,0.008984902,0.0005810484,0.0002376103,0.050773896,0.0038168044,0.00027431527,0.06400208,0.008920151,0.7526124],"study_design_scores_gemma":[0.00037156764,0.001208224,0.56590164,0.03742224,0.0009158473,0.0003735264,0.13949317,0.012690263,0.0029372561,0.042724088,0.19540837,0.0005539025],"about_ca_topic_score_codex":0.817817,"about_ca_topic_score_gemma":0.82373494,"teacher_disagreement_score":0.18218303,"about_ca_system_score_codex":0.1166715,"about_ca_system_score_gemma":0.20409213,"threshold_uncertainty_score":0.84651494},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9291434,0.0043683294,0.004083432,0.033179637,0.00017941878,0.0007319263,0.0003349675,0.000025604935,0.02795325],"genre_scores_gemma":[0.98979867,0.0016212449,0.0017058863,0.0025986976,0.00001304224,0.00017896171,0.00006261458,0.000033290966,0.003987526],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9566923,0.029845376,0.0012743772,0.0015558107,0.0038890128,0.00674323],"domain_scores_gemma":[0.91463464,0.059391882,0.0024083818,0.0013303893,0.01222858,0.010006104],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03573291,0.0007181594,0.001125512,0.0030937337,0.048659723,0.012688727,0.0045416728,0.004097574,0.003369244],"category_scores_gemma":[0.042726442,0.0009993112,0.0005160017,0.0068172915,0.028112859,0.003457543,0.008771829,0.006165061,0.0002541816],"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":true,"study_design_scores_codex":[0.000050482035,0.000028614655,0.0033565843,0.00024085768,0.0000092356695,0.0028750978,0.98304445,0.00021952711,0.00051919644,0.0036523829,0.0014286155,0.0045749648],"study_design_scores_gemma":[0.0000047929084,0.000011951155,0.0010710587,0.00035118713,0.0000056862077,0.00013176214,0.98628193,0.00013881834,0.00013458534,0.00035582122,0.011491677,0.000020628862],"about_ca_topic_score_codex":0.95768136,"about_ca_topic_score_gemma":0.97504956,"teacher_disagreement_score":0.9642671,"about_ca_system_score_codex":0.18667305,"about_ca_system_score_gemma":0.20689012,"threshold_uncertainty_score":0.943344},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068024104,0.0026137577,0.8158563,0.06487997,0.000704396,0.0011627574,0.000078947836,0.00069188926,0.10720955],"genre_scores_gemma":[0.18533695,0.0022649097,0.7975312,0.00393203,0.00015702438,0.0019117768,0.00009172709,0.0003028673,0.008471456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9295334,0.060570523,0.0019803573,0.0013807394,0.004870213,0.0016647807],"domain_scores_gemma":[0.93010575,0.04954509,0.0015892719,0.0038595195,0.010377136,0.0045232307],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07858788,0.0014792884,0.001024814,0.0059077917,0.008998682,0.014829419,0.0046965107,0.0047757546,0.0051193265],"category_scores_gemma":[0.05447143,0.0009083378,0.0012390988,0.0036218832,0.035574775,0.013672595,0.008342273,0.010645579,0.0014041261],"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":[0.000019985597,0.00012943229,0.0005295515,0.00029462087,0.000007910486,0.00013509841,0.031436276,0.0010978141,0.0004015137,0.91158235,0.009194953,0.04517048],"study_design_scores_gemma":[0.000053200827,0.000081366576,0.00056754914,0.002731179,0.00002495852,0.000235442,0.026874837,0.007203903,0.0012489833,0.71830285,0.24258947,0.000086152024],"about_ca_topic_score_codex":0.048736982,"about_ca_topic_score_gemma":0.07509736,"teacher_disagreement_score":0.9680924,"about_ca_system_score_codex":0.031907625,"about_ca_system_score_gemma":0.046898596,"threshold_uncertainty_score":0.4156174},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035549959,0.38400698,0.008705455,0.5512236,0.009897004,0.000047661353,0.000040893272,0.000038327078,0.042485144],"genre_scores_gemma":[0.34759802,0.39673385,0.021402933,0.1751209,0.040699363,0.00025388505,0.00009506118,0.00017921561,0.017916743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.95274895,0.03183836,0.0026526304,0.0012174795,0.010399295,0.0011433596],"domain_scores_gemma":[0.7239303,0.23864685,0.0046540378,0.0025344815,0.026999721,0.0032346162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059267018,0.00039928523,0.0015740336,0.0055929557,0.0063283225,0.021509908,0.00212296,0.009989798,0.0040074755],"category_scores_gemma":[0.10887345,0.00036404168,0.0005304155,0.0072250124,0.030413931,0.013333376,0.003962767,0.013044993,0.00053493347],"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":[0.00010659716,0.00007845281,0.0017739225,0.0022104608,0.000036522622,0.00019662747,0.0037086504,0.00040427918,0.00021339986,0.64928186,0.080307946,0.26168123],"study_design_scores_gemma":[0.000031564014,0.00015865156,0.0055395514,0.015214743,0.000054374337,0.00061046483,0.019972261,0.0011121298,0.00043224002,0.413378,0.5433765,0.000119521435],"about_ca_topic_score_codex":0.020637106,"about_ca_topic_score_gemma":0.04753363,"teacher_disagreement_score":0.059267018,"about_ca_system_score_codex":0.018391246,"about_ca_system_score_gemma":0.021419898,"threshold_uncertainty_score":0.3134377},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0184759,0.021436706,0.040976375,0.71019405,0.0021247643,0.000444185,0.000057231147,0.00028646702,0.20600428],"genre_scores_gemma":[0.914181,0.009550297,0.027141983,0.036046457,0.00061320054,0.0005183718,0.000031911102,0.00028296013,0.011633834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8925642,0.07092739,0.0028277184,0.0032239337,0.021637565,0.008819172],"domain_scores_gemma":[0.89584094,0.06300464,0.0037218162,0.0038746556,0.022401532,0.011156353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09699455,0.0013528463,0.0017331848,0.005439301,0.019402796,0.04089967,0.0040228907,0.00928574,0.008007508],"category_scores_gemma":[0.10484587,0.00075761596,0.000854121,0.0055784727,0.118943214,0.026275266,0.020964859,0.015939327,0.0008999187],"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":[0.00009124759,0.00013049763,0.0018812971,0.00087392254,0.00007174958,0.00023908225,0.047721673,0.0016567685,0.00028456777,0.84648657,0.036498826,0.06406386],"study_design_scores_gemma":[0.00007785969,0.00009339225,0.0041221865,0.005541742,0.00006118479,0.00020911104,0.08921511,0.0035145725,0.0012709142,0.6475223,0.2480953,0.0002764573],"about_ca_topic_score_codex":0.20988105,"about_ca_topic_score_gemma":0.20888996,"teacher_disagreement_score":0.20988105,"about_ca_system_score_codex":0.06259954,"about_ca_system_score_gemma":0.1142117,"threshold_uncertainty_score":0.51296234},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8503391,0.00219993,0.011618783,0.014662872,0.00013205496,0.0011162523,0.00025375636,0.00014942969,0.119527735],"genre_scores_gemma":[0.98694056,0.0003748871,0.0052058967,0.0003053516,0.000018888035,0.00025640283,0.0000770755,0.00002555166,0.0067953467],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95670724,0.032110523,0.00068608177,0.000809044,0.0072246934,0.002462401],"domain_scores_gemma":[0.9507432,0.030937146,0.0018949006,0.0011699208,0.013054118,0.0022007932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05166192,0.000694691,0.0005609323,0.0020748905,0.006395874,0.006641739,0.0012535302,0.0014803369,0.0061237565],"category_scores_gemma":[0.045926705,0.0002756339,0.0007025824,0.002015162,0.0050743017,0.0020748186,0.0022967,0.0023578405,0.00042160542],"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":[0.0022069684,0.0034921772,0.0933639,0.0018324218,0.00039094794,0.0009520578,0.2099529,0.02706485,0.004633678,0.057214167,0.027496632,0.57139933],"study_design_scores_gemma":[0.001262875,0.006533144,0.400292,0.0031549947,0.0004996244,0.0004484868,0.18414362,0.080848135,0.012555149,0.019780071,0.2898604,0.00062153774],"about_ca_topic_score_codex":0.686123,"about_ca_topic_score_gemma":0.714624,"teacher_disagreement_score":0.313877,"about_ca_system_score_codex":0.07561025,"about_ca_system_score_gemma":0.047574967,"threshold_uncertainty_score":0.6314509},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30937752,0.0074796337,0.009293631,0.22456567,0.0008195826,0.000694085,0.00036064663,0.00019397825,0.44721526],"genre_scores_gemma":[0.9522599,0.0013619213,0.003349856,0.011638486,0.0000735516,0.00012861645,0.000083043145,0.000089972265,0.031014705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"case_report","domain_scores_codex":[0.9633363,0.010728722,0.00077733095,0.0015271669,0.007612989,0.016017513],"domain_scores_gemma":[0.95445484,0.01291086,0.0011236763,0.0015436116,0.017773671,0.012193344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021376686,0.00052390003,0.0006678798,0.0023945794,0.04822576,0.019078486,0.003658313,0.007590089,0.010015654],"category_scores_gemma":[0.038158458,0.0007075048,0.0009978318,0.0061297314,0.013283928,0.006642695,0.010873402,0.009684163,0.0005669351],"study_design_candidate":"case_report","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":[0.00038144787,0.0005759644,0.057725366,0.00049904024,0.00017776492,0.015915796,0.08414686,0.009859061,0.0007176413,0.64884,0.07954172,0.101619415],"study_design_scores_gemma":[0.00027311093,0.00020873945,0.05357627,0.002060719,0.00024240286,0.0022893033,0.2623076,0.012266387,0.0012828615,0.09020158,0.57489103,0.00040006696],"about_ca_topic_score_codex":0.983429,"about_ca_topic_score_gemma":0.9886656,"teacher_disagreement_score":0.7839619,"about_ca_system_score_codex":0.21603812,"about_ca_system_score_gemma":0.354462,"threshold_uncertainty_score":0.90928465},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1516031,0.007921119,0.4234115,0.080646716,0.0007493836,0.0034363067,0.00021061585,0.00033000138,0.33169124],"genre_scores_gemma":[0.9098697,0.0021656624,0.081491396,0.0017291822,0.00013632055,0.0014118761,0.00009747288,0.000095573094,0.0030028601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8299057,0.13851042,0.004866718,0.0035479849,0.01730375,0.005865452],"domain_scores_gemma":[0.7664269,0.19027485,0.009282489,0.012898933,0.016440326,0.004676458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12005572,0.0013992651,0.0011928083,0.014403521,0.014951003,0.026118381,0.004850885,0.0077847484,0.0036509354],"category_scores_gemma":[0.12636858,0.001343708,0.0016006373,0.0120747,0.08787927,0.04915483,0.018944472,0.011677249,0.00053358934],"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":[0.000031899635,0.00008208353,0.0021334894,0.00048506615,0.00001737888,0.0010021162,0.24087563,0.00072157045,0.00031247892,0.73841697,0.00085137563,0.015069981],"study_design_scores_gemma":[0.000052026622,0.00015306071,0.0029195955,0.0026916396,0.000074203,0.0022394017,0.43829873,0.004129803,0.0016162765,0.41256258,0.13516028,0.00010242417],"about_ca_topic_score_codex":0.007322255,"about_ca_topic_score_gemma":0.00447234,"teacher_disagreement_score":0.87994426,"about_ca_system_score_codex":0.02327156,"about_ca_system_score_gemma":0.019953256,"threshold_uncertainty_score":0.6349229},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09760371,0.01627671,0.0855184,0.66588455,0.0068490035,0.0020784405,0.00021097099,0.00039074983,0.1251874],"genre_scores_gemma":[0.8858237,0.007866113,0.053163294,0.026400851,0.0017279979,0.0035309533,0.00012648024,0.00036752486,0.020993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.582725,0.35034055,0.013661397,0.0037687507,0.04361277,0.00589156],"domain_scores_gemma":[0.64980507,0.24208876,0.018562708,0.012912407,0.07086478,0.0057663047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23185703,0.0010998102,0.001314426,0.0021070554,0.009115308,0.026136253,0.0025470427,0.0069660773,0.0065813554],"category_scores_gemma":[0.38389015,0.0007069181,0.0009666152,0.0028109644,0.024444697,0.02140926,0.006824226,0.012759962,0.0016988185],"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":[0.0006990002,0.0005725098,0.009329514,0.0044327616,0.00024409071,0.0013333467,0.32963133,0.0009341358,0.0049807015,0.33258146,0.07262436,0.24263681],"study_design_scores_gemma":[0.00019870438,0.00036028682,0.006498012,0.010288866,0.00015920274,0.0008701531,0.32854968,0.0027216983,0.0074804565,0.07296982,0.56959146,0.00031158942],"about_ca_topic_score_codex":0.012129348,"about_ca_topic_score_gemma":0.012630758,"teacher_disagreement_score":0.23185703,"about_ca_system_score_codex":0.016111195,"about_ca_system_score_gemma":0.025132762,"threshold_uncertainty_score":0.94725704},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06490901,0.0013023099,0.52922004,0.03195895,0.0008720084,0.051571112,0.0027388989,0.0009972039,0.3164304],"genre_scores_gemma":[0.420819,0.00094590423,0.48908022,0.0031787227,0.00019974897,0.044060368,0.0017147498,0.00022889017,0.03977238],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86392313,0.10874876,0.004947471,0.0048147882,0.014474667,0.0030912217],"domain_scores_gemma":[0.89593536,0.04969297,0.0052214507,0.010582915,0.035291344,0.0032760152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10470312,0.0014309462,0.00096013653,0.0064737406,0.008878045,0.005840401,0.0038447855,0.002344322,0.023906497],"category_scores_gemma":[0.113255225,0.0007522,0.0008779111,0.0040832697,0.0047874954,0.006482487,0.015405656,0.0030954576,0.0045168907],"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":[0.00036890776,0.00067504443,0.008958698,0.0036932013,0.000118420714,0.0006982869,0.12719277,0.0036658589,0.0042592324,0.17162134,0.059619464,0.61912876],"study_design_scores_gemma":[0.0002738989,0.00073978317,0.008044377,0.0048689325,0.000114200375,0.0007029115,0.11066094,0.009232208,0.008132917,0.23516493,0.6218414,0.00022359347],"about_ca_topic_score_codex":0.0055210586,"about_ca_topic_score_gemma":0.0077940244,"teacher_disagreement_score":0.10470312,"about_ca_system_score_codex":0.010124786,"about_ca_system_score_gemma":0.034352947,"threshold_uncertainty_score":0.55372965},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29807574,0.009463581,0.34168717,0.099393345,0.00129665,0.011225907,0.000076878576,0.0010921684,0.23768863],"genre_scores_gemma":[0.8838538,0.0017938194,0.10612451,0.0018946056,0.000089250425,0.0034330685,0.000028988197,0.00008533237,0.0026965886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.71756506,0.2557055,0.0046500955,0.0039461483,0.01380665,0.004326647],"domain_scores_gemma":[0.71411616,0.23578697,0.010341018,0.015411387,0.01684986,0.007494603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18208636,0.0010052109,0.0011874331,0.0034731238,0.009796745,0.01233983,0.003312476,0.003131866,0.0034224538],"category_scores_gemma":[0.23236744,0.0006535362,0.0008100287,0.0027439818,0.018964317,0.010939922,0.01503426,0.0044326833,0.00036540933],"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":[0.0003666412,0.0022884621,0.010956674,0.0032358705,0.00017562682,0.0004962352,0.14611045,0.0037486334,0.0013090268,0.124729,0.0082944175,0.6982889],"study_design_scores_gemma":[0.0010157774,0.0038281444,0.021491,0.019333344,0.00041640594,0.00090620643,0.28742164,0.017265506,0.012570276,0.40679353,0.2283494,0.0006089087],"about_ca_topic_score_codex":0.006482002,"about_ca_topic_score_gemma":0.00973941,"teacher_disagreement_score":0.18208636,"about_ca_system_score_codex":0.015694955,"about_ca_system_score_gemma":0.045566544,"threshold_uncertainty_score":0.9629762},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6071491,0.00721719,0.11733204,0.007663191,0.00047410457,0.0074510016,0.20810431,0.0011969687,0.043412056],"genre_scores_gemma":[0.8375343,0.0015773252,0.07873173,0.00049210817,0.00017672408,0.0093417205,0.07126604,0.00014000277,0.00074003084],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.7948192,0.1382796,0.021878494,0.0067420173,0.03640224,0.0018785362],"domain_scores_gemma":[0.3959359,0.42674437,0.065810345,0.058094252,0.050581343,0.002833815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13582814,0.0007629352,0.0016120232,0.022289906,0.0017127483,0.005167927,0.0031636711,0.0016183725,0.00429649],"category_scores_gemma":[0.40939793,0.00073890435,0.0013592046,0.04539038,0.0013985683,0.005904757,0.004137615,0.0016867531,0.00058770453],"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":[0.0037369179,0.0021020705,0.6225036,0.0063045886,0.006113406,0.0002812121,0.0029630943,0.021648547,0.000493855,0.05721881,0.029734617,0.2468993],"study_design_scores_gemma":[0.004094995,0.0027231683,0.69989103,0.0059733163,0.0073419674,0.0010091292,0.011531677,0.08274887,0.008757305,0.06302207,0.11232553,0.0005810625],"about_ca_topic_score_codex":0.036140125,"about_ca_topic_score_gemma":0.024031837,"teacher_disagreement_score":0.13582814,"about_ca_system_score_codex":0.0065254136,"about_ca_system_score_gemma":0.013284753,"threshold_uncertainty_score":0.71833646},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007866156,0.6391927,0.15605383,0.09247004,0.021561194,0.0027680008,0.022414172,0.0030891742,0.054584634],"genre_scores_gemma":[0.10675965,0.4857678,0.32575142,0.013884526,0.0068078944,0.008301915,0.021633515,0.0022011243,0.02889218],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9753955,0.013456445,0.0035359475,0.00089080626,0.006456602,0.0002647551],"domain_scores_gemma":[0.7768481,0.16901529,0.007954167,0.006682684,0.03822521,0.0012745651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059194922,0.0033799023,0.0029527885,0.014213123,0.0029041837,0.0055477675,0.0054934644,0.003628844,0.02310231],"category_scores_gemma":[0.20297639,0.0037891907,0.0024843994,0.016963787,0.0064305514,0.0105788605,0.0033396343,0.012019303,0.019130196],"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":[0.00023771025,0.000107186206,0.004726475,0.0034840442,0.00030014396,0.000097602344,0.0020786389,0.0009096494,0.00052744563,0.008214064,0.52190495,0.45741206],"study_design_scores_gemma":[0.00040758666,0.00048444458,0.063412614,0.030381233,0.001583751,0.001663526,0.004690334,0.002455316,0.003305581,0.074847825,0.8160446,0.0007231947],"about_ca_topic_score_codex":0.02273084,"about_ca_topic_score_gemma":0.036893133,"teacher_disagreement_score":0.059194922,"about_ca_system_score_codex":0.0046991794,"about_ca_system_score_gemma":0.0057320753,"threshold_uncertainty_score":0.3130564},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009620108,0.011494019,0.7234622,0.22104904,0.004438373,0.0062939753,0.00016495869,0.0009918385,0.022485452],"genre_scores_gemma":[0.10335739,0.005423062,0.8620447,0.00950015,0.00092189095,0.012140956,0.00023166559,0.00025355074,0.006126661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5686244,0.36095563,0.020982165,0.0070971563,0.03861604,0.0037246153],"domain_scores_gemma":[0.59627444,0.23637351,0.013991804,0.024144944,0.12189274,0.0073225372],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38477072,0.004243354,0.002821813,0.013245676,0.0083729755,0.031984862,0.009666139,0.013635123,0.007060355],"category_scores_gemma":[0.29334787,0.0020385387,0.004210293,0.008134787,0.034932185,0.04194219,0.012098926,0.017363342,0.0025990175],"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":[0.00036430647,0.0007190278,0.0026878088,0.0059146425,0.0001672831,0.00054827373,0.03083374,0.004291665,0.0022991856,0.71412194,0.025881192,0.21217103],"study_design_scores_gemma":[0.00083676295,0.0007830011,0.004424693,0.021349812,0.0003215668,0.0014768357,0.045337,0.026592446,0.0053299326,0.39217746,0.50066626,0.00070432277],"about_ca_topic_score_codex":0.014679041,"about_ca_topic_score_gemma":0.015873538,"teacher_disagreement_score":0.38477072,"about_ca_system_score_codex":0.022951864,"about_ca_system_score_gemma":0.053018246,"threshold_uncertainty_score":0.75868726},"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":"methods","genre_gemma":"commentary","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029872678,0.020406784,0.65828234,0.23288369,0.0024445069,0.009525017,0.0001514187,0.0005725681,0.04586096],"genre_scores_gemma":[0.4675425,0.0033303439,0.5080053,0.009958536,0.0011299566,0.007989422,0.00010021831,0.00022819666,0.0017155203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.056632116,0.8443934,0.030708393,0.0067243897,0.059464097,0.002077758],"domain_scores_gemma":[0.08857952,0.7135817,0.041596197,0.0735992,0.078546084,0.004097336],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.85428953,0.0024554888,0.0053001675,0.016311174,0.011894235,0.038366985,0.00957213,0.012723169,0.0026669544],"category_scores_gemma":[0.8375267,0.003585883,0.0038192316,0.009978873,0.054453082,0.03452598,0.039634626,0.017342536,0.00063556276],"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":[0.0009924883,0.0007521068,0.010936908,0.008974115,0.0013194939,0.00048590632,0.04142318,0.00923504,0.0014006613,0.4841944,0.009823225,0.4304625],"study_design_scores_gemma":[0.0012011983,0.0021713492,0.011459658,0.025826868,0.0008343076,0.0007119417,0.013535291,0.020374542,0.0051525594,0.8231656,0.09478112,0.0007855067],"about_ca_topic_score_codex":0.004479147,"about_ca_topic_score_gemma":0.004681074,"teacher_disagreement_score":0.85428953,"about_ca_system_score_codex":0.034016695,"about_ca_system_score_gemma":0.08559014,"threshold_uncertainty_score":0.2468096},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005982614,0.77933085,0.024334706,0.14636798,0.009735936,0.00017439848,0.0026297357,0.00047011042,0.036358003],"genre_scores_gemma":[0.024618773,0.8592781,0.047667414,0.025859533,0.004981661,0.00050497556,0.0013237788,0.00054853485,0.035217233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962198,0.0016397316,0.0005837149,0.00020361212,0.0012394577,0.00011371067],"domain_scores_gemma":[0.9498587,0.03455071,0.0037562458,0.0009903773,0.009663407,0.0011804445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013747628,0.0017632877,0.0012628705,0.0055794334,0.0013756263,0.004198913,0.0021595038,0.0039426307,0.023870623],"category_scores_gemma":[0.043084126,0.0016351381,0.00085168035,0.007679006,0.0024294842,0.0069908476,0.0016341505,0.007272916,0.01618344],"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":[0.000098708166,0.000029595734,0.0005359522,0.0025545426,0.000054565506,0.00009818737,0.00029953226,0.00035649602,0.00014020725,0.017591974,0.7415391,0.2367011],"study_design_scores_gemma":[0.00011579198,0.00010592403,0.005607372,0.018967984,0.0002623491,0.0008283124,0.00066154305,0.0007480832,0.00093589263,0.10388215,0.8677451,0.00013954185],"about_ca_topic_score_codex":0.013798277,"about_ca_topic_score_gemma":0.026519192,"teacher_disagreement_score":0.023870623,"about_ca_system_score_codex":0.002196768,"about_ca_system_score_gemma":0.0065971273,"threshold_uncertainty_score":0.079855144},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4253618,0.011452066,0.05200597,0.43229944,0.0019926433,0.011658623,0.00013016257,0.00023805846,0.06486128],"genre_scores_gemma":[0.9534406,0.0015126186,0.03132602,0.005816479,0.00015627529,0.0055960543,0.000032869422,0.000047214704,0.0020718744],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.4504746,0.50718516,0.0072745928,0.004579244,0.021782048,0.008704356],"domain_scores_gemma":[0.5545055,0.34099033,0.013756819,0.013122677,0.05346692,0.024157796],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43739492,0.000877498,0.0014061374,0.0018008249,0.031048752,0.020885034,0.0059744394,0.0059390333,0.003415263],"category_scores_gemma":[0.31519786,0.001056637,0.0009177786,0.0022728248,0.019789126,0.011034527,0.017043136,0.007573728,0.00033627648],"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":[0.0008423651,0.0020989364,0.021220522,0.004428713,0.00027114566,0.0022933565,0.559488,0.0036317972,0.001712424,0.099792846,0.021012586,0.2832073],"study_design_scores_gemma":[0.00064805243,0.0016281551,0.010185019,0.007416705,0.00016302036,0.0010360668,0.78831816,0.0056669763,0.0024789423,0.06398937,0.11816719,0.00030220833],"about_ca_topic_score_codex":0.039167486,"about_ca_topic_score_gemma":0.052268554,"teacher_disagreement_score":0.43739492,"about_ca_system_score_codex":0.032122966,"about_ca_system_score_gemma":0.12838002,"threshold_uncertainty_score":0.6937922},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015245883,0.001831743,0.9298493,0.011236088,0.00015763205,0.01661417,0.0008956222,0.00071452296,0.023454957],"genre_scores_gemma":[0.11049445,0.00042656003,0.87404466,0.0004802855,0.000033394073,0.013507869,0.00058782316,0.00003785784,0.00038703703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.69460446,0.24882779,0.02136827,0.00554729,0.026694972,0.0029572023],"domain_scores_gemma":[0.83619404,0.10738709,0.009833679,0.0061645135,0.036816437,0.0036043671],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25966123,0.0029428531,0.0031703704,0.012277091,0.004122999,0.011646829,0.0052339607,0.0037196458,0.002528373],"category_scores_gemma":[0.1742519,0.0011637566,0.0043261526,0.008378762,0.008632029,0.009412399,0.007581614,0.0050959755,0.0006045768],"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":[0.00028683795,0.0013396604,0.019025207,0.003759588,0.0006354081,0.00039378094,0.013062814,0.036332034,0.0012381376,0.62628984,0.0106551,0.2869817],"study_design_scores_gemma":[0.0008083613,0.0024852557,0.01969249,0.018499158,0.0011509791,0.0005896715,0.016019715,0.19244574,0.0049388153,0.6766936,0.06621879,0.00045741655],"about_ca_topic_score_codex":0.024670143,"about_ca_topic_score_gemma":0.021276472,"teacher_disagreement_score":0.25966123,"about_ca_system_score_codex":0.03203842,"about_ca_system_score_gemma":0.050733685,"threshold_uncertainty_score":0.9129695},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884088,0.0012316424,0.022754394,0.035402533,0.00006909833,0.00056691683,0.00005766102,0.00012831022,0.051380727],"genre_scores_gemma":[0.9935714,0.0003087676,0.0047706435,0.00038206513,0.000010380011,0.000103592494,0.0000140683915,0.000014279827,0.0008247052],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9630778,0.028327504,0.0008742556,0.00065986137,0.003665907,0.003394587],"domain_scores_gemma":[0.8884618,0.0873106,0.0053766523,0.002501184,0.008393232,0.007956474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044865698,0.00045851563,0.00035153577,0.0025408657,0.0040684566,0.008686027,0.0016757709,0.0016135029,0.0021360575],"category_scores_gemma":[0.06958214,0.000457893,0.0003145345,0.0018504469,0.0065693106,0.0059287646,0.0052838847,0.0034551125,0.00024754164],"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":[0.00017159042,0.0016974456,0.083954334,0.001091387,0.00004558303,0.002109223,0.5711557,0.0012182578,0.0024680663,0.07529641,0.0069066877,0.25388533],"study_design_scores_gemma":[0.000051999526,0.0002672499,0.047492485,0.0016707868,0.000031263742,0.0009946779,0.8443321,0.005308205,0.0039025005,0.056851815,0.038971838,0.00012515172],"about_ca_topic_score_codex":0.004128863,"about_ca_topic_score_gemma":0.0070888256,"teacher_disagreement_score":0.044865698,"about_ca_system_score_codex":0.008676663,"about_ca_system_score_gemma":0.013279779,"threshold_uncertainty_score":0.2372753},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010098,0.38537884,0.052930765,0.2881183,0.008600447,0.00076090224,0.0036828185,0.0009922115,0.24943767],"genre_scores_gemma":[0.11391478,0.5169319,0.09280069,0.030702364,0.0012857453,0.0007158182,0.0015377676,0.00070891995,0.2414021],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988403,0.00030961557,0.000095392556,0.00010170844,0.00059125974,0.000061759456],"domain_scores_gemma":[0.99066895,0.005437575,0.0005637508,0.00017429593,0.0026661581,0.0004892397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046154987,0.00058926776,0.00031816238,0.0023527986,0.0021669278,0.0035098153,0.0010668794,0.0018154236,0.025242306],"category_scores_gemma":[0.017569277,0.00073894736,0.00029193537,0.002288796,0.0013549326,0.005849029,0.001081756,0.002208268,0.011190134],"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":[0.000050103983,0.000058781803,0.0014793262,0.000761866,0.000011712292,0.000087134824,0.0014432059,0.00010577305,0.00029407247,0.0026532444,0.60888547,0.38416922],"study_design_scores_gemma":[0.000044111315,0.00009070643,0.019714544,0.004854448,0.00007349597,0.0006836523,0.0055092312,0.0002978194,0.0015241395,0.015310897,0.95182014,0.000076852884],"about_ca_topic_score_codex":0.024577368,"about_ca_topic_score_gemma":0.10378164,"teacher_disagreement_score":0.025242306,"about_ca_system_score_codex":0.0014014842,"about_ca_system_score_gemma":0.0039053687,"threshold_uncertainty_score":0.08444393},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68113416,0.00057366677,0.07950834,0.023381084,0.000037795333,0.0007148582,0.00034111197,0.00019072295,0.21411829],"genre_scores_gemma":[0.96834105,0.00019479576,0.027801637,0.00032616462,0.0000047519034,0.00012332418,0.00010192732,0.00003626419,0.0030700073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9817394,0.014925487,0.00031074294,0.0004706092,0.0015675324,0.0009861687],"domain_scores_gemma":[0.9363941,0.054336995,0.0014477981,0.0015991207,0.004949168,0.0012727848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016264448,0.00048780785,0.0003741382,0.0017385159,0.0059428997,0.010447438,0.0022286272,0.0014898728,0.0038352609],"category_scores_gemma":[0.03997668,0.00041132275,0.00052752317,0.0024253677,0.00712247,0.0041307183,0.0035476326,0.0025728703,0.00026843857],"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":[0.00042805658,0.00086260395,0.04022264,0.000506082,0.0000963781,0.0021142066,0.14853838,0.09688661,0.0013973204,0.59260815,0.007137608,0.109201975],"study_design_scores_gemma":[0.00021791145,0.00024114296,0.017005317,0.0009019607,0.00013870391,0.0004906233,0.24379468,0.41487667,0.0022511494,0.25574964,0.06414935,0.00018281469],"about_ca_topic_score_codex":0.56017035,"about_ca_topic_score_gemma":0.59267473,"teacher_disagreement_score":0.43982965,"about_ca_system_score_codex":0.031927325,"about_ca_system_score_gemma":0.039262842,"threshold_uncertainty_score":0.8848398},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001631786,0.8769675,0.014824546,0.026941746,0.0031918625,0.00017705717,0.0023446558,0.0005785821,0.07334219],"genre_scores_gemma":[0.00858249,0.9328973,0.015539724,0.0009929847,0.00057543966,0.00011676515,0.00094100373,0.0001996981,0.040154494],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99842876,0.00032599695,0.00017623152,0.00012060818,0.000873499,0.00007478191],"domain_scores_gemma":[0.9940631,0.0030550617,0.0005105666,0.00018016674,0.0018416421,0.00034946293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039622234,0.0014036782,0.0010953174,0.0034996935,0.0011317045,0.0039429264,0.0014917672,0.0016306071,0.028217364],"category_scores_gemma":[0.009146737,0.0011550714,0.0007565377,0.004154129,0.0012089158,0.0049283532,0.0010520578,0.002816971,0.025296552],"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":[0.00003489283,0.000041195868,0.00076563976,0.0015767418,0.00002021527,0.000053882195,0.0005956198,0.0002727693,0.00022253142,0.00258045,0.40044853,0.59338754],"study_design_scores_gemma":[0.000016198923,0.000057242014,0.0049245544,0.005659291,0.00007685878,0.00057989307,0.0011592389,0.00022505994,0.00065864925,0.0073723835,0.97921205,0.000058551876],"about_ca_topic_score_codex":0.03276519,"about_ca_topic_score_gemma":0.07735658,"teacher_disagreement_score":0.03276519,"about_ca_system_score_codex":0.002062039,"about_ca_system_score_gemma":0.007884875,"threshold_uncertainty_score":0.09439653},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025178177,0.64227706,0.18998672,0.029565709,0.01696799,0.06784783,0.0104388995,0.002357204,0.0153803965],"genre_scores_gemma":[0.3841808,0.089818805,0.38352862,0.008918387,0.0024611673,0.12419115,0.0038406716,0.0008679447,0.0021924286],"study_design_codex":"meta_analysis","study_design_gemma":"qualitative","domain_scores_codex":[0.24525215,0.6534663,0.055706967,0.011114732,0.033023138,0.001436695],"domain_scores_gemma":[0.2137147,0.6713465,0.040806673,0.039967068,0.032048285,0.0021168482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5605815,0.0065931156,0.022414906,0.01828751,0.0029705185,0.012880186,0.008840191,0.009127746,0.0073047457],"category_scores_gemma":[0.7187894,0.004439696,0.04626917,0.014352146,0.0063521597,0.009593047,0.007657841,0.008368249,0.00075028394],"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":[0.010218103,0.00016766715,0.0042633624,0.33935347,0.5570449,0.00031189254,0.0013611089,0.005262394,0.00062718336,0.011824605,0.008868886,0.06069645],"study_design_scores_gemma":[0.008853332,0.0032378074,0.006272707,0.16967058,0.7379692,0.00022097761,0.00077166094,0.0074445037,0.002761218,0.02343993,0.03884091,0.00051723263],"about_ca_topic_score_codex":0.0072464305,"about_ca_topic_score_gemma":0.008389569,"teacher_disagreement_score":0.4394185,"about_ca_system_score_codex":0.022731338,"about_ca_system_score_gemma":0.020412836,"threshold_uncertainty_score":0.54188126},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104435235,0.011662257,0.06262589,0.2963946,0.008467258,0.00079847645,0.0012803794,0.0016720456,0.5126639],"genre_scores_gemma":[0.6101758,0.009912703,0.063293956,0.03130382,0.0011995962,0.0006463848,0.0005712171,0.001061424,0.2818351],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921876,0.0035466175,0.00017997711,0.00063357264,0.0026803182,0.0007719198],"domain_scores_gemma":[0.9854483,0.0054237833,0.001044123,0.0010244513,0.004975134,0.0020842238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108747855,0.000736425,0.0006121872,0.00091830123,0.0052462546,0.006139483,0.0012589103,0.002359206,0.05179239],"category_scores_gemma":[0.03703518,0.0002917011,0.0006552032,0.001213818,0.0051976386,0.006539869,0.0025964219,0.006069471,0.008085007],"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":[0.00072343444,0.0008041572,0.015353809,0.0011545889,0.00020752978,0.0014900365,0.01603697,0.002140437,0.0051361253,0.2725843,0.35484874,0.32951993],"study_design_scores_gemma":[0.000081291335,0.0005462992,0.009917348,0.0017005897,0.00011205982,0.001079353,0.014336566,0.0011706583,0.0051041096,0.053008623,0.9127585,0.0001845543],"about_ca_topic_score_codex":0.027602883,"about_ca_topic_score_gemma":0.041837938,"teacher_disagreement_score":0.05179239,"about_ca_system_score_codex":0.0060777063,"about_ca_system_score_gemma":0.0103777805,"threshold_uncertainty_score":0.17326277},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001137338,0.9154152,0.0093242545,0.03434037,0.0041916748,0.00006511968,0.0014666223,0.0003417125,0.033717662],"genre_scores_gemma":[0.009355267,0.93545586,0.008671648,0.0016528411,0.0010566809,0.000058567624,0.0006960609,0.00012571077,0.042927317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984775,0.00044504827,0.00011495977,0.0001815731,0.00069409335,0.00008685542],"domain_scores_gemma":[0.99489355,0.0024096176,0.00029732013,0.00013976159,0.0019342147,0.00032545908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035563041,0.0016151614,0.0010699593,0.0028039266,0.00091511454,0.0042512813,0.0013935162,0.002137548,0.027050842],"category_scores_gemma":[0.0073691946,0.0010200216,0.00043622294,0.0046285116,0.0010574295,0.0051023304,0.001031792,0.0021433858,0.01819072],"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":[0.00005744723,0.000029096682,0.0007689129,0.0016228495,0.000026949325,0.000046546942,0.0005456414,0.00047673594,0.00017311102,0.002856027,0.5894893,0.4039074],"study_design_scores_gemma":[0.000026915583,0.000037529622,0.0032370691,0.0036986067,0.00008022905,0.00021104969,0.0009386429,0.00032398052,0.0008103264,0.005244094,0.9853495,0.000042052594],"about_ca_topic_score_codex":0.06428203,"about_ca_topic_score_gemma":0.14759018,"teacher_disagreement_score":0.06428203,"about_ca_system_score_codex":0.002757591,"about_ca_system_score_gemma":0.0072442014,"threshold_uncertainty_score":0.12781572},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81185305,0.0021353217,0.026601056,0.015633931,0.00023323447,0.0013557412,0.00040411568,0.00062215317,0.14116137],"genre_scores_gemma":[0.979388,0.00039491543,0.009912152,0.00049016025,0.000033534692,0.00037899317,0.000118937074,0.00007973521,0.009203564],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9180002,0.053743783,0.0024443294,0.002082518,0.020048527,0.0036806234],"domain_scores_gemma":[0.7768592,0.15442881,0.0059432895,0.0068827937,0.05014703,0.0057388814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.057618354,0.0007671224,0.0005572413,0.002455872,0.007221262,0.008110403,0.0015499198,0.0023407638,0.004910282],"category_scores_gemma":[0.10174118,0.0005142152,0.00068967696,0.002409832,0.0048728525,0.0024966425,0.0032676186,0.0024468922,0.00061715505],"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":[0.002507118,0.0035644907,0.10648521,0.0031789613,0.0005021795,0.002707517,0.08049993,0.03229525,0.028100519,0.041132607,0.022667287,0.676359],"study_design_scores_gemma":[0.0011722189,0.008397176,0.5133616,0.0035846715,0.00066841044,0.0009389591,0.06875515,0.045249544,0.060848527,0.012507986,0.2835401,0.00097560725],"about_ca_topic_score_codex":0.5848097,"about_ca_topic_score_gemma":0.5856932,"teacher_disagreement_score":0.9600584,"about_ca_system_score_codex":0.039941594,"about_ca_system_score_gemma":0.043524638,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021454824,0.27471104,0.004868824,0.5680349,0.08189624,0.00059926236,0.0022097402,0.00027935347,0.04594585],"genre_scores_gemma":[0.3638857,0.22583319,0.021493828,0.2134878,0.03330845,0.0027316045,0.0038919067,0.0006882611,0.1346793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9285316,0.023293925,0.009728003,0.0033585143,0.030549286,0.0045386255],"domain_scores_gemma":[0.7839078,0.063842654,0.015907228,0.006953795,0.11660831,0.012780349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10877324,0.0011938467,0.0014027507,0.006306199,0.0032867081,0.011884683,0.0028470655,0.008692045,0.0069882027],"category_scores_gemma":[0.17910767,0.0007671926,0.0019731536,0.0067068934,0.005062959,0.0038223441,0.005100145,0.010868858,0.0019064641],"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":[0.0014139793,0.00039108988,0.0084616635,0.008210481,0.00042350098,0.00076000724,0.0198163,0.0012251217,0.005453448,0.038118813,0.6021819,0.31354377],"study_design_scores_gemma":[0.000067453555,0.00013664993,0.0133402245,0.0058569214,0.00013287949,0.00011348455,0.002550831,0.0001165991,0.0017663194,0.0016236167,0.9742138,0.00008130193],"about_ca_topic_score_codex":0.22992335,"about_ca_topic_score_gemma":0.26410633,"teacher_disagreement_score":0.9626744,"about_ca_system_score_codex":0.037325602,"about_ca_system_score_gemma":0.08860423,"threshold_uncertainty_score":0.57525474},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080807894,0.019391375,0.17680924,0.03321411,0.027815225,0.013682728,0.02303982,0.008087579,0.6171521],"genre_scores_gemma":[0.39308587,0.015077216,0.20955239,0.0034941877,0.004255692,0.023936236,0.012789364,0.0038848934,0.3339241],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9482058,0.01745829,0.0075622494,0.0034004918,0.020811316,0.0025618123],"domain_scores_gemma":[0.86031747,0.033732813,0.0058630346,0.009372525,0.086637095,0.0040771156],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03903316,0.0015089134,0.0014043922,0.009309327,0.004886231,0.0090657575,0.0018930221,0.0019318279,0.080548525],"category_scores_gemma":[0.1003389,0.00086447847,0.001406657,0.0050154193,0.0022209045,0.0057236976,0.004741706,0.005061343,0.029518165],"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":[0.0021430673,0.00030366099,0.012002124,0.002739342,0.00009327125,0.0007676321,0.0058450885,0.0010997962,0.010167626,0.08051061,0.23722301,0.64710474],"study_design_scores_gemma":[0.00012852497,0.0004270073,0.015005251,0.0014510967,0.000040121144,0.0009476738,0.0036687162,0.0016765617,0.011206236,0.005492732,0.9597936,0.00016240263],"about_ca_topic_score_codex":0.012988829,"about_ca_topic_score_gemma":0.007327744,"teacher_disagreement_score":0.9609668,"about_ca_system_score_codex":0.008643104,"about_ca_system_score_gemma":0.009410789,"threshold_uncertainty_score":0.26946163},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020257624,0.0008544832,0.00030059155,0.7560992,0.24171141,0.000014404019,0.0000560181,0.000043931137,0.0007173723],"genre_scores_gemma":[0.0032138852,0.0011834166,0.0010627104,0.8014431,0.18441027,0.000047629645,0.000027476372,0.00007468204,0.008536814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98531437,0.002485628,0.0031972213,0.0021516222,0.0055113817,0.0013397697],"domain_scores_gemma":[0.87862736,0.04040028,0.00818009,0.0037825939,0.059220105,0.009789491],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022458509,0.0011897116,0.0020288406,0.0010032654,0.0047460604,0.008776648,0.003897532,0.02777386,0.006994546],"category_scores_gemma":[0.15238777,0.0009434187,0.0019312376,0.0014006484,0.004488702,0.0055731614,0.003018796,0.050292153,0.0055841208],"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":[0.00002604281,0.000011205894,0.00018325615,0.00005995901,0.000012722026,0.00015784084,0.0001281339,0.000025388266,0.00005372098,0.00066158146,0.9962174,0.0024626849],"study_design_scores_gemma":[0.00006302376,0.000041686046,0.0013149957,0.00053518417,0.000072553674,0.0006093728,0.0011389161,0.0003611236,0.0004768489,0.0033394701,0.9919098,0.00013701674],"about_ca_topic_score_codex":0.00795879,"about_ca_topic_score_gemma":0.016794322,"teacher_disagreement_score":0.9775415,"about_ca_system_score_codex":0.004164551,"about_ca_system_score_gemma":0.009609121,"threshold_uncertainty_score":0.11877334},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27239677,0.013677155,0.10701197,0.35899815,0.0020507558,0.00074605265,0.000105359344,0.00087409373,0.24413976],"genre_scores_gemma":[0.9635128,0.003070448,0.017043183,0.010281767,0.0005116174,0.00023554775,0.00004074524,0.00016935091,0.005134731],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7629034,0.18716301,0.0056029484,0.0025818124,0.03759671,0.0041521452],"domain_scores_gemma":[0.6346002,0.27669862,0.019291548,0.016900824,0.041683793,0.0108250445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1080659,0.0006719336,0.00082823663,0.0022831813,0.008539323,0.0182383,0.001968287,0.005425428,0.0045195003],"category_scores_gemma":[0.28937492,0.00061160635,0.00055820425,0.0011730789,0.014125547,0.014323776,0.011466245,0.008659351,0.0011010934],"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":[0.0004003011,0.00076065795,0.030993892,0.002152093,0.00024854526,0.0027705908,0.23851646,0.0021149165,0.002615201,0.07905122,0.05729309,0.58308303],"study_design_scores_gemma":[0.00021986377,0.001515726,0.03845779,0.011782215,0.0003085365,0.007862164,0.28901526,0.006814487,0.013092779,0.29697463,0.33328333,0.00067315024],"about_ca_topic_score_codex":0.002764856,"about_ca_topic_score_gemma":0.0032100938,"teacher_disagreement_score":0.8919341,"about_ca_system_score_codex":0.006700238,"about_ca_system_score_gemma":0.011281131,"threshold_uncertainty_score":0.57151395},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04864324,0.017272495,0.09471501,0.7133722,0.0019766544,0.0005866474,0.000038695915,0.00012504376,0.12327016],"genre_scores_gemma":[0.9358225,0.003963969,0.029519476,0.02648015,0.0005941353,0.00051038375,0.000016539714,0.00017704909,0.0029157521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6287852,0.33212945,0.0061753695,0.0052202586,0.02112908,0.0065606856],"domain_scores_gemma":[0.6564512,0.2802008,0.010632851,0.011955998,0.03332828,0.007430883],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2813388,0.0011968612,0.0019927267,0.0053325896,0.023931775,0.060404424,0.0071983594,0.016373862,0.0020497504],"category_scores_gemma":[0.16680953,0.0013325125,0.0014174667,0.005810956,0.2204433,0.03328304,0.023791045,0.036356363,0.0003083672],"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":[0.000043725227,0.00008411501,0.00077163725,0.0002601276,0.000031201726,0.00035216263,0.2111118,0.00060429913,0.00018720215,0.7700631,0.0039017468,0.012588851],"study_design_scores_gemma":[0.00012511195,0.00012487319,0.000817602,0.0021119874,0.000033052274,0.00058951415,0.3103488,0.0027147175,0.00074173155,0.5346395,0.14757816,0.00017496862],"about_ca_topic_score_codex":0.022409875,"about_ca_topic_score_gemma":0.01075391,"teacher_disagreement_score":0.7186612,"about_ca_system_score_codex":0.050644543,"about_ca_system_score_gemma":0.04717123,"threshold_uncertainty_score":0.8862372},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089936316,0.099405356,0.0070351767,0.7463313,0.018041797,0.00054373307,0.00075119716,0.00041699462,0.037538163],"genre_scores_gemma":[0.8284143,0.045956206,0.015189126,0.070438355,0.0029000272,0.00088368804,0.0009151359,0.0003216939,0.03498151],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9176175,0.049046088,0.0043194206,0.0024331629,0.017178627,0.009405205],"domain_scores_gemma":[0.84847814,0.035316754,0.009583428,0.005762397,0.05665063,0.04420864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.115402,0.0009275298,0.0010932991,0.0020439045,0.0062077753,0.01774278,0.0033545725,0.0044471193,0.007511135],"category_scores_gemma":[0.18074769,0.00048461804,0.0011993463,0.0030057158,0.00604977,0.012476697,0.010425021,0.012097558,0.0013614589],"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":[0.0009547692,0.0011685689,0.01813171,0.0015151118,0.0001829585,0.00066884805,0.044347517,0.0007238952,0.0013721647,0.039326172,0.17511734,0.716491],"study_design_scores_gemma":[0.00014047045,0.001610656,0.03894117,0.0062334435,0.00021302803,0.00055733806,0.16577159,0.00054566393,0.0024004634,0.021818342,0.7614441,0.0003237271],"about_ca_topic_score_codex":0.04032911,"about_ca_topic_score_gemma":0.080328,"teacher_disagreement_score":0.9808179,"about_ca_system_score_codex":0.019182075,"about_ca_system_score_gemma":0.08079951,"threshold_uncertainty_score":0.6103114},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15379876,0.0051578926,0.20179833,0.2598564,0.0024118358,0.0021769896,0.000039491268,0.0011417727,0.37361857],"genre_scores_gemma":[0.90028733,0.0014301633,0.06907823,0.012625655,0.0006558445,0.0008484211,0.00003288395,0.00018523129,0.014856204],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88442945,0.09089446,0.0023985824,0.0015593264,0.017398957,0.0033192204],"domain_scores_gemma":[0.89302915,0.054008644,0.00832499,0.0054766955,0.016786937,0.022373555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08290006,0.00055301125,0.0005980583,0.0020562322,0.007868476,0.019676616,0.001692952,0.00333467,0.0027910753],"category_scores_gemma":[0.11287352,0.0005278536,0.0005388848,0.0009015507,0.0128065385,0.0063367714,0.015866397,0.0067785294,0.0011369891],"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":[0.00018752296,0.0015654323,0.017616985,0.0011388339,0.0002312305,0.0014429818,0.14828894,0.0018376596,0.0039420095,0.24166958,0.10960292,0.4724759],"study_design_scores_gemma":[0.00026365634,0.0009441081,0.024703933,0.0035902462,0.00011875307,0.002494254,0.12684749,0.009034522,0.004577732,0.41117194,0.41595197,0.0003014765],"about_ca_topic_score_codex":0.0008829373,"about_ca_topic_score_gemma":0.0012541577,"teacher_disagreement_score":0.91709995,"about_ca_system_score_codex":0.00674492,"about_ca_system_score_gemma":0.02261755,"threshold_uncertainty_score":0.43842268},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7514963,0.0019949449,0.00411264,0.12276025,0.0010778785,0.00040234497,0.00012557102,0.00012947222,0.1179006],"genre_scores_gemma":[0.97019494,0.00070181047,0.0020505877,0.00672133,0.000037060945,0.000070890106,0.00005136235,0.00008364598,0.020088414],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.96092457,0.01956055,0.000651796,0.00184542,0.0071965386,0.009821148],"domain_scores_gemma":[0.9597682,0.006826143,0.0012361159,0.00080549985,0.018277172,0.0130868405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033956867,0.00066841656,0.00062514225,0.0017422887,0.062271778,0.017836973,0.0033658398,0.0051611313,0.00416262],"category_scores_gemma":[0.031915337,0.00067251304,0.00059309084,0.0019140189,0.01742392,0.004162744,0.008619846,0.010775846,0.00064786547],"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":[0.00017297255,0.00040138027,0.015292489,0.000097087395,0.000028476348,0.003007609,0.88802487,0.0007498288,0.0013954351,0.014801916,0.042999566,0.033028327],"study_design_scores_gemma":[0.000018728402,0.00013099312,0.004769409,0.00020051993,0.000017266153,0.00034837882,0.85404944,0.00072620396,0.0007596398,0.0013173,0.13753892,0.00012315116],"about_ca_topic_score_codex":0.86538696,"about_ca_topic_score_gemma":0.92952615,"teacher_disagreement_score":0.86538696,"about_ca_system_score_codex":0.10247467,"about_ca_system_score_gemma":0.16718788,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083173433,0.67058295,0.013470799,0.19708247,0.01085303,0.00021098582,0.002410615,0.0011873607,0.10337001],"genre_scores_gemma":[0.022817718,0.58136624,0.024612624,0.04175556,0.004635599,0.00056559336,0.001490403,0.0006841716,0.3220721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987344,0.00027607172,0.00010075643,0.00012864449,0.0006978951,0.000062209176],"domain_scores_gemma":[0.99361426,0.0025066475,0.0004374546,0.00015540449,0.0027901991,0.00049614825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046310145,0.0010907718,0.0006107227,0.0021224187,0.0015966942,0.003006502,0.0013011018,0.0027547928,0.06369612],"category_scores_gemma":[0.013986163,0.0009049403,0.00043056384,0.0029803286,0.0011028916,0.0049561486,0.0013651003,0.003812054,0.04316023],"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":[0.00002352737,0.000008702536,0.00020602225,0.00032413765,0.0000041873664,0.000027059281,0.00017828344,0.000050966322,0.000065997665,0.001547089,0.83153886,0.1660252],"study_design_scores_gemma":[0.000019177161,0.000023927236,0.0023511886,0.0026436776,0.000019583878,0.00016789867,0.00042260534,0.00015144027,0.0002982802,0.0071558794,0.9867207,0.000025573489],"about_ca_topic_score_codex":0.03598174,"about_ca_topic_score_gemma":0.085955076,"teacher_disagreement_score":0.06369612,"about_ca_system_score_codex":0.0020335875,"about_ca_system_score_gemma":0.0046157986,"threshold_uncertainty_score":0.21308476},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02074848,0.0201788,0.072374254,0.796637,0.0067908494,0.00037417642,0.00006427853,0.0001089665,0.08272331],"genre_scores_gemma":[0.8214272,0.00975,0.035232745,0.117151946,0.007253844,0.0022482602,0.00006285919,0.00024096457,0.006632163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5929572,0.32963073,0.011332957,0.010242273,0.046205364,0.009631424],"domain_scores_gemma":[0.36318266,0.5541038,0.014142974,0.019178862,0.045708086,0.0036836783],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27318898,0.0008854066,0.0023740851,0.011253179,0.016345954,0.03151998,0.008212117,0.01705809,0.0031200396],"category_scores_gemma":[0.3093868,0.0008633984,0.0014708085,0.009000392,0.13443771,0.043746162,0.027998103,0.022412911,0.00046571222],"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":[0.000057915277,0.00004339342,0.0008831046,0.000702577,0.00002681204,0.00018786752,0.08562596,0.00015628566,0.00008868066,0.8740487,0.010146681,0.02803203],"study_design_scores_gemma":[0.00010418375,0.00009870394,0.0019482129,0.007984812,0.00006980399,0.0003459404,0.17144151,0.0022812176,0.0010532315,0.6346399,0.1799109,0.00012145562],"about_ca_topic_score_codex":0.021163223,"about_ca_topic_score_gemma":0.020485526,"teacher_disagreement_score":0.27318898,"about_ca_system_score_codex":0.039251845,"about_ca_system_score_gemma":0.057242207,"threshold_uncertainty_score":0.8962874},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009638444,0.9168148,0.007172968,0.038016967,0.00290747,0.000044489017,0.00044559655,0.00025807478,0.033375848],"genre_scores_gemma":[0.016445292,0.9594483,0.0084043415,0.0015594157,0.0010012536,0.00007190623,0.00034710273,0.00012302322,0.012599296],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790037,0.0006923617,0.00021089193,0.00015954857,0.0008936631,0.00014314435],"domain_scores_gemma":[0.99062085,0.0056305104,0.00074665056,0.00023957285,0.0020066116,0.0007557412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052207275,0.0020535784,0.001544994,0.0069184443,0.0028189095,0.010855809,0.0025301266,0.003629873,0.015680177],"category_scores_gemma":[0.009553848,0.0014091186,0.0007996526,0.011428085,0.0038479848,0.011960128,0.002285247,0.0050205877,0.013477738],"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":[0.000047815975,0.00003158451,0.0010744516,0.0024548348,0.000027739527,0.000089586916,0.004776347,0.00030994133,0.0001655685,0.012592867,0.41963887,0.5587904],"study_design_scores_gemma":[0.000021082144,0.00006154831,0.008468274,0.01012415,0.00012534222,0.0008176965,0.009634145,0.0006710299,0.0007660263,0.030831585,0.93837804,0.00010104375],"about_ca_topic_score_codex":0.09269927,"about_ca_topic_score_gemma":0.16106826,"teacher_disagreement_score":0.09269927,"about_ca_system_score_codex":0.0070421724,"about_ca_system_score_gemma":0.011977875,"threshold_uncertainty_score":0.18431938},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024604704,0.011967886,0.8883484,0.036936335,0.0010176608,0.010025615,0.00026388373,0.00020329218,0.0266322],"genre_scores_gemma":[0.28934184,0.0026552638,0.68108594,0.0024587628,0.00032975356,0.02276178,0.00013803561,0.00008697549,0.001141676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.15560761,0.79644513,0.013500574,0.0044490565,0.028457252,0.0015403287],"domain_scores_gemma":[0.0967725,0.86387074,0.009154318,0.011853422,0.01759116,0.00075786404],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6036283,0.0032024316,0.004953809,0.014630278,0.0054597845,0.02739398,0.008672878,0.007792033,0.006512147],"category_scores_gemma":[0.6628566,0.0024760775,0.003939976,0.011270494,0.03735066,0.020650912,0.0073201796,0.009732491,0.00063118775],"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":[0.0009313287,0.0006203581,0.006158619,0.009949105,0.0012309465,0.00029445195,0.03031107,0.009582896,0.0004487502,0.79303306,0.0028656155,0.14457376],"study_design_scores_gemma":[0.001771961,0.0010236251,0.00504836,0.019922096,0.00082126545,0.000484867,0.022864584,0.061558083,0.0026221361,0.85633886,0.027236933,0.00030726974],"about_ca_topic_score_codex":0.009107343,"about_ca_topic_score_gemma":0.008521074,"teacher_disagreement_score":0.6036283,"about_ca_system_score_codex":0.026795799,"about_ca_system_score_gemma":0.025064696,"threshold_uncertainty_score":0.48879695},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73958564,0.017113188,0.1226222,0.015789649,0.0045497105,0.0017896006,0.008833422,0.0012950652,0.08842161],"genre_scores_gemma":[0.9594042,0.0011327587,0.02613532,0.00068842573,0.00042090483,0.0011956777,0.0038617016,0.0003603632,0.0068006925],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.70132285,0.1713891,0.03909529,0.017464438,0.063708305,0.0070199594],"domain_scores_gemma":[0.5187461,0.2622524,0.035950735,0.032611176,0.14724843,0.0031911775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2950604,0.0010331253,0.0014209719,0.012062749,0.0025888719,0.012339656,0.0024954195,0.002085993,0.006959401],"category_scores_gemma":[0.40961647,0.0009925932,0.0030414532,0.012716475,0.0025565056,0.008409068,0.0067675845,0.0033980203,0.0020350998],"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":[0.0028100174,0.0004694953,0.71193594,0.0015240189,0.0020098374,0.00012662214,0.016624566,0.003299503,0.002748073,0.016899448,0.013044026,0.22850853],"study_design_scores_gemma":[0.00015298456,0.0013145884,0.8986744,0.00140985,0.000986213,0.00019720565,0.014200872,0.008776364,0.007526082,0.007393509,0.059098907,0.00026905764],"about_ca_topic_score_codex":0.03041928,"about_ca_topic_score_gemma":0.03232493,"teacher_disagreement_score":0.2950604,"about_ca_system_score_codex":0.0076490263,"about_ca_system_score_gemma":0.0065550427,"threshold_uncertainty_score":0.86931604},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019725263,0.1077392,0.3162091,0.4749127,0.002825992,0.0002258826,0.0000872068,0.00021663221,0.07805812],"genre_scores_gemma":[0.7400798,0.04176936,0.1856506,0.021252455,0.0037581963,0.00085802743,0.00006566448,0.00022771485,0.006338153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89984393,0.07138677,0.003453863,0.005056389,0.01818264,0.002076389],"domain_scores_gemma":[0.7177234,0.23915824,0.007715237,0.015877321,0.016776815,0.0027489213],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.11424989,0.0012974994,0.0025768825,0.009465032,0.0068814214,0.021871146,0.0034488563,0.009859524,0.00273326],"category_scores_gemma":[0.11532116,0.0010331101,0.0016470607,0.0068920334,0.09614849,0.03206502,0.007037946,0.01197009,0.0007431365],"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":[0.000022171993,0.00003593118,0.00034293445,0.00029130376,0.000014083541,0.000022235346,0.0026219327,0.00072775857,0.00006420943,0.97693187,0.0015894715,0.017336076],"study_design_scores_gemma":[0.000042346142,0.000038829152,0.0002544486,0.00084320165,0.000016243583,0.000053365187,0.0018520713,0.002839424,0.00022924793,0.9632863,0.03050791,0.00003656103],"about_ca_topic_score_codex":0.014640359,"about_ca_topic_score_gemma":0.007472212,"teacher_disagreement_score":0.9931186,"about_ca_system_score_codex":0.030877495,"about_ca_system_score_gemma":0.03263015,"threshold_uncertainty_score":0.60421836},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8173508,0.0022246868,0.0026168157,0.0037793964,0.00021800092,0.0003604192,0.0005959396,0.00039454616,0.17245941],"genre_scores_gemma":[0.9710533,0.0017726336,0.00264295,0.00029265406,0.00007071834,0.0001493266,0.0003632717,0.000044709206,0.023610324],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98809505,0.004549107,0.00025965538,0.0005558683,0.005138219,0.0014021076],"domain_scores_gemma":[0.9931409,0.0023756824,0.0008439426,0.0003155496,0.0020827272,0.0012413022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066273017,0.0010184495,0.0004888244,0.002449184,0.0043047806,0.0056741782,0.0012507943,0.000907794,0.018318353],"category_scores_gemma":[0.015272842,0.0002751167,0.00087926857,0.0016473855,0.0026414758,0.0014228229,0.004028751,0.0015772232,0.0016089911],"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":[0.0017123598,0.004901104,0.24728398,0.0014249309,0.0004096301,0.0042901793,0.033695877,0.0066737193,0.0049425126,0.031512678,0.016365012,0.64678794],"study_design_scores_gemma":[0.000488206,0.004110787,0.47300845,0.0020826515,0.00045814228,0.0028796531,0.09445693,0.007450567,0.016146107,0.0058380337,0.39286226,0.0002182624],"about_ca_topic_score_codex":0.34939498,"about_ca_topic_score_gemma":0.27637857,"teacher_disagreement_score":0.34939498,"about_ca_system_score_codex":0.015755711,"about_ca_system_score_gemma":0.014989381,"threshold_uncertainty_score":0.69472253},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04627936,0.01292762,0.14115614,0.54745597,0.0032274358,0.0027242827,0.0014400211,0.0010788376,0.24371031],"genre_scores_gemma":[0.6570574,0.020390086,0.27047372,0.03585735,0.0022188642,0.0029948342,0.0016552077,0.00031901174,0.009033539],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9131217,0.06349521,0.0049316697,0.0012597352,0.015068518,0.0021232562],"domain_scores_gemma":[0.6724858,0.2513666,0.010663929,0.010110733,0.048378505,0.0069944295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11048151,0.000550705,0.0010986929,0.0046926094,0.0023403761,0.011031775,0.0020190484,0.0042577717,0.011475487],"category_scores_gemma":[0.3996285,0.00048543638,0.0008285879,0.002520592,0.004421723,0.017024126,0.0037128346,0.0037233655,0.0047383495],"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":[0.00025935288,0.0003904603,0.010202877,0.0054246844,0.00006532096,0.0006089721,0.006858673,0.0014589524,0.0007537956,0.060239073,0.0848222,0.82891566],"study_design_scores_gemma":[0.00027036018,0.0006073852,0.030167848,0.04225212,0.00022547318,0.0021445777,0.03627266,0.006858163,0.007963678,0.27853152,0.59419096,0.0005152265],"about_ca_topic_score_codex":0.005503506,"about_ca_topic_score_gemma":0.0057057883,"teacher_disagreement_score":0.11048151,"about_ca_system_score_codex":0.006639955,"about_ca_system_score_gemma":0.019726863,"threshold_uncertainty_score":0.5842891},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2298,0.008110638,0.32674366,0.24692023,0.0015232262,0.0031490545,0.000051524326,0.00040966223,0.18329199],"genre_scores_gemma":[0.9484185,0.00084219873,0.041915786,0.004157866,0.00018566615,0.0008748783,0.000014187463,0.00007156511,0.0035193835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.44514537,0.48261926,0.0098932395,0.008094491,0.046110965,0.008136689],"domain_scores_gemma":[0.43897426,0.47199103,0.017655779,0.017777922,0.040841263,0.012759657],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.3555969,0.001139191,0.0014625778,0.0037265122,0.028971473,0.04102395,0.0057563265,0.010962229,0.0031650881],"category_scores_gemma":[0.3510148,0.0011300688,0.0012368184,0.0032701495,0.048129782,0.021035107,0.020856285,0.012428555,0.00042814418],"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":[0.0004955954,0.00077077607,0.008575915,0.0012957262,0.00025554944,0.0018488722,0.25725287,0.0052292943,0.0012282181,0.50071704,0.019279333,0.20305073],"study_design_scores_gemma":[0.0006673573,0.0010604766,0.006077688,0.0042757494,0.00021329858,0.0013980563,0.22874288,0.017494887,0.0052720336,0.5819577,0.1521536,0.00068628864],"about_ca_topic_score_codex":0.013864966,"about_ca_topic_score_gemma":0.014577748,"teacher_disagreement_score":0.9710285,"about_ca_system_score_codex":0.024539312,"about_ca_system_score_gemma":0.054551117,"threshold_uncertainty_score":0.7946638},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015992334,0.42825475,0.1302726,0.236384,0.010367001,0.0030232396,0.0055520283,0.0018890374,0.16826494],"genre_scores_gemma":[0.28291956,0.43632653,0.17356172,0.025858862,0.0020594217,0.005833111,0.0032226942,0.0014830806,0.06873498],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98999864,0.005510069,0.0010836344,0.00036207456,0.0027404858,0.00030507974],"domain_scores_gemma":[0.8707728,0.10473908,0.0039838753,0.002368253,0.015752183,0.0023838077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03660505,0.0010698675,0.0010125682,0.0060159294,0.006923459,0.007479951,0.002162678,0.0025394836,0.01726693],"category_scores_gemma":[0.090365656,0.0022599418,0.0006896513,0.005085458,0.007658895,0.0133683495,0.0046806782,0.008209786,0.006003886],"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":[0.00016691044,0.00009889446,0.00455375,0.007941968,0.00008431146,0.00033677564,0.047303468,0.00027957966,0.0021894074,0.04318325,0.43714288,0.4567188],"study_design_scores_gemma":[0.00012027954,0.0002540722,0.021664772,0.026900921,0.00026205933,0.0007208247,0.070537664,0.00041791526,0.0033066818,0.104521565,0.7710294,0.0002638677],"about_ca_topic_score_codex":0.01821965,"about_ca_topic_score_gemma":0.043473035,"teacher_disagreement_score":0.03660505,"about_ca_system_score_codex":0.004800465,"about_ca_system_score_gemma":0.009593559,"threshold_uncertainty_score":0},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007626058,0.0029650624,0.3746683,0.02068361,0.004736697,0.41159067,0.0105412165,0.0015830926,0.16560523],"genre_scores_gemma":[0.038883656,0.0012961696,0.3314489,0.005533864,0.000646712,0.5891288,0.0044178674,0.0006143277,0.028029712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.58978933,0.2997561,0.040550172,0.012699575,0.04808339,0.009121463],"domain_scores_gemma":[0.6087349,0.14789909,0.016570302,0.05111136,0.16950226,0.006182175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.36948496,0.0024394256,0.0022301653,0.012859848,0.007810921,0.016743038,0.0073772417,0.0068768635,0.034801107],"category_scores_gemma":[0.3469156,0.0024790198,0.0026327292,0.008927803,0.0109352805,0.0057123955,0.009330296,0.009143851,0.010878741],"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":[0.0014815426,0.0005871155,0.0035137627,0.008816883,0.00021218657,0.0007732143,0.030619156,0.005068922,0.0016237629,0.4243706,0.19038934,0.3325435],"study_design_scores_gemma":[0.00051451765,0.00033630978,0.0028511866,0.009506358,0.00007563562,0.00015044992,0.004850543,0.002385832,0.0032520283,0.03375244,0.942134,0.00019066561],"about_ca_topic_score_codex":0.015672518,"about_ca_topic_score_gemma":0.012873493,"teacher_disagreement_score":0.36948496,"about_ca_system_score_codex":0.027814765,"about_ca_system_score_gemma":0.13662419,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006042542,0.35301042,0.10174153,0.265619,0.009806522,0.0007896755,0.006202791,0.0018819823,0.25490552],"genre_scores_gemma":[0.1314972,0.39577597,0.1928045,0.039339766,0.0032255286,0.0012147358,0.0035992153,0.0013320311,0.23121096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715483,0.00093448046,0.00019905745,0.00015384314,0.0014549133,0.00010273566],"domain_scores_gemma":[0.97982603,0.012211774,0.0012003904,0.00048017167,0.005649583,0.00063202303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008296529,0.00085257925,0.00048778384,0.0026983428,0.0021618311,0.0043844944,0.0013108149,0.0024681543,0.03078804],"category_scores_gemma":[0.030359926,0.00083270966,0.00044617523,0.0029892258,0.0015367006,0.0063948194,0.00141708,0.0030092346,0.017157972],"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":[0.000066305554,0.00003454045,0.0014764755,0.00066451787,0.000016011842,0.000049015252,0.0006632703,0.00019477733,0.00023606591,0.008112027,0.70885533,0.27963164],"study_design_scores_gemma":[0.0000547092,0.00012068902,0.014816774,0.004017811,0.0001328471,0.00032613648,0.0019704734,0.0006632442,0.0022082287,0.043275636,0.93232995,0.0000835284],"about_ca_topic_score_codex":0.027974587,"about_ca_topic_score_gemma":0.103822716,"teacher_disagreement_score":0.03078804,"about_ca_system_score_codex":0.0020934916,"about_ca_system_score_gemma":0.00541152,"threshold_uncertainty_score":0},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023752272,0.6874312,0.17441784,0.07459945,0.017649611,0.0016972425,0.005353742,0.0018292945,0.0346464],"genre_scores_gemma":[0.043647304,0.5754998,0.32876047,0.012686284,0.006595378,0.004632444,0.0040788148,0.0014060406,0.022693472],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9655444,0.022156283,0.0037405665,0.0010230797,0.007297401,0.00023826858],"domain_scores_gemma":[0.6689225,0.28717962,0.0071633337,0.007556975,0.027778478,0.0013990266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08951511,0.0021231007,0.001865355,0.009662995,0.0030759326,0.008052217,0.0033650722,0.00401185,0.022108901],"category_scores_gemma":[0.19284564,0.0032607182,0.001746037,0.01061719,0.006112538,0.010670396,0.0034353568,0.008275385,0.012407974],"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":[0.00020924056,0.00007092467,0.0019667218,0.0075637475,0.00029516403,0.00009559317,0.0023345356,0.00061463227,0.000631025,0.01758959,0.39787838,0.57075036],"study_design_scores_gemma":[0.00030292833,0.0003605711,0.014214536,0.03242386,0.0010416151,0.00081796,0.0033701519,0.0018842221,0.00321817,0.08742186,0.8545617,0.00038251665],"about_ca_topic_score_codex":0.013944429,"about_ca_topic_score_gemma":0.031272523,"teacher_disagreement_score":0.08951511,"about_ca_system_score_codex":0.003413454,"about_ca_system_score_gemma":0.0075284136,"threshold_uncertainty_score":0.4734068},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36438033,0.004014792,0.3194521,0.024842512,0.0006061473,0.003447558,0.00061323855,0.0012263723,0.28141692],"genre_scores_gemma":[0.89333713,0.0013228653,0.094307855,0.00050910393,0.00019809626,0.0025676237,0.00034630953,0.00015499837,0.007256091],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.63313067,0.27027604,0.014353713,0.008119024,0.06916414,0.0049563837],"domain_scores_gemma":[0.4969657,0.40824398,0.016607272,0.021940224,0.050423093,0.005819819],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19419444,0.002276762,0.0009405101,0.006513359,0.0056110793,0.025010375,0.0022586347,0.0046115923,0.009511078],"category_scores_gemma":[0.29758897,0.0013121832,0.002277181,0.0040265415,0.0074552186,0.014772208,0.0067855245,0.0059558013,0.001983823],"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":[0.0011622875,0.0014998534,0.07350793,0.0022091572,0.00057461846,0.0013952174,0.066677764,0.01417874,0.005193706,0.24223277,0.008304559,0.58306354],"study_design_scores_gemma":[0.0012916496,0.0029873431,0.109612934,0.009054398,0.0012031865,0.0028340353,0.082027785,0.100813426,0.03544678,0.3839637,0.2697593,0.0010054001],"about_ca_topic_score_codex":0.013209067,"about_ca_topic_score_gemma":0.0075762873,"teacher_disagreement_score":0.19419444,"about_ca_system_score_codex":0.010948181,"about_ca_system_score_gemma":0.014638343,"threshold_uncertainty_score":0.9937017},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03981146,0.00057357945,0.86187094,0.004977835,0.0008772229,0.05976003,0.00019424058,0.00059533323,0.031339362],"genre_scores_gemma":[0.071929336,0.00036049247,0.8722822,0.000637926,0.00013714157,0.052047044,0.00005236096,0.00015835151,0.002395155],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.34212998,0.60420716,0.016451383,0.0036589494,0.031639654,0.0019128323],"domain_scores_gemma":[0.5753041,0.3326742,0.009167216,0.022452122,0.057545464,0.0028568679],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3784713,0.0022564568,0.0020650318,0.010040768,0.007172154,0.0060959673,0.0032041413,0.0023802684,0.010406978],"category_scores_gemma":[0.32956684,0.0018769492,0.0013155884,0.006516421,0.009790544,0.0065864143,0.015763018,0.0064116293,0.0022521461],"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":[0.0012068702,0.0008302667,0.0021693106,0.005599879,0.0002046603,0.00081762887,0.29076824,0.0029106368,0.017306715,0.07881551,0.01720865,0.5821616],"study_design_scores_gemma":[0.0023133743,0.006126159,0.01368456,0.017129606,0.00041580718,0.0024690528,0.22028083,0.034646653,0.032665394,0.27729622,0.39146784,0.0015044846],"about_ca_topic_score_codex":0.0012804382,"about_ca_topic_score_gemma":0.002470285,"teacher_disagreement_score":0.3784713,"about_ca_system_score_codex":0.004406443,"about_ca_system_score_gemma":0.013149284,"threshold_uncertainty_score":0.7664556},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038070926,0.51325005,0.0734856,0.23302624,0.0132776555,0.00044813467,0.0018701789,0.001852128,0.15898296],"genre_scores_gemma":[0.06831374,0.5444366,0.09763504,0.028947914,0.0051176473,0.0007858944,0.0013468354,0.0009920023,0.25242442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988116,0.00028468337,0.00009388917,0.000095473,0.00067545683,0.000038856368],"domain_scores_gemma":[0.9886348,0.0061731213,0.0005093447,0.00020088175,0.003961393,0.0005204232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040431647,0.00083952234,0.0005034769,0.002449284,0.0016711402,0.0026435833,0.0010087471,0.00246554,0.049490884],"category_scores_gemma":[0.017352305,0.00071229227,0.00031738562,0.00248036,0.0011269099,0.006482321,0.0013253456,0.002579741,0.02022372],"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":[0.00004583425,0.000019869818,0.0005573317,0.00057546905,0.000007039348,0.00006121257,0.00057214516,0.00008012724,0.00026007913,0.0044620885,0.63922876,0.35413003],"study_design_scores_gemma":[0.00004475528,0.000093008246,0.008203352,0.0027654925,0.000049236638,0.00054861244,0.0010551204,0.0005095608,0.0016165519,0.019909116,0.96515846,0.00004664851],"about_ca_topic_score_codex":0.011525727,"about_ca_topic_score_gemma":0.03326983,"teacher_disagreement_score":0.049490884,"about_ca_system_score_codex":0.0012668569,"about_ca_system_score_gemma":0.0024912662,"threshold_uncertainty_score":0.16556352},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7161269,0.0049200323,0.016621932,0.043653805,0.00042959047,0.0011322037,0.0004961338,0.00024167873,0.21637775],"genre_scores_gemma":[0.9729953,0.002026563,0.013257282,0.0016335,0.000056715126,0.00013141605,0.00015953611,0.000019421135,0.009720315],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967996,0.002003017,0.00009252339,0.000053333762,0.00038616857,0.0006652828],"domain_scores_gemma":[0.9953661,0.0021391995,0.00019085442,0.00015157035,0.0013892486,0.000763144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004686202,0.00029411414,0.00014715466,0.0009505044,0.0023171008,0.0016398459,0.00056996656,0.001621654,0.0076949224],"category_scores_gemma":[0.0056584543,0.0001108958,0.0003377071,0.0012001283,0.00074178865,0.0011784761,0.00205887,0.0010607828,0.00113083],"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":[0.00090146175,0.0049036993,0.10134289,0.0030904498,0.00004283924,0.011155096,0.05680302,0.006123028,0.004717394,0.03618125,0.06572472,0.7090142],"study_design_scores_gemma":[0.00051944284,0.0030071074,0.20558895,0.0045192274,0.000121454905,0.013367357,0.16240124,0.015556379,0.014285033,0.013414326,0.5670361,0.00018339424],"about_ca_topic_score_codex":0.011094477,"about_ca_topic_score_gemma":0.0299994,"teacher_disagreement_score":0.011094477,"about_ca_system_score_codex":0.0029608689,"about_ca_system_score_gemma":0.006473118,"threshold_uncertainty_score":0.025742114},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011916039,0.8736547,0.059769794,0.043280717,0.0044461405,0.0017484275,0.00086009793,0.00023035826,0.0040937546],"genre_scores_gemma":[0.5841991,0.21382408,0.16561003,0.020156162,0.0057756277,0.0076859826,0.0009853799,0.0005739366,0.0011897478],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.21929681,0.6183816,0.08684938,0.009819954,0.06416585,0.0014863564],"domain_scores_gemma":[0.073889814,0.7753016,0.048300467,0.060285132,0.041391637,0.0008314764],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6752882,0.0027791983,0.015005322,0.020827059,0.0029801612,0.021160515,0.007963373,0.005497147,0.0028056952],"category_scores_gemma":[0.8506874,0.0034660776,0.019307712,0.021724703,0.009118379,0.019103894,0.0067348224,0.0081061,0.0004035423],"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":[0.0033182877,0.0002566147,0.02763932,0.24230118,0.29775676,0.00026450938,0.004959663,0.0037093554,0.0012160268,0.045452368,0.014897595,0.35822836],"study_design_scores_gemma":[0.0027299041,0.0018510869,0.03490398,0.53111345,0.25862548,0.00085797906,0.0033134334,0.010121474,0.0057693417,0.07452521,0.07553737,0.00065124],"about_ca_topic_score_codex":0.014393453,"about_ca_topic_score_gemma":0.018086972,"teacher_disagreement_score":0.97746056,"about_ca_system_score_codex":0.022539437,"about_ca_system_score_gemma":0.024614146,"threshold_uncertainty_score":0.40042752},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16553141,0.004003033,0.60150963,0.05401365,0.0010131199,0.08648338,0.0023347791,0.0014679229,0.08364294],"genre_scores_gemma":[0.4996287,0.0008193658,0.470756,0.0014549975,0.00008395852,0.025585352,0.00036374712,0.00012288748,0.0011849386],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.57652116,0.35756174,0.020782795,0.006106496,0.033830814,0.0051969183],"domain_scores_gemma":[0.28542137,0.4727946,0.037565526,0.044903636,0.15095577,0.008359139],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.41322884,0.0011258541,0.001901044,0.0048225396,0.008168668,0.014384147,0.005010139,0.0031942101,0.0025321108],"category_scores_gemma":[0.6437905,0.001927073,0.0012651936,0.0103190085,0.009698749,0.0116422735,0.009484575,0.0054618954,0.0009149549],"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":[0.0015558514,0.0020180177,0.123550095,0.009077248,0.0006561511,0.0004115592,0.059221346,0.051473178,0.002738642,0.1282359,0.024413284,0.59664875],"study_design_scores_gemma":[0.0033041774,0.0036922703,0.16713206,0.019424295,0.0011128249,0.00035807004,0.081485845,0.16452867,0.011434322,0.38974246,0.15689567,0.0008893116],"about_ca_topic_score_codex":0.16175327,"about_ca_topic_score_gemma":0.27602822,"teacher_disagreement_score":0.41322884,"about_ca_system_score_codex":0.049494293,"about_ca_system_score_gemma":0.17254335,"threshold_uncertainty_score":0.72359335},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001355672,0.021626564,0.0031295836,0.9568571,0.006364068,0.00006212104,0.00006748772,0.00006657976,0.010470792],"genre_scores_gemma":[0.24304211,0.092157684,0.040511627,0.5660455,0.02364116,0.0009775356,0.0004629514,0.00034464872,0.032816757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90759754,0.05856508,0.004749766,0.0033712925,0.019568432,0.00614795],"domain_scores_gemma":[0.65818304,0.16992746,0.017824916,0.01881961,0.10580531,0.029439729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.25691396,0.00068974466,0.0019531138,0.0017975544,0.004332201,0.019026436,0.0026800511,0.016849661,0.014180428],"category_scores_gemma":[0.30198434,0.00043910937,0.0014598742,0.0018692743,0.014814199,0.03643085,0.0072977054,0.012774038,0.004959969],"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":[0.00060532737,0.00030701986,0.0035595882,0.0024662379,0.000113852344,0.00021500244,0.0014011546,0.0008314068,0.00034160278,0.42120036,0.26356572,0.30539268],"study_design_scores_gemma":[0.00030854935,0.0004588964,0.004048165,0.009277311,0.000117594085,0.0005451985,0.0048740073,0.0016152551,0.0009457137,0.36930364,0.6083395,0.00016615893],"about_ca_topic_score_codex":0.005901466,"about_ca_topic_score_gemma":0.0051082256,"teacher_disagreement_score":0.25691396,"about_ca_system_score_codex":0.011403993,"about_ca_system_score_gemma":0.060234748,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009371903,0.0006125479,0.9843604,0.00078936975,0.00011931018,0.0018543357,0.00045923813,0.00030350286,0.0021293692],"genre_scores_gemma":[0.040072616,0.00026057608,0.9546357,0.00010455603,0.000024394109,0.0041965684,0.00016562465,0.00007829227,0.00046166085],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8110041,0.17030345,0.005692065,0.005744469,0.006572404,0.0006834547],"domain_scores_gemma":[0.5966243,0.3752499,0.004376133,0.014318107,0.009110492,0.00032109016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12039581,0.0025536548,0.0030789622,0.011508746,0.0022888505,0.008066302,0.003264123,0.0020540778,0.008220129],"category_scores_gemma":[0.20893878,0.001322972,0.0047671096,0.012074506,0.005568277,0.006972688,0.0039380174,0.004353388,0.0008446171],"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":[0.0007345112,0.0003606174,0.015340074,0.0073168566,0.0027392406,0.0002797131,0.03574351,0.00936466,0.0042705596,0.35717562,0.005437919,0.5612368],"study_design_scores_gemma":[0.0015771452,0.0011094274,0.028187362,0.0073285503,0.0022382557,0.001754498,0.030905329,0.14716394,0.014438791,0.6452977,0.11903879,0.0009601903],"about_ca_topic_score_codex":0.009377238,"about_ca_topic_score_gemma":0.008387332,"teacher_disagreement_score":0.8796042,"about_ca_system_score_codex":0.0036919324,"about_ca_system_score_gemma":0.008989386,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09611199,0.030467872,0.7693117,0.05122063,0.0016955179,0.008582356,0.00049278827,0.00030613024,0.04181104],"genre_scores_gemma":[0.6766781,0.0050513884,0.2924297,0.0043036705,0.00065958,0.019211322,0.00018674576,0.000213923,0.0012655441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3220897,0.57610995,0.038209103,0.0136496015,0.04654845,0.0033932137],"domain_scores_gemma":[0.13887297,0.7620833,0.022597432,0.030564148,0.044471204,0.0014109926],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5136543,0.0015565916,0.002606742,0.011141113,0.009070501,0.02476512,0.008456855,0.004912969,0.0032414186],"category_scores_gemma":[0.6456859,0.0016621698,0.0023951,0.014055703,0.038284402,0.025180113,0.013194387,0.007836842,0.00061631505],"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":[0.00024730197,0.0006942366,0.02691387,0.014672646,0.0006403093,0.00030778904,0.116285205,0.0031441771,0.001073537,0.61094874,0.003164774,0.22190735],"study_design_scores_gemma":[0.00035750197,0.0009070359,0.017552495,0.018639619,0.00058010593,0.00079060026,0.16190557,0.012699507,0.0056399666,0.71408755,0.06653776,0.00030230466],"about_ca_topic_score_codex":0.007767413,"about_ca_topic_score_gemma":0.004852144,"teacher_disagreement_score":0.4863457,"about_ca_system_score_codex":0.016143676,"about_ca_system_score_gemma":0.028117009,"threshold_uncertainty_score":0.5997509},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003914469,0.016241742,0.016657203,0.9329439,0.005094341,0.00025474938,0.0000519847,0.0001205609,0.024721038],"genre_scores_gemma":[0.60922915,0.016966628,0.056181774,0.30188364,0.0076192715,0.0017986961,0.000119834134,0.00027380357,0.0059272344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60665894,0.3052572,0.02256578,0.006812635,0.053788543,0.0049168384],"domain_scores_gemma":[0.22918646,0.6286788,0.013875626,0.05303248,0.062949166,0.012277447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.353658,0.000822185,0.00256768,0.0052229045,0.008942256,0.029035408,0.0043998077,0.010679073,0.003920452],"category_scores_gemma":[0.44887072,0.0011514967,0.0012603621,0.0033595997,0.077280976,0.044399943,0.01873572,0.026371043,0.0007883733],"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":[0.00012301878,0.00028633073,0.0028904662,0.0018756471,0.000077670265,0.0002956429,0.027813917,0.0005019939,0.00033709768,0.71525854,0.08077608,0.16976362],"study_design_scores_gemma":[0.00014371176,0.00017690155,0.0017762976,0.006042819,0.000066236935,0.00034422884,0.030143417,0.0008729195,0.0005523886,0.7162625,0.24352492,0.00009366114],"about_ca_topic_score_codex":0.0070136553,"about_ca_topic_score_gemma":0.007928526,"teacher_disagreement_score":0.353658,"about_ca_system_score_codex":0.018475506,"about_ca_system_score_gemma":0.065648,"threshold_uncertainty_score":0.79705477},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988526,0.00008042163,0.000051847463,0.00020116217,0.000003083829,0.0000064909996,0.000020510028,0.0000013495255,0.0007824098],"genre_scores_gemma":[0.9994167,0.00012924151,0.000079607285,0.000117456984,0.000004637139,0.000012999015,0.000032550193,0.0000015209445,0.00020522738],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99700016,0.0014894415,0.00025375612,0.00014605962,0.0007366411,0.00037394062],"domain_scores_gemma":[0.97869796,0.008170498,0.0051533654,0.0005954231,0.004698186,0.0026846514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062625213,0.00014884486,0.00024978656,0.0015171531,0.0017578371,0.0019147925,0.00039067704,0.0005108755,0.0014993344],"category_scores_gemma":[0.013388731,0.00028325478,0.0002155526,0.0013965965,0.0013626446,0.0014152896,0.0014151057,0.0011285901,0.00016053174],"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":[0.00010958777,0.0005095811,0.87840205,0.000054544747,0.00003477609,0.00019782409,0.10180008,0.00008702505,0.000723458,0.00031003248,0.0009649418,0.016806094],"study_design_scores_gemma":[0.000005544783,0.0002753934,0.72388524,0.00009597367,0.000014221283,0.00027440584,0.2699771,0.00029724665,0.00033664794,0.00010185786,0.004709234,0.000027125558],"about_ca_topic_score_codex":0.020128012,"about_ca_topic_score_gemma":0.02235081,"teacher_disagreement_score":0.99373746,"about_ca_system_score_codex":0.0012750791,"about_ca_system_score_gemma":0.0015756381,"threshold_uncertainty_score":0.040021718},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98323214,0.0013259456,0.00031489896,0.0017713043,0.000026559557,0.00031081858,0.0037457624,0.000042008833,0.009230587],"genre_scores_gemma":[0.9947267,0.0009212614,0.000458687,0.0003646868,0.000006441916,0.00011453011,0.0015059544,0.000012850289,0.001888883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900315,0.0019005003,0.001008623,0.00065815874,0.00498871,0.0014125452],"domain_scores_gemma":[0.948512,0.005336603,0.005197521,0.0007521881,0.03516505,0.0050366702],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0085466495,0.00018918814,0.00047642755,0.0028082016,0.00397619,0.002199906,0.00096860604,0.00041047254,0.0019851518],"category_scores_gemma":[0.022482483,0.0003299501,0.0004913379,0.005911293,0.001196126,0.00079479674,0.0021012942,0.0008134666,0.00035198467],"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":[0.00015258456,0.00017355499,0.9424674,0.0003142573,0.000047051937,0.00010829611,0.015140682,0.00016039432,0.00014302056,0.00021900651,0.0058356836,0.035238132],"study_design_scores_gemma":[0.0000064605892,0.000048891772,0.98368466,0.00009134769,0.000008230203,0.000022287744,0.011814306,0.0002228629,0.00007330291,0.000021978543,0.003989306,0.000016442435],"about_ca_topic_score_codex":0.976583,"about_ca_topic_score_gemma":0.9800149,"teacher_disagreement_score":0.99145335,"about_ca_system_score_codex":0.04357096,"about_ca_system_score_gemma":0.08101599,"threshold_uncertainty_score":0.31613094},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091692716,0.051148295,0.7380828,0.059419133,0.0007998967,0.006331582,0.00063197786,0.00054933643,0.051344264],"genre_scores_gemma":[0.45893657,0.008586422,0.5254512,0.0017932504,0.00012522064,0.0041280612,0.0001602611,0.000052793388,0.0007661629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.69194406,0.2441415,0.020042991,0.0064628185,0.03583988,0.0015687001],"domain_scores_gemma":[0.5136204,0.40767604,0.021917215,0.0127522,0.041664254,0.0023698644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24181436,0.0019865145,0.0032837181,0.009771752,0.002981006,0.018019456,0.005269121,0.00337281,0.0034022795],"category_scores_gemma":[0.3668606,0.0010693244,0.0023563704,0.008171338,0.0107668135,0.016408712,0.008128679,0.006054844,0.0004169261],"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":[0.0003388526,0.00092160655,0.011350586,0.014003073,0.0016174945,0.00014244442,0.013077065,0.034381203,0.00096603343,0.29763073,0.0035104426,0.62206054],"study_design_scores_gemma":[0.0004719101,0.0027594427,0.011509126,0.023656145,0.0014374305,0.0002713619,0.025741933,0.09238636,0.006525356,0.7963075,0.038336318,0.000597083],"about_ca_topic_score_codex":0.0067185424,"about_ca_topic_score_gemma":0.010635905,"teacher_disagreement_score":0.24181436,"about_ca_system_score_codex":0.018971438,"about_ca_system_score_gemma":0.026615638,"threshold_uncertainty_score":0.9349779},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.868348,0.0015425954,0.016612835,0.02455105,0.0002341317,0.003534382,0.0014560706,0.0011437683,0.08257709],"genre_scores_gemma":[0.970454,0.0006118142,0.01894417,0.0007700323,0.00002448927,0.00068425376,0.00049908727,0.00005350954,0.00795854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9914192,0.0041731265,0.00026174623,0.00061088527,0.0020466524,0.001488331],"domain_scores_gemma":[0.98366714,0.0041594277,0.0015658634,0.0009927743,0.0050400165,0.0045746835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01547181,0.00036545115,0.00029927518,0.0023384308,0.010496885,0.0042190584,0.002580072,0.0013608225,0.0037187112],"category_scores_gemma":[0.024262229,0.00032213418,0.00022954412,0.0032631909,0.0022354706,0.002272363,0.00534279,0.0019371491,0.0004418321],"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":[0.0007496034,0.0015683781,0.16637628,0.001281516,0.00008633894,0.0021778243,0.118011154,0.0031362867,0.0045962236,0.008941418,0.0501444,0.64293057],"study_design_scores_gemma":[0.00021035329,0.0028152154,0.35431463,0.0011595904,0.00015203164,0.0008341979,0.21841694,0.007368778,0.014130632,0.007906268,0.39240867,0.00028271883],"about_ca_topic_score_codex":0.15673204,"about_ca_topic_score_gemma":0.3161669,"teacher_disagreement_score":0.15673204,"about_ca_system_score_codex":0.016437905,"about_ca_system_score_gemma":0.04910012,"threshold_uncertainty_score":0.3116395},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.478321,0.045855,0.12434194,0.13322447,0.0052755033,0.005585002,0.0009835126,0.00035695633,0.20605654],"genre_scores_gemma":[0.93195677,0.007830192,0.048119437,0.0033910295,0.0001807698,0.0018527693,0.00021544984,0.00006899186,0.0063845697],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9267847,0.056049433,0.003134672,0.0015733939,0.010809061,0.0016487477],"domain_scores_gemma":[0.9372095,0.040402077,0.0028374915,0.003120278,0.015318202,0.0011125504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.094451755,0.0013279895,0.0012063214,0.004237724,0.0056684217,0.011763805,0.0030230542,0.0030517203,0.0029409023],"category_scores_gemma":[0.070615746,0.0007607757,0.0010938835,0.003832438,0.013687739,0.009092196,0.0074680443,0.006384741,0.00029763364],"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":[0.0008092993,0.0012859193,0.026671695,0.0060604727,0.00022147536,0.0011186632,0.16169171,0.0027189623,0.003008894,0.2876316,0.014542063,0.49423924],"study_design_scores_gemma":[0.0004987316,0.0016489417,0.049939692,0.03480801,0.00050152466,0.0015577475,0.38132435,0.0147839375,0.022659943,0.061688535,0.43005192,0.00053673005],"about_ca_topic_score_codex":0.100996174,"about_ca_topic_score_gemma":0.092731394,"teacher_disagreement_score":0.100996174,"about_ca_system_score_codex":0.024538912,"about_ca_system_score_gemma":0.030818647,"threshold_uncertainty_score":0.49951458},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48051417,0.006482151,0.24928185,0.06888618,0.0013468185,0.011729275,0.00073447026,0.00071557786,0.1803095],"genre_scores_gemma":[0.6252468,0.001564365,0.34622204,0.0022752522,0.000082804,0.005133758,0.0006301268,0.00025330123,0.018591646],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8269049,0.15225029,0.0033148646,0.0024103555,0.008842278,0.0062773116],"domain_scores_gemma":[0.8904195,0.050786827,0.0035398563,0.0064023947,0.04026256,0.008588855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14451192,0.0010529261,0.001259972,0.0055504222,0.022567198,0.022714434,0.0040632198,0.004727135,0.005133824],"category_scores_gemma":[0.07802901,0.00095843605,0.0012093126,0.0072649545,0.011306615,0.012148498,0.014462769,0.0075284205,0.0010300276],"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":[0.0005693142,0.0029644445,0.008455049,0.0012873324,0.00008079622,0.0016235601,0.35272563,0.0042799343,0.001892406,0.3408367,0.024551772,0.260733],"study_design_scores_gemma":[0.00025651985,0.001841733,0.009454016,0.0048299213,0.00015394132,0.00080434687,0.5114921,0.015366748,0.004549241,0.07664236,0.37427402,0.00033502677],"about_ca_topic_score_codex":0.04071216,"about_ca_topic_score_gemma":0.05466838,"teacher_disagreement_score":0.14451192,"about_ca_system_score_codex":0.040951565,"about_ca_system_score_gemma":0.052520633,"threshold_uncertainty_score":0.76426125},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020112855,0.9941255,0.00049036526,0.0028344798,0.00019488917,0.00006762453,0.00001495441,0.000006125203,0.0020648113],"genre_scores_gemma":[0.0076949396,0.9884411,0.002478233,0.00073260936,0.00008490045,0.00013158232,0.000021775086,0.000007543914,0.00040729603],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96831405,0.0153196,0.0024686127,0.00095020456,0.012277433,0.0006701026],"domain_scores_gemma":[0.89883405,0.06674171,0.003976667,0.0011554608,0.02792174,0.0013704109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06013727,0.0015615893,0.0031539116,0.021262405,0.0032274534,0.006891155,0.0035231388,0.0025096447,0.0026225497],"category_scores_gemma":[0.07079015,0.001025526,0.0012960562,0.026376298,0.007856394,0.004752601,0.0028663012,0.003474963,0.0005336913],"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":[0.000057282756,0.000078847064,0.0008121797,0.05368756,0.00020536763,0.00007693146,0.0023381095,0.0005358941,0.00013037215,0.021202205,0.020348944,0.90052634],"study_design_scores_gemma":[0.00006166431,0.00015453414,0.008799219,0.23242533,0.0007096594,0.0003949812,0.0062525566,0.000887238,0.00055313995,0.012208679,0.7373717,0.0001812776],"about_ca_topic_score_codex":0.25270903,"about_ca_topic_score_gemma":0.43892172,"teacher_disagreement_score":0.25270903,"about_ca_system_score_codex":0.051245,"about_ca_system_score_gemma":0.095736384,"threshold_uncertainty_score":0.5024762},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014665557,0.001990157,0.00042133828,0.25656658,0.724978,0.00006143684,0.0003364325,0.0003570393,0.01514232],"genre_scores_gemma":[0.003463786,0.0030197606,0.0018021199,0.4816312,0.33446896,0.00023032313,0.00038783666,0.0004753755,0.17452064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889233,0.001102022,0.0010371859,0.001971014,0.005709233,0.0012572447],"domain_scores_gemma":[0.96216714,0.006404685,0.0018428734,0.0024234038,0.022057986,0.0051039425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009194723,0.0016013896,0.00159921,0.0022440187,0.0042250385,0.009611264,0.0050435783,0.017848488,0.11464453],"category_scores_gemma":[0.07745363,0.00079023297,0.002661982,0.0015876996,0.002700217,0.0057691834,0.0039465106,0.018355258,0.07994871],"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":[0.000010772106,0.0000065671206,0.00003478084,0.00004774045,0.000002818972,0.00007470737,0.000022670756,0.000014135758,0.000036278932,0.0008944688,0.99381316,0.005041834],"study_design_scores_gemma":[0.0000078224175,0.0000068974164,0.000105552914,0.00012384632,0.0000030529668,0.00009469465,0.000048568396,0.00003066479,0.00008601014,0.00073652784,0.9987453,0.000010953676],"about_ca_topic_score_codex":0.0034606878,"about_ca_topic_score_gemma":0.0060274256,"teacher_disagreement_score":0.11464453,"about_ca_system_score_codex":0.004112032,"about_ca_system_score_gemma":0.009466333,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9250827,0.0010316189,0.012443949,0.006203986,0.00013153993,0.012713761,0.00010777985,0.00006218728,0.04222238],"genre_scores_gemma":[0.983968,0.0003419893,0.009348609,0.00030116248,0.000011948763,0.0042914487,0.000026682394,0.000007248971,0.0017027605],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.84584314,0.14035666,0.0023110106,0.0014641809,0.0064898506,0.0035351277],"domain_scores_gemma":[0.90233976,0.076349646,0.004298133,0.0034820985,0.01133177,0.0021985022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.120977364,0.00073760987,0.0006350194,0.0011841829,0.004331765,0.0046714884,0.0013732564,0.0016997318,0.002786132],"category_scores_gemma":[0.11298126,0.00034410722,0.0004769269,0.0010762679,0.0055607515,0.002805627,0.0057704253,0.00186215,0.00020409201],"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":[0.005573667,0.010484647,0.020936057,0.0067364303,0.00043443235,0.0019976723,0.30779433,0.014220627,0.006321367,0.04644775,0.0067427102,0.5723103],"study_design_scores_gemma":[0.0077229883,0.042531025,0.059026875,0.010935584,0.0008357771,0.00071148714,0.60803074,0.015351334,0.04026481,0.05534844,0.15881014,0.0004308251],"about_ca_topic_score_codex":0.0062581394,"about_ca_topic_score_gemma":0.011955762,"teacher_disagreement_score":0.120977364,"about_ca_system_score_codex":0.008267351,"about_ca_system_score_gemma":0.016040245,"threshold_uncertainty_score":0.6397971},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3470622,0.0071193883,0.2766681,0.1361324,0.0022507585,0.0006625323,0.000056306402,0.0006610015,0.22938722],"genre_scores_gemma":[0.9578455,0.0009139758,0.027850948,0.0035618728,0.0003130036,0.00016542697,0.000015581883,0.00014781339,0.009185871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8811838,0.09828088,0.0026452392,0.0042009605,0.010109996,0.0035791488],"domain_scores_gemma":[0.89713013,0.064392574,0.007101493,0.006331218,0.018532798,0.0065118694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07541827,0.00048286904,0.0005533395,0.002142358,0.008917939,0.019565254,0.001711762,0.0047347937,0.004592645],"category_scores_gemma":[0.07684847,0.00057550817,0.0004848091,0.0012551675,0.023365667,0.01357185,0.010187322,0.006333481,0.0011181996],"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":[0.00039091057,0.00056638283,0.026698219,0.0007326401,0.00007254583,0.0020285444,0.29119337,0.0019771021,0.0069315177,0.48691785,0.010236285,0.17225467],"study_design_scores_gemma":[0.00017494043,0.0009895551,0.020057451,0.0030464723,0.00013392237,0.0019346254,0.22436291,0.012267506,0.013096499,0.31799272,0.40550414,0.00043928626],"about_ca_topic_score_codex":0.0018456515,"about_ca_topic_score_gemma":0.0017579978,"teacher_disagreement_score":0.07541827,"about_ca_system_score_codex":0.0062346905,"about_ca_system_score_gemma":0.011263603,"threshold_uncertainty_score":0.39885473},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011788729,0.020346973,0.062393542,0.8289315,0.004634685,0.00042201098,0.00005795704,0.00029210275,0.0711324],"genre_scores_gemma":[0.8231661,0.015000363,0.08143722,0.06560046,0.002043735,0.0017617283,0.00011062381,0.00038856713,0.010491167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.43095413,0.5047524,0.011640584,0.007303404,0.036511783,0.008837685],"domain_scores_gemma":[0.44913292,0.4361589,0.009103415,0.022158526,0.07054829,0.012897945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4280559,0.0012813788,0.0013164174,0.006330268,0.0125543745,0.034654535,0.0076265237,0.009635604,0.0036356726],"category_scores_gemma":[0.41988832,0.0015696865,0.0015297141,0.0048792087,0.05936373,0.025450679,0.018163892,0.02571559,0.00080618163],"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":[0.00014979587,0.00020226947,0.0031520536,0.0015438936,0.00010713568,0.0004665994,0.06347961,0.003993361,0.0001206817,0.63715065,0.07454047,0.21509351],"study_design_scores_gemma":[0.00016270937,0.00031410885,0.0037894365,0.016252078,0.000075091,0.00044725585,0.09623911,0.0053036716,0.001141124,0.4200722,0.45574507,0.00045810788],"about_ca_topic_score_codex":0.032056455,"about_ca_topic_score_gemma":0.030336373,"teacher_disagreement_score":0.4280559,"about_ca_system_score_codex":0.07631671,"about_ca_system_score_gemma":0.095456794,"threshold_uncertainty_score":0.7053089},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007217729,0.0033544519,0.00019518317,0.10078361,0.87620443,0.000039872786,0.000109457025,0.00014772324,0.019093052],"genre_scores_gemma":[0.0014184486,0.005978342,0.0006350871,0.1247442,0.73935133,0.00015721255,0.00025578417,0.00021432144,0.12724525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99311125,0.0007503144,0.0009524151,0.0009651618,0.0033981032,0.0008228106],"domain_scores_gemma":[0.9730988,0.0052637206,0.001172164,0.0015324175,0.016414825,0.0025180068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009173739,0.0021018593,0.0019566612,0.0027724325,0.0032937198,0.011748099,0.003831797,0.015502076,0.056372453],"category_scores_gemma":[0.032176144,0.0010556133,0.001984656,0.002183694,0.00274901,0.009026061,0.0029325904,0.013834499,0.05805431],"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":[0.00000832822,0.000006858275,0.000021421985,0.000045320987,9.852835e-7,0.000030375435,0.000008891906,0.0000081854305,0.000027968435,0.00051102485,0.9957008,0.0036299278],"study_design_scores_gemma":[0.000010561478,0.000011048781,0.00021567235,0.00013772945,0.000003396839,0.000075494856,0.000040622923,0.000033592132,0.000045891233,0.0008783628,0.99853766,0.000009922556],"about_ca_topic_score_codex":0.0033512693,"about_ca_topic_score_gemma":0.005384062,"teacher_disagreement_score":0.056372453,"about_ca_system_score_codex":0.0030551055,"about_ca_system_score_gemma":0.0043888055,"threshold_uncertainty_score":0.18858463},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010254399,0.5285437,0.023137059,0.12048449,0.0119215995,0.0006021757,0.00631579,0.0012613006,0.3067084],"genre_scores_gemma":[0.017154677,0.47879374,0.052334886,0.018491067,0.0012720673,0.0012339498,0.0024452407,0.00061107817,0.42766333],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986426,0.0003303738,0.000116644616,0.00011432274,0.0006792475,0.00011671327],"domain_scores_gemma":[0.9953679,0.0022373348,0.0002528015,0.000115796145,0.0017145426,0.00031160304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005721432,0.0010899081,0.0008281151,0.0037133307,0.0024979596,0.0030873884,0.0012088461,0.0034022601,0.0786862],"category_scores_gemma":[0.01073735,0.0010462616,0.00037526968,0.00489553,0.0013976276,0.0056828563,0.001394393,0.003999034,0.043913774],"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":[0.000014967955,0.000008332716,0.00025031096,0.0003395578,0.0000019402057,0.00003229054,0.00032930818,0.000053717038,0.00006204536,0.004128353,0.77387375,0.22090541],"study_design_scores_gemma":[0.000008272156,0.000010770995,0.0010568602,0.0018016362,0.000004206835,0.00010616024,0.00055691233,0.000056603993,0.00014934101,0.00640154,0.9898225,0.000025234222],"about_ca_topic_score_codex":0.10215637,"about_ca_topic_score_gemma":0.2315739,"teacher_disagreement_score":0.10215637,"about_ca_system_score_codex":0.0064814095,"about_ca_system_score_gemma":0.013315704,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932225,0.000024558947,0.001230655,0.00029756725,0.00004883734,0.0024483579,0.00004708346,0.000046556717,0.0026339968],"genre_scores_gemma":[0.98420584,0.000056211775,0.0074227755,0.0003011936,0.000042300537,0.0041687964,0.00026981425,0.0000357357,0.0034973044],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97800887,0.015695248,0.0011153541,0.0010461592,0.0025099395,0.0016244573],"domain_scores_gemma":[0.931825,0.029559469,0.002648722,0.0059415502,0.024214363,0.0058109066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056190718,0.0005695109,0.000722226,0.0010844134,0.0048046154,0.0015576791,0.0014491018,0.0013059189,0.0036145637],"category_scores_gemma":[0.050290763,0.0009786045,0.0007388417,0.0007338455,0.0016668576,0.0017425996,0.0030487406,0.002576447,0.0008968445],"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":[0.012188407,0.15099198,0.28277797,0.00094425795,0.0003109568,0.0018927631,0.21605058,0.004155488,0.014389489,0.0032927305,0.017348794,0.2956566],"study_design_scores_gemma":[0.007025252,0.139349,0.6205212,0.0003457063,0.00037698637,0.00045099264,0.12399674,0.009868419,0.030326117,0.0013662939,0.065913215,0.0004601176],"about_ca_topic_score_codex":0.010424268,"about_ca_topic_score_gemma":0.023972923,"teacher_disagreement_score":0.056190718,"about_ca_system_score_codex":0.0038079731,"about_ca_system_score_gemma":0.008589119,"threshold_uncertainty_score":0.29716843},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2711659,0.0019386996,0.6333087,0.009423501,0.0003754436,0.0040093036,0.00034514305,0.0011610652,0.07827227],"genre_scores_gemma":[0.6739617,0.00036389258,0.32122567,0.00036416267,0.000024392582,0.0015893674,0.00009363671,0.00014109963,0.002235985],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85292476,0.13052794,0.0023061107,0.0016605407,0.011487135,0.0010935222],"domain_scores_gemma":[0.86078906,0.1091401,0.0076119113,0.0065170247,0.014662663,0.0012793229],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10416995,0.00086238794,0.00072557974,0.006451403,0.0025604642,0.00764063,0.001806398,0.0012714464,0.0033573348],"category_scores_gemma":[0.1423541,0.00051316275,0.00078998646,0.0048234896,0.0051116752,0.005528688,0.0064409245,0.0018820507,0.00031066322],"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":[0.0009953418,0.00090766087,0.02865857,0.0020121422,0.00022870694,0.0002397898,0.037821505,0.0109853735,0.0024863468,0.08241904,0.0070609706,0.8261846],"study_design_scores_gemma":[0.0025370424,0.008399565,0.12306282,0.010919689,0.0011292069,0.00064821145,0.15367143,0.17557572,0.030752225,0.33184364,0.16089544,0.00056500494],"about_ca_topic_score_codex":0.0076117604,"about_ca_topic_score_gemma":0.015882174,"teacher_disagreement_score":0.10416995,"about_ca_system_score_codex":0.009318927,"about_ca_system_score_gemma":0.011046857,"threshold_uncertainty_score":0.55090994},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84038097,0.0035797153,0.08122147,0.0022510292,0.00018934842,0.005383189,0.004523396,0.0002307408,0.062240057],"genre_scores_gemma":[0.97955143,0.00034237595,0.01587673,0.00008038825,0.00005111436,0.0013297856,0.00076247484,0.000020530983,0.0019851488],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9594744,0.028672317,0.0013123002,0.000764744,0.0083004935,0.001475762],"domain_scores_gemma":[0.8215002,0.13911209,0.01408961,0.0029077318,0.020502867,0.0018874393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031585045,0.0007343674,0.0010531227,0.0084098475,0.000717791,0.0023752055,0.0020256718,0.0007781131,0.006573684],"category_scores_gemma":[0.12238358,0.00022545482,0.0013276985,0.0075276224,0.0011384316,0.0024230625,0.0018693525,0.0013412553,0.00032283514],"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":[0.005126314,0.003584716,0.13229737,0.0052235015,0.0017383425,0.00017450585,0.003968918,0.11432875,0.00087373174,0.11824745,0.008724183,0.6057121],"study_design_scores_gemma":[0.0009837023,0.0130161885,0.39229655,0.0043686093,0.0028806312,0.00019675537,0.007902815,0.42376316,0.011740456,0.10386189,0.038613148,0.0003760663],"about_ca_topic_score_codex":0.012744252,"about_ca_topic_score_gemma":0.009224384,"teacher_disagreement_score":0.031585045,"about_ca_system_score_codex":0.010153629,"about_ca_system_score_gemma":0.005722164,"threshold_uncertainty_score":0.16703969},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026889527,0.52610254,0.013161722,0.27449474,0.024367863,0.000473443,0.0010286239,0.00058737467,0.15709484],"genre_scores_gemma":[0.096184626,0.7045427,0.03012639,0.037758186,0.0081788255,0.0007506378,0.0011426752,0.0007217591,0.12059419],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937443,0.0025896234,0.0006442674,0.00022467315,0.002627516,0.00016951053],"domain_scores_gemma":[0.9288735,0.031017017,0.003544238,0.0015303415,0.032568995,0.0024659473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018662946,0.0004753878,0.0004731953,0.0041131293,0.0019411601,0.0046272334,0.001738108,0.001859186,0.016132742],"category_scores_gemma":[0.07393756,0.00037250787,0.00037832724,0.0038941493,0.0032966656,0.0029897715,0.0019223884,0.003323115,0.009165023],"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":[0.00004184248,0.00001691426,0.00096698524,0.0017985186,0.000018334988,0.00006387102,0.0017915812,0.00008036702,0.00023465158,0.002692835,0.70600146,0.28629264],"study_design_scores_gemma":[0.000013415685,0.000030346902,0.005739252,0.0065439693,0.0000447178,0.00023287657,0.0016913292,0.000094690615,0.0004413649,0.002828064,0.9823101,0.000029947676],"about_ca_topic_score_codex":0.03597296,"about_ca_topic_score_gemma":0.10424514,"teacher_disagreement_score":0.03597296,"about_ca_system_score_codex":0.0036324125,"about_ca_system_score_gemma":0.011156584,"threshold_uncertainty_score":0.098700285},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017000688,0.018396404,0.5717394,0.29496694,0.0033444266,0.00201972,0.00033406125,0.0007630296,0.09143543],"genre_scores_gemma":[0.4868591,0.0053361175,0.4684272,0.02566255,0.0018357728,0.0039970893,0.0001925537,0.00029088362,0.0073986757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4982219,0.4232413,0.012989632,0.00967039,0.05312068,0.0027561353],"domain_scores_gemma":[0.5944596,0.30889222,0.0146278525,0.036824286,0.042908233,0.002287871],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3288297,0.001969506,0.0029623231,0.0068509667,0.004127048,0.027467743,0.009255858,0.011912221,0.009080827],"category_scores_gemma":[0.24822062,0.0012981923,0.0038032744,0.003934316,0.03007935,0.019661814,0.010867684,0.016007239,0.0018753598],"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":[0.00028867702,0.0003729081,0.001355286,0.0046321037,0.00045141077,0.00016604163,0.008559674,0.006529707,0.0006950184,0.87583965,0.01015514,0.0909544],"study_design_scores_gemma":[0.00068141724,0.00078755146,0.0023442793,0.01162401,0.000343409,0.00048616165,0.0063116755,0.019293174,0.0037495948,0.7206769,0.23343806,0.00026377983],"about_ca_topic_score_codex":0.006955909,"about_ca_topic_score_gemma":0.008750296,"teacher_disagreement_score":0.3288297,"about_ca_system_score_codex":0.02224774,"about_ca_system_score_gemma":0.02126961,"threshold_uncertainty_score":0.8276725},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011693836,0.0013491136,0.9252312,0.011684489,0.0002262129,0.0029672023,0.0003115727,0.0005278,0.0460085],"genre_scores_gemma":[0.33505094,0.0005438331,0.6583263,0.00066348666,0.00007971766,0.0032373047,0.00030715042,0.000045859102,0.0017454351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80779636,0.1622148,0.00736896,0.0037614084,0.015212749,0.003645776],"domain_scores_gemma":[0.81172043,0.11650855,0.011371481,0.0065432987,0.049444005,0.0044122557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1646614,0.0015739055,0.0018723363,0.012821154,0.0043899,0.010492878,0.003945225,0.0033733535,0.0038466384],"category_scores_gemma":[0.09562767,0.00082688575,0.0018278656,0.007141176,0.011188741,0.009076683,0.007671768,0.0042404495,0.00040455954],"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":[0.000066753324,0.00042193165,0.0061324043,0.0010934096,0.00015485617,0.0001916052,0.0022968417,0.042487588,0.00029903415,0.860638,0.005694437,0.08052304],"study_design_scores_gemma":[0.00023745121,0.0006209163,0.0039681327,0.004533578,0.00029798737,0.000247379,0.005928094,0.17799343,0.0029449959,0.7261481,0.07689296,0.0001868353],"about_ca_topic_score_codex":0.02023976,"about_ca_topic_score_gemma":0.01823334,"teacher_disagreement_score":0.1646614,"about_ca_system_score_codex":0.022707554,"about_ca_system_score_gemma":0.04416173,"threshold_uncertainty_score":0.8708231},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03583585,0.009016717,0.6721793,0.04696322,0.0011138306,0.00088649034,0.00018957071,0.00040172366,0.23341334],"genre_scores_gemma":[0.7357295,0.005341709,0.24178416,0.0018597931,0.00033860691,0.0016378047,0.00012552843,0.00018148727,0.013001352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85362154,0.11062159,0.0046250774,0.0045945235,0.024367874,0.0021693786],"domain_scores_gemma":[0.7772335,0.17878322,0.006564211,0.013041899,0.022769567,0.0016076284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.092643395,0.002047318,0.0015129651,0.008133075,0.0034067368,0.023152187,0.002875239,0.004855869,0.009172873],"category_scores_gemma":[0.12805757,0.0010638924,0.002397269,0.006043198,0.025553873,0.018493952,0.0054532457,0.004645412,0.0016976447],"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":[0.00007047567,0.00011194594,0.0020432456,0.0008685955,0.00007526863,0.00012033182,0.0046229893,0.00638863,0.00043397132,0.92337763,0.0019178807,0.059968993],"study_design_scores_gemma":[0.00015374151,0.000488724,0.004060528,0.0031553968,0.0002177909,0.00059713,0.0081065325,0.05884143,0.00589173,0.7828751,0.13542515,0.0001867906],"about_ca_topic_score_codex":0.017772697,"about_ca_topic_score_gemma":0.010550375,"teacher_disagreement_score":0.092643395,"about_ca_system_score_codex":0.020701848,"about_ca_system_score_gemma":0.0211975,"threshold_uncertainty_score":0.48995095},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050726395,0.045094904,0.47321656,0.08819317,0.0017760178,0.005913796,0.000104235434,0.00032617358,0.33464873],"genre_scores_gemma":[0.84812254,0.012399233,0.12672842,0.0027702479,0.000261002,0.0046778754,0.000041795578,0.00009054661,0.0049082115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6934641,0.27975798,0.0043153367,0.0041404497,0.015377793,0.0029443745],"domain_scores_gemma":[0.73566157,0.23040223,0.0055596502,0.0098323785,0.014830669,0.00371357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1842238,0.0010992488,0.0020001887,0.0074119153,0.011766759,0.018235307,0.0035786154,0.0049903253,0.0046031093],"category_scores_gemma":[0.13445424,0.00072581315,0.00078691426,0.009274482,0.05269681,0.012091371,0.017273065,0.0056035337,0.00043335135],"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":[0.00012118088,0.00051445054,0.0034574084,0.0042389138,0.00008485945,0.0004860458,0.090504795,0.0043852516,0.0003190163,0.6117073,0.005393375,0.27878743],"study_design_scores_gemma":[0.00019408442,0.00046693828,0.0028513372,0.015173351,0.00007616817,0.0005050507,0.11700287,0.0067704595,0.0012690768,0.6927023,0.16286007,0.00012832858],"about_ca_topic_score_codex":0.0110686375,"about_ca_topic_score_gemma":0.010381096,"teacher_disagreement_score":0.1842238,"about_ca_system_score_codex":0.024115924,"about_ca_system_score_gemma":0.049104907,"threshold_uncertainty_score":0.97428024},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056648266,0.7196775,0.014689191,0.1325517,0.011223479,0.00014795832,0.0031062118,0.0013925941,0.11664488],"genre_scores_gemma":[0.01999297,0.7228971,0.029957525,0.018311262,0.0038336865,0.00059906923,0.0020650795,0.0013069522,0.20103627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972277,0.0007399407,0.00035503384,0.00021794894,0.0013535578,0.00010577142],"domain_scores_gemma":[0.97927195,0.010468837,0.0011166444,0.00074186723,0.00745853,0.0009422429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007688899,0.0017185705,0.0010246212,0.0047493814,0.0029489442,0.004490746,0.0021912165,0.0050714645,0.07290011],"category_scores_gemma":[0.026444947,0.0017291445,0.00064090156,0.0047429143,0.0023380516,0.009390293,0.0020140978,0.0053066146,0.04277909],"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":[0.000028560617,0.00001322701,0.00021255368,0.0007501645,0.000008816745,0.000043997334,0.0005277631,0.00008181243,0.00012162311,0.0048347847,0.83975244,0.15362439],"study_design_scores_gemma":[0.000023693785,0.000018375258,0.0026411766,0.0044889636,0.000040007468,0.00020327856,0.0007248255,0.00013252159,0.00044696423,0.012609954,0.97862476,0.000045513912],"about_ca_topic_score_codex":0.064036146,"about_ca_topic_score_gemma":0.16368827,"teacher_disagreement_score":0.07290011,"about_ca_system_score_codex":0.0045015435,"about_ca_system_score_gemma":0.008925153,"threshold_uncertainty_score":0.2438752},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052314546,0.022607671,0.14163987,0.6089982,0.0015305895,0.0014011873,0.00010878515,0.0004306323,0.17096852],"genre_scores_gemma":[0.8113225,0.011205622,0.15883754,0.012823965,0.00041796188,0.0011776083,0.000060427228,0.00012327025,0.004031157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.95056665,0.037324384,0.0016869798,0.0015197826,0.005090894,0.0038113692],"domain_scores_gemma":[0.8370237,0.113426134,0.004137492,0.0070327595,0.015889606,0.022490257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08879726,0.0010436017,0.001010843,0.0045539844,0.009648121,0.0193727,0.003705436,0.006203955,0.006872322],"category_scores_gemma":[0.07113439,0.00080930575,0.00135096,0.003039375,0.038599744,0.01331576,0.014751612,0.010787121,0.0007809529],"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":[0.00015204068,0.000665737,0.0062577883,0.0015573851,0.00007611114,0.0002970359,0.0141477315,0.0034014555,0.00029753364,0.7102151,0.018145218,0.24478693],"study_design_scores_gemma":[0.00021529694,0.0003007617,0.008085953,0.0053686006,0.00007235869,0.00027037814,0.029840104,0.009585979,0.0012502027,0.82658786,0.11821719,0.00020531772],"about_ca_topic_score_codex":0.02356003,"about_ca_topic_score_gemma":0.038032047,"teacher_disagreement_score":0.08879726,"about_ca_system_score_codex":0.029231288,"about_ca_system_score_gemma":0.10883571,"threshold_uncertainty_score":0.4696104},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11287017,0.00405388,0.21355736,0.08930738,0.0045153275,0.04831483,0.0018589039,0.0034930469,0.52202916],"genre_scores_gemma":[0.5933992,0.001958079,0.29347065,0.006888285,0.0008708077,0.021048132,0.0017767069,0.001065237,0.0795229],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.77747875,0.1450579,0.013495904,0.006990395,0.04056575,0.01641133],"domain_scores_gemma":[0.7021986,0.09660797,0.016231988,0.01718799,0.15115954,0.01661385],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28409865,0.0009949271,0.0008101962,0.008862161,0.012928941,0.027195988,0.00411694,0.003292438,0.010058027],"category_scores_gemma":[0.22070137,0.0011724958,0.00080949394,0.005161041,0.009835794,0.008343898,0.010636606,0.0067801634,0.003117088],"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":[0.0003518341,0.0004229235,0.013802777,0.0014083796,0.00014049768,0.0011124181,0.06816839,0.01523529,0.0025702382,0.22048336,0.211353,0.46495092],"study_design_scores_gemma":[0.00021699262,0.00046069088,0.017649967,0.0034516002,0.000104700266,0.00017114104,0.055262376,0.0062799556,0.0061841654,0.03916227,0.87047696,0.0005791355],"about_ca_topic_score_codex":0.08084298,"about_ca_topic_score_gemma":0.1143203,"teacher_disagreement_score":0.28409865,"about_ca_system_score_codex":0.07973497,"about_ca_system_score_gemma":0.19916448,"threshold_uncertainty_score":0.88283384},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015295975,0.027519178,0.1809328,0.7331759,0.005275179,0.001670858,0.00009237571,0.00088183576,0.035156008],"genre_scores_gemma":[0.60958177,0.018356407,0.29711056,0.06079642,0.0031501867,0.0028281969,0.0001368059,0.000720174,0.0073194425],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.40113857,0.48983103,0.028452964,0.0073620467,0.06455124,0.008664235],"domain_scores_gemma":[0.17887315,0.55838627,0.02383618,0.055552486,0.16616221,0.017189741],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.55871564,0.0017279875,0.0024319873,0.0061111245,0.013817173,0.031631663,0.0066264826,0.009906914,0.002858269],"category_scores_gemma":[0.6229061,0.0017858571,0.0016375717,0.0066641383,0.034144673,0.026519222,0.015685815,0.021028148,0.00078803493],"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":[0.0003405541,0.0005000432,0.012805076,0.0038124288,0.00029794633,0.00058066106,0.04720318,0.005294644,0.0005607492,0.1711644,0.10041312,0.65702724],"study_design_scores_gemma":[0.00065267604,0.00072310306,0.008861854,0.018315999,0.00021400196,0.00078222284,0.029611403,0.007378082,0.00271685,0.6089078,0.3212598,0.00057617936],"about_ca_topic_score_codex":0.027980564,"about_ca_topic_score_gemma":0.028283065,"teacher_disagreement_score":0.55871564,"about_ca_system_score_codex":0.03536398,"about_ca_system_score_gemma":0.14628084,"threshold_uncertainty_score":0.5441822},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44019035,0.019314632,0.012461631,0.059781995,0.013638442,0.012672517,0.035428934,0.0021623648,0.4043491],"genre_scores_gemma":[0.66912436,0.0076806615,0.027659085,0.007344205,0.0063720355,0.008059189,0.022598898,0.0010912804,0.2500703],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99404126,0.0024099997,0.0001573204,0.00052600267,0.0010992874,0.0017660847],"domain_scores_gemma":[0.98046553,0.0013700689,0.00065166334,0.0008830839,0.0064483797,0.010181294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015747763,0.0017745923,0.0011586176,0.0026656457,0.0021599908,0.0043840846,0.0016857473,0.0019021066,0.019449156],"category_scores_gemma":[0.008903221,0.00036404774,0.0012103382,0.0027728637,0.00084162847,0.0013928091,0.004668006,0.0023167415,0.007498921],"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":[0.012956478,0.010453554,0.045053255,0.0022440737,0.000291139,0.0002211652,0.0026429927,0.007187976,0.005353405,0.0203109,0.4085761,0.4847089],"study_design_scores_gemma":[0.0023179676,0.009520375,0.30161563,0.00227969,0.00041386342,0.00027671634,0.006876873,0.0056511085,0.013865942,0.009971027,0.64702666,0.00018409934],"about_ca_topic_score_codex":0.02683958,"about_ca_topic_score_gemma":0.04963402,"teacher_disagreement_score":0.02683958,"about_ca_system_score_codex":0.0071324995,"about_ca_system_score_gemma":0.027346946,"threshold_uncertainty_score":0.083283186},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42939627,0.022589331,0.09977549,0.36188087,0.0025014686,0.0015427563,0.00022432752,0.0002998053,0.08178969],"genre_scores_gemma":[0.9365269,0.007874059,0.029163431,0.017958397,0.00029041572,0.0008209505,0.00008278853,0.00028307718,0.006999994],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.80202585,0.1742926,0.0034054446,0.0040636915,0.009393641,0.006818847],"domain_scores_gemma":[0.7921978,0.16867837,0.0071220016,0.0072706933,0.01540022,0.009330953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12789254,0.0008610504,0.001209429,0.005958608,0.029521765,0.03353783,0.004569173,0.005844267,0.0027138893],"category_scores_gemma":[0.15199292,0.0014427546,0.0011511632,0.0056402925,0.03975452,0.04294775,0.020872826,0.012737246,0.00073305116],"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":[0.000017104388,0.000030556585,0.0018290945,0.00028391328,0.000019674118,0.0006452144,0.952174,0.000089305424,0.00015073805,0.022507051,0.0039342702,0.018319085],"study_design_scores_gemma":[0.0000065459726,0.000026481599,0.00071136415,0.00077563367,0.000013596037,0.00045524785,0.9464454,0.00018493617,0.00013234942,0.016666392,0.034557886,0.000024132338],"about_ca_topic_score_codex":0.009631323,"about_ca_topic_score_gemma":0.027379058,"teacher_disagreement_score":0.12789254,"about_ca_system_score_codex":0.016436284,"about_ca_system_score_gemma":0.039871383,"threshold_uncertainty_score":0.6763685},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13414061,0.018659996,0.1891179,0.3178084,0.002659491,0.010525707,0.0004013235,0.001456701,0.3252299],"genre_scores_gemma":[0.93383926,0.002808004,0.0413161,0.0072830184,0.00048536487,0.0026251168,0.00029211945,0.00017231153,0.011178744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.67729443,0.26490942,0.009830038,0.0048437403,0.026509736,0.016612578],"domain_scores_gemma":[0.4765844,0.29013535,0.018997058,0.02353546,0.1398759,0.05087184],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3211932,0.0007156821,0.0010829386,0.007004542,0.011325782,0.02377819,0.005880182,0.0044297297,0.011676106],"category_scores_gemma":[0.2585513,0.0009144655,0.00081395934,0.0035883118,0.011974551,0.0133665195,0.027980436,0.005864471,0.0014712036],"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":[0.00038194243,0.0017754477,0.017292032,0.004222904,0.00023726474,0.0005452415,0.017380944,0.010636721,0.00092830113,0.42180824,0.07991373,0.4448772],"study_design_scores_gemma":[0.00049836695,0.0007991048,0.018369067,0.012853254,0.00008654835,0.00053519453,0.06476327,0.018860165,0.004390621,0.41565478,0.46281275,0.00037688948],"about_ca_topic_score_codex":0.013603959,"about_ca_topic_score_gemma":0.01311068,"teacher_disagreement_score":0.986396,"about_ca_system_score_codex":0.029099034,"about_ca_system_score_gemma":0.17360468,"threshold_uncertainty_score":0.83708966},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82351047,0.008506458,0.0017988371,0.011456039,0.00022342525,0.0013224487,0.006128909,0.00022498034,0.14682841],"genre_scores_gemma":[0.90216565,0.0034230228,0.0036853182,0.0009979255,0.00003772233,0.0005180271,0.0033410494,0.000065678454,0.08576557],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99379,0.001677789,0.00031309912,0.0002467223,0.002726167,0.0012461368],"domain_scores_gemma":[0.96708226,0.003883409,0.0020107073,0.0009831798,0.020945268,0.0050951974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007817531,0.00016287022,0.00024030101,0.0016045658,0.004659677,0.0025867256,0.00089009706,0.00048916537,0.0036997243],"category_scores_gemma":[0.020710869,0.00037611692,0.0001480567,0.0039653163,0.0012494362,0.00073545193,0.0018894712,0.001004803,0.0005718817],"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":[0.0014544145,0.00078080356,0.4005199,0.0011168986,0.00017008839,0.00095708214,0.026857594,0.0030175552,0.002050449,0.009916772,0.09483707,0.45832145],"study_design_scores_gemma":[0.000049727878,0.0002046813,0.8249551,0.00041200023,0.000045152574,0.00012209613,0.015370355,0.00073689065,0.001764671,0.000334275,0.15596098,0.000044062763],"about_ca_topic_score_codex":0.9499614,"about_ca_topic_score_gemma":0.9790822,"teacher_disagreement_score":0.9290291,"about_ca_system_score_codex":0.070970915,"about_ca_system_score_gemma":0.14101477,"threshold_uncertainty_score":0.51493245},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08383043,0.040008105,0.0053360276,0.58107436,0.0015779481,0.0016900019,0.0010656147,0.00026808938,0.2851494],"genre_scores_gemma":[0.86364126,0.019175204,0.010526115,0.037643008,0.0006190796,0.00097021204,0.000532434,0.0001595332,0.0667332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9305533,0.027247876,0.004966387,0.0029702014,0.022033982,0.012228158],"domain_scores_gemma":[0.7844888,0.053548332,0.011634219,0.004553046,0.103387535,0.04238797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065396,0.0004043001,0.00070478563,0.0039352146,0.018212158,0.014508276,0.0036386256,0.0061850157,0.011465932],"category_scores_gemma":[0.11066097,0.00095684984,0.0006699542,0.006398629,0.013435913,0.0046404097,0.008437608,0.0033148746,0.0006305468],"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":[0.00067077694,0.00040940903,0.062184263,0.0046061147,0.00017727545,0.0015103704,0.044680886,0.0057119224,0.0011499363,0.40587625,0.23742768,0.23559508],"study_design_scores_gemma":[0.00025567322,0.00020552661,0.09092442,0.0048745256,0.00008441836,0.00030875154,0.021262482,0.0028067399,0.0007910827,0.029106315,0.8492006,0.0001795535],"about_ca_topic_score_codex":0.96499455,"about_ca_topic_score_gemma":0.9723541,"teacher_disagreement_score":0.65528166,"about_ca_system_score_codex":0.3447183,"about_ca_system_score_gemma":0.6178708,"threshold_uncertainty_score":0.7600339},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5245639,0.033008337,0.0022756835,0.19570239,0.0012153948,0.0011062023,0.0024454626,0.00037801312,0.23930457],"genre_scores_gemma":[0.87743455,0.0068566008,0.0032672214,0.017259194,0.0001137253,0.00046105732,0.0011880969,0.00006936413,0.09335016],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.989565,0.003739759,0.00045442538,0.00058778666,0.001777826,0.0038751748],"domain_scores_gemma":[0.9645447,0.0065119304,0.0020313717,0.0012748007,0.016366916,0.009270213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013021618,0.00023524144,0.00038156315,0.0010129123,0.0086648045,0.005546615,0.0012367324,0.0012607973,0.008604782],"category_scores_gemma":[0.014921832,0.00039152656,0.00033065263,0.0014805694,0.0033604058,0.0022166257,0.003832083,0.002495557,0.00064009184],"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":[0.0024842694,0.0012011584,0.20919351,0.0023346955,0.0002491039,0.003099523,0.039711814,0.0023729852,0.0031554874,0.023390235,0.33342463,0.37938255],"study_design_scores_gemma":[0.00014230303,0.00035386108,0.60252154,0.002310918,0.00012892928,0.00045924247,0.05099547,0.00061317265,0.002356398,0.0014151039,0.338579,0.00012405844],"about_ca_topic_score_codex":0.9358274,"about_ca_topic_score_gemma":0.97813934,"teacher_disagreement_score":0.8780897,"about_ca_system_score_codex":0.121910274,"about_ca_system_score_gemma":0.15151578,"threshold_uncertainty_score":0.88452506},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09433067,0.018665107,0.01201209,0.60223305,0.0029374196,0.0008518718,0.0007484678,0.000723466,0.26749787],"genre_scores_gemma":[0.8686604,0.0062092603,0.020178758,0.048773963,0.0005661076,0.0001889625,0.0004831326,0.000100163794,0.05483928],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9723389,0.0074936147,0.0008497603,0.0011203601,0.01280335,0.005393962],"domain_scores_gemma":[0.94923866,0.005065725,0.0017516448,0.0012932001,0.033062704,0.009587943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02070764,0.00032439164,0.00033721986,0.0021140913,0.008317769,0.0094914725,0.0022625322,0.0025154206,0.0044912146],"category_scores_gemma":[0.037554998,0.0003043387,0.00050779217,0.0026451917,0.003988736,0.0020928413,0.0031479555,0.0033626647,0.00038091734],"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":[0.00032657827,0.00045815465,0.04048671,0.0013068327,0.00014924917,0.00044895604,0.0054373783,0.004651286,0.0012885655,0.1934554,0.25090984,0.5010811],"study_design_scores_gemma":[0.00016087915,0.00026857297,0.10365492,0.0019493009,0.00015423128,0.00023084045,0.008463077,0.005244394,0.0019717275,0.019583702,0.8581417,0.00017661705],"about_ca_topic_score_codex":0.97153676,"about_ca_topic_score_gemma":0.98449755,"teacher_disagreement_score":0.83641416,"about_ca_system_score_codex":0.16358584,"about_ca_system_score_gemma":0.42860642,"threshold_uncertainty_score":0.97012186},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988193,0.000022160499,0.00016831837,0.00005753705,0.0000018795618,0.000058728576,0.0000060671605,0.0000040306377,0.00086192274],"genre_scores_gemma":[0.9991536,0.000026626702,0.0004816443,0.000030110721,0.00000280405,0.00007144114,0.00001138729,0.0000018027192,0.00022057763],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9761721,0.017937828,0.00075502566,0.00090766966,0.0017284192,0.0024990297],"domain_scores_gemma":[0.87796223,0.07186505,0.014158406,0.0064716344,0.019654142,0.009888516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025815103,0.00033756965,0.00027237163,0.001041308,0.003744675,0.0021287773,0.0014668412,0.0007234177,0.0029005047],"category_scores_gemma":[0.0632002,0.00057680055,0.0002895893,0.00065358565,0.0024022448,0.0014387517,0.0023968755,0.0016354807,0.00038550163],"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":[0.0013999403,0.01691382,0.56937367,0.0007544888,0.00018796128,0.0008119243,0.23538657,0.0015600034,0.0068398756,0.0014267637,0.0020783911,0.16326655],"study_design_scores_gemma":[0.00031490804,0.010524827,0.68309563,0.00042003242,0.0001026438,0.00037281113,0.28563353,0.0027330688,0.006841015,0.0005505122,0.009281681,0.00012928774],"about_ca_topic_score_codex":0.009282048,"about_ca_topic_score_gemma":0.014984841,"teacher_disagreement_score":0.025815103,"about_ca_system_score_codex":0.0034995603,"about_ca_system_score_gemma":0.00862353,"threshold_uncertainty_score":0.13652492},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14791556,0.023464592,0.031163575,0.4406171,0.0007179286,0.0015993774,0.000079547855,0.00016524534,0.35427713],"genre_scores_gemma":[0.96145916,0.0059106466,0.014508014,0.008178806,0.00019618907,0.0013169628,0.000025276615,0.0000888155,0.008316094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.86281,0.120226786,0.0014825509,0.0018336353,0.008305597,0.0053414577],"domain_scores_gemma":[0.86168414,0.12326635,0.0020751855,0.0025453386,0.006244695,0.004184265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11440589,0.0004376088,0.00073312555,0.0018750795,0.01657893,0.012275865,0.0028502145,0.0036573033,0.002881603],"category_scores_gemma":[0.06990275,0.00052317197,0.0005812797,0.0017718357,0.040139567,0.0065839184,0.012417509,0.007959238,0.0001779829],"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":[0.0002194756,0.0007138069,0.0052757245,0.0011056021,0.000054019165,0.0006879563,0.18760332,0.0025155444,0.00024095211,0.53758925,0.024748554,0.23924586],"study_design_scores_gemma":[0.0005697805,0.0006428216,0.027810274,0.006620818,0.00013506925,0.00048230262,0.2817785,0.004818689,0.0016737647,0.2132202,0.46196815,0.00027968484],"about_ca_topic_score_codex":0.2194252,"about_ca_topic_score_gemma":0.41494521,"teacher_disagreement_score":0.7805748,"about_ca_system_score_codex":0.060684178,"about_ca_system_score_gemma":0.08575929,"threshold_uncertainty_score":0.6050434},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13328937,0.47091603,0.0026245464,0.10227308,0.017134896,0.000980063,0.035424933,0.0008510211,0.23650604],"genre_scores_gemma":[0.5032083,0.37632537,0.0072561554,0.008393533,0.0036894828,0.0004023476,0.009028038,0.00041602386,0.09128072],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9792164,0.002271401,0.0016344601,0.0007108988,0.014132466,0.0020343142],"domain_scores_gemma":[0.7932322,0.025953218,0.0121346675,0.0023714588,0.1572644,0.009044044],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.013752905,0.0008279095,0.0010796998,0.039771855,0.0061093,0.012317696,0.0012469711,0.0009547576,0.011966374],"category_scores_gemma":[0.07836136,0.0005103849,0.00072266976,0.07263093,0.0021566758,0.00243422,0.002263975,0.0014073477,0.0013363633],"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":[0.00061304204,0.00016582526,0.043134872,0.012267698,0.00028990605,0.0013548128,0.014404199,0.0006324756,0.002264576,0.009488835,0.35572687,0.5596569],"study_design_scores_gemma":[0.000026797681,0.000098466415,0.13021034,0.006586279,0.0002106519,0.000452544,0.010634871,0.0002148435,0.0020324502,0.00075285335,0.8486638,0.000116099276],"about_ca_topic_score_codex":0.81893736,"about_ca_topic_score_gemma":0.9176964,"teacher_disagreement_score":0.9862471,"about_ca_system_score_codex":0.048256643,"about_ca_system_score_gemma":0.20109467,"threshold_uncertainty_score":0.36425787},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08735348,0.18977617,0.0066053844,0.5984897,0.003163983,0.00091428723,0.0007425468,0.00039692086,0.112557516],"genre_scores_gemma":[0.8323859,0.093599394,0.01863761,0.029886292,0.00097564555,0.00042900274,0.0006024138,0.00019866388,0.023285093],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9406428,0.021041576,0.003103721,0.0017636233,0.024421886,0.009026441],"domain_scores_gemma":[0.82354265,0.045295157,0.0057719643,0.0024671499,0.09553846,0.027384594],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07108818,0.00070178905,0.0012252172,0.0059498562,0.013692581,0.017395679,0.0039831325,0.0029928687,0.004789586],"category_scores_gemma":[0.070773035,0.0005737079,0.0009409909,0.008214218,0.0110410545,0.0045762463,0.008374476,0.0041241054,0.00032352345],"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":[0.0003956318,0.00047253328,0.026651202,0.0046257223,0.00020058069,0.0005357727,0.01378448,0.0018775787,0.00042815713,0.100749895,0.09942221,0.75085616],"study_design_scores_gemma":[0.00024557073,0.0008328798,0.15633567,0.01838,0.00025277297,0.00060728233,0.07270643,0.0052850717,0.002624099,0.03715588,0.70502955,0.0005447658],"about_ca_topic_score_codex":0.96633786,"about_ca_topic_score_gemma":0.9721376,"teacher_disagreement_score":0.9289118,"about_ca_system_score_codex":0.22502282,"about_ca_system_score_gemma":0.4947649,"threshold_uncertainty_score":0.8988637},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105188094,0.07331518,0.05484761,0.46495983,0.0023314697,0.0013922777,0.0017443782,0.0003646486,0.29585657],"genre_scores_gemma":[0.93367463,0.008676417,0.023775414,0.009663273,0.000377461,0.0010060223,0.0003004164,0.00007822493,0.022448111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8555624,0.10354166,0.003928179,0.0027467757,0.029702738,0.004518235],"domain_scores_gemma":[0.8203124,0.1286358,0.0044456027,0.0050325897,0.038599554,0.002974193],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10296227,0.00077922683,0.001190008,0.0033467046,0.0051556183,0.014325748,0.002310881,0.0034811308,0.0055618673],"category_scores_gemma":[0.14516272,0.0005127239,0.00083447853,0.0038111743,0.008744864,0.004943644,0.002870491,0.0045867697,0.000299939],"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":true,"study_design_scores_codex":[0.00048633124,0.00023880498,0.0123858815,0.0035004965,0.00048548,0.0002805737,0.004881867,0.019522727,0.00080506806,0.6726613,0.047333956,0.23741753],"study_design_scores_gemma":[0.00086084974,0.0009129391,0.09100897,0.017537942,0.0005890562,0.00024146432,0.01044513,0.04379198,0.0052245134,0.25063702,0.5782811,0.00046905645],"about_ca_topic_score_codex":0.90076786,"about_ca_topic_score_gemma":0.8946522,"teacher_disagreement_score":0.89703774,"about_ca_system_score_codex":0.13913907,"about_ca_system_score_gemma":0.17542313,"threshold_uncertainty_score":0.9984767},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06804227,0.08868457,0.07445431,0.7318006,0.0032443053,0.0019204833,0.000113319365,0.00066993263,0.031070186],"genre_scores_gemma":[0.77778584,0.03579507,0.13603397,0.040928554,0.0015345458,0.002648434,0.000079075544,0.00026939437,0.0049251486],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.68224657,0.27599293,0.009094464,0.0035494603,0.023488652,0.005627943],"domain_scores_gemma":[0.33863306,0.53411674,0.012267459,0.01688073,0.08451486,0.013587149],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35738865,0.0012623841,0.0017246463,0.003855799,0.00911328,0.015086489,0.0057115965,0.0066329297,0.0026527317],"category_scores_gemma":[0.35783193,0.0012814763,0.0014623062,0.0026381337,0.015794624,0.017175285,0.013350142,0.01327816,0.0005925368],"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":[0.00076283293,0.001113998,0.016407607,0.005866358,0.00020349302,0.0012780043,0.053452328,0.0029726296,0.00035115235,0.059389688,0.04203808,0.81616384],"study_design_scores_gemma":[0.0017041964,0.0030686134,0.047766387,0.05533019,0.000513076,0.004105741,0.15373553,0.015038676,0.0056892703,0.2980651,0.41384646,0.0011367033],"about_ca_topic_score_codex":0.032482494,"about_ca_topic_score_gemma":0.055835545,"teacher_disagreement_score":0.6426114,"about_ca_system_score_codex":0.019611448,"about_ca_system_score_gemma":0.06721988,"threshold_uncertainty_score":0.79245424},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015150067,0.0028178198,0.0006331058,0.17370543,0.799202,0.000062160994,0.0003851914,0.00029359653,0.02274924],"genre_scores_gemma":[0.0037147817,0.005350847,0.0022436685,0.28294617,0.43091407,0.00024771102,0.0006327707,0.0007628571,0.27318704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98686975,0.0012863125,0.0012986967,0.0023791802,0.00684538,0.0013206964],"domain_scores_gemma":[0.9485488,0.007732955,0.0025348614,0.003701853,0.032353837,0.0051277736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009801211,0.0017397278,0.0014697389,0.0034399556,0.0043442217,0.012406035,0.004849035,0.011649046,0.14512321],"category_scores_gemma":[0.07096635,0.0007382456,0.0023669829,0.0027235784,0.0025404696,0.008683663,0.0045414036,0.013323945,0.103916034],"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":[0.000010106271,0.000007463611,0.000038941507,0.00007396696,0.000003514489,0.00006263626,0.000038014623,0.000016317425,0.000054880362,0.0013480292,0.99087733,0.007468728],"study_design_scores_gemma":[0.0000050316903,0.0000050314075,0.00007331655,0.00012503185,0.0000028838765,0.00007061248,0.000069919915,0.00002346124,0.000083152096,0.0006709051,0.9988631,0.0000074848085],"about_ca_topic_score_codex":0.0022986159,"about_ca_topic_score_gemma":0.0043702987,"teacher_disagreement_score":0.14512321,"about_ca_system_score_codex":0.004571151,"about_ca_system_score_gemma":0.008785435,"threshold_uncertainty_score":0.4854855},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01426341,0.030530225,0.023984585,0.18618177,0.5184828,0.007788865,0.0071812915,0.007648211,0.20393886],"genre_scores_gemma":[0.06067723,0.023228126,0.0378653,0.023918798,0.14462148,0.0040375446,0.0078041838,0.004696654,0.6931508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9711604,0.007982126,0.0022346198,0.0013595475,0.016024506,0.0012388257],"domain_scores_gemma":[0.68648857,0.015823957,0.008565571,0.006435243,0.26817083,0.014515893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020319872,0.0013828981,0.0022305239,0.008370513,0.0036517975,0.007231802,0.0022984662,0.0029141728,0.1357425],"category_scores_gemma":[0.1169099,0.00074437185,0.0012393686,0.004777718,0.001236823,0.0029049541,0.0025661439,0.0024230718,0.085240826],"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":[0.000047723115,0.00001927863,0.00041060822,0.00028092175,0.000010213231,0.00005871858,0.00006799687,0.000020738431,0.00033614767,0.00023140323,0.9582965,0.040219814],"study_design_scores_gemma":[0.0000437286,0.00008272306,0.0036396915,0.00053818605,0.000024209736,0.00031233174,0.00026789366,0.00032632504,0.00062224985,0.00067193975,0.9934355,0.000035183526],"about_ca_topic_score_codex":0.0032193412,"about_ca_topic_score_gemma":0.011592816,"teacher_disagreement_score":0.1357425,"about_ca_system_score_codex":0.0022107773,"about_ca_system_score_gemma":0.011944901,"threshold_uncertainty_score":0.4541039},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035915997,0.008623664,0.7875485,0.09559957,0.00033039,0.0010638521,0.0003231409,0.0005332466,0.070061654],"genre_scores_gemma":[0.5495127,0.0036930093,0.43884346,0.0036921815,0.00026208803,0.0018106318,0.00023283999,0.00012312648,0.0018299634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.83762866,0.14902061,0.0025070903,0.001702791,0.0076830997,0.0014577139],"domain_scores_gemma":[0.56654334,0.40036082,0.007638621,0.005654497,0.017163852,0.0026387998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11063437,0.0014708632,0.0023309195,0.006006106,0.0039119683,0.017431365,0.0035935545,0.003900321,0.0049617956],"category_scores_gemma":[0.2325443,0.0012367954,0.0015528181,0.005197979,0.020192502,0.023511413,0.007228509,0.007977723,0.00046793048],"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":[0.00011605528,0.00012445833,0.0015196075,0.0005606399,0.00007074548,0.00009797405,0.0015416179,0.032582894,0.00007774511,0.9154327,0.0030325167,0.044843078],"study_design_scores_gemma":[0.00008100703,0.000057257384,0.0001711922,0.00057872274,0.00003127528,0.00002304015,0.0010992627,0.058199972,0.00016134494,0.9340514,0.0055110184,0.000034528304],"about_ca_topic_score_codex":0.0313589,"about_ca_topic_score_gemma":0.029856874,"teacher_disagreement_score":0.11063437,"about_ca_system_score_codex":0.028512713,"about_ca_system_score_gemma":0.031260237,"threshold_uncertainty_score":0.58509743},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15633462,0.00025828995,0.7568213,0.014749601,0.00037888144,0.002181063,0.00012994684,0.0028304516,0.06631594],"genre_scores_gemma":[0.34985834,0.0005125292,0.6360174,0.0015548735,0.00013955099,0.0020667096,0.00025326334,0.00032741812,0.009269984],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9811933,0.015402426,0.0003172448,0.000801176,0.0015980073,0.0006878796],"domain_scores_gemma":[0.941784,0.047085077,0.00166306,0.0032040507,0.0032356554,0.003028233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021292537,0.0013368891,0.0005395665,0.0015445931,0.0023585428,0.0066589066,0.0030332764,0.002313236,0.012139504],"category_scores_gemma":[0.04848566,0.00073759054,0.0009366276,0.0009986645,0.002606616,0.008690548,0.00987584,0.0045305924,0.0028232208],"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":[0.0007590596,0.009188925,0.007040577,0.0015972327,0.00006533417,0.0014339549,0.12599272,0.01463026,0.012210256,0.085520476,0.0603227,0.6812385],"study_design_scores_gemma":[0.0013263951,0.004943251,0.006399428,0.004282466,0.00018560071,0.0023787306,0.09157533,0.14208965,0.030556928,0.28948864,0.42624712,0.0005264465],"about_ca_topic_score_codex":0.00095911336,"about_ca_topic_score_gemma":0.0016276583,"teacher_disagreement_score":0.021292537,"about_ca_system_score_codex":0.0022853937,"about_ca_system_score_gemma":0.0051067546,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041917935,0.0014833929,0.013133563,0.8178988,0.0047844136,0.0006423848,0.00008948836,0.00043927575,0.11961077],"genre_scores_gemma":[0.8212199,0.0030474574,0.020340625,0.06973874,0.004606206,0.0008470131,0.00025081798,0.00022080845,0.07972834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95735526,0.018577978,0.0011198375,0.0013866669,0.011016915,0.010543383],"domain_scores_gemma":[0.7867095,0.061912365,0.013017939,0.010017891,0.057788555,0.07055376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065220594,0.00040540544,0.00044004296,0.002030729,0.014902681,0.021382933,0.0027849306,0.007434697,0.014253767],"category_scores_gemma":[0.09983563,0.00047117705,0.0005277512,0.0015524529,0.008816408,0.008949721,0.013332291,0.00906067,0.001862876],"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":[0.00008821533,0.00047453187,0.012171293,0.0004130187,0.000032632423,0.0009452122,0.016220164,0.0019090826,0.0011918795,0.34244785,0.44256896,0.18153709],"study_design_scores_gemma":[0.00009616759,0.00015692125,0.009390992,0.00083327934,0.000014862099,0.00032747394,0.03525698,0.002070157,0.0012320509,0.12157651,0.82892734,0.00011724089],"about_ca_topic_score_codex":0.032846626,"about_ca_topic_score_gemma":0.067346625,"teacher_disagreement_score":0.065220594,"about_ca_system_score_codex":0.023446733,"about_ca_system_score_gemma":0.15239277,"threshold_uncertainty_score":0.34492362},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021833573,0.0058138324,0.79757,0.031560045,0.0005402861,0.037085224,0.0016940965,0.0007677663,0.10313519],"genre_scores_gemma":[0.12365363,0.0008923991,0.850735,0.0011976673,0.00008218567,0.01896292,0.0004475704,0.000041434112,0.0039872397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.83340037,0.13191012,0.009484444,0.0028598672,0.019293081,0.003052137],"domain_scores_gemma":[0.92365825,0.04128277,0.0038161462,0.0014750249,0.027463969,0.0023038443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1529129,0.0018440877,0.0018634514,0.0122339325,0.0052117235,0.012157021,0.0034228375,0.0038055768,0.0062782713],"category_scores_gemma":[0.08315117,0.00084674725,0.002178412,0.005489175,0.0046111955,0.0065620854,0.004634038,0.0034798607,0.0008784659],"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":[0.00044519224,0.00090157625,0.0032252127,0.0020518801,0.00014715435,0.00031749438,0.0031513902,0.03903068,0.00057234406,0.7757938,0.02132255,0.15304069],"study_design_scores_gemma":[0.0018061362,0.004490494,0.0075035812,0.015441978,0.00059724035,0.00045694024,0.013263072,0.2931352,0.0039710207,0.45502675,0.20375411,0.0005535219],"about_ca_topic_score_codex":0.036297362,"about_ca_topic_score_gemma":0.040797107,"teacher_disagreement_score":0.1529129,"about_ca_system_score_codex":0.0394933,"about_ca_system_score_gemma":0.052401006,"threshold_uncertainty_score":0.80869037},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26779166,0.06977011,0.011424125,0.5181228,0.0021481416,0.0005577259,0.00046300446,0.0005046148,0.12921777],"genre_scores_gemma":[0.95619905,0.011206483,0.007118754,0.012720135,0.0001361078,0.00010627629,0.0001112509,0.00014002994,0.012261916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95343316,0.018737558,0.0023407356,0.002720642,0.015122498,0.0076453686],"domain_scores_gemma":[0.8678962,0.029023584,0.005405185,0.0029405002,0.072322644,0.022411903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0414603,0.00036979123,0.0008504559,0.003753958,0.028604334,0.015683386,0.0038173923,0.0028535775,0.0036611718],"category_scores_gemma":[0.081521794,0.00065036793,0.0004701882,0.007945572,0.014670587,0.0036056838,0.0074982573,0.00419044,0.00027350645],"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":[0.00048268784,0.00031890365,0.08389584,0.0022693449,0.00017354108,0.0019540507,0.13380314,0.0023721268,0.0017829849,0.0701118,0.15566854,0.54716706],"study_design_scores_gemma":[0.00007907645,0.00020220494,0.16957715,0.004248861,0.000120051576,0.0005325184,0.23327696,0.003307701,0.0017085663,0.016572993,0.56996477,0.00040914086],"about_ca_topic_score_codex":0.97932005,"about_ca_topic_score_gemma":0.9874286,"teacher_disagreement_score":0.7795285,"about_ca_system_score_codex":0.22047152,"about_ca_system_score_gemma":0.4262967,"threshold_uncertainty_score":0.90414256},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67776185,0.008318827,0.016902953,0.051694866,0.0004592322,0.0027140903,0.0010495677,0.00033395234,0.24076472],"genre_scores_gemma":[0.96231836,0.003921584,0.01868228,0.001823765,0.0000406154,0.00035752376,0.00017239491,0.000041512594,0.012642011],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98600996,0.0057435143,0.0004466476,0.0003524893,0.0040389886,0.0034083712],"domain_scores_gemma":[0.98718923,0.0033984066,0.00045852744,0.0003161512,0.006464973,0.0021727711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006715495,0.0006960014,0.00063426327,0.002252575,0.01949128,0.0050747255,0.0022971272,0.0038214254,0.0024509367],"category_scores_gemma":[0.013642706,0.00035820933,0.00076933036,0.007479338,0.003519831,0.0011627022,0.0032985243,0.0028068612,0.0002585755],"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":[0.0008732962,0.0037259602,0.12005438,0.0028521798,0.00025904118,0.095538735,0.123581946,0.041955676,0.0028969531,0.19970731,0.08569396,0.3228606],"study_design_scores_gemma":[0.00060064666,0.0015367853,0.12054501,0.0034505676,0.0004834734,0.01751044,0.28396267,0.04466803,0.006929276,0.021449301,0.49837056,0.0004932442],"about_ca_topic_score_codex":0.9652263,"about_ca_topic_score_gemma":0.9825832,"teacher_disagreement_score":0.9080779,"about_ca_system_score_codex":0.091922104,"about_ca_system_score_gemma":0.11910085,"threshold_uncertainty_score":0.6669447},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3166333,0.004351654,0.18927376,0.32980728,0.0036093753,0.011039301,0.00014368644,0.004115926,0.14102572],"genre_scores_gemma":[0.6604341,0.002683945,0.28882614,0.014030714,0.000885881,0.0050797765,0.000100301506,0.00024378973,0.027715286],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94006246,0.04655019,0.0023993521,0.0015034069,0.005568607,0.0039159274],"domain_scores_gemma":[0.88055193,0.043475352,0.009642871,0.008723272,0.023276461,0.03433007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08626521,0.0011521045,0.00053267187,0.002653029,0.009596082,0.00998917,0.0044807186,0.0045630196,0.0104048615],"category_scores_gemma":[0.11938839,0.00069875125,0.00084564945,0.001234063,0.0039913966,0.0057616397,0.020099597,0.0061281836,0.003127837],"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":[0.0001880758,0.002514324,0.013042257,0.00064757233,0.000050731604,0.0017336993,0.13214183,0.0006556004,0.0022434858,0.009140532,0.072595626,0.76504624],"study_design_scores_gemma":[0.00040938228,0.0031987021,0.021285484,0.0044045206,0.00013213365,0.0038372823,0.5211771,0.004577505,0.007896773,0.03661672,0.39598906,0.00047533924],"about_ca_topic_score_codex":0.001645405,"about_ca_topic_score_gemma":0.006382902,"teacher_disagreement_score":0.08626521,"about_ca_system_score_codex":0.0047087725,"about_ca_system_score_gemma":0.022203691,"threshold_uncertainty_score":0.4562195},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09028004,0.08551733,0.67350215,0.046877366,0.0018110862,0.01163848,0.0027475301,0.0036299308,0.08399603],"genre_scores_gemma":[0.13810858,0.011644207,0.84396154,0.0012007155,0.0001063167,0.0031884322,0.00044599109,0.00011897088,0.0012252146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8711482,0.07261737,0.01265225,0.0027661698,0.039837502,0.0009784382],"domain_scores_gemma":[0.75559145,0.14452621,0.014639815,0.011657592,0.07156159,0.002023294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1680062,0.0028255763,0.004129073,0.031794105,0.0027373936,0.013272027,0.0059489817,0.003953441,0.00423664],"category_scores_gemma":[0.22856022,0.0012083787,0.0030907951,0.014078718,0.0034968508,0.007193866,0.0042781984,0.0036179759,0.0019958292],"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":[0.00050580094,0.0014064412,0.029953917,0.023084758,0.0017144355,0.00040922276,0.0043193162,0.00884143,0.002016489,0.030396199,0.012250124,0.8851019],"study_design_scores_gemma":[0.0023794195,0.0067279567,0.10427959,0.18783867,0.008337312,0.0032450173,0.051651806,0.07186404,0.029532813,0.29463288,0.23828864,0.0012218674],"about_ca_topic_score_codex":0.008672764,"about_ca_topic_score_gemma":0.012845691,"teacher_disagreement_score":0.1680062,"about_ca_system_score_codex":0.008723243,"about_ca_system_score_gemma":0.018504601,"threshold_uncertainty_score":0.8885123},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009184559,0.0022009404,0.0003145359,0.3047094,0.68706834,0.00005000053,0.00019157332,0.00019112203,0.0051821745],"genre_scores_gemma":[0.0022009127,0.0040362803,0.0012687101,0.5438503,0.38466963,0.00018896985,0.00023494677,0.000336529,0.06321369],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98639804,0.0014326479,0.0012075789,0.0020340849,0.0075227884,0.0014048201],"domain_scores_gemma":[0.9367948,0.0109830005,0.0028004327,0.0027258536,0.03869456,0.008001283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013626744,0.001771624,0.0018864486,0.0023863271,0.0045066834,0.009936625,0.006091698,0.018247591,0.06098552],"category_scores_gemma":[0.104374304,0.0007442502,0.0029013776,0.0020579454,0.0036832935,0.0073754336,0.0038442547,0.021706004,0.03935422],"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":[0.000009232716,0.000006918033,0.000042991785,0.000052641994,0.0000031756722,0.000048678783,0.000028928025,0.000015282556,0.000023386023,0.0005196376,0.9949157,0.0043333815],"study_design_scores_gemma":[0.000007943433,0.0000078859775,0.0001331231,0.00014834636,0.000004244756,0.00007999877,0.0000815392,0.000033167533,0.000055191755,0.0005412541,0.99889356,0.0000137609995],"about_ca_topic_score_codex":0.007841386,"about_ca_topic_score_gemma":0.015200086,"teacher_disagreement_score":0.06098552,"about_ca_system_score_codex":0.006231911,"about_ca_system_score_gemma":0.014106497,"threshold_uncertainty_score":0.20401686},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005974466,0.9958228,0.0010258957,0.0012555921,0.0001141284,0.000018816045,0.00001585614,0.000005158822,0.0011442992],"genre_scores_gemma":[0.0117623955,0.9857348,0.0017614608,0.00040694143,0.00013089433,0.000065454136,0.000022324295,0.0000049872747,0.0001106727],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98690027,0.0066268495,0.002037454,0.00092519727,0.0032055848,0.0003047224],"domain_scores_gemma":[0.8633461,0.11880514,0.0048172106,0.0015913601,0.010817832,0.0006223974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028768942,0.0010653457,0.0033491992,0.022223797,0.0016553702,0.007738108,0.0022188872,0.002386074,0.0022885099],"category_scores_gemma":[0.05061668,0.00093030406,0.0009372753,0.032476448,0.0049433256,0.006564529,0.0024334048,0.0021805926,0.0004883645],"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":[0.0000498778,0.00010127401,0.0017395593,0.09200201,0.00032674073,0.00022796934,0.005080316,0.0005637713,0.0003943204,0.010035025,0.0048125624,0.88466656],"study_design_scores_gemma":[0.00004231523,0.00024148727,0.015189089,0.4662342,0.0015343052,0.001426686,0.021760132,0.0009242818,0.0014688915,0.024093226,0.4669188,0.00016662231],"about_ca_topic_score_codex":0.014517844,"about_ca_topic_score_gemma":0.03136452,"teacher_disagreement_score":0.028768942,"about_ca_system_score_codex":0.0070049725,"about_ca_system_score_gemma":0.022718808,"threshold_uncertainty_score":0.15214652},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021988653,0.023541307,0.020794347,0.25866792,0.46503258,0.010751965,0.008872881,0.0074734567,0.18287696],"genre_scores_gemma":[0.07399514,0.024224728,0.054838832,0.05025235,0.10016009,0.00578446,0.010561267,0.0037676864,0.67641544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96738875,0.006770847,0.003421316,0.001885488,0.01910372,0.0014297826],"domain_scores_gemma":[0.67592156,0.015821204,0.010316445,0.006025712,0.27340665,0.018508323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028351687,0.0011839635,0.0019217499,0.006455371,0.0040864414,0.009072614,0.0021384412,0.003711586,0.11312512],"category_scores_gemma":[0.11600365,0.00076797017,0.0015751242,0.003781685,0.0017357277,0.0035915955,0.003126972,0.0036442655,0.07036998],"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":[0.00015380983,0.000038666698,0.0009352689,0.00039812608,0.00002369125,0.00009147202,0.00017186797,0.00003626713,0.00058053894,0.0003676054,0.95620644,0.04099619],"study_design_scores_gemma":[0.00011577779,0.00018258159,0.005698478,0.00062306947,0.00005287899,0.00025511868,0.00060724345,0.00034070938,0.00097098964,0.0008419214,0.9902519,0.000059396545],"about_ca_topic_score_codex":0.005143807,"about_ca_topic_score_gemma":0.020050243,"teacher_disagreement_score":0.99724364,"about_ca_system_score_codex":0.002756339,"about_ca_system_score_gemma":0.02591227,"threshold_uncertainty_score":0.3784412},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23034425,0.009731822,0.2395965,0.346315,0.0035310616,0.01765434,0.0003257014,0.001137399,0.15136403],"genre_scores_gemma":[0.8073453,0.001862777,0.15296632,0.018269299,0.000500769,0.01118786,0.00018034304,0.00034048245,0.007346862],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.35301426,0.60245615,0.0074095097,0.0038636196,0.02308621,0.010170262],"domain_scores_gemma":[0.5126684,0.38036805,0.012647475,0.020591417,0.057790395,0.015934326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.43329552,0.0016615277,0.0019597355,0.0030051286,0.015905883,0.020456092,0.0063143163,0.010579509,0.0051660696],"category_scores_gemma":[0.29199874,0.0014920223,0.0021587363,0.0029863764,0.012288,0.013322654,0.023163995,0.012208789,0.0012582114],"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":[0.0021190685,0.007102436,0.0139512,0.0054339743,0.00040503303,0.0022786707,0.10357945,0.0065709497,0.001562412,0.102302656,0.041640818,0.7130534],"study_design_scores_gemma":[0.004610161,0.010818732,0.027699567,0.027272236,0.0006476526,0.002117084,0.22377582,0.025267404,0.0109389145,0.3690916,0.296854,0.00090695167],"about_ca_topic_score_codex":0.010449612,"about_ca_topic_score_gemma":0.014304628,"teacher_disagreement_score":0.9755508,"about_ca_system_score_codex":0.024449257,"about_ca_system_score_gemma":0.09463937,"threshold_uncertainty_score":0.69884753},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27684182,0.04169432,0.036317296,0.36998945,0.0032188783,0.001269047,0.00021275465,0.0007069956,0.26974937],"genre_scores_gemma":[0.9246249,0.010419329,0.031663697,0.016299123,0.0004741495,0.00017596953,0.00014123942,0.00007248221,0.016129002],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94227874,0.03276136,0.0015791329,0.0015116467,0.01704665,0.004822525],"domain_scores_gemma":[0.953581,0.014939484,0.0018040119,0.002454865,0.021848582,0.0053720116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040680934,0.0003621779,0.00041444768,0.0029236653,0.0075915256,0.013824953,0.0026215194,0.0029505992,0.0013977428],"category_scores_gemma":[0.029932601,0.00028655858,0.00036057184,0.004320791,0.0152125675,0.00324851,0.006078764,0.0031242187,0.00013540828],"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":[0.00031730896,0.00033726537,0.027417604,0.0017446711,0.00009251794,0.0010714612,0.033101562,0.008560936,0.0026964794,0.19693677,0.04834745,0.67937607],"study_design_scores_gemma":[0.00018133523,0.00047206134,0.13182235,0.0040547005,0.00017778586,0.00076294586,0.09494033,0.008895115,0.00435484,0.0709081,0.68297356,0.0004568303],"about_ca_topic_score_codex":0.8401447,"about_ca_topic_score_gemma":0.9171151,"teacher_disagreement_score":0.8733185,"about_ca_system_score_codex":0.12668149,"about_ca_system_score_gemma":0.18053994,"threshold_uncertainty_score":0.91914284},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9379852,0.002551616,0.0006768134,0.017845988,0.00017080519,0.0016344379,0.0031098446,0.00024667758,0.035778508],"genre_scores_gemma":[0.9544093,0.001041397,0.0016391968,0.0042103217,0.000030604053,0.00058822124,0.0015791304,0.00004903473,0.03645274],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937849,0.0014380717,0.00027540445,0.00032043896,0.0020865477,0.00209458],"domain_scores_gemma":[0.9645117,0.004108152,0.0018799468,0.00063768594,0.019340048,0.009522616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052549616,0.00031992138,0.0003860231,0.002250819,0.0062878584,0.0031355005,0.0022208337,0.0010685332,0.004812965],"category_scores_gemma":[0.01630205,0.00045459726,0.00018443902,0.003389194,0.0017918907,0.0008311768,0.0037084275,0.0023388248,0.0006533677],"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":[0.002907067,0.0031059633,0.43777475,0.0012442605,0.00021213529,0.0018947484,0.016257595,0.00289797,0.0026850281,0.0052663656,0.15261187,0.37314224],"study_design_scores_gemma":[0.00022957324,0.0006397496,0.89529586,0.0004732633,0.00009234256,0.0001664244,0.025312146,0.0016444818,0.0017415872,0.00047438935,0.07383695,0.00009329378],"about_ca_topic_score_codex":0.9638356,"about_ca_topic_score_gemma":0.98586214,"teacher_disagreement_score":0.9638356,"about_ca_system_score_codex":0.10591988,"about_ca_system_score_gemma":0.16727692,"threshold_uncertainty_score":0.76850617},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57235616,0.015518112,0.002462591,0.27216455,0.00050652743,0.001168809,0.00060949154,0.00026757136,0.13494611],"genre_scores_gemma":[0.92586255,0.0050422177,0.0055314936,0.008582468,0.000079222365,0.00038378782,0.0002466667,0.00004521856,0.054226313],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9883909,0.0037286538,0.0008138903,0.00051969546,0.0034105578,0.0031362218],"domain_scores_gemma":[0.93125635,0.021597631,0.0024664612,0.0016419443,0.029742064,0.013295602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01656867,0.00013975064,0.00026518808,0.0015250578,0.013878559,0.007527095,0.0024020907,0.0026601686,0.00516854],"category_scores_gemma":[0.032722253,0.0005105131,0.00021037876,0.00252634,0.0062192767,0.0014227051,0.0041555376,0.0027839574,0.00036665003],"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":[0.0008067348,0.00074990594,0.18525527,0.0033620365,0.00017658694,0.004364153,0.12461865,0.0075083277,0.0041139806,0.16168754,0.17505418,0.33230266],"study_design_scores_gemma":[0.00014506587,0.0003303021,0.3184354,0.0027666225,0.00006705012,0.000550318,0.1819204,0.003741195,0.0027159275,0.009607398,0.47953406,0.00018637383],"about_ca_topic_score_codex":0.94429755,"about_ca_topic_score_gemma":0.9564343,"teacher_disagreement_score":0.8784646,"about_ca_system_score_codex":0.12153545,"about_ca_system_score_gemma":0.3734533,"threshold_uncertainty_score":0.88180554},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70744306,0.12580849,0.0012209333,0.12465866,0.00037676765,0.00016931229,0.00032928705,0.00011187678,0.03988151],"genre_scores_gemma":[0.94178724,0.047176376,0.0018665291,0.0038993184,0.00012472869,0.000059258913,0.00016996634,0.000016764203,0.0048998534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9916761,0.003821917,0.0003786893,0.00030570684,0.0021943133,0.0016232972],"domain_scores_gemma":[0.9582844,0.010259605,0.0052760723,0.0006413208,0.01914123,0.0063973283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012054745,0.00018580772,0.00026700457,0.0032170513,0.0048197233,0.0059867566,0.0012978838,0.0008896035,0.0021216634],"category_scores_gemma":[0.018593144,0.00031498013,0.00024350086,0.006469295,0.0029122338,0.0014630342,0.0020393382,0.00153056,0.00019421834],"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":[0.0003008432,0.00059780304,0.51356715,0.003022643,0.00018133954,0.00091996574,0.027087452,0.001345597,0.0017370917,0.010184938,0.0133025935,0.42775247],"study_design_scores_gemma":[0.000033809156,0.00048178114,0.7987017,0.0039736466,0.000103242026,0.00066911784,0.06488622,0.00089754886,0.001275142,0.0011879742,0.12769476,0.00009513261],"about_ca_topic_score_codex":0.6264371,"about_ca_topic_score_gemma":0.80511636,"teacher_disagreement_score":0.9517466,"about_ca_system_score_codex":0.048253443,"about_ca_system_score_gemma":0.12224995,"threshold_uncertainty_score":0.7515257},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101666994,0.035560716,0.13950089,0.42613184,0.003961268,0.00036087693,0.00012207302,0.0002876786,0.29240778],"genre_scores_gemma":[0.920054,0.010343784,0.027488101,0.015157294,0.0010392965,0.00035212518,0.000075753625,0.00034849162,0.025141202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.608226,0.33001524,0.008260268,0.008511296,0.04004351,0.0049437503],"domain_scores_gemma":[0.5609182,0.33601087,0.014118421,0.018368904,0.06388389,0.006699803],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.20898621,0.0014330716,0.0016619088,0.009231237,0.023208285,0.044637434,0.005008131,0.014223315,0.0054541845],"category_scores_gemma":[0.22842641,0.00086848193,0.0014579806,0.006630014,0.06962361,0.029670456,0.018077984,0.016366206,0.0013653712],"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":[0.00008291851,0.000053335327,0.0015531091,0.000541575,0.000048714046,0.00077192823,0.40667585,0.00040641465,0.00071678706,0.54784584,0.006709047,0.0345944],"study_design_scores_gemma":[0.000044294717,0.0001008184,0.0019193796,0.0036420056,0.00007067443,0.0007881194,0.36735708,0.0014321225,0.0013719182,0.17139205,0.45173317,0.00014841791],"about_ca_topic_score_codex":0.05857982,"about_ca_topic_score_gemma":0.05927814,"teacher_disagreement_score":0.97679174,"about_ca_system_score_codex":0.038041674,"about_ca_system_score_gemma":0.037046842,"threshold_uncertainty_score":0.9754608},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010050366,0.010893583,0.76241046,0.091033325,0.0019116626,0.00072605774,0.000072748866,0.00027053413,0.12263132],"genre_scores_gemma":[0.56788665,0.008063321,0.39300996,0.0109943785,0.0021122284,0.0034604205,0.00009370441,0.00080090377,0.0135784885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7174971,0.24792866,0.0055784266,0.00574485,0.019836552,0.0034143613],"domain_scores_gemma":[0.56375355,0.39148563,0.0035934946,0.016247476,0.022956451,0.001963435],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23964888,0.0014250734,0.0020564417,0.008922871,0.008250631,0.022929596,0.0063835797,0.0072371033,0.00697528],"category_scores_gemma":[0.21049608,0.0013800918,0.0023172298,0.0068000495,0.074351944,0.029936627,0.016556732,0.014674041,0.0013994856],"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":[0.00001885318,0.000024415982,0.00039162143,0.00029306544,0.000020653391,0.000049897553,0.011956578,0.0003478204,0.00007822732,0.9544989,0.0020178573,0.030301953],"study_design_scores_gemma":[0.000023956994,0.000028939072,0.00037312388,0.0013796292,0.000013493569,0.00012163639,0.006638133,0.0021272902,0.00042357788,0.92773,0.06110235,0.00003779114],"about_ca_topic_score_codex":0.004086325,"about_ca_topic_score_gemma":0.0022017413,"teacher_disagreement_score":0.7603511,"about_ca_system_score_codex":0.0137039395,"about_ca_system_score_gemma":0.016292213,"threshold_uncertainty_score":0.9376483},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006181868,0.085918196,0.071784884,0.5264191,0.007543043,0.00040922614,0.00011481447,0.0001147478,0.3015141],"genre_scores_gemma":[0.81011033,0.04170438,0.04718464,0.065992996,0.010391277,0.0015539808,0.0000949084,0.00025018438,0.022717286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86022747,0.11782805,0.0032631278,0.0032281482,0.012325102,0.0031280888],"domain_scores_gemma":[0.7419045,0.2286951,0.0039896183,0.004076466,0.018774264,0.0025600863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10371626,0.0018851327,0.0013411005,0.008379459,0.012941957,0.026379084,0.0035432575,0.011677738,0.006269097],"category_scores_gemma":[0.10662824,0.00060685317,0.0011511786,0.004406982,0.09889882,0.021267075,0.009505519,0.015948253,0.000661045],"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":[0.000013000045,0.000014262609,0.000057338217,0.00023497212,0.000006074618,0.000048940718,0.0076808725,0.00016936404,0.000021745394,0.9794668,0.006253975,0.00603276],"study_design_scores_gemma":[0.000029651776,0.000027537175,0.00009844961,0.0019312075,0.000011011872,0.00009597991,0.009669893,0.0004098247,0.00021672541,0.8360851,0.15140381,0.000020846977],"about_ca_topic_score_codex":0.0068737348,"about_ca_topic_score_gemma":0.005398698,"teacher_disagreement_score":0.10371626,"about_ca_system_score_codex":0.03419914,"about_ca_system_score_gemma":0.016906913,"threshold_uncertainty_score":0.54851055},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.982337,0.000795675,0.007869649,0.0012245857,0.000054973716,0.001299936,0.0001956735,0.000038405375,0.0061840955],"genre_scores_gemma":[0.9925638,0.00015604662,0.006207662,0.000058121543,0.000012509751,0.00038938693,0.00016622282,0.000004047518,0.00044217973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93422437,0.043310393,0.0053526377,0.00081102544,0.014950161,0.0013512985],"domain_scores_gemma":[0.7898999,0.118546546,0.021837132,0.0046450472,0.061148755,0.0039225942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.100732446,0.0003833985,0.0005449968,0.002180603,0.0012972325,0.0014649057,0.0008085785,0.00042330692,0.0011487375],"category_scores_gemma":[0.18477301,0.00017256464,0.0012200146,0.0019334946,0.0010502823,0.0015611002,0.0014443836,0.0007399614,0.00012087788],"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":[0.0038492656,0.0019317917,0.54011065,0.0020128635,0.00052100205,0.00008280664,0.022281043,0.004590618,0.0018165138,0.0020220468,0.0036193556,0.417162],"study_design_scores_gemma":[0.00026869238,0.009009643,0.9486605,0.00089350843,0.00038286872,0.000082267434,0.018506812,0.008301161,0.006714799,0.0020725972,0.0049880287,0.00011915196],"about_ca_topic_score_codex":0.017878562,"about_ca_topic_score_gemma":0.027905922,"teacher_disagreement_score":0.100732446,"about_ca_system_score_codex":0.007149948,"about_ca_system_score_gemma":0.0079898685,"threshold_uncertainty_score":0.53273046},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021008071,0.8585406,0.009107484,0.04509138,0.0051280856,0.000052321906,0.0011575328,0.0005791438,0.07824275],"genre_scores_gemma":[0.020872854,0.8485375,0.017068416,0.005509592,0.0014372405,0.00010192367,0.00073736615,0.00024518892,0.10548985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925953,0.00021258251,0.00005989278,0.00008708117,0.00032856822,0.00005232657],"domain_scores_gemma":[0.99740785,0.0011479702,0.00026273757,0.00012234486,0.0007927838,0.00026619155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028170485,0.0011953311,0.00062554755,0.0020921007,0.0008989859,0.0030751198,0.0011081558,0.0026714874,0.021030733],"category_scores_gemma":[0.003912539,0.00075449515,0.00031996498,0.003359523,0.0007772294,0.0036364896,0.0011979064,0.0022923716,0.01824982],"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":[0.00007751564,0.000032655676,0.0005654173,0.00076016603,0.000010466227,0.00013519147,0.0010410879,0.0003502661,0.00026584588,0.0033662478,0.40562707,0.58776814],"study_design_scores_gemma":[0.000010015387,0.000034374727,0.0013879106,0.001328637,0.000021349148,0.00034308343,0.0007324343,0.0001369848,0.0005589406,0.003108722,0.99232095,0.000016519762],"about_ca_topic_score_codex":0.025317019,"about_ca_topic_score_gemma":0.070059694,"teacher_disagreement_score":0.025317019,"about_ca_system_score_codex":0.0012420577,"about_ca_system_score_gemma":0.0033362412,"threshold_uncertainty_score":0.07035476},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32063138,0.0027858466,0.0010725666,0.47489113,0.009984124,0.00075287087,0.0037273525,0.0004214962,0.18573329],"genre_scores_gemma":[0.84975106,0.0009390724,0.0014944994,0.042305823,0.0016284523,0.0003106147,0.0021554374,0.00020774185,0.101207286],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.93230146,0.009597945,0.0014809328,0.002502065,0.034822367,0.019295178],"domain_scores_gemma":[0.80530864,0.019020513,0.0039876197,0.0020789194,0.06012927,0.10947499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.054954425,0.0016561593,0.0015389111,0.005522936,0.030236697,0.019662557,0.007208249,0.017714,0.019805662],"category_scores_gemma":[0.0772465,0.0014313421,0.0029283564,0.004243368,0.0076163355,0.0036425688,0.010102588,0.01357185,0.0018187205],"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":[0.0027573656,0.004949879,0.040007297,0.0002594492,0.00023944174,0.00074378296,0.004043961,0.005143281,0.0011321041,0.04462577,0.832504,0.06359376],"study_design_scores_gemma":[0.0014236683,0.0016075338,0.4465851,0.0005307807,0.00023003273,0.00023073601,0.025662202,0.009281665,0.0017897754,0.008581955,0.5031083,0.0009682468],"about_ca_topic_score_codex":0.92792046,"about_ca_topic_score_gemma":0.98084325,"teacher_disagreement_score":0.9450456,"about_ca_system_score_codex":0.13145523,"about_ca_system_score_gemma":0.28379616,"threshold_uncertainty_score":0.9537789},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945421,0.003825994,0.007003064,0.0031850508,0.00012123478,0.004366324,0.0036562143,0.00019122993,0.03222975],"genre_scores_gemma":[0.98500353,0.0008082085,0.009963767,0.00010493299,0.000025367955,0.00095167774,0.0008347661,0.000013206488,0.0022945376],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93991375,0.040427685,0.0018137043,0.0012203722,0.014258911,0.0023655454],"domain_scores_gemma":[0.94679236,0.026595272,0.006497441,0.0012373119,0.01535715,0.0035203188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03922086,0.00069669925,0.000725004,0.002915143,0.0015761077,0.0039063445,0.0013284087,0.0006907425,0.0065138685],"category_scores_gemma":[0.09358173,0.00028749256,0.0010983339,0.0034943477,0.0013855234,0.001386821,0.0025511102,0.00109976,0.0004507659],"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":[0.00858295,0.0028709567,0.31947038,0.0051569375,0.0018040029,0.0002762618,0.004216133,0.03552092,0.0011985472,0.014127969,0.009893058,0.59688187],"study_design_scores_gemma":[0.0027489846,0.013621668,0.83211666,0.0049751983,0.0026819916,0.00036542138,0.0075268075,0.081253015,0.0101278275,0.0056268233,0.038782913,0.00017276107],"about_ca_topic_score_codex":0.30404377,"about_ca_topic_score_gemma":0.2976422,"teacher_disagreement_score":0.30404377,"about_ca_system_score_codex":0.03527757,"about_ca_system_score_gemma":0.03599968,"threshold_uncertainty_score":0.6045481},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007749876,0.8479762,0.014591724,0.07511101,0.004110946,0.0001548161,0.00040128906,0.0004023095,0.056476638],"genre_scores_gemma":[0.006969497,0.9143191,0.018533764,0.0058201957,0.0015897136,0.000116678595,0.00022942654,0.00016216715,0.052259512],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960372,0.0008976661,0.00022582339,0.00038006637,0.0023620508,0.00009720234],"domain_scores_gemma":[0.98818713,0.0069010193,0.0010401488,0.00037917384,0.002531058,0.0009614016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092328815,0.0018489468,0.001999047,0.004878072,0.0016119159,0.0056832707,0.0022609206,0.0041491683,0.025686039],"category_scores_gemma":[0.013212194,0.0017429398,0.0007135525,0.0059668156,0.0026535704,0.009293907,0.0016618669,0.005180477,0.021587227],"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":[0.000078840625,0.000073334086,0.0006226234,0.001600649,0.000038980877,0.00007904141,0.0008304537,0.00038004515,0.00018711518,0.009583455,0.62927896,0.3572466],"study_design_scores_gemma":[0.0000649992,0.00008879526,0.0027223187,0.0049416446,0.0001190394,0.0007408612,0.0011676509,0.00043305763,0.0006153376,0.028527716,0.9604924,0.000086207074],"about_ca_topic_score_codex":0.012883853,"about_ca_topic_score_gemma":0.043486074,"teacher_disagreement_score":0.025686039,"about_ca_system_score_codex":0.0022151656,"about_ca_system_score_gemma":0.007007182,"threshold_uncertainty_score":0.08592832},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008294657,0.57253504,0.037039813,0.3366677,0.017086674,0.000496166,0.0024804918,0.00031315576,0.032551423],"genre_scores_gemma":[0.049335677,0.71082044,0.106617235,0.09061256,0.011554891,0.001670294,0.0015705856,0.00058025174,0.027238026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97685015,0.01193452,0.0026306661,0.00082508073,0.00749645,0.0002630346],"domain_scores_gemma":[0.65383595,0.28735512,0.009339053,0.0042128065,0.042260673,0.002996329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04698713,0.0015281577,0.0023811494,0.01011974,0.0024408682,0.007954481,0.0037360038,0.007100559,0.019121408],"category_scores_gemma":[0.24190752,0.0017585192,0.0012178834,0.008067072,0.005135763,0.011787504,0.0028608607,0.009514848,0.0097385645],"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":[0.00015546325,0.000038360402,0.001327041,0.0057710153,0.00019641321,0.00012429933,0.0010410363,0.0002421894,0.00014466797,0.024658032,0.7177722,0.24852929],"study_design_scores_gemma":[0.00026185406,0.00011074367,0.005599207,0.029486647,0.0008760626,0.000599908,0.0020540247,0.0007180349,0.00130217,0.17134456,0.7873992,0.00024749653],"about_ca_topic_score_codex":0.013380487,"about_ca_topic_score_gemma":0.040783882,"teacher_disagreement_score":0.04698713,"about_ca_system_score_codex":0.0032197821,"about_ca_system_score_gemma":0.008947772,"threshold_uncertainty_score":0.24849468},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38712975,0.0019580238,0.13380979,0.040329672,0.00049347867,0.013615393,0.0062345117,0.0049802945,0.41144902],"genre_scores_gemma":[0.8588647,0.0005873714,0.10564185,0.0014542852,0.000112653186,0.0028473223,0.0021567661,0.00013449046,0.028200563],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9437034,0.021007095,0.0024571249,0.0017408942,0.02641697,0.0046745534],"domain_scores_gemma":[0.9125701,0.030037751,0.005383,0.0051709386,0.03958656,0.007251636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.064672075,0.00053770235,0.00042849572,0.0064780293,0.0041513285,0.008071882,0.0035523067,0.0013285916,0.0051626493],"category_scores_gemma":[0.06505205,0.0005915835,0.00037182597,0.008516576,0.0035005447,0.002528202,0.005557868,0.0015620072,0.00058706966],"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":[0.0007474561,0.0010081226,0.19492735,0.0008478131,0.0001530611,0.0002679518,0.0052046757,0.016809087,0.0025263936,0.14794262,0.061435763,0.5681298],"study_design_scores_gemma":[0.0014117949,0.0027001065,0.5437616,0.0014231033,0.00046826314,0.0003166228,0.007594119,0.050995905,0.012650483,0.03527405,0.34277967,0.00062429335],"about_ca_topic_score_codex":0.6778377,"about_ca_topic_score_gemma":0.7182222,"teacher_disagreement_score":0.95056605,"about_ca_system_score_codex":0.04943396,"about_ca_system_score_gemma":0.1757294,"threshold_uncertainty_score":0.6481191},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014408121,0.48882264,0.035497822,0.14902498,0.018707871,0.0003180773,0.005041899,0.0014179618,0.29972795],"genre_scores_gemma":[0.020291425,0.5251048,0.03674367,0.024379162,0.0030145803,0.0003810792,0.0017269066,0.0006919369,0.38766637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918073,0.00012245905,0.00008420814,0.00013847186,0.0004235399,0.0000505805],"domain_scores_gemma":[0.9963247,0.0010938525,0.00022734868,0.00011796967,0.0018915096,0.00034453886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023361302,0.0012489222,0.00065192743,0.0032544814,0.0017434086,0.0029723337,0.0010779815,0.0028030868,0.06389378],"category_scores_gemma":[0.006695775,0.00081808947,0.0005703081,0.0039325263,0.001112954,0.0036208802,0.0012757491,0.0029681046,0.039638348],"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":[0.000016135644,0.0000257305,0.0003324334,0.000453328,0.0000062623094,0.000049768067,0.00025935037,0.00011114234,0.00012479776,0.0049801804,0.75512,0.2385209],"study_design_scores_gemma":[0.000012323333,0.0000200822,0.0017041105,0.0010917983,0.000018045572,0.00022328457,0.00022525202,0.0001401971,0.00048792493,0.006500707,0.98955697,0.000019349827],"about_ca_topic_score_codex":0.026629342,"about_ca_topic_score_gemma":0.06920133,"teacher_disagreement_score":0.06389378,"about_ca_system_score_codex":0.002245799,"about_ca_system_score_gemma":0.005425623,"threshold_uncertainty_score":0.21374601},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022101285,0.022266325,0.023005066,0.71946156,0.0061440314,0.0046288036,0.0006652668,0.00040657597,0.20132118],"genre_scores_gemma":[0.7147912,0.007948408,0.05494276,0.1348868,0.0013801742,0.0037538316,0.0010534163,0.0004290927,0.080814414],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.67918277,0.14838426,0.019956356,0.009922837,0.11987326,0.022680482],"domain_scores_gemma":[0.39711723,0.1484782,0.014264778,0.016333831,0.37103266,0.052773345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27957958,0.0012308382,0.0013648538,0.0065284753,0.02093001,0.0228874,0.0070412895,0.014894953,0.005023719],"category_scores_gemma":[0.27342546,0.0013123051,0.001728198,0.005965526,0.014526149,0.0052516223,0.009455769,0.013437387,0.0006761537],"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":[0.00029569023,0.00039625427,0.021381522,0.0027476621,0.00023943877,0.0008303541,0.02113313,0.0034611244,0.0018176427,0.24670514,0.5049697,0.19602238],"study_design_scores_gemma":[0.0001393938,0.00018759596,0.046532124,0.005898186,0.00010707219,0.00022840542,0.008153873,0.0037533399,0.0015095416,0.0149825085,0.9180688,0.00043910794],"about_ca_topic_score_codex":0.921229,"about_ca_topic_score_gemma":0.9309818,"teacher_disagreement_score":0.921229,"about_ca_system_score_codex":0.19131435,"about_ca_system_score_gemma":0.56986356,"threshold_uncertainty_score":0.93796074},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004678083,0.004918967,0.0003040882,0.06448668,0.9292025,0.000044325938,0.00013428195,0.00008454233,0.00077790546],"genre_scores_gemma":[0.0011205893,0.01068705,0.0010091467,0.17699465,0.7987597,0.00016412835,0.00019990683,0.000110167966,0.010954612],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875373,0.0032870772,0.0022025078,0.0011649504,0.0051058475,0.000702408],"domain_scores_gemma":[0.9145736,0.029365908,0.0062994566,0.0016662825,0.040880226,0.0072144843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0162313,0.004713819,0.0049742884,0.0058321645,0.0030334452,0.0073891687,0.00687186,0.017914282,0.015043999],"category_scores_gemma":[0.06840839,0.0015137668,0.0043876264,0.0037594745,0.0030337148,0.005549359,0.002569372,0.019626664,0.009831002],"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":[0.00003098585,0.000010426292,0.0000381772,0.00021449143,0.000013983677,0.00003360648,0.000007197466,0.000027996773,0.000019509143,0.0001230948,0.99559057,0.0038899523],"study_design_scores_gemma":[0.00009963145,0.000059996728,0.00075772125,0.0015627121,0.00010052661,0.00022145032,0.00007758721,0.0004207259,0.00017050712,0.0013848396,0.99509454,0.000049743783],"about_ca_topic_score_codex":0.0032430072,"about_ca_topic_score_gemma":0.008424613,"teacher_disagreement_score":0.017914282,"about_ca_system_score_codex":0.004350182,"about_ca_system_score_gemma":0.0057598697,"threshold_uncertainty_score":0.085840344},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06679287,0.0014055918,0.9027958,0.0038214815,0.00010930038,0.0008491392,0.0007640158,0.0007057384,0.022756072],"genre_scores_gemma":[0.36320087,0.0011691587,0.6317355,0.00017445716,0.000028653925,0.000985129,0.0006639312,0.00012367859,0.0019186354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940606,0.004459422,0.00025991173,0.0004229229,0.0006691807,0.00012805712],"domain_scores_gemma":[0.9854548,0.011855148,0.00059199496,0.0010362079,0.000917121,0.00014474709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072352462,0.0011903187,0.00055123726,0.0055402145,0.0014296282,0.007023858,0.0011196529,0.0014953214,0.0065508885],"category_scores_gemma":[0.018284574,0.00067665486,0.0019291101,0.004109223,0.0047995746,0.007999421,0.0018256978,0.002090579,0.00058247737],"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":[0.0003683898,0.00020270882,0.013588616,0.0024691997,0.000321893,0.0008515762,0.08238324,0.117399566,0.0052009467,0.53491616,0.004532718,0.23776504],"study_design_scores_gemma":[0.00018766076,0.00028170223,0.008576965,0.0031612446,0.00032308284,0.0010386988,0.041919515,0.39507076,0.0041380725,0.3981968,0.14690033,0.00020524944],"about_ca_topic_score_codex":0.020962948,"about_ca_topic_score_gemma":0.010746953,"teacher_disagreement_score":0.020962948,"about_ca_system_score_codex":0.004005354,"about_ca_system_score_gemma":0.0056895018,"threshold_uncertainty_score":0.041681886},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85568625,0.0020771055,0.0009716725,0.062219962,0.00039361333,0.00044617144,0.0002896524,0.00007054352,0.07784502],"genre_scores_gemma":[0.9784741,0.0016575108,0.0009233147,0.0039689313,0.000035791956,0.000093925155,0.00011246602,0.00003722527,0.01469667],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9882194,0.0036173335,0.00017244795,0.0006211641,0.0033249108,0.004044763],"domain_scores_gemma":[0.9859365,0.0032817286,0.00044145994,0.0003324059,0.0028069655,0.0072009857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007503856,0.00032371873,0.00040236823,0.00087272463,0.0267524,0.003631781,0.0013509408,0.0014497014,0.005197804],"category_scores_gemma":[0.013512806,0.0004195845,0.00035263808,0.0017271849,0.009996157,0.0013542152,0.008051882,0.0046949997,0.00022359237],"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":[0.0003202492,0.000868096,0.05628619,0.0002498218,0.000036795234,0.0050573507,0.69140995,0.00048033465,0.0013423765,0.02807218,0.056609873,0.15926684],"study_design_scores_gemma":[0.00012977407,0.00036352262,0.07650081,0.00042837192,0.000032038308,0.0013005612,0.519062,0.0006606707,0.0009863285,0.0023118365,0.39808744,0.00013664144],"about_ca_topic_score_codex":0.9637845,"about_ca_topic_score_gemma":0.98606956,"teacher_disagreement_score":0.9637845,"about_ca_system_score_codex":0.08252995,"about_ca_system_score_gemma":0.14928102,"threshold_uncertainty_score":0.59879947},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017303592,0.0112981135,0.76803297,0.147382,0.0026648855,0.009330576,0.0001664442,0.00021502493,0.043606363],"genre_scores_gemma":[0.29484832,0.0037610596,0.67599374,0.0069189607,0.000841902,0.015204085,0.0001074108,0.00011670657,0.0022077425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.21798395,0.7306292,0.017219389,0.0043586437,0.027757838,0.0020509434],"domain_scores_gemma":[0.16617191,0.7284421,0.018690955,0.02658963,0.05677134,0.0033340822],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5944983,0.0014925253,0.003301887,0.008468526,0.012294056,0.015236131,0.0069562583,0.008028075,0.0057100374],"category_scores_gemma":[0.7190122,0.0015624475,0.0025045457,0.01050906,0.03510976,0.023992805,0.012470048,0.0087279035,0.000903721],"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":[0.0003376079,0.00020437856,0.006514747,0.0050955475,0.00022312625,0.00043812458,0.06469868,0.0036046864,0.00054447853,0.6120976,0.013563723,0.29267734],"study_design_scores_gemma":[0.00029068286,0.0010817145,0.007074947,0.018005993,0.00025623626,0.00079094124,0.070333056,0.012712651,0.0018153609,0.8053412,0.08193454,0.0003627349],"about_ca_topic_score_codex":0.010933362,"about_ca_topic_score_gemma":0.016703317,"teacher_disagreement_score":0.5944983,"about_ca_system_score_codex":0.017546114,"about_ca_system_score_gemma":0.04780449,"threshold_uncertainty_score":0.50005585},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83441895,0.0015253233,0.12548165,0.011356339,0.00018464413,0.0126934685,0.0012290612,0.0009058355,0.01220486],"genre_scores_gemma":[0.6228972,0.0009586852,0.36571696,0.0010968297,0.000065043714,0.006167505,0.0010841726,0.00018110102,0.001832441],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9424902,0.04144612,0.004173732,0.0010611824,0.00895957,0.0018691994],"domain_scores_gemma":[0.85784274,0.072158135,0.00982279,0.011415093,0.040287934,0.008473343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.094937794,0.0007102171,0.00051260885,0.0018076417,0.0023190007,0.0026108106,0.0014877114,0.0009498807,0.0014220218],"category_scores_gemma":[0.11643113,0.00049635215,0.00062971446,0.0018401659,0.0022998706,0.0023208184,0.0048144567,0.0031985054,0.00036400263],"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":[0.0007177227,0.0041223387,0.12734856,0.0018269649,0.00017640191,0.0002868209,0.031827394,0.0051832106,0.0075406306,0.004964369,0.0086957915,0.8073097],"study_design_scores_gemma":[0.0012662441,0.033534568,0.6295746,0.0052655363,0.0009087924,0.00237665,0.0572362,0.032300062,0.05039872,0.01272507,0.17363346,0.0007801491],"about_ca_topic_score_codex":0.020223964,"about_ca_topic_score_gemma":0.024587817,"teacher_disagreement_score":0.094937794,"about_ca_system_score_codex":0.0065407306,"about_ca_system_score_gemma":0.026578534,"threshold_uncertainty_score":0.50208503},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018379341,0.5298956,0.01801625,0.28630042,0.012554213,0.00020258299,0.0014281842,0.0010534386,0.14871134],"genre_scores_gemma":[0.069362946,0.5595507,0.03587208,0.07786647,0.007084167,0.00041127758,0.0010336017,0.0009106514,0.24790807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998722,0.0003484542,0.00009070219,0.00009176996,0.00068195787,0.00006501794],"domain_scores_gemma":[0.98661333,0.008299298,0.0007776368,0.00021112317,0.0033227566,0.0007758219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006130833,0.0009720257,0.0004910158,0.002123061,0.0020297735,0.0042089797,0.0014167448,0.004348635,0.053719502],"category_scores_gemma":[0.017566742,0.00075822155,0.00037555242,0.0018608901,0.0014608456,0.0073013334,0.0012435184,0.0037520719,0.020197418],"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":[0.00009347051,0.0000216628,0.0006652893,0.00061417813,0.00000975384,0.00006944006,0.000618559,0.000104837665,0.00017969226,0.0038109648,0.74606395,0.24774818],"study_design_scores_gemma":[0.00007812306,0.00008892314,0.009005989,0.004605006,0.00007346188,0.00043535416,0.0022436823,0.0005598989,0.00085415354,0.027944842,0.9540235,0.00008718583],"about_ca_topic_score_codex":0.035065394,"about_ca_topic_score_gemma":0.13252147,"teacher_disagreement_score":0.053719502,"about_ca_system_score_codex":0.002225421,"about_ca_system_score_gemma":0.004350632,"threshold_uncertainty_score":0.17970967},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14160661,0.007974494,0.34731856,0.08584093,0.0007184728,0.00504701,0.00013024344,0.0009771077,0.41038656],"genre_scores_gemma":[0.8737463,0.0012272511,0.11907706,0.0013704064,0.00007176377,0.0013928397,0.00003179515,0.00006025609,0.0030223343],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.89440954,0.09307454,0.0019312896,0.0012396654,0.0073729237,0.0019720853],"domain_scores_gemma":[0.8250256,0.13868837,0.006986865,0.005026484,0.017104514,0.00716826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09324118,0.000664796,0.00064494356,0.0036164634,0.003636735,0.007818966,0.0014163575,0.0013271385,0.0050835568],"category_scores_gemma":[0.09997675,0.00034521223,0.0005574145,0.0016092316,0.00935917,0.008180084,0.007812447,0.0024767711,0.0003149318],"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":[0.0002797074,0.0013281262,0.017325912,0.0015922656,0.000098961056,0.00026954178,0.016442226,0.002565686,0.0010402197,0.2995805,0.013325687,0.64615124],"study_design_scores_gemma":[0.0010025954,0.0027811825,0.05940411,0.014938952,0.0005499644,0.0011038136,0.0627189,0.03283847,0.019445498,0.5599658,0.24476662,0.00048409257],"about_ca_topic_score_codex":0.0028379867,"about_ca_topic_score_gemma":0.0045686504,"teacher_disagreement_score":0.09324118,"about_ca_system_score_codex":0.008623999,"about_ca_system_score_gemma":0.025181795,"threshold_uncertainty_score":0.4931124},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109169394,0.0014904949,0.44628587,0.009728139,0.00075176934,0.41401538,0.00030300874,0.0008628281,0.017393012],"genre_scores_gemma":[0.1555472,0.00049878244,0.58760375,0.0015595952,0.00014211625,0.2535721,0.00006943751,0.00008316497,0.0009238596],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3548291,0.5930945,0.022239583,0.0056696157,0.02105355,0.0031136486],"domain_scores_gemma":[0.5526016,0.3150714,0.023074578,0.039926145,0.05910266,0.01022365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.5691479,0.0016445615,0.0022441924,0.004523512,0.007832068,0.007505304,0.005005651,0.003755897,0.0042243884],"category_scores_gemma":[0.47468078,0.0018220328,0.0017402902,0.0033199275,0.0052327667,0.0061034253,0.008178057,0.0038583751,0.0012150754],"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":[0.0049680993,0.009510919,0.024353884,0.013866437,0.00066130265,0.00077750284,0.10926953,0.0031526426,0.015568658,0.015340245,0.013433186,0.78909755],"study_design_scores_gemma":[0.038533006,0.080905765,0.16669841,0.04675826,0.0030387458,0.002068086,0.17124155,0.037580427,0.11035032,0.112202026,0.22853248,0.0020909458],"about_ca_topic_score_codex":0.0025294481,"about_ca_topic_score_gemma":0.008134464,"teacher_disagreement_score":0.5691479,"about_ca_system_score_codex":0.0069223274,"about_ca_system_score_gemma":0.03539768,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026566786,0.24886297,0.00063402863,0.72064906,0.011821008,0.000021269901,0.0001459319,0.000045765228,0.01755429],"genre_scores_gemma":[0.028188147,0.5717323,0.0041715405,0.29776093,0.019921849,0.00019538047,0.0004258901,0.00027348788,0.07733043],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97800463,0.011430721,0.0014368161,0.0007458776,0.0070191347,0.0013628252],"domain_scores_gemma":[0.9330597,0.03785126,0.002015421,0.0018424831,0.020811027,0.0044200616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033732332,0.00085120986,0.0009399882,0.0055447537,0.004000844,0.00963539,0.0021848714,0.009011797,0.021888409],"category_scores_gemma":[0.098682344,0.00055155205,0.0007946032,0.008216534,0.009523821,0.012226305,0.0057982397,0.010019344,0.004127162],"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":[0.000041206273,0.000035002875,0.00018820925,0.00042134683,0.000010302866,0.00004303506,0.0006173525,0.00012672035,0.000031790707,0.013321467,0.8781398,0.107023746],"study_design_scores_gemma":[0.0000124393355,0.000014076821,0.0008877593,0.002337611,0.000007836074,0.000036416375,0.0010517063,0.000024658748,0.00004172328,0.008183042,0.98738724,0.000015520873],"about_ca_topic_score_codex":0.09703814,"about_ca_topic_score_gemma":0.15890811,"teacher_disagreement_score":0.09703814,"about_ca_system_score_codex":0.01628014,"about_ca_system_score_gemma":0.02459967,"threshold_uncertainty_score":0.19294667},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027281934,0.95318127,0.0033729484,0.020199735,0.003549626,0.00003055867,0.00039516,0.00015273361,0.018845163],"genre_scores_gemma":[0.0034314906,0.95138067,0.0041316333,0.0016862247,0.0017791748,0.000039612416,0.00024869433,0.00008497578,0.037217587],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988663,0.0003044512,0.000103467806,0.000113501555,0.0005536234,0.000058648002],"domain_scores_gemma":[0.99602675,0.002137483,0.00027556674,0.000083978455,0.0011503288,0.0003258609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034960783,0.0022674862,0.0015430106,0.0027974956,0.0010384431,0.0039610774,0.0015229413,0.0028650123,0.039102186],"category_scores_gemma":[0.006123753,0.0014734511,0.0005002698,0.0044078487,0.0015263166,0.0071879053,0.0010244221,0.002408113,0.028085783],"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":[0.00003788987,0.000025472968,0.00033677637,0.0012589503,0.000014760024,0.00003721468,0.0002612209,0.00021590636,0.000106440944,0.0022869385,0.6904423,0.30497605],"study_design_scores_gemma":[0.000018597892,0.00004134154,0.0018223565,0.0030934326,0.00005565909,0.00034777346,0.000595522,0.00025241432,0.00042877832,0.008418081,0.9848904,0.00003550311],"about_ca_topic_score_codex":0.03255333,"about_ca_topic_score_gemma":0.09606973,"teacher_disagreement_score":0.039102186,"about_ca_system_score_codex":0.0022103123,"about_ca_system_score_gemma":0.0051011373,"threshold_uncertainty_score":0.1308099},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12416125,0.0020649445,0.6609525,0.13679838,0.0012146084,0.005674545,0.000098729775,0.0022519364,0.0667831],"genre_scores_gemma":[0.36718163,0.0011522373,0.60030943,0.0076569957,0.00021452273,0.0062432354,0.00017112543,0.00042725602,0.016643578],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6514503,0.28825524,0.012989446,0.007828985,0.032764863,0.006711126],"domain_scores_gemma":[0.59919757,0.26307985,0.02487104,0.030508012,0.066819705,0.015523912],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2811746,0.0016530133,0.001075801,0.004586817,0.012543349,0.020007074,0.0085645635,0.008646193,0.0057410016],"category_scores_gemma":[0.28694367,0.0017976707,0.0013749191,0.003304091,0.023167528,0.020064035,0.025849458,0.015219478,0.0020697422],"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":[0.00044160336,0.0017495024,0.017095858,0.0029526036,0.00015836844,0.0015726209,0.25003397,0.006613582,0.0032035864,0.25917324,0.030372426,0.42663255],"study_design_scores_gemma":[0.00047142382,0.0016930505,0.010702738,0.0066829287,0.00017278874,0.0021037706,0.19348629,0.038674857,0.00799692,0.37986097,0.3575155,0.0006387458],"about_ca_topic_score_codex":0.0066921664,"about_ca_topic_score_gemma":0.011893517,"teacher_disagreement_score":0.2811746,"about_ca_system_score_codex":0.025434695,"about_ca_system_score_gemma":0.084332116,"threshold_uncertainty_score":0.8864397},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.288871,0.009469324,0.52057874,0.056817092,0.0007159407,0.014769424,0.00047939227,0.00045994058,0.10783919],"genre_scores_gemma":[0.8152835,0.0011785292,0.17510736,0.00081111985,0.0002527373,0.006100713,0.00023924261,0.000049861417,0.0009770365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6971689,0.20275392,0.033584554,0.010502016,0.051181607,0.0048089875],"domain_scores_gemma":[0.27700692,0.59785,0.04321802,0.02303786,0.0539307,0.004956513],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23962875,0.0010492501,0.0020612658,0.0038850633,0.005266835,0.01670891,0.0030029693,0.009813621,0.004926057],"category_scores_gemma":[0.52592283,0.0011353007,0.0009931485,0.0030963728,0.026095493,0.023989886,0.010197319,0.0082632275,0.00073844544],"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":[0.0012119701,0.0013775573,0.024138307,0.0073570046,0.00013123399,0.0019018133,0.06947345,0.0060448516,0.0070448415,0.7184053,0.004949204,0.15796453],"study_design_scores_gemma":[0.0011534315,0.0031465068,0.039074518,0.017296458,0.0003286629,0.0052709533,0.07386509,0.04626368,0.04001469,0.65188473,0.120802075,0.0008992118],"about_ca_topic_score_codex":0.0022312265,"about_ca_topic_score_gemma":0.0021029557,"teacher_disagreement_score":0.23962875,"about_ca_system_score_codex":0.009496669,"about_ca_system_score_gemma":0.022895904,"threshold_uncertainty_score":0.93767315},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065401033,0.68665653,0.0011217721,0.26108244,0.0073148864,0.000037192065,0.0022547483,0.000114777475,0.040763643],"genre_scores_gemma":[0.04351656,0.71734905,0.00573704,0.03032607,0.0056468947,0.00017941327,0.0021021867,0.00027761556,0.19486526],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761343,0.000481956,0.00022864816,0.00020993924,0.001140004,0.0003259905],"domain_scores_gemma":[0.9926162,0.002387842,0.00056002627,0.00022062403,0.0031798065,0.0010354291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003500282,0.001211955,0.0007618774,0.003073312,0.0042927344,0.006849776,0.0014663733,0.006071709,0.03404266],"category_scores_gemma":[0.010023071,0.0013368941,0.00059772516,0.007221529,0.003593693,0.009400672,0.0018776917,0.0060451636,0.02159485],"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":[0.00002477461,0.0000040972113,0.0003654719,0.00035921743,0.0000039619686,0.00004222917,0.0011507554,0.00005002309,0.000054701264,0.009943025,0.9455509,0.0424509],"study_design_scores_gemma":[0.000013607255,0.000006541683,0.0030847082,0.001206864,0.000012884379,0.000050518865,0.0013009047,0.000021764787,0.00009255942,0.0065841535,0.98760813,0.00001733434],"about_ca_topic_score_codex":0.42622468,"about_ca_topic_score_gemma":0.64725363,"teacher_disagreement_score":0.42622468,"about_ca_system_score_codex":0.015637584,"about_ca_system_score_gemma":0.031296678,"threshold_uncertainty_score":0.84748757},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17867963,0.010665153,0.14370652,0.14189333,0.0012085335,0.0030497427,0.00037425302,0.00044585398,0.519977],"genre_scores_gemma":[0.89001834,0.008639698,0.06989365,0.0029035981,0.00013049188,0.0011948672,0.00016878742,0.00015636923,0.026894119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97309405,0.017840195,0.000974557,0.0009432489,0.0048055737,0.002342398],"domain_scores_gemma":[0.97052985,0.012414188,0.0042738197,0.0010127763,0.0055755745,0.006193727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024719166,0.0010872295,0.0004936624,0.0033935097,0.00662144,0.019715438,0.0022095721,0.003157456,0.014891366],"category_scores_gemma":[0.03330408,0.0005561803,0.00046603772,0.0034457978,0.015312184,0.02054775,0.0111938855,0.0042767525,0.0012034372],"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":[0.00021764562,0.00034523912,0.0055630817,0.0016656561,0.000049662445,0.0006712133,0.036335364,0.0067490707,0.0017199406,0.71945786,0.021157855,0.20606747],"study_design_scores_gemma":[0.000057073004,0.00053485483,0.004897997,0.003152908,0.00005236449,0.00037940926,0.12682919,0.0025176038,0.0029613094,0.39417422,0.4643323,0.000110751746],"about_ca_topic_score_codex":0.010574519,"about_ca_topic_score_gemma":0.018980967,"teacher_disagreement_score":0.024719166,"about_ca_system_score_codex":0.02022053,"about_ca_system_score_gemma":0.04680686,"threshold_uncertainty_score":0.14671093},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87771916,0.0015213623,0.005575449,0.013793387,0.00015558644,0.0021559447,0.00014760075,0.00005775137,0.098873764],"genre_scores_gemma":[0.9650899,0.0016023052,0.011188518,0.001644212,0.000016766267,0.00053828023,0.00008179042,0.00003323785,0.019804887],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9808019,0.010527275,0.0003248023,0.0009233989,0.003052509,0.004370141],"domain_scores_gemma":[0.98705614,0.006105243,0.00055972993,0.00062218175,0.0024470137,0.0032097392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014839934,0.0009369989,0.000756257,0.0016622365,0.050221235,0.0060504465,0.00415136,0.0035863349,0.0022855091],"category_scores_gemma":[0.013961335,0.00071143813,0.00052657747,0.005183417,0.016904013,0.0016387814,0.0053846748,0.0035259174,0.00024208831],"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":[0.00033439224,0.0010721487,0.013313846,0.00048215166,0.000042841413,0.0128917005,0.8382281,0.003143124,0.0021681145,0.036268648,0.010373432,0.081681445],"study_design_scores_gemma":[0.00006808726,0.00035980155,0.012396562,0.00027654905,0.000036116344,0.00063027174,0.87629634,0.0013982643,0.0011207127,0.0027027433,0.104589745,0.00012482732],"about_ca_topic_score_codex":0.9790735,"about_ca_topic_score_gemma":0.9939366,"teacher_disagreement_score":0.121270336,"about_ca_system_score_codex":0.121270336,"about_ca_system_score_gemma":0.22847262,"threshold_uncertainty_score":0.879882},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031552773,0.07048778,0.38241285,0.1450883,0.016019087,0.20614733,0.00784717,0.0024468747,0.13799798],"genre_scores_gemma":[0.10881067,0.017976291,0.7455416,0.014398413,0.0011446258,0.10745287,0.0014219196,0.00029875516,0.0029548174],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.32228002,0.6166063,0.032625396,0.007006461,0.016974052,0.004507809],"domain_scores_gemma":[0.17634375,0.7220816,0.025787758,0.029209476,0.04076079,0.0058166836],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.56359214,0.0047806166,0.00857676,0.016451463,0.0044389796,0.022573525,0.008767382,0.012768423,0.021436982],"category_scores_gemma":[0.70746833,0.0034538943,0.0060769203,0.009395359,0.008156738,0.029864933,0.014030126,0.010457617,0.003966418],"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":[0.0052619395,0.002735756,0.011098086,0.08252006,0.0049765715,0.0009278093,0.017460883,0.016620804,0.0012412383,0.20268425,0.054228667,0.600244],"study_design_scores_gemma":[0.009175105,0.006098203,0.008251616,0.21477702,0.006079392,0.0003532265,0.028534614,0.013853078,0.0053896243,0.39942703,0.3068912,0.0011699753],"about_ca_topic_score_codex":0.0065663178,"about_ca_topic_score_gemma":0.0076194215,"teacher_disagreement_score":0.43640786,"about_ca_system_score_codex":0.02289014,"about_ca_system_score_gemma":0.058676314,"threshold_uncertainty_score":0.53816867},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018647894,0.020110391,0.0080003375,0.016601639,0.0017292656,0.00008809919,0.000073320974,0.00008217113,0.9531284],"genre_scores_gemma":[0.014864195,0.014255916,0.0062911413,0.011290797,0.001786019,0.00026666035,0.00012295299,0.00018297207,0.95093936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929255,0.0036459311,0.0001949482,0.00045445628,0.002515022,0.00026412634],"domain_scores_gemma":[0.99460924,0.003631004,0.00011425379,0.00043734303,0.0010616515,0.00014649828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068056593,0.001281117,0.0013848039,0.0031425476,0.0027285316,0.011374673,0.001411496,0.006735448,0.04427163],"category_scores_gemma":[0.013152415,0.00064911984,0.0003926071,0.002892568,0.008159243,0.009946317,0.0030375188,0.0061778063,0.01720572],"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":[0.0000038782555,0.000015391814,0.000025198424,0.00010437575,0.0000031759773,0.000013807084,0.00022026771,0.00030292533,0.000033959157,0.78686506,0.16464104,0.047770876],"study_design_scores_gemma":[0.0000031555041,0.000006083542,0.000069777125,0.00037522157,0.0000030450028,0.000027643684,0.00020304965,0.00037878475,0.000066220535,0.47716567,0.5216939,0.0000075321573],"about_ca_topic_score_codex":0.008571487,"about_ca_topic_score_gemma":0.015855983,"teacher_disagreement_score":0.04427163,"about_ca_system_score_codex":0.009276379,"about_ca_system_score_gemma":0.007337611,"threshold_uncertainty_score":0.1481033},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003077824,0.22784965,0.057522956,0.65539724,0.022126747,0.00014455615,0.0002541099,0.0001555533,0.03347141],"genre_scores_gemma":[0.19216979,0.3741029,0.16616935,0.19760771,0.05977839,0.0014704415,0.00050416443,0.0010990833,0.007098165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8354298,0.09900581,0.016144278,0.006418205,0.040106006,0.0028959203],"domain_scores_gemma":[0.64398474,0.26855865,0.02029034,0.022215849,0.0409445,0.004005893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19391637,0.0022337374,0.007050353,0.015897714,0.0049784463,0.039824896,0.0049123513,0.012374049,0.006270054],"category_scores_gemma":[0.42454892,0.0016360016,0.00362512,0.019949693,0.05114944,0.079581715,0.015518852,0.027672658,0.0023002164],"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":[0.000120753,0.000060881004,0.0020683056,0.0018230771,0.00033574697,0.000076242985,0.0026645511,0.00067003036,0.00012347895,0.8348618,0.03280911,0.12438608],"study_design_scores_gemma":[0.00007119587,0.0000838494,0.0020730258,0.011113773,0.00032304684,0.00022661762,0.004350774,0.00063029054,0.0002741459,0.8530756,0.12763515,0.00014245442],"about_ca_topic_score_codex":0.007455109,"about_ca_topic_score_gemma":0.00479407,"teacher_disagreement_score":0.19391637,"about_ca_system_score_codex":0.010237116,"about_ca_system_score_gemma":0.013349916,"threshold_uncertainty_score":0.9940446},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014030808,0.0124263875,0.02577602,0.029286308,0.057921015,0.0019816721,0.009600853,0.0034925928,0.8581121],"genre_scores_gemma":[0.003472344,0.004125514,0.009528905,0.002707349,0.0036242295,0.0004651027,0.0034756667,0.0009791955,0.97162175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956363,0.0010349437,0.0002422038,0.00043632893,0.0024645543,0.00018562122],"domain_scores_gemma":[0.9766917,0.004597092,0.0005428962,0.0020426502,0.013762464,0.002363091],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005766216,0.0008199743,0.0008464616,0.004922251,0.0014240681,0.0055334093,0.0018255588,0.0016693869,0.46411774],"category_scores_gemma":[0.03675953,0.00036475572,0.00046502994,0.0033831706,0.0006553968,0.0036779742,0.002323599,0.0016911324,0.24279983],"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":[0.000016546548,0.00001759309,0.0001548469,0.00014318389,0.0000032720402,0.000025417447,0.000073658164,0.0000620519,0.00008682414,0.0051039704,0.8843636,0.10994888],"study_design_scores_gemma":[0.0000065099107,0.0000060156726,0.0001843112,0.00017986367,0.000003888617,0.000047169062,0.000064492815,0.00007950536,0.00010063002,0.002723535,0.996599,0.000005035797],"about_ca_topic_score_codex":0.0023626597,"about_ca_topic_score_gemma":0.0040456965,"teacher_disagreement_score":0.53588223,"about_ca_system_score_codex":0.0025530206,"about_ca_system_score_gemma":0.0036830537,"threshold_uncertainty_score":0.76437104},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9009079,0.0073592486,0.018932644,0.0035870746,0.00009115421,0.0007189142,0.0073532546,0.00038888102,0.06066098],"genre_scores_gemma":[0.97681135,0.0017072882,0.016560022,0.000079071084,0.00006282394,0.00035981493,0.0030707018,0.00008492917,0.0012639074],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.970072,0.009499074,0.0040969267,0.0019960173,0.013231129,0.0011048934],"domain_scores_gemma":[0.79125154,0.1454677,0.01879381,0.008817275,0.032918748,0.002750931],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.026829874,0.00040092223,0.0011500978,0.12527387,0.003685173,0.012655406,0.0015764567,0.0007979878,0.0033863604],"category_scores_gemma":[0.16916615,0.00034492734,0.0010605913,0.14047614,0.0027334315,0.009467424,0.007208819,0.0009078874,0.0004928934],"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":[0.00027209183,0.0002661617,0.33573732,0.0070297024,0.0008201654,0.00058252184,0.06657989,0.003792511,0.0051555866,0.06101358,0.00948098,0.5092696],"study_design_scores_gemma":[0.00007686843,0.00027566432,0.64408475,0.0041414276,0.0011552043,0.0012563863,0.15300715,0.019638233,0.0053568,0.06619788,0.104527116,0.00028252575],"about_ca_topic_score_codex":0.007533724,"about_ca_topic_score_gemma":0.009056518,"teacher_disagreement_score":0.9731701,"about_ca_system_score_codex":0.004900929,"about_ca_system_score_gemma":0.011842112,"threshold_uncertainty_score":0.1418916},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054582987,0.20536418,0.22030555,0.377593,0.009996478,0.005427288,0.0010782088,0.00070761924,0.12494468],"genre_scores_gemma":[0.6718757,0.07122224,0.19779499,0.040254332,0.0037514116,0.009920941,0.0010060106,0.00035112398,0.0038232116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4085834,0.3868751,0.07522758,0.010971097,0.11395051,0.0043923515],"domain_scores_gemma":[0.18770123,0.51962656,0.07969655,0.037982367,0.1644551,0.010538133],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43465808,0.00063944614,0.0017138429,0.012720025,0.0051858295,0.014436083,0.003407177,0.0053636394,0.0020516387],"category_scores_gemma":[0.58375597,0.0010375555,0.0017082269,0.012841678,0.026981153,0.012409798,0.011965224,0.008647631,0.00056732976],"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":[0.00017119956,0.00039031653,0.042695813,0.021592636,0.0003028905,0.00017590781,0.020214416,0.0015257286,0.00078194484,0.3325015,0.05727337,0.52237433],"study_design_scores_gemma":[0.0002003601,0.0008126503,0.07158183,0.120838925,0.0004867852,0.0010883593,0.019024761,0.0026042259,0.0024749818,0.22347048,0.5570782,0.0003385371],"about_ca_topic_score_codex":0.012877403,"about_ca_topic_score_gemma":0.012242584,"teacher_disagreement_score":0.56534195,"about_ca_system_score_codex":0.020893939,"about_ca_system_score_gemma":0.141306,"threshold_uncertainty_score":0.6971673},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008898399,0.051832598,0.06853526,0.30281705,0.004451139,0.00019937378,0.00025593437,0.00029813946,0.5627122],"genre_scores_gemma":[0.7011384,0.06403612,0.082028106,0.047629897,0.0040722406,0.0008809878,0.0004022324,0.0007569484,0.099055104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9404853,0.03648507,0.0018777908,0.0020346527,0.017879866,0.0012373229],"domain_scores_gemma":[0.9030025,0.075471185,0.0018284209,0.0054873275,0.013169711,0.0010409509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049085375,0.00061690924,0.0008232272,0.0030567585,0.002259071,0.0192259,0.0021274206,0.0032601245,0.006116659],"category_scores_gemma":[0.09223979,0.00064802176,0.00051014364,0.003659038,0.0269844,0.016511234,0.0042825458,0.008034723,0.0014781577],"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":[0.000005540252,0.000010264582,0.00016794224,0.00014593832,0.0000046291248,0.000013213989,0.0008804258,0.0003289448,0.00004518156,0.9541625,0.010642461,0.033593047],"study_design_scores_gemma":[0.000009244909,0.00001856216,0.0007213489,0.0016944922,0.000008401867,0.00004081614,0.0024445883,0.00083969167,0.00038082412,0.7936774,0.20013295,0.000031739142],"about_ca_topic_score_codex":0.00669848,"about_ca_topic_score_gemma":0.00619375,"teacher_disagreement_score":0.049085375,"about_ca_system_score_codex":0.01053827,"about_ca_system_score_gemma":0.009164702,"threshold_uncertainty_score":0.2595914},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984676,0.000014777861,0.00028327797,0.00010461155,0.000004977186,0.00009308559,0.0000073106476,0.000001408837,0.0010229031],"genre_scores_gemma":[0.99817026,0.00003195087,0.0010017835,0.00010799381,0.000007549079,0.00014344507,0.000015185356,0.0000022607423,0.0005194992],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98589724,0.010016715,0.00057475094,0.00062780065,0.0021642707,0.0007192246],"domain_scores_gemma":[0.9618075,0.018811584,0.008136522,0.0036386591,0.006023074,0.0015826618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023311855,0.00016338538,0.00024017823,0.0005001604,0.0028614618,0.0014625612,0.0007221382,0.00053779467,0.0021118894],"category_scores_gemma":[0.060030594,0.00027470232,0.0003726846,0.00032976078,0.0020816063,0.0011200289,0.0015811431,0.0013138284,0.00035472825],"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":[0.0013149155,0.0057650697,0.7050245,0.00014761668,0.00006442478,0.00026140228,0.20255607,0.0001816291,0.0020860424,0.0019143824,0.0008440033,0.07984006],"study_design_scores_gemma":[0.00013293375,0.0076337466,0.82472867,0.00022385672,0.000077234545,0.00034735416,0.15524362,0.0017332167,0.0033011972,0.0010838975,0.0054115034,0.00008285124],"about_ca_topic_score_codex":0.02288559,"about_ca_topic_score_gemma":0.0627389,"teacher_disagreement_score":0.023311855,"about_ca_system_score_codex":0.00227156,"about_ca_system_score_gemma":0.005632903,"threshold_uncertainty_score":0.12328637},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001527864,0.0059540663,0.0003388344,0.0648208,0.9032221,0.00006261175,0.0005696288,0.00020527975,0.024674047],"genre_scores_gemma":[0.0026417044,0.012124437,0.0007404834,0.05824245,0.60339093,0.00008777719,0.00062710926,0.00028870816,0.3218564],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973686,0.00030891979,0.0002974734,0.00035271893,0.0014987994,0.00017352196],"domain_scores_gemma":[0.9796198,0.0034418332,0.00085591146,0.0009960666,0.0129805505,0.0021058372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027679629,0.0012906448,0.00094755815,0.0024311717,0.0016909706,0.006417051,0.0017722903,0.0036507796,0.20531692],"category_scores_gemma":[0.027484324,0.00055150373,0.0006921982,0.0013542713,0.00089777086,0.002803712,0.0014215587,0.004358153,0.11390867],"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":[0.00001000044,0.0000041554304,0.000026253765,0.000068012385,0.0000019722272,0.000029338426,0.000005116378,0.000006921007,0.000034288485,0.00016123167,0.9895208,0.010131955],"study_design_scores_gemma":[0.0000050963195,0.0000067226847,0.0001272175,0.00011614467,0.00000286677,0.00007766681,0.00001704653,0.000014481682,0.00006451331,0.00013297348,0.9994307,0.000004492531],"about_ca_topic_score_codex":0.0026885387,"about_ca_topic_score_gemma":0.0065628286,"teacher_disagreement_score":0.20531692,"about_ca_system_score_codex":0.0015464504,"about_ca_system_score_gemma":0.003082536,"threshold_uncertainty_score":0.6868535},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083802156,0.014684737,0.071721956,0.76352036,0.0043730275,0.000584449,0.00006500858,0.00079135655,0.06045701],"genre_scores_gemma":[0.7817616,0.01076962,0.08398671,0.09212858,0.0030770334,0.0010501026,0.00012258446,0.00045818463,0.02664566],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.85422975,0.11510977,0.0038892638,0.0036153267,0.016071368,0.007084548],"domain_scores_gemma":[0.59851396,0.24490304,0.017936341,0.015171752,0.08644867,0.037026223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17755692,0.00087834115,0.0010646811,0.002188819,0.008922302,0.023677541,0.0028298858,0.005399364,0.007904977],"category_scores_gemma":[0.18269081,0.0007156722,0.0007141907,0.0009225427,0.009942832,0.012611985,0.015002983,0.01348913,0.0028179716],"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":[0.00021000602,0.0014747367,0.018179959,0.0017242528,0.00014807988,0.0004887077,0.071878694,0.0021657804,0.0017242596,0.070080236,0.26161352,0.5703118],"study_design_scores_gemma":[0.00028945852,0.0008883237,0.013419819,0.0083546555,0.00010396119,0.0009286759,0.15983182,0.0061244457,0.0045426637,0.14174926,0.6634736,0.00029330075],"about_ca_topic_score_codex":0.0027129902,"about_ca_topic_score_gemma":0.0053114416,"teacher_disagreement_score":0.17755692,"about_ca_system_score_codex":0.008452885,"about_ca_system_score_gemma":0.029420016,"threshold_uncertainty_score":0.93902194},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7353532,0.00031834698,0.011242261,0.030110948,0.0012575717,0.0009359054,0.00027377365,0.00026757072,0.22024046],"genre_scores_gemma":[0.9365143,0.00013979794,0.006224395,0.0018201668,0.0000820241,0.00022409657,0.00014631136,0.00012554551,0.054723293],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9739604,0.0111135915,0.0004891384,0.0016999504,0.007248088,0.0054887924],"domain_scores_gemma":[0.9720063,0.0074897944,0.0009049813,0.0014111369,0.008212745,0.009974995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021708632,0.0006018087,0.0004985437,0.0021129025,0.019451944,0.01359042,0.002550939,0.0027640644,0.009603619],"category_scores_gemma":[0.031300712,0.00034115303,0.00053891743,0.0015007943,0.007964598,0.0026522535,0.009988921,0.0047217607,0.0013427851],"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":[0.000268575,0.0012769593,0.025123125,0.00016077222,0.000026494487,0.0040555396,0.5868398,0.0020178214,0.005327994,0.066322535,0.13654208,0.1720383],"study_design_scores_gemma":[0.000028397357,0.000395936,0.016412875,0.0002391196,0.0000141685205,0.0008184853,0.5330135,0.0027540075,0.0026009423,0.006024853,0.43750027,0.00019744129],"about_ca_topic_score_codex":0.31727856,"about_ca_topic_score_gemma":0.66644615,"teacher_disagreement_score":0.31727856,"about_ca_system_score_codex":0.041495744,"about_ca_system_score_gemma":0.045987874,"threshold_uncertainty_score":0.6308636},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022577872,0.042620372,0.016427994,0.8713218,0.013973818,0.00034581323,0.0003891783,0.0005690255,0.05209426],"genre_scores_gemma":[0.14093596,0.1689,0.16862918,0.44618803,0.0221651,0.0038769362,0.0023214105,0.0014065517,0.04557685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8960354,0.077986605,0.0043902523,0.0031714248,0.0131342765,0.0052820924],"domain_scores_gemma":[0.75609106,0.13073711,0.0070233447,0.019516157,0.05611706,0.03051524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14139847,0.0010375802,0.0013677113,0.0036997786,0.004764757,0.022890829,0.0040027373,0.0074709854,0.017082939],"category_scores_gemma":[0.22259797,0.00068175694,0.0015871957,0.0042994143,0.008882074,0.030569652,0.012524304,0.016243609,0.0067313784],"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":[0.00005264946,0.00030610582,0.0021825382,0.002567788,0.000048319664,0.00020155373,0.0065155886,0.00031673117,0.00015373263,0.068893336,0.54850155,0.37026012],"study_design_scores_gemma":[0.00004515281,0.00016384477,0.002310506,0.012722819,0.000031241263,0.00022296813,0.007388561,0.0003002708,0.0003074848,0.05119148,0.9252431,0.00007255779],"about_ca_topic_score_codex":0.0045608785,"about_ca_topic_score_gemma":0.007751058,"teacher_disagreement_score":0.14139847,"about_ca_system_score_codex":0.009910089,"about_ca_system_score_gemma":0.033676118,"threshold_uncertainty_score":0.7477956},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002514425,0.004476465,0.0013773901,0.082326844,0.8476825,0.0002833709,0.0012798432,0.0010180675,0.061304037],"genre_scores_gemma":[0.0054283957,0.006673466,0.0039891843,0.07715555,0.35934982,0.0008984807,0.0020257637,0.002347938,0.54213136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871104,0.001619672,0.0011633869,0.0018134563,0.007019895,0.0012731921],"domain_scores_gemma":[0.9314541,0.011097775,0.003980978,0.0060141194,0.037981365,0.0094717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013784205,0.0016558502,0.001433176,0.0036227903,0.0037963525,0.012497247,0.004984005,0.006270865,0.27928305],"category_scores_gemma":[0.09551546,0.00084612507,0.0014799181,0.0026911267,0.0017879715,0.006175213,0.0065838685,0.009190381,0.19321989],"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":[0.000013087679,0.000008644119,0.000022917011,0.00009177791,0.000001350594,0.00003925272,0.000055450473,0.000016902071,0.00010202687,0.0009928804,0.98828083,0.0103747435],"study_design_scores_gemma":[0.000004531181,0.000005727545,0.00004042852,0.000097613854,0.0000011859054,0.00003582455,0.00004323368,0.000014391318,0.000067631074,0.0003793928,0.99930537,0.000004650009],"about_ca_topic_score_codex":0.001671881,"about_ca_topic_score_gemma":0.0028902832,"teacher_disagreement_score":0.27928305,"about_ca_system_score_codex":0.0036934463,"about_ca_system_score_gemma":0.009378722,"threshold_uncertainty_score":0.9342949},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29730415,0.0036520434,0.12730302,0.48860243,0.0018283367,0.0064694304,0.0000959257,0.00018095943,0.0745638],"genre_scores_gemma":[0.90317243,0.0010667316,0.061909817,0.025826175,0.0001988929,0.0035827805,0.00002526277,0.000132344,0.0040855715],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.59020454,0.35326412,0.00789268,0.004382724,0.034022607,0.010233398],"domain_scores_gemma":[0.5541908,0.32496807,0.013976832,0.017340017,0.0648672,0.024657035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.30738473,0.000494906,0.00091630104,0.0017724035,0.025479386,0.018828021,0.004182367,0.0057570604,0.0026018957],"category_scores_gemma":[0.29263413,0.00071775645,0.00082125165,0.0011740951,0.04001332,0.00988692,0.023473611,0.013333231,0.0003095929],"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":[0.00020446249,0.0011624191,0.010020015,0.0010725039,0.00005688471,0.0025304225,0.69666517,0.0007838491,0.0016815915,0.15274012,0.0187971,0.11428555],"study_design_scores_gemma":[0.00020793322,0.00088003126,0.005100981,0.0041947723,0.00008385605,0.0016512849,0.6747142,0.0019464706,0.0034836598,0.13495135,0.17256232,0.00022304701],"about_ca_topic_score_codex":0.03510644,"about_ca_topic_score_gemma":0.087069646,"teacher_disagreement_score":0.30738473,"about_ca_system_score_codex":0.032446727,"about_ca_system_score_gemma":0.15207547,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015832102,0.065653555,0.045885623,0.37230068,0.008191938,0.0004871729,0.00020757022,0.00027532806,0.49116603],"genre_scores_gemma":[0.80244625,0.031137472,0.0417997,0.04920461,0.004966083,0.0015847695,0.0002445674,0.0005445981,0.06807195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.840089,0.12325708,0.0029153735,0.012067741,0.0151289785,0.0065417765],"domain_scores_gemma":[0.92459947,0.05096672,0.0024160477,0.008713767,0.007710147,0.0055938475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1066115,0.0011434702,0.0022272037,0.0065148682,0.023555998,0.043059707,0.0047528422,0.009849465,0.007969686],"category_scores_gemma":[0.0439343,0.0010439975,0.001248861,0.008114812,0.21560064,0.02697351,0.01728602,0.018693384,0.0013723106],"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":[0.000009802968,0.000010614244,0.00018642984,0.00009490247,0.0000055504,0.00004470861,0.05073654,0.000050896164,0.00003538426,0.93396777,0.0061698174,0.008687587],"study_design_scores_gemma":[0.000020556645,0.0000295872,0.0004855731,0.00082918006,0.000008961651,0.0001159721,0.06037614,0.0002898588,0.00008303175,0.49154416,0.44618696,0.000029993947],"about_ca_topic_score_codex":0.076327145,"about_ca_topic_score_gemma":0.057614826,"teacher_disagreement_score":0.1066115,"about_ca_system_score_codex":0.059339423,"about_ca_system_score_gemma":0.046392106,"threshold_uncertainty_score":0.56382227},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20573835,0.004378278,0.053717814,0.065504365,0.0038413352,0.031486887,0.13169461,0.01062353,0.49301484],"genre_scores_gemma":[0.24373496,0.007885348,0.43406478,0.006902008,0.00039455027,0.037097022,0.08953727,0.0012518278,0.17913236],"study_design_codex":"not_applicable","study_design_gemma":"design_other","domain_scores_codex":[0.9936314,0.001049176,0.0007126111,0.0002805309,0.0034448563,0.0008813757],"domain_scores_gemma":[0.9646315,0.008173228,0.0016737939,0.00085504475,0.020737045,0.0039294134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009541623,0.0010191489,0.00075798243,0.009148976,0.003755223,0.0038854121,0.0023849346,0.0013280679,0.025597865],"category_scores_gemma":[0.021099383,0.0008559606,0.0013824543,0.007823454,0.0009895049,0.0032518234,0.0044406215,0.0021713781,0.005939797],"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":[0.00019795776,0.00037319664,0.076873444,0.0007273662,0.00006144417,0.00091417757,0.006519798,0.0021252153,0.0009970696,0.0067521394,0.64665633,0.25780186],"study_design_scores_gemma":[0.00013318841,0.00013499778,0.22527838,0.0015747236,0.000045571807,0.00032314437,0.009333885,0.0019187666,0.0013214091,0.0011965075,0.75845075,0.00028870304],"about_ca_topic_score_codex":0.60783243,"about_ca_topic_score_gemma":0.81642103,"teacher_disagreement_score":0.39216757,"about_ca_system_score_codex":0.021429634,"about_ca_system_score_gemma":0.056000765,"threshold_uncertainty_score":0.78895426},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91609246,0.0014411419,0.0065015494,0.020968698,0.00009236013,0.00089827966,0.0006502783,0.00007819121,0.053277045],"genre_scores_gemma":[0.98553306,0.0008374944,0.0055782986,0.0014026389,0.000005127768,0.00036368187,0.00019690525,0.00001948734,0.0060632955],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97549766,0.012467157,0.0014531162,0.0014536956,0.0046238373,0.004504477],"domain_scores_gemma":[0.93875575,0.028098686,0.0034165569,0.0032055906,0.020127667,0.0063957702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024602816,0.00023999102,0.0004810968,0.0030267297,0.016083116,0.011131531,0.0026086385,0.0008033518,0.0023761468],"category_scores_gemma":[0.040382158,0.00073382875,0.00032544977,0.010290156,0.008702425,0.0023783862,0.009296749,0.0028818606,0.0001979406],"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":true,"study_design_scores_codex":[0.0003384252,0.00039943156,0.29971677,0.0009108342,0.00017114224,0.0012131248,0.3026335,0.0062168683,0.0050916863,0.14576583,0.013834915,0.22370744],"study_design_scores_gemma":[0.00007409225,0.00018781603,0.30949083,0.0013924729,0.0000991687,0.00018931735,0.5407911,0.0057490747,0.0016238188,0.018309638,0.121837035,0.00025566472],"about_ca_topic_score_codex":0.9676055,"about_ca_topic_score_gemma":0.9916397,"teacher_disagreement_score":0.82797605,"about_ca_system_score_codex":0.17202394,"about_ca_system_score_gemma":0.37985048,"threshold_uncertainty_score":0.9603349},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.516187,0.0008695009,0.03754679,0.022126963,0.00010498295,0.000145662,0.000525677,0.00012844724,0.4223649],"genre_scores_gemma":[0.97767055,0.00019631219,0.0032566504,0.00027194468,0.000005533737,0.00003419032,0.00007276634,0.000023655133,0.018468507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99643505,0.0012170962,0.000083888066,0.00042596651,0.001120643,0.0007174396],"domain_scores_gemma":[0.99246585,0.0021935848,0.00081183773,0.0004623974,0.0032238993,0.00084251113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003631788,0.00027732385,0.0002524901,0.0016310867,0.005463058,0.009294514,0.00082980626,0.0013874877,0.013346544],"category_scores_gemma":[0.009186151,0.0003602219,0.00046878273,0.0016949284,0.010498346,0.004480944,0.0029068415,0.0026662163,0.00061949965],"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":[0.000104321705,0.00003962374,0.038828578,0.00015450543,0.000042212814,0.00041557787,0.07153778,0.0040114275,0.0019761487,0.8402615,0.0066849478,0.03594337],"study_design_scores_gemma":[0.000049148017,0.000107316184,0.1854225,0.0009046297,0.00008917134,0.00021195195,0.26162463,0.014184102,0.0025786802,0.2506169,0.283935,0.000275927],"about_ca_topic_score_codex":0.69570374,"about_ca_topic_score_gemma":0.7772497,"teacher_disagreement_score":0.9607857,"about_ca_system_score_codex":0.039214306,"about_ca_system_score_gemma":0.037822094,"threshold_uncertainty_score":0.61217666},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09810622,0.02925804,0.11215023,0.09183344,0.0019998979,0.00043572776,0.00012089365,0.00028715597,0.6658084],"genre_scores_gemma":[0.9366799,0.007174598,0.027905477,0.004256265,0.00050953473,0.00033522907,0.00007256484,0.0001083919,0.022958113],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.97451586,0.020738836,0.00051089365,0.0012202475,0.002338425,0.0006757409],"domain_scores_gemma":[0.9719928,0.018500788,0.0016363738,0.0040589687,0.0020669738,0.0017441134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0213181,0.0005823416,0.0007289515,0.0027747725,0.0043121753,0.015093262,0.0016286738,0.0030478407,0.004043597],"category_scores_gemma":[0.016348239,0.00031059422,0.000568603,0.001673162,0.077562235,0.019079186,0.01113079,0.0046780556,0.0006394924],"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":[0.0000104893,0.000028014872,0.0005795422,0.00012535165,0.000011008554,0.000096311196,0.081740774,0.00017012969,0.00027453256,0.9026633,0.0022838446,0.012016785],"study_design_scores_gemma":[0.000017635446,0.000047314377,0.00042468938,0.0005098187,0.000009548723,0.00027745735,0.043070767,0.00038224465,0.00024603851,0.77793825,0.17704476,0.00003146177],"about_ca_topic_score_codex":0.0014416821,"about_ca_topic_score_gemma":0.0013435053,"teacher_disagreement_score":0.0213181,"about_ca_system_score_codex":0.0027270657,"about_ca_system_score_gemma":0.0053804424,"threshold_uncertainty_score":0.112742186},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022942666,0.9974004,0.00035468224,0.0009953004,0.00024628962,0.0002180106,0.000087923945,0.000006631308,0.000461277],"genre_scores_gemma":[0.0025155793,0.9949126,0.001226726,0.0007265733,0.00010775752,0.00032593374,0.00007797592,0.0000060403477,0.00010074709],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.96663976,0.016069345,0.009270841,0.0011238669,0.0062822565,0.00061404426],"domain_scores_gemma":[0.8802144,0.092206,0.010515202,0.0018392408,0.014239345,0.0009857251],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045476984,0.0018760087,0.005800241,0.024337865,0.0015754963,0.0063263103,0.0022502302,0.003288094,0.0032539584],"category_scores_gemma":[0.14658177,0.0011107477,0.0045119724,0.022470819,0.002307384,0.004756558,0.004045546,0.0025606286,0.00047206832],"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":[0.00017043033,0.00010287614,0.00060014887,0.58249617,0.0016964442,0.00012355598,0.00073570735,0.00024791557,0.00031072367,0.0023392586,0.009693715,0.40148312],"study_design_scores_gemma":[0.000045823595,0.00007014805,0.0010405162,0.93449664,0.0042082206,0.00017167968,0.00053076516,0.00007444673,0.00020717707,0.0011946666,0.0579281,0.00003188257],"about_ca_topic_score_codex":0.01229493,"about_ca_topic_score_gemma":0.034514982,"teacher_disagreement_score":0.954523,"about_ca_system_score_codex":0.008975261,"about_ca_system_score_gemma":0.042787917,"threshold_uncertainty_score":0.2405082},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07824771,0.0025087541,0.6020537,0.0962491,0.0014016272,0.0019845783,0.000306219,0.000911978,0.21633634],"genre_scores_gemma":[0.8636854,0.00077122275,0.12547019,0.0047981464,0.0002875074,0.0010936913,0.00007306126,0.00015153957,0.0036692254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.80513173,0.15987396,0.0032959357,0.004502823,0.022444101,0.004751509],"domain_scores_gemma":[0.6231195,0.2965793,0.026639692,0.013442267,0.03460641,0.0056129033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16025019,0.0016501349,0.0017833378,0.007815852,0.006374401,0.014941603,0.003208706,0.0051326454,0.012702228],"category_scores_gemma":[0.31490186,0.0009658424,0.0015930837,0.0037201408,0.016977103,0.009787572,0.010901422,0.009849865,0.0008776435],"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":[0.00030524418,0.0003846593,0.0046559675,0.00087026117,0.0002680658,0.00016710097,0.004907314,0.033428613,0.00055340806,0.78699464,0.017173417,0.15029141],"study_design_scores_gemma":[0.0001803256,0.00031124416,0.0028854506,0.0015991483,0.00015421465,0.000057474816,0.004115433,0.054873146,0.0016216116,0.9025019,0.03153473,0.00016542891],"about_ca_topic_score_codex":0.008435458,"about_ca_topic_score_gemma":0.007229806,"teacher_disagreement_score":0.9915645,"about_ca_system_score_codex":0.020592922,"about_ca_system_score_gemma":0.044819806,"threshold_uncertainty_score":0.8474941},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7976025,0.011806813,0.0024611675,0.03799789,0.00042921313,0.0023113862,0.005613894,0.0002659402,0.14151122],"genre_scores_gemma":[0.9482687,0.003591171,0.0067866906,0.0020180466,0.00005336743,0.00056651275,0.0016287855,0.000060854993,0.037025884],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935515,0.0021167267,0.00012775518,0.00025426832,0.0022586095,0.0016910849],"domain_scores_gemma":[0.9880298,0.0022425514,0.0011380846,0.00021082345,0.005227237,0.003151506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059774197,0.00054128445,0.0003876296,0.0019383508,0.004882699,0.004447322,0.0035673887,0.00180835,0.004061925],"category_scores_gemma":[0.015459393,0.00039251352,0.00035054385,0.0031246268,0.0016287208,0.0016215862,0.0020789397,0.0018375139,0.00056819856],"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":[0.0005328024,0.001007103,0.38213703,0.001125977,0.00022692709,0.0006477613,0.020390483,0.008595863,0.0020381985,0.0075321677,0.0971466,0.478619],"study_design_scores_gemma":[0.000082151164,0.0005561805,0.90166587,0.0007097955,0.000098527074,0.00009983309,0.03430732,0.0038672688,0.0012244954,0.0004154493,0.05686762,0.00010543389],"about_ca_topic_score_codex":0.99016833,"about_ca_topic_score_gemma":0.99649376,"teacher_disagreement_score":0.108689696,"about_ca_system_score_codex":0.108689696,"about_ca_system_score_gemma":0.16886806,"threshold_uncertainty_score":0.7886026},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9088024,0.00034476793,0.0099623585,0.007779231,0.00011734503,0.0019242343,0.00017914562,0.00017050543,0.07072008],"genre_scores_gemma":[0.9849857,0.00011218751,0.004018185,0.00029041534,0.000011423455,0.00044139146,0.000062046354,0.000022828277,0.010055963],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97368085,0.018992934,0.00037319193,0.0011767664,0.0012361148,0.0045401864],"domain_scores_gemma":[0.9792532,0.0068649035,0.0015847833,0.0015566391,0.002047068,0.008693379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012768218,0.00025786133,0.0003307371,0.0015106515,0.012650463,0.011883934,0.0024109443,0.0015170289,0.009711869],"category_scores_gemma":[0.018291753,0.0007801273,0.00023837938,0.0016928883,0.005961535,0.004026815,0.01657603,0.0020654849,0.0010294346],"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":[0.0006556033,0.0033696447,0.15842465,0.0007642743,0.00010988711,0.0031992549,0.40840036,0.0043091592,0.0028636258,0.15350285,0.030766362,0.23363432],"study_design_scores_gemma":[0.00020364473,0.0009990544,0.05669093,0.00039788705,0.00007701742,0.0003618126,0.71844995,0.0026632673,0.0016308025,0.014622172,0.2038015,0.00010194125],"about_ca_topic_score_codex":0.013436368,"about_ca_topic_score_gemma":0.047308035,"teacher_disagreement_score":0.013436368,"about_ca_system_score_codex":0.009101308,"about_ca_system_score_gemma":0.02467187,"threshold_uncertainty_score":0.067525625},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079164153,0.16797566,0.0058637736,0.6014861,0.20261651,0.0056552095,0.0026967723,0.00016669316,0.012747623],"genre_scores_gemma":[0.02106911,0.2219844,0.034559947,0.562957,0.10733395,0.031476475,0.003789822,0.00046199607,0.016367355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.79722536,0.06971893,0.069031544,0.008388524,0.051678415,0.003957255],"domain_scores_gemma":[0.535514,0.28619158,0.042389505,0.01376481,0.114185974,0.007954161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17317584,0.0022423824,0.0058261487,0.01849305,0.00490568,0.01990362,0.0056082276,0.027554985,0.02889272],"category_scores_gemma":[0.49271554,0.0019808551,0.006292341,0.015050274,0.0069522476,0.017779507,0.01368223,0.020937648,0.009585045],"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":[0.0003087164,0.00008977667,0.0008869271,0.1666303,0.0006030716,0.00025787065,0.0033230823,0.00015787553,0.000545436,0.028433794,0.5639371,0.23482598],"study_design_scores_gemma":[0.00017925218,0.000110687746,0.0008019174,0.22802435,0.00060268654,0.0003520455,0.00235022,0.00013030479,0.00035000278,0.016399218,0.75064206,0.00005721987],"about_ca_topic_score_codex":0.0022544758,"about_ca_topic_score_gemma":0.0027365815,"teacher_disagreement_score":0.17317584,"about_ca_system_score_codex":0.015389283,"about_ca_system_score_gemma":0.039962422,"threshold_uncertainty_score":0.9158523},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007503388,0.00037191162,0.9787025,0.0036125754,0.00010871685,0.0012953598,0.00018400104,0.00042307386,0.0077984612],"genre_scores_gemma":[0.066193484,0.00035403162,0.93009377,0.00070317846,0.00011416389,0.0016181412,0.00015153221,0.000096727534,0.00067487813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6856788,0.270567,0.011598388,0.0076133534,0.021997197,0.0025453223],"domain_scores_gemma":[0.42000934,0.50743985,0.019638637,0.0355919,0.01543917,0.0018811278],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23203579,0.0023716763,0.0026863397,0.009214223,0.0043419283,0.015905123,0.004366628,0.0022969653,0.009551064],"category_scores_gemma":[0.35279796,0.001728445,0.0035104775,0.0074977926,0.009946256,0.018507281,0.011741031,0.0072304048,0.0014474964],"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":[0.0010889882,0.00045128935,0.00290941,0.0027205655,0.00040820357,0.00044948538,0.0105309095,0.027930137,0.003463201,0.5368164,0.0048691626,0.4083623],"study_design_scores_gemma":[0.0005137276,0.0005480463,0.0010420197,0.002038666,0.00038524444,0.00022631398,0.0042784577,0.079577655,0.0048924093,0.8775319,0.02876423,0.00020138132],"about_ca_topic_score_codex":0.004430504,"about_ca_topic_score_gemma":0.0068181176,"teacher_disagreement_score":0.76796424,"about_ca_system_score_codex":0.008046342,"about_ca_system_score_gemma":0.02184824,"threshold_uncertainty_score":0.9470366},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018647894,0.020110391,0.0080003375,0.016601639,0.0017292656,0.00008809919,0.000073320974,0.00008217113,0.9531284],"genre_scores_gemma":[0.014864195,0.014255916,0.0062911413,0.011290797,0.001786019,0.00026666035,0.00012295299,0.00018297207,0.95093936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929255,0.0036459311,0.0001949482,0.00045445628,0.002515022,0.00026412634],"domain_scores_gemma":[0.99460924,0.003631004,0.00011425379,0.00043734303,0.0010616515,0.00014649828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068056593,0.001281117,0.0013848039,0.0031425476,0.0027285316,0.011374673,0.001411496,0.006735448,0.04427163],"category_scores_gemma":[0.013152415,0.00064911984,0.0003926071,0.002892568,0.008159243,0.009946317,0.0030375188,0.0061778063,0.01720572],"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":[0.0000038782555,0.000015391814,0.000025198424,0.00010437575,0.0000031759773,0.000013807084,0.00022026771,0.00030292533,0.000033959157,0.78686506,0.16464104,0.047770876],"study_design_scores_gemma":[0.0000031555041,0.000006083542,0.000069777125,0.00037522157,0.0000030450028,0.000027643684,0.00020304965,0.00037878475,0.000066220535,0.47716567,0.5216939,0.0000075321573],"about_ca_topic_score_codex":0.008571487,"about_ca_topic_score_gemma":0.015855983,"teacher_disagreement_score":0.04427163,"about_ca_system_score_codex":0.009276379,"about_ca_system_score_gemma":0.007337611,"threshold_uncertainty_score":0.1481033},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13169526,0.011822789,0.0020852198,0.093749546,0.0002754209,0.00017015733,0.00066238357,0.000083931285,0.75945526],"genre_scores_gemma":[0.61803836,0.006367472,0.00086173625,0.0019216101,0.00007009451,0.00008649551,0.0001423575,0.000065723354,0.3724462],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965538,0.0006031076,0.0000867712,0.0002015164,0.0011123047,0.001442626],"domain_scores_gemma":[0.99508625,0.0015351734,0.00040501342,0.00017424377,0.0011428825,0.0016564092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024699618,0.00028463433,0.00036521116,0.0016416556,0.016659195,0.010923867,0.0015302247,0.0029999244,0.020135364],"category_scores_gemma":[0.0074359854,0.00058317924,0.00031420004,0.0054494194,0.008319653,0.004290355,0.0027817213,0.0019079119,0.0008928715],"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":[0.00009296859,0.00005219364,0.013500394,0.00028790344,0.00002342799,0.0003451183,0.03584659,0.0019187505,0.00026400038,0.7818267,0.09615283,0.069689125],"study_design_scores_gemma":[0.000057079957,0.000036392183,0.058236644,0.00059511984,0.00004501603,0.000097866214,0.04539128,0.0027105752,0.00036299689,0.077630095,0.81474036,0.0000966189],"about_ca_topic_score_codex":0.9890287,"about_ca_topic_score_gemma":0.9967758,"teacher_disagreement_score":0.8041681,"about_ca_system_score_codex":0.19583188,"about_ca_system_score_gemma":0.21898423,"threshold_uncertainty_score":0.932721},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038244918,0.15693696,0.006823875,0.67994666,0.059992857,0.00008971931,0.00008306492,0.00017967622,0.09212263],"genre_scores_gemma":[0.25620514,0.16662782,0.013334115,0.36080873,0.07126009,0.00074077694,0.00037407162,0.0009489304,0.12970038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8518575,0.0891575,0.0063681505,0.012116587,0.030946674,0.009553588],"domain_scores_gemma":[0.64578295,0.16731161,0.0108926045,0.043091767,0.06318517,0.06973591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1128803,0.0010048667,0.002569411,0.0061254133,0.011571961,0.03570265,0.003687215,0.011564988,0.028636198],"category_scores_gemma":[0.20510858,0.0007640222,0.0009984386,0.008300943,0.030535333,0.02476026,0.034331046,0.017399697,0.009692842],"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":[0.00006822909,0.00017577487,0.0020745522,0.0016990653,0.000188699,0.0004384257,0.017796673,0.00022884192,0.0004405097,0.4248037,0.4135049,0.13858058],"study_design_scores_gemma":[0.000018891827,0.000053932952,0.00095833774,0.0032094584,0.00001669806,0.00023332957,0.01151808,0.00015556371,0.0001614495,0.11681277,0.86683494,0.000026467944],"about_ca_topic_score_codex":0.002136523,"about_ca_topic_score_gemma":0.002793124,"teacher_disagreement_score":0.1128803,"about_ca_system_score_codex":0.010763116,"about_ca_system_score_gemma":0.03415945,"threshold_uncertainty_score":0.5969752},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008049404,0.008503474,0.0008201157,0.21736848,0.017151471,0.00027402118,0.00073256454,0.00024502294,0.7468554],"genre_scores_gemma":[0.016591702,0.0019723314,0.00041073683,0.027628109,0.00023180895,0.00004435913,0.0001669772,0.00008618347,0.9528677],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968838,0.00014304178,0.000031105174,0.00019433376,0.0010312226,0.0017163336],"domain_scores_gemma":[0.9967163,0.00010274338,0.00003332346,0.00006156445,0.0011428032,0.0019432585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001754794,0.00072651077,0.00040512034,0.0010873149,0.019123409,0.0079201395,0.0014692135,0.005596359,0.07747035],"category_scores_gemma":[0.003583056,0.00042315602,0.0006903444,0.0009754318,0.0021717676,0.0021701523,0.0041446593,0.0075871907,0.01290181],"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":[0.00001794844,0.00002428579,0.0006642571,0.000035128607,0.000004318954,0.0002176602,0.0009010234,0.00006012849,0.00018617196,0.023059325,0.9513643,0.023465395],"study_design_scores_gemma":[0.0000027288986,0.000006122615,0.0005404998,0.00003229776,0.0000017287391,0.000024057299,0.0017167345,0.000017782679,0.000044704793,0.000684968,0.9969194,0.000008923088],"about_ca_topic_score_codex":0.94100714,"about_ca_topic_score_gemma":0.98328155,"teacher_disagreement_score":0.07747035,"about_ca_system_score_codex":0.031145351,"about_ca_system_score_gemma":0.16245253,"threshold_uncertainty_score":0.25916415},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014187928,0.0011763237,0.00025145142,0.08803855,0.9074597,0.00018402158,0.00085294613,0.00011582378,0.0017793544],"genre_scores_gemma":[0.0016076394,0.0024491374,0.0007774814,0.072405465,0.90301067,0.0004292614,0.00060207216,0.00022680928,0.01849137],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97495496,0.003989741,0.0037595762,0.0024008579,0.013442385,0.0014524636],"domain_scores_gemma":[0.82406974,0.06380019,0.008346944,0.0043271836,0.08010925,0.019346653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036978304,0.0027478286,0.0070244162,0.0059496756,0.0080357455,0.018198475,0.0062435186,0.020703418,0.01913118],"category_scores_gemma":[0.1461306,0.0020752598,0.0035102607,0.004359039,0.0048394534,0.0047633713,0.0025433104,0.017087257,0.010722748],"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":[0.000030328547,0.000010655778,0.00006434027,0.00011990164,0.000025384545,0.000045349963,0.000015276526,0.000011955093,0.00001306774,0.00009580657,0.99838614,0.0011818444],"study_design_scores_gemma":[0.00043567157,0.000038187278,0.00173913,0.0017364162,0.00026265226,0.00015381066,0.00027390494,0.00042633482,0.0001244382,0.0014634688,0.9932801,0.00006575562],"about_ca_topic_score_codex":0.036165737,"about_ca_topic_score_gemma":0.07835974,"teacher_disagreement_score":0.9638343,"about_ca_system_score_codex":0.008867281,"about_ca_system_score_gemma":0.026939658,"threshold_uncertainty_score":0.1955623},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014187928,0.0011763237,0.00025145142,0.08803855,0.9074597,0.00018402158,0.00085294613,0.00011582378,0.0017793544],"genre_scores_gemma":[0.0016076394,0.0024491374,0.0007774814,0.072405465,0.90301067,0.0004292614,0.00060207216,0.00022680928,0.01849137],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97495496,0.003989741,0.0037595762,0.0024008579,0.013442385,0.0014524636],"domain_scores_gemma":[0.82406974,0.06380019,0.008346944,0.0043271836,0.08010925,0.019346653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036978304,0.0027478286,0.0070244162,0.0059496756,0.0080357455,0.018198475,0.0062435186,0.020703418,0.01913118],"category_scores_gemma":[0.1461306,0.0020752598,0.0035102607,0.004359039,0.0048394534,0.0047633713,0.0025433104,0.017087257,0.010722748],"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":[0.000030328547,0.000010655778,0.00006434027,0.00011990164,0.000025384545,0.000045349963,0.000015276526,0.000011955093,0.00001306774,0.00009580657,0.99838614,0.0011818444],"study_design_scores_gemma":[0.00043567157,0.000038187278,0.00173913,0.0017364162,0.00026265226,0.00015381066,0.00027390494,0.00042633482,0.0001244382,0.0014634688,0.9932801,0.00006575562],"about_ca_topic_score_codex":0.036165737,"about_ca_topic_score_gemma":0.07835974,"teacher_disagreement_score":0.9638343,"about_ca_system_score_codex":0.008867281,"about_ca_system_score_gemma":0.026939658,"threshold_uncertainty_score":0.1955623},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025100986,0.02507047,0.03591965,0.018533891,0.0021332703,0.00035405558,0.00016575935,0.00044910784,0.8922728],"genre_scores_gemma":[0.17686152,0.010307719,0.018363776,0.0019226212,0.00010455657,0.00011513724,0.00010468179,0.0005089678,0.79171103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870384,0.0003133841,0.00004582255,0.00016255782,0.0005264668,0.00024796397],"domain_scores_gemma":[0.9992403,0.00022502724,0.000030492163,0.00006932619,0.00029701725,0.00013797154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021026284,0.0005271073,0.00027773238,0.0014041882,0.0018050744,0.0051041343,0.0010805525,0.00092747115,0.014368087],"category_scores_gemma":[0.0044662426,0.00042110635,0.0001764498,0.0015582318,0.002760438,0.0022620996,0.002885882,0.0014221139,0.0011627593],"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":[0.00006675798,0.000017620578,0.00047722636,0.00012860798,0.000005378454,0.00010145465,0.0025107262,0.0010519767,0.0007641854,0.5431788,0.05031248,0.4013848],"study_design_scores_gemma":[0.000014681963,0.00002951927,0.0011685663,0.00027640606,0.000006558164,0.00007812543,0.0010709806,0.0011314711,0.001050867,0.047770638,0.94738466,0.00001747045],"about_ca_topic_score_codex":0.33980268,"about_ca_topic_score_gemma":0.5073587,"teacher_disagreement_score":0.6601973,"about_ca_system_score_codex":0.012810777,"about_ca_system_score_gemma":0.018166706,"threshold_uncertainty_score":0.67564964},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028284578,0.025690993,0.7577092,0.12133362,0.0025374265,0.004956522,0.00028555907,0.00020179269,0.05900034],"genre_scores_gemma":[0.43985206,0.008062737,0.52649313,0.009445358,0.00062604126,0.013608864,0.00007722468,0.00016502777,0.0016695516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4145441,0.56134546,0.00802737,0.0059316247,0.00818992,0.0019615171],"domain_scores_gemma":[0.51348513,0.44694486,0.010028986,0.019661747,0.0072266674,0.002652644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30675027,0.0024398689,0.0034846247,0.01396796,0.011000724,0.02591443,0.0053136367,0.009916853,0.006310081],"category_scores_gemma":[0.250827,0.0029272162,0.0026577003,0.007882339,0.108116746,0.029160429,0.021464095,0.015497251,0.0005670162],"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":[0.00010184973,0.00016331077,0.0025269804,0.0039657946,0.00015929964,0.00052737957,0.11524227,0.0010937266,0.0005318906,0.8259899,0.001917421,0.047780074],"study_design_scores_gemma":[0.00018044015,0.00044055507,0.0019981668,0.011600114,0.00015181983,0.00055030326,0.08799421,0.0025453093,0.0012795251,0.8229904,0.07013142,0.00013765889],"about_ca_topic_score_codex":0.005606595,"about_ca_topic_score_gemma":0.0064330744,"teacher_disagreement_score":0.30675027,"about_ca_system_score_codex":0.01773217,"about_ca_system_score_gemma":0.034315906,"threshold_uncertainty_score":0.85490036},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012888896,0.04500093,0.3201897,0.3431069,0.026929194,0.007946671,0.000946452,0.002058592,0.25253266],"genre_scores_gemma":[0.017812798,0.04469061,0.8411406,0.06001336,0.0052993484,0.008051625,0.0009356065,0.00067043473,0.021385586],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6461954,0.24102034,0.02883609,0.008618218,0.071579315,0.0037505853],"domain_scores_gemma":[0.4506763,0.45255333,0.009096752,0.039338507,0.040099896,0.008235263],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33547598,0.002272945,0.0037724427,0.009488518,0.003929733,0.028425626,0.008965193,0.016356453,0.018301833],"category_scores_gemma":[0.35215038,0.0030528884,0.0029692843,0.0055457843,0.015688334,0.02228634,0.017609445,0.022150306,0.015655542],"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":[0.000051117837,0.00033253766,0.00051161874,0.011214045,0.00033441625,0.00039244926,0.0043417853,0.0014021276,0.0007892517,0.3010998,0.2883095,0.39122123],"study_design_scores_gemma":[0.00013950974,0.00019916342,0.0005751663,0.03366035,0.00011523068,0.0003284132,0.0030684224,0.0010788072,0.0009296676,0.2515717,0.7082225,0.000111017354],"about_ca_topic_score_codex":0.0019872605,"about_ca_topic_score_gemma":0.002640584,"teacher_disagreement_score":0.664524,"about_ca_system_score_codex":0.007823595,"about_ca_system_score_gemma":0.046631444,"threshold_uncertainty_score":0.8194764},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007610387,0.114971355,0.0027547728,0.2677553,0.004122881,0.00028323408,0.0021744235,0.00020124279,0.6001264],"genre_scores_gemma":[0.2230921,0.14835124,0.015620698,0.06390179,0.0013574843,0.00032909462,0.0015010127,0.0004174055,0.5454292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98449904,0.0025992107,0.000741397,0.00079811976,0.00889575,0.0024665366],"domain_scores_gemma":[0.98256797,0.004838827,0.0003560064,0.0004981207,0.008730783,0.0030083738],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011987099,0.00076542795,0.001032744,0.008537805,0.013612452,0.020653285,0.0028652765,0.006651571,0.021560451],"category_scores_gemma":[0.03457353,0.00103223,0.0009214534,0.014598615,0.007433149,0.0039957305,0.004506422,0.006091574,0.0013539426],"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":[0.0000334819,0.00004360675,0.0023370269,0.00060857984,0.00004901525,0.00033562176,0.0024415094,0.0011478078,0.000103556784,0.35072714,0.4958112,0.14636141],"study_design_scores_gemma":[0.000021272752,0.000015501751,0.003970419,0.0011936028,0.00003484536,0.0000740745,0.0018138903,0.00062170194,0.00012502464,0.025408324,0.9666521,0.00006927845],"about_ca_topic_score_codex":0.9948955,"about_ca_topic_score_gemma":0.9974431,"teacher_disagreement_score":0.9880129,"about_ca_system_score_codex":0.18983188,"about_ca_system_score_gemma":0.48408404,"threshold_uncertainty_score":0.93968016},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054678945,0.10173453,0.004401326,0.17774774,0.005015593,0.00009982026,0.0010673419,0.00029343474,0.7041724],"genre_scores_gemma":[0.0824917,0.06203465,0.005081204,0.017318778,0.0011225163,0.00007335106,0.00045038186,0.00035951572,0.831068],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917624,0.0010394849,0.00023060525,0.0005235311,0.0046687257,0.0017752699],"domain_scores_gemma":[0.98942065,0.002944362,0.00019999694,0.00028528902,0.005488842,0.0016608887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00591073,0.0010903972,0.0011708239,0.0048917453,0.019290451,0.022571063,0.002397675,0.006337339,0.024410816],"category_scores_gemma":[0.01698781,0.0010339805,0.00064251095,0.0139023075,0.010417094,0.004177256,0.002732549,0.006597696,0.002712905],"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":[0.000019441464,0.000025707215,0.00061908824,0.000202012,0.000013369914,0.000094353156,0.0019167947,0.0010475852,0.00007721869,0.37188685,0.5284144,0.09568319],"study_design_scores_gemma":[0.000005065679,0.0000040228124,0.0014942216,0.0003892234,0.000010633153,0.00002077055,0.0016745775,0.0007433168,0.00007676369,0.035823904,0.95972395,0.00003363198],"about_ca_topic_score_codex":0.99506515,"about_ca_topic_score_gemma":0.99743795,"teacher_disagreement_score":0.73885953,"about_ca_system_score_codex":0.2611405,"about_ca_system_score_gemma":0.5051139,"threshold_uncertainty_score":0.8569723},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005298082,0.024269775,0.025819227,0.26339385,0.0053549516,0.00006332064,0.000070943344,0.00012755574,0.6756022],"genre_scores_gemma":[0.44916606,0.0371602,0.026053129,0.07426937,0.0067235003,0.00038932363,0.00017882715,0.00038939065,0.4056702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99035347,0.005329434,0.000254123,0.00074820296,0.0025269678,0.0007878049],"domain_scores_gemma":[0.9906697,0.0069831586,0.00029162667,0.00066362874,0.0010355078,0.00035637108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009394515,0.00048311878,0.0005176019,0.0012726451,0.0042888513,0.015750159,0.0012981521,0.0035038614,0.0063877064],"category_scores_gemma":[0.016603483,0.0003307803,0.0004112277,0.0014880027,0.02545861,0.015362406,0.0056140623,0.0059298268,0.0015006757],"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":[0.000003008152,0.000004965501,0.00006190032,0.000029225868,0.0000012920256,0.000014436278,0.0027926937,0.00017727984,0.000018308941,0.95365644,0.028341765,0.014898663],"study_design_scores_gemma":[0.000005361138,0.00000923588,0.00013818727,0.00026187985,0.0000023493963,0.000034153163,0.0027335717,0.00046773857,0.000058431648,0.4821102,0.51417166,0.000007248488],"about_ca_topic_score_codex":0.008253971,"about_ca_topic_score_gemma":0.011557322,"teacher_disagreement_score":0.015750159,"about_ca_system_score_codex":0.008951126,"about_ca_system_score_gemma":0.010254602,"threshold_uncertainty_score":0.06494528},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017325229,0.013659929,0.40476924,0.017090505,0.0011286533,0.0010836372,0.00026004118,0.00025232974,0.5600232],"genre_scores_gemma":[0.13342851,0.023034163,0.72940785,0.007820978,0.0003615977,0.0062838113,0.0002582091,0.00021387535,0.09919095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98804516,0.009346669,0.00026587985,0.00042834543,0.0016808854,0.00023308789],"domain_scores_gemma":[0.9777076,0.020593276,0.00046610084,0.00035308662,0.00066597085,0.0002140121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013249497,0.002131727,0.0015314792,0.0034823818,0.0015913624,0.006746009,0.0035530122,0.0037894067,0.019859878],"category_scores_gemma":[0.015216483,0.00076041906,0.0011026437,0.0025397541,0.013206512,0.005434175,0.002046644,0.0036997206,0.002385147],"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":[0.000015131015,0.00006720328,0.00015757965,0.00060435955,0.000029200108,0.000038963248,0.0010632738,0.0018794888,0.00015798637,0.9387141,0.00903612,0.048236594],"study_design_scores_gemma":[0.000029816965,0.00007419804,0.00029923662,0.0010964813,0.000034770685,0.00007693303,0.0015773257,0.0031636732,0.00029446397,0.9313473,0.06198549,0.000020336545],"about_ca_topic_score_codex":0.0057569947,"about_ca_topic_score_gemma":0.0097501865,"teacher_disagreement_score":0.019859878,"about_ca_system_score_codex":0.006469577,"about_ca_system_score_gemma":0.009761869,"threshold_uncertainty_score":0.07007092},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015292387,0.019179419,0.0007081594,0.26686007,0.0076626,0.0005008226,0.006712688,0.00023670185,0.6828472],"genre_scores_gemma":[0.031133208,0.0071234303,0.00083568145,0.01769006,0.0004968264,0.00016523896,0.0011111057,0.00010811655,0.9413364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.988602,0.0006498231,0.00032505087,0.00036143142,0.006999111,0.0030626259],"domain_scores_gemma":[0.9920021,0.0006873543,0.00025076847,0.00030910745,0.004701369,0.0020492096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043967594,0.000826136,0.00048528743,0.003483408,0.009419153,0.007533463,0.0014640458,0.0060265996,0.024809545],"category_scores_gemma":[0.008266436,0.0006350596,0.0007258661,0.0078034042,0.0028575817,0.0024520387,0.0033792919,0.0044564875,0.0030977996],"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":[0.00007727044,0.000039517025,0.0019324761,0.00020624521,0.000007910772,0.00023016457,0.0019288174,0.00014872606,0.00023453971,0.048105888,0.9165144,0.030574106],"study_design_scores_gemma":[0.000010180741,0.0000070094693,0.004380497,0.00007866417,0.0000069449925,0.00002139184,0.0009716657,0.00002291768,0.000086761305,0.0006904462,0.993708,0.000015431713],"about_ca_topic_score_codex":0.972976,"about_ca_topic_score_gemma":0.98844355,"teacher_disagreement_score":0.89918035,"about_ca_system_score_codex":0.100819655,"about_ca_system_score_gemma":0.27546096,"threshold_uncertainty_score":0.7315012},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9512456,0.0011831629,0.010522882,0.012797124,0.00008845147,0.00018318852,0.00013589974,0.000034093602,0.023809526],"genre_scores_gemma":[0.99776757,0.00013615147,0.001446766,0.00020265741,0.000015952115,0.0000377115,0.000021675047,0.000009146502,0.00036245928],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.90996855,0.054968417,0.0030557485,0.0064750654,0.017760584,0.0077716084],"domain_scores_gemma":[0.60392857,0.28540513,0.03081444,0.025739571,0.032690693,0.021421494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11124712,0.00040092017,0.0011476534,0.009932732,0.019705767,0.02346273,0.0044596787,0.0035285836,0.006682515],"category_scores_gemma":[0.22026177,0.0016546258,0.00059214025,0.007881527,0.06479296,0.018468253,0.017178891,0.00445147,0.0005511855],"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":[0.00039603887,0.00034727718,0.26142988,0.0009246626,0.000088834386,0.00031161195,0.5325286,0.0007832209,0.0006741045,0.13446969,0.0028423776,0.06520371],"study_design_scores_gemma":[0.000063865555,0.0001962584,0.22766617,0.0012995533,0.000058896225,0.0002859158,0.6143251,0.0054792142,0.0008114366,0.13085765,0.018855566,0.000100440324],"about_ca_topic_score_codex":0.07946313,"about_ca_topic_score_gemma":0.104889266,"teacher_disagreement_score":0.11124712,"about_ca_system_score_codex":0.028721176,"about_ca_system_score_gemma":0.03663458,"threshold_uncertainty_score":0.588338},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032896485,0.009827822,0.19918856,0.30972728,0.006691965,0.00097207096,0.0000921636,0.0007393064,0.4398644],"genre_scores_gemma":[0.733602,0.008682368,0.1708067,0.034543503,0.0013000936,0.0014724799,0.00009717273,0.00088132394,0.048614524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8736375,0.10173652,0.0026515967,0.003476143,0.014442765,0.0040555466],"domain_scores_gemma":[0.85521805,0.0958932,0.0059169712,0.016081106,0.017035367,0.009855398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08620828,0.0012214949,0.00123157,0.0032296896,0.020196285,0.04180485,0.002705671,0.0067887907,0.012378641],"category_scores_gemma":[0.083425894,0.0010106234,0.0015615374,0.0023773795,0.06011745,0.026003813,0.028867792,0.0152964685,0.003401054],"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":[0.000055147117,0.00040841263,0.0023689773,0.0011417745,0.00008269694,0.0004288551,0.20697002,0.0007566025,0.0009671484,0.58054376,0.045003463,0.16127317],"study_design_scores_gemma":[0.00003298732,0.00019252686,0.0011687198,0.003586837,0.0000722462,0.0005644477,0.12147985,0.00063893426,0.0018337223,0.2672217,0.6030712,0.00013671299],"about_ca_topic_score_codex":0.006135495,"about_ca_topic_score_gemma":0.011188477,"teacher_disagreement_score":0.08620828,"about_ca_system_score_codex":0.012914715,"about_ca_system_score_gemma":0.04615595,"threshold_uncertainty_score":0.45591837},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02222889,0.0066269618,0.028359488,0.9041465,0.0020616,0.0020091862,0.00007167401,0.0003962621,0.034099452],"genre_scores_gemma":[0.3728612,0.013032928,0.39586705,0.1820149,0.0010901854,0.0048167226,0.0004073704,0.00041628903,0.029493455],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.70612216,0.2048449,0.027071472,0.0058596157,0.045475,0.010626839],"domain_scores_gemma":[0.3560893,0.3174069,0.025942337,0.037076194,0.2331691,0.030316126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.37710905,0.0007766522,0.0011058805,0.006146379,0.017960127,0.02510639,0.008301705,0.013310692,0.0024822426],"category_scores_gemma":[0.34402335,0.0018058384,0.0012332769,0.0044248058,0.025021378,0.015058421,0.027319212,0.02437482,0.0011483156],"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":[0.00011844744,0.0009518553,0.015520112,0.0030346974,0.0001537848,0.0024917,0.13541482,0.0039209053,0.0024907785,0.17393371,0.31876555,0.3432037],"study_design_scores_gemma":[0.00013561142,0.0002812249,0.013410406,0.010310459,0.00008060391,0.00083969976,0.11920225,0.0032188566,0.003340724,0.07564934,0.7730136,0.0005173018],"about_ca_topic_score_codex":0.20752802,"about_ca_topic_score_gemma":0.357684,"teacher_disagreement_score":0.935634,"about_ca_system_score_codex":0.06436601,"about_ca_system_score_gemma":0.39682817,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035574535,0.009286715,0.0046644723,0.9780294,0.0038181522,0.00010901707,0.00002372856,0.0001673186,0.0035454873],"genre_scores_gemma":[0.046713118,0.028432723,0.073660895,0.8336502,0.009620207,0.0011502982,0.00024076174,0.0004441969,0.006087637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5569977,0.31049633,0.020453338,0.012415177,0.08443131,0.015206262],"domain_scores_gemma":[0.23639418,0.5403627,0.015614744,0.028726771,0.1026893,0.076212265],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.47655994,0.0026374464,0.0063250065,0.0068225944,0.016423509,0.03952872,0.011889372,0.050506614,0.013898084],"category_scores_gemma":[0.4634505,0.0018376757,0.0060335337,0.005496797,0.0584407,0.054259703,0.03205206,0.08239473,0.0034328261],"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":[0.0002383213,0.0007080132,0.0018778481,0.0032331848,0.00020890133,0.0003364424,0.0078092264,0.0010796812,0.0004210241,0.11997579,0.6620186,0.20209289],"study_design_scores_gemma":[0.0002388752,0.00025106638,0.0020215514,0.013279169,0.00012163305,0.00037786487,0.015713962,0.0011513082,0.00041565925,0.22223616,0.7438359,0.0003568543],"about_ca_topic_score_codex":0.030877324,"about_ca_topic_score_gemma":0.04381654,"teacher_disagreement_score":0.47655994,"about_ca_system_score_codex":0.043432917,"about_ca_system_score_gemma":0.29931867,"threshold_uncertainty_score":0.6454948},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008512108,0.086389825,0.72615564,0.10269904,0.01327352,0.047096666,0.0016725032,0.0036611897,0.010539576],"genre_scores_gemma":[0.042027358,0.008288886,0.910902,0.006850825,0.0010013707,0.029494552,0.00019043486,0.0006393413,0.0006052293],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.20118618,0.6808654,0.07364676,0.01334003,0.02995046,0.0010110479],"domain_scores_gemma":[0.10407138,0.7660106,0.028252834,0.05536739,0.043625455,0.0026723556],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73589355,0.0056881206,0.016567249,0.023653269,0.0051441235,0.01873817,0.01031617,0.010666465,0.008334951],"category_scores_gemma":[0.8568293,0.0067315823,0.023323044,0.015301704,0.010111398,0.020891467,0.008308283,0.0138868755,0.002551945],"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":[0.0037234193,0.0006951511,0.00872676,0.18181618,0.10635383,0.0010080608,0.024327809,0.009681293,0.0033492194,0.07576649,0.090260774,0.49429107],"study_design_scores_gemma":[0.009671102,0.0023873202,0.0060161403,0.28314972,0.0641422,0.0017693358,0.006718431,0.04947226,0.009313372,0.36335212,0.20209791,0.0019100746],"about_ca_topic_score_codex":0.0035197856,"about_ca_topic_score_gemma":0.0045403475,"teacher_disagreement_score":0.26410645,"about_ca_system_score_codex":0.011770397,"about_ca_system_score_gemma":0.030556781,"threshold_uncertainty_score":0.32569033},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064779416,0.15401174,0.006029264,0.795745,0.019726936,0.000072391165,0.00008408653,0.00011526822,0.02356743],"genre_scores_gemma":[0.04923505,0.4403208,0.03762157,0.30244738,0.046175625,0.00052133406,0.0002215826,0.00058028655,0.12287637],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98163086,0.01014774,0.0011369677,0.0010188054,0.0056482884,0.00041735003],"domain_scores_gemma":[0.94162714,0.04119348,0.0021203628,0.001350489,0.010295504,0.0034129173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031491786,0.0010741466,0.0009500997,0.003951888,0.0044515445,0.012235989,0.00097489747,0.0054662125,0.0035120426],"category_scores_gemma":[0.05435523,0.00066581176,0.0007253627,0.004194047,0.013842647,0.013622803,0.0034632145,0.009902462,0.0024197719],"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":[0.000023426644,0.000017200311,0.000646208,0.0003715912,0.00002051374,0.000061017217,0.0012222277,0.00017013164,0.00019848433,0.040557787,0.9011478,0.05556376],"study_design_scores_gemma":[0.00001119497,0.000033592518,0.0012609564,0.0014708404,0.000018288058,0.0002673507,0.0018877214,0.0005541447,0.00039068828,0.08813342,0.905909,0.00006273988],"about_ca_topic_score_codex":0.016247496,"about_ca_topic_score_gemma":0.05561706,"teacher_disagreement_score":0.031491786,"about_ca_system_score_codex":0.0057221865,"about_ca_system_score_gemma":0.011813149,"threshold_uncertainty_score":0.16654646},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049440876,0.10410572,0.013003888,0.61071557,0.01884759,0.00023821677,0.00020547939,0.00031461785,0.20312808],"genre_scores_gemma":[0.64954436,0.06893246,0.027368162,0.062309925,0.0075141997,0.00047749106,0.00035763488,0.00053330604,0.18296252],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95566714,0.025727237,0.0014682837,0.0012810319,0.014121688,0.0017346862],"domain_scores_gemma":[0.9264641,0.036549173,0.003180574,0.0041919407,0.021759285,0.007854957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05801743,0.00038446282,0.000556481,0.0018642233,0.0045073186,0.01061994,0.00076429016,0.0032591328,0.008093248],"category_scores_gemma":[0.06788648,0.0003349402,0.0005308464,0.0018877857,0.0074374774,0.006683639,0.0070043295,0.0075803897,0.0012024868],"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":[0.00031817236,0.00024592938,0.0033916235,0.0016482072,0.00006494239,0.00047487972,0.045838073,0.00025427403,0.0021288206,0.11655709,0.34283593,0.48624212],"study_design_scores_gemma":[0.000022034834,0.00019222652,0.005410658,0.002680049,0.00002738427,0.00043797996,0.015658407,0.00027326477,0.0009927228,0.01139131,0.96285164,0.00006236892],"about_ca_topic_score_codex":0.0120759,"about_ca_topic_score_gemma":0.052670117,"teacher_disagreement_score":0.05801743,"about_ca_system_score_codex":0.010515027,"about_ca_system_score_gemma":0.019099794,"threshold_uncertainty_score":0.30682915},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023072952,0.031309508,0.011601224,0.6364505,0.010412597,0.00017519579,0.000029876463,0.00017577267,0.2867723],"genre_scores_gemma":[0.7971361,0.017557962,0.021010691,0.082590625,0.007067809,0.0003571037,0.0000287694,0.00037892855,0.07387201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.93717045,0.047717724,0.0013226969,0.0016499468,0.009614033,0.0025252646],"domain_scores_gemma":[0.9277114,0.0523948,0.0030281185,0.0038088558,0.007041654,0.0060152505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06698744,0.00045405896,0.0006648891,0.0024038123,0.022697309,0.027672004,0.001889884,0.0069679446,0.0067238105],"category_scores_gemma":[0.0708657,0.0004678917,0.00045602478,0.001880668,0.06601474,0.017659454,0.018238017,0.012358215,0.0008102649],"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":[0.000041990206,0.00008145909,0.00050945487,0.00056778005,0.000020133082,0.00038591537,0.30703503,0.000090044196,0.0004960202,0.51399577,0.07659627,0.1001802],"study_design_scores_gemma":[0.000015191615,0.0000771747,0.0010460854,0.0014997742,0.000023002249,0.0003910647,0.15233633,0.00018642317,0.0006019163,0.13159479,0.7121693,0.00005888845],"about_ca_topic_score_codex":0.010448182,"about_ca_topic_score_gemma":0.037890572,"teacher_disagreement_score":0.06698744,"about_ca_system_score_codex":0.016707877,"about_ca_system_score_gemma":0.028050799,"threshold_uncertainty_score":0.35426766},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000085379965,0.002224633,0.00028975957,0.1405941,0.8403657,0.000050735922,0.00024846502,0.00022862248,0.015912585],"genre_scores_gemma":[0.0026788446,0.0044749565,0.0010449672,0.2659414,0.5134832,0.00021649725,0.00048024912,0.0005609736,0.21111888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9902024,0.00096109754,0.00085557875,0.0017004744,0.0050277626,0.0012526686],"domain_scores_gemma":[0.96969664,0.0050286613,0.0015040626,0.0018989602,0.01730104,0.0045706644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008796125,0.0017800558,0.0015397011,0.0025814665,0.004401504,0.012516652,0.0047790622,0.013515113,0.1538858],"category_scores_gemma":[0.058198765,0.0007411869,0.0023608746,0.0019453542,0.0023223658,0.0069226297,0.004077528,0.014372692,0.10136002],"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":[0.000008368158,0.000006237374,0.000023046865,0.00005090818,0.0000019994295,0.000040239665,0.000022016317,0.000011555231,0.00003091674,0.00072614755,0.99377453,0.005304018],"study_design_scores_gemma":[0.0000062285476,0.000005435315,0.0000753971,0.00009700606,0.0000020435195,0.000046779285,0.00004421373,0.000022557111,0.00005061526,0.000509451,0.9991334,0.0000069525363],"about_ca_topic_score_codex":0.0021830322,"about_ca_topic_score_gemma":0.0039777127,"teacher_disagreement_score":0.1538858,"about_ca_system_score_codex":0.00359109,"about_ca_system_score_gemma":0.008573257,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006091165,0.10783412,0.0016058763,0.8480071,0.024554444,0.00004670236,0.00009184448,0.000084194304,0.017714785],"genre_scores_gemma":[0.011541122,0.09038875,0.008678679,0.7676393,0.07018544,0.0006785678,0.00022481024,0.00047787075,0.050185487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.90246725,0.05833368,0.0055180336,0.0033511107,0.027517447,0.0028124906],"domain_scores_gemma":[0.87121165,0.08855741,0.0050502317,0.005006727,0.025361506,0.004812379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.073643945,0.0014203192,0.0021259594,0.0020571356,0.0046385424,0.013827482,0.0022652077,0.018447088,0.009137097],"category_scores_gemma":[0.11462553,0.000938415,0.00128714,0.0021585731,0.021798154,0.012670794,0.0054725255,0.024158409,0.0071480973],"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":[0.000015898422,0.000005942098,0.00007333773,0.00027798922,0.000011516981,0.000024066007,0.000367466,0.000024039602,0.000043401596,0.033165377,0.9482549,0.017736062],"study_design_scores_gemma":[0.000021667598,0.000017716027,0.0006969647,0.0021804087,0.0000143927555,0.00016856544,0.00064220896,0.00010913128,0.00011175026,0.07716455,0.91884273,0.000029885861],"about_ca_topic_score_codex":0.028200548,"about_ca_topic_score_gemma":0.05304781,"teacher_disagreement_score":0.073643945,"about_ca_system_score_codex":0.012778717,"about_ca_system_score_gemma":0.023771334,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23604089,0.0096600475,0.17769986,0.389787,0.0010585503,0.0017040258,0.00024380392,0.00042391202,0.18338193],"genre_scores_gemma":[0.9133282,0.0016212966,0.07231256,0.009763255,0.00023159252,0.000763366,0.00003405922,0.000039533432,0.0019061157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8806897,0.087573454,0.0054661776,0.004977956,0.015362516,0.0059301252],"domain_scores_gemma":[0.9052849,0.059512947,0.011753673,0.007130949,0.009982511,0.006334919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.093286574,0.0008264359,0.0016677538,0.0037711563,0.0030669007,0.010883011,0.0021242253,0.0061237793,0.0058501964],"category_scores_gemma":[0.16255246,0.00041837114,0.0009438836,0.002660443,0.01218451,0.011590318,0.013428033,0.004952845,0.0006845604],"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":[0.00047765468,0.0010039255,0.032972004,0.00257217,0.00046014372,0.0004085928,0.013512315,0.0064681433,0.0018745532,0.53348833,0.012679003,0.3940831],"study_design_scores_gemma":[0.00042706382,0.0014350957,0.018231077,0.0041321944,0.00038873928,0.00059510523,0.013294471,0.010844259,0.004387282,0.8682166,0.07787069,0.00017739387],"about_ca_topic_score_codex":0.0022328172,"about_ca_topic_score_gemma":0.004108987,"teacher_disagreement_score":0.093286574,"about_ca_system_score_codex":0.005347459,"about_ca_system_score_gemma":0.017320396,"threshold_uncertainty_score":0.49335247},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26096663,0.028907362,0.072127424,0.3562782,0.0018527922,0.0039568744,0.00016805547,0.00023600268,0.27550668],"genre_scores_gemma":[0.93869025,0.006554197,0.03057944,0.012949093,0.00032223575,0.0018583006,0.000055624296,0.00008401518,0.008906828],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8939484,0.08808715,0.0023731487,0.002029183,0.010840744,0.0027213928],"domain_scores_gemma":[0.8753252,0.09823618,0.005271917,0.004631156,0.014342186,0.0021934067],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.1251525,0.0005981837,0.0010731943,0.002268957,0.005930704,0.013490012,0.0024530198,0.003192703,0.0029701611],"category_scores_gemma":[0.14569844,0.0002512251,0.00052094064,0.0020630155,0.023701312,0.008664678,0.007878756,0.0050284495,0.00022861542],"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":[0.00026599204,0.0012456386,0.00955941,0.0040189023,0.00018040945,0.00046485802,0.12126325,0.0031805374,0.0011281793,0.41199362,0.017317234,0.42938203],"study_design_scores_gemma":[0.0005016222,0.0028019017,0.0279962,0.018674126,0.00028125392,0.00041792612,0.24234709,0.006396172,0.00555642,0.4047858,0.28996664,0.00027484036],"about_ca_topic_score_codex":0.018778842,"about_ca_topic_score_gemma":0.023424318,"teacher_disagreement_score":0.9940693,"about_ca_system_score_codex":0.018316686,"about_ca_system_score_gemma":0.032241378,"threshold_uncertainty_score":0.6618776},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17547934,0.017478954,0.20677488,0.33217523,0.0014860582,0.0005176537,0.000046987603,0.00029219082,0.26574886],"genre_scores_gemma":[0.9470583,0.002649654,0.038455352,0.005134314,0.00016702905,0.00026227385,0.00001835455,0.00009909875,0.006155612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9402883,0.049140457,0.0015739918,0.0015786972,0.005620776,0.0017978072],"domain_scores_gemma":[0.92694545,0.04970439,0.0025483305,0.0071161836,0.011064434,0.0026212328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0991257,0.0008830522,0.0010703875,0.003756659,0.0109323505,0.021347879,0.003016984,0.0036912062,0.0034472377],"category_scores_gemma":[0.06810753,0.000548788,0.000687439,0.0017170038,0.085738435,0.026897654,0.019973015,0.010494686,0.00042125268],"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":[0.000048505226,0.000102164544,0.0028390451,0.00032159567,0.00002814363,0.0003275721,0.19248894,0.00078347663,0.00035499997,0.73890734,0.0025874046,0.061210833],"study_design_scores_gemma":[0.000029897232,0.00009123068,0.0012744254,0.0015628196,0.000025497087,0.00018566774,0.12886742,0.0026072355,0.0009830998,0.79317355,0.07111086,0.000088225184],"about_ca_topic_score_codex":0.022950977,"about_ca_topic_score_gemma":0.020509355,"teacher_disagreement_score":0.0991257,"about_ca_system_score_codex":0.01730256,"about_ca_system_score_gemma":0.021080714,"threshold_uncertainty_score":0.5242331},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074412905,0.09326548,0.08483768,0.5860204,0.015433447,0.00029894317,0.00017941097,0.0005576393,0.14499407],"genre_scores_gemma":[0.83716637,0.07125701,0.027307976,0.038303968,0.0056505245,0.0005171696,0.00010699108,0.0005328546,0.019157011],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9587737,0.029613761,0.0011377549,0.0019368994,0.00658149,0.001956382],"domain_scores_gemma":[0.8777664,0.09246243,0.004286974,0.0040189447,0.0149954865,0.006469792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.048137426,0.00081324455,0.001174146,0.004885443,0.009315771,0.021473257,0.0019507423,0.0047660735,0.00843758],"category_scores_gemma":[0.09351322,0.00085813453,0.0008839757,0.003921972,0.0323546,0.03953877,0.009086746,0.010644383,0.0015603572],"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":[0.00011458036,0.00013351213,0.0047876984,0.0014079695,0.000030279667,0.00019394784,0.46100017,0.00027697542,0.0013106209,0.30904883,0.036848687,0.18484677],"study_design_scores_gemma":[0.00003311446,0.00032808929,0.006209423,0.004417518,0.000054999215,0.00017854897,0.4456803,0.0006728133,0.00097078655,0.17421032,0.36708957,0.00015444304],"about_ca_topic_score_codex":0.009152538,"about_ca_topic_score_gemma":0.007123796,"teacher_disagreement_score":0.9518626,"about_ca_system_score_codex":0.008766425,"about_ca_system_score_gemma":0.013791013,"threshold_uncertainty_score":0.2545781},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13330148,0.02401012,0.06969296,0.45272702,0.005315774,0.00019102315,0.000048696806,0.00007614785,0.31463677],"genre_scores_gemma":[0.96696836,0.003985229,0.0048716785,0.013305105,0.00084727956,0.0001410313,0.00001497306,0.000047817106,0.009818562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.95272315,0.038414087,0.000982255,0.0012140651,0.005138212,0.0015282329],"domain_scores_gemma":[0.96332866,0.0270815,0.0022133768,0.0017298308,0.0030668913,0.0025797654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033766147,0.0004486356,0.0006670862,0.0019055324,0.010140917,0.024957033,0.0016986189,0.0059191245,0.0023222687],"category_scores_gemma":[0.04091698,0.00041916213,0.0005073137,0.0012965106,0.09720758,0.017491225,0.014328664,0.011042194,0.00026738262],"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":[0.000028231465,0.000035678928,0.0013070734,0.0001357555,0.000011365205,0.00012956759,0.18888092,0.00016820048,0.0003293058,0.78316045,0.005356898,0.020456519],"study_design_scores_gemma":[0.000017768049,0.00007721939,0.0028161476,0.0008372183,0.000022494487,0.00031920403,0.22623551,0.00067414384,0.000455552,0.6162753,0.15219513,0.00007432464],"about_ca_topic_score_codex":0.0035788193,"about_ca_topic_score_gemma":0.0050215526,"teacher_disagreement_score":0.033766147,"about_ca_system_score_codex":0.0065643857,"about_ca_system_score_gemma":0.010836047,"threshold_uncertainty_score":0.17857462},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8383791,0.002953587,0.0047333553,0.071644425,0.00021315775,0.0012374296,0.00087497995,0.00006349248,0.07990048],"genre_scores_gemma":[0.9760902,0.0017719025,0.005724991,0.0043468312,0.000028418897,0.00017226655,0.00014979843,0.00006013791,0.011655532],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98399276,0.006892997,0.00071217946,0.00074104255,0.0039616744,0.003699334],"domain_scores_gemma":[0.9710537,0.013304583,0.0010353776,0.00070872955,0.009809852,0.004087705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013080022,0.00042746472,0.00066356297,0.0019100524,0.021833103,0.009960004,0.0028400063,0.0045523546,0.002807709],"category_scores_gemma":[0.031359173,0.00039907653,0.0005118696,0.0053542657,0.006433233,0.0029287252,0.0035991406,0.0047062747,0.00035381786],"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":[0.0006657575,0.0018793216,0.15631826,0.0019425907,0.00014360057,0.04242128,0.40509936,0.005845088,0.0038970988,0.13971004,0.05550953,0.18656802],"study_design_scores_gemma":[0.00013951412,0.00046503198,0.08176555,0.002176244,0.00011105842,0.003523356,0.6771809,0.00608386,0.0025586982,0.0093769785,0.21627292,0.00034585557],"about_ca_topic_score_codex":0.9804437,"about_ca_topic_score_gemma":0.9884851,"teacher_disagreement_score":0.98692,"about_ca_system_score_codex":0.119510934,"about_ca_system_score_gemma":0.19780247,"threshold_uncertainty_score":0.8671166},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037636461,0.2607487,0.038182165,0.42753702,0.006731536,0.000120228025,0.0001877329,0.00045377045,0.26227522],"genre_scores_gemma":[0.31140372,0.2885322,0.09444292,0.109938964,0.022507124,0.0008974547,0.00051300233,0.0015319919,0.17023273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97265935,0.015671507,0.00091847836,0.0013562837,0.0081492,0.0012452448],"domain_scores_gemma":[0.94646627,0.040617716,0.00096337294,0.001957418,0.0077525065,0.002242769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022133302,0.0010169452,0.0014896089,0.006165984,0.0055020214,0.022442665,0.0015464931,0.006043041,0.004290098],"category_scores_gemma":[0.030642308,0.0010308498,0.00058340665,0.013150232,0.061733726,0.017892163,0.005769807,0.011045366,0.002262403],"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":[0.000015300651,0.000018985427,0.0004585881,0.0002450477,0.000016915,0.000034453693,0.006156003,0.0002671958,0.00005316619,0.8246172,0.08987893,0.07823829],"study_design_scores_gemma":[0.000011701444,0.000014349082,0.00091889984,0.0006676012,0.000009019576,0.000046169105,0.0037500958,0.0004490077,0.00008234349,0.6104864,0.3835333,0.00003115081],"about_ca_topic_score_codex":0.07561993,"about_ca_topic_score_gemma":0.1015604,"teacher_disagreement_score":0.07561993,"about_ca_system_score_codex":0.020735197,"about_ca_system_score_gemma":0.0298055,"threshold_uncertainty_score":0.1504451},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040043797,0.11477846,0.027263794,0.5554129,0.20864442,0.0031299496,0.017475132,0.0027367945,0.06655417],"genre_scores_gemma":[0.0529944,0.26994896,0.10149154,0.17314559,0.0997335,0.005607032,0.04278819,0.0047957357,0.24949506],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9333273,0.012019572,0.00592173,0.0025517156,0.04222943,0.003950185],"domain_scores_gemma":[0.6847064,0.061599698,0.009315443,0.010925184,0.20058605,0.03286718],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.053953473,0.001577525,0.0012453444,0.0054444782,0.004326023,0.013125082,0.0026563408,0.005127578,0.018736443],"category_scores_gemma":[0.15275948,0.0011207365,0.0013230274,0.0101204375,0.0022451282,0.0068762647,0.0069465255,0.009471844,0.012664861],"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":[0.00008202389,0.000047241505,0.0007414339,0.0011315693,0.000019794848,0.0000900207,0.00075989205,0.00012870163,0.00029432127,0.0051143277,0.9063985,0.085192226],"study_design_scores_gemma":[0.000025874893,0.000103778686,0.0042526927,0.0019279184,0.000028132932,0.00013792029,0.0010517789,0.00008869207,0.0004966792,0.002190053,0.9896355,0.00006100258],"about_ca_topic_score_codex":0.1466808,"about_ca_topic_score_gemma":0.1676217,"teacher_disagreement_score":0.99567395,"about_ca_system_score_codex":0.021525098,"about_ca_system_score_gemma":0.08219792,"threshold_uncertainty_score":0.29165405},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012189096,0.0020639997,0.00156554,0.9851147,0.001832063,0.00010957388,0.000015539577,0.000022819904,0.008056843],"genre_scores_gemma":[0.15662116,0.0073116394,0.017405668,0.7916972,0.004475653,0.0025736564,0.00008826158,0.0005806158,0.019246163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.587704,0.29743055,0.013456103,0.010835683,0.067961164,0.022612618],"domain_scores_gemma":[0.27705958,0.5761722,0.007083676,0.016258633,0.05867954,0.06474649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5002483,0.0010403488,0.002226229,0.003684228,0.033641282,0.0662425,0.009976419,0.048586536,0.015360767],"category_scores_gemma":[0.49341527,0.0016463044,0.0018552012,0.00560864,0.085653715,0.05959857,0.059790622,0.07685366,0.0019128679],"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":[0.00013460497,0.00042498994,0.000994156,0.00074274454,0.00003858557,0.00035443754,0.057189588,0.00021224271,0.00021722204,0.5440878,0.32929057,0.06631293],"study_design_scores_gemma":[0.00032085562,0.00029296766,0.0017923405,0.003304986,0.00004703314,0.0002151141,0.08886648,0.0005105178,0.0006102073,0.1927803,0.71110445,0.00015475319],"about_ca_topic_score_codex":0.03586662,"about_ca_topic_score_gemma":0.047430504,"teacher_disagreement_score":0.4997517,"about_ca_system_score_codex":0.0464288,"about_ca_system_score_gemma":0.18116805,"threshold_uncertainty_score":0.6162828},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014244005,0.072852835,0.000971014,0.3409128,0.0023974145,0.000079331636,0.0007355756,0.000094513256,0.5677125],"genre_scores_gemma":[0.14936297,0.037606467,0.0010377524,0.011529202,0.000508987,0.0000652189,0.00020452782,0.00011980728,0.79956514],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753606,0.0003061786,0.000060301303,0.0001513461,0.001100458,0.00084569794],"domain_scores_gemma":[0.99747026,0.00042514622,0.00011709638,0.00009355578,0.0009766379,0.00091740553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002060152,0.0004413678,0.00040999582,0.0019317655,0.012233989,0.011722804,0.001329874,0.0038712644,0.021098921],"category_scores_gemma":[0.005054425,0.00070729543,0.00033718048,0.006487089,0.008137342,0.003908455,0.0024799388,0.0027368458,0.0016648348],"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":[0.0000345976,0.000021967571,0.0021188601,0.00022683205,0.000007980598,0.0001353647,0.010404404,0.00040517744,0.00010257992,0.31311616,0.59903663,0.07438941],"study_design_scores_gemma":[0.0000059620547,0.0000049624596,0.004409654,0.00026450705,0.0000049688765,0.000021093341,0.006548736,0.00011401342,0.000047433226,0.012385062,0.9761755,0.000018009343],"about_ca_topic_score_codex":0.9886423,"about_ca_topic_score_gemma":0.9975448,"teacher_disagreement_score":0.793892,"about_ca_system_score_codex":0.20610797,"about_ca_system_score_gemma":0.25357595,"threshold_uncertainty_score":0.92080224},"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":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032681823,0.30532005,0.5075019,0.026137594,0.010182871,0.08789684,0.0033001783,0.0009701377,0.026008556],"genre_scores_gemma":[0.1904199,0.06524088,0.5718796,0.013836912,0.00531399,0.14697222,0.0012189083,0.000668236,0.0044492558],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.25036278,0.6688023,0.033018015,0.009703741,0.03700372,0.0011093778],"domain_scores_gemma":[0.13968226,0.7751594,0.03035427,0.027996287,0.025044426,0.0017633259],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37900573,0.0021434512,0.006609877,0.017211502,0.0051777572,0.014424079,0.0052088317,0.005756856,0.014037033],"category_scores_gemma":[0.6599316,0.00264768,0.0032565612,0.015684277,0.0056749647,0.009517108,0.0052532395,0.0031667375,0.002003828],"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":[0.0016971119,0.0014980246,0.010509407,0.109329954,0.0105474815,0.00026847023,0.0073488033,0.0007383172,0.0009507128,0.035295524,0.0216217,0.80019444],"study_design_scores_gemma":[0.0068663973,0.0089195995,0.04561306,0.2828698,0.028428543,0.0022652145,0.023387425,0.016634155,0.01183755,0.31312072,0.2587487,0.0013088954],"about_ca_topic_score_codex":0.002265557,"about_ca_topic_score_gemma":0.0056114197,"teacher_disagreement_score":0.62099427,"about_ca_system_score_codex":0.00716808,"about_ca_system_score_gemma":0.01843604,"threshold_uncertainty_score":0.7657965},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017473118,0.048252486,0.04473133,0.2195915,0.0018753947,0.00077046274,0.001304406,0.0003486333,0.66565263],"genre_scores_gemma":[0.33953658,0.10744374,0.29373223,0.033109024,0.0011466781,0.0014626024,0.002547136,0.00043849557,0.22058359],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99108195,0.0046103476,0.000524088,0.00041879862,0.0025536555,0.0008111225],"domain_scores_gemma":[0.98404425,0.007752854,0.0014547702,0.0009570351,0.0050194985,0.00077170506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021871615,0.0008248975,0.00063970307,0.0044789175,0.001582455,0.014231133,0.0022898146,0.0030277616,0.010683996],"category_scores_gemma":[0.0314572,0.0003861308,0.0004207581,0.0039270627,0.0044393865,0.008116536,0.0051323287,0.0030590831,0.0016734495],"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":[0.000045914243,0.00019862485,0.0049355,0.0017209847,0.000087528846,0.0003696859,0.0030200721,0.0018144384,0.0011156906,0.3153625,0.08127212,0.5900569],"study_design_scores_gemma":[0.000032500768,0.0001920707,0.011466485,0.009386185,0.00013982106,0.000180227,0.010014384,0.0022186418,0.0021146303,0.22136098,0.74278677,0.00010722988],"about_ca_topic_score_codex":0.06714895,"about_ca_topic_score_gemma":0.1626743,"teacher_disagreement_score":0.06714895,"about_ca_system_score_codex":0.009009876,"about_ca_system_score_gemma":0.03750886,"threshold_uncertainty_score":0.13351619},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22189528,0.13764235,0.12718685,0.4359006,0.0033267455,0.003252058,0.00322903,0.0010846946,0.06648246],"genre_scores_gemma":[0.7772966,0.027952353,0.17312737,0.00914684,0.0005275267,0.0018072191,0.0012378284,0.00016583067,0.008738517],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.873614,0.09522774,0.007369845,0.005308703,0.013983595,0.0044960226],"domain_scores_gemma":[0.7000861,0.17224522,0.020428607,0.01417099,0.08117744,0.011891574],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19608048,0.0012178598,0.0009885951,0.0061550187,0.0047515817,0.013007194,0.0031503278,0.003835922,0.0046145017],"category_scores_gemma":[0.16613473,0.00073804165,0.001109177,0.0042367484,0.0073853224,0.012364274,0.005088098,0.0051218164,0.000812923],"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":[0.00069425866,0.00036133538,0.078048326,0.007510873,0.00031404756,0.0010530583,0.06256038,0.0040173465,0.0028492145,0.09619615,0.04735025,0.69904464],"study_design_scores_gemma":[0.0003148757,0.0013251523,0.15654126,0.04056525,0.0003290501,0.0015731284,0.078670345,0.011177317,0.0049582254,0.032311417,0.6715534,0.00068065064],"about_ca_topic_score_codex":0.20324488,"about_ca_topic_score_gemma":0.11185553,"teacher_disagreement_score":0.20324488,"about_ca_system_score_codex":0.04285113,"about_ca_system_score_gemma":0.085200846,"threshold_uncertainty_score":0.9913759},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19884014,0.048588783,0.004969342,0.054744318,0.0012623694,0.00038297437,0.005051055,0.001155584,0.6850055],"genre_scores_gemma":[0.42485243,0.012405393,0.0051752175,0.0032457125,0.00011819643,0.000106801745,0.0016146412,0.0001529523,0.5523287],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998221,0.00021429878,0.00004451455,0.00020129894,0.00056560256,0.00075337116],"domain_scores_gemma":[0.997985,0.00025562962,0.00007345651,0.00005340432,0.0011981548,0.00043440994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014623466,0.0004344168,0.0002658313,0.0030105193,0.005437944,0.0037734054,0.0012879978,0.0011172822,0.012565753],"category_scores_gemma":[0.0031180365,0.00039719,0.0003344673,0.005011214,0.0010664343,0.0008130969,0.0010864902,0.0010927884,0.0008615543],"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":[0.00016527342,0.00017914051,0.030859996,0.00030118038,0.000041025993,0.0005241045,0.0059524374,0.0035488063,0.0013468735,0.12702236,0.24125248,0.58880633],"study_design_scores_gemma":[0.000019941155,0.000055237164,0.09442572,0.00030105867,0.00002111634,0.000111828864,0.0033356862,0.0018186837,0.00084086857,0.0018126423,0.89720374,0.000053525495],"about_ca_topic_score_codex":0.9946366,"about_ca_topic_score_gemma":0.99592507,"teacher_disagreement_score":0.09559774,"about_ca_system_score_codex":0.09559774,"about_ca_system_score_gemma":0.13931262,"threshold_uncertainty_score":0.6936134},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889127,0.0005091556,0.0011702444,0.0021621373,0.0001289747,0.00028690003,0.000040227827,0.000022215896,0.0067674066],"genre_scores_gemma":[0.98846334,0.000580328,0.0017182607,0.0010675748,0.000045827604,0.00046258295,0.00005878419,0.000026594027,0.0075767036],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9708892,0.01596064,0.0017283029,0.0014123826,0.006795029,0.0032143488],"domain_scores_gemma":[0.93244404,0.022448186,0.0072219307,0.0025267906,0.023475239,0.011883831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031637527,0.0005364231,0.00076532946,0.001498326,0.005887816,0.00826682,0.00127176,0.0020977617,0.005740346],"category_scores_gemma":[0.08604466,0.000533919,0.0008992322,0.0009307154,0.00498997,0.0037710276,0.005122633,0.0037999933,0.001016171],"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":[0.00079603423,0.0012423905,0.20060727,0.0005873374,0.000103732025,0.0012709145,0.7168342,0.00016615471,0.0029911257,0.0027759986,0.0031320076,0.069492854],"study_design_scores_gemma":[0.000048003167,0.0013749072,0.20761758,0.0008210933,0.00008720048,0.00043745263,0.7487275,0.0005985042,0.0014218779,0.0010102644,0.03770303,0.00015259477],"about_ca_topic_score_codex":0.036312025,"about_ca_topic_score_gemma":0.04427436,"teacher_disagreement_score":0.036312025,"about_ca_system_score_codex":0.008153557,"about_ca_system_score_gemma":0.01831225,"threshold_uncertainty_score":0.16731727},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988582,0.000088185654,0.0002847564,0.00012719908,0.00000416783,0.000071961105,0.0000072192156,0.0000030323752,0.0005552798],"genre_scores_gemma":[0.99911827,0.00006755093,0.00035170463,0.00004728663,0.0000039086403,0.00007837891,0.0000072928915,0.000002741637,0.0003228787],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9773931,0.016167637,0.0010684037,0.0009368339,0.0020397143,0.0023943274],"domain_scores_gemma":[0.9494316,0.032558523,0.006349203,0.0013537277,0.006597117,0.0037098238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02664589,0.00047670328,0.00057168363,0.0018879881,0.0038307998,0.0047164904,0.0015175453,0.0011355928,0.00090946665],"category_scores_gemma":[0.05740148,0.0004185191,0.000319192,0.000997944,0.0032551251,0.001898871,0.0026471599,0.0013780029,0.0002160388],"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":[0.0003179522,0.0018659867,0.19710948,0.00030012795,0.00001802882,0.0007620457,0.7536552,0.00018481628,0.0021586784,0.0004395905,0.00021031415,0.04297781],"study_design_scores_gemma":[0.00002951633,0.0017612919,0.26683688,0.0003681505,0.000032247142,0.00036609813,0.7244643,0.0007110893,0.0017722159,0.00024720037,0.0033524337,0.000058588328],"about_ca_topic_score_codex":0.016667008,"about_ca_topic_score_gemma":0.026649915,"teacher_disagreement_score":0.02664589,"about_ca_system_score_codex":0.0066591273,"about_ca_system_score_gemma":0.0070188344,"threshold_uncertainty_score":0.14091861},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9762482,0.00063256285,0.0099141365,0.0013786886,0.000048918162,0.0010783232,0.0007791999,0.00010621314,0.009813746],"genre_scores_gemma":[0.9896437,0.00016602343,0.008580854,0.00015669988,0.000018842878,0.00046593338,0.00029819878,0.000018419905,0.0006513838],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.86583966,0.072937615,0.014027316,0.0041756574,0.03712603,0.0058937166],"domain_scores_gemma":[0.27492023,0.5742486,0.06008754,0.019142836,0.06740734,0.00419349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1403445,0.00039362715,0.00082712696,0.006243495,0.0015414004,0.004304733,0.0023970844,0.0021567978,0.0017147657],"category_scores_gemma":[0.47924355,0.0004319795,0.0011777041,0.0066333003,0.002144554,0.0036177023,0.0032097157,0.0025906663,0.00028293979],"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":[0.0023282906,0.0012337306,0.694978,0.0024633761,0.0010830784,0.00034759965,0.028615804,0.0051738336,0.0038083026,0.009927282,0.0022694485,0.24777123],"study_design_scores_gemma":[0.00012020142,0.002945334,0.9440984,0.000669608,0.0006058497,0.00012392054,0.030922065,0.0063216845,0.004712217,0.0031917968,0.006171566,0.00011739301],"about_ca_topic_score_codex":0.008596142,"about_ca_topic_score_gemma":0.011923592,"teacher_disagreement_score":0.8596555,"about_ca_system_score_codex":0.005717031,"about_ca_system_score_gemma":0.012118394,"threshold_uncertainty_score":0.74222153},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4306343,0.027616818,0.10307873,0.061483778,0.0029375623,0.0042570652,0.0023132209,0.0012488278,0.36642963],"genre_scores_gemma":[0.8537045,0.006588309,0.057618372,0.0034078944,0.00020886885,0.0024699715,0.000932146,0.00021246541,0.074857496],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9815869,0.007955452,0.0012174088,0.001316366,0.005289214,0.0026347416],"domain_scores_gemma":[0.9651146,0.008346266,0.0028451565,0.0013168214,0.0145509485,0.007826215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018913155,0.000771688,0.0006783055,0.003690012,0.0033418206,0.008417987,0.0020322313,0.0024819733,0.017986294],"category_scores_gemma":[0.045104373,0.00061621814,0.00088726915,0.0035400419,0.0037022491,0.004714541,0.0073570344,0.0040087774,0.0032535642],"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":[0.00092810456,0.0012155747,0.06729796,0.0019732718,0.00008638647,0.00033447915,0.03490288,0.0019607334,0.0038413617,0.14962046,0.023114791,0.714724],"study_design_scores_gemma":[0.00023888588,0.0023735443,0.28894997,0.005846998,0.000097098055,0.0005093468,0.0298516,0.0023022136,0.010084533,0.040387597,0.6190132,0.0003451396],"about_ca_topic_score_codex":0.08363681,"about_ca_topic_score_gemma":0.10632965,"teacher_disagreement_score":0.08363681,"about_ca_system_score_codex":0.020439312,"about_ca_system_score_gemma":0.050722167,"threshold_uncertainty_score":0.1663},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6251174,0.011389516,0.10616361,0.021310994,0.00047173462,0.0025570702,0.0005286559,0.00040317266,0.23205787],"genre_scores_gemma":[0.9514723,0.0022973784,0.034544695,0.0007150019,0.00007839841,0.0012796395,0.00015958339,0.00008763633,0.009365334],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8785671,0.0753865,0.006545879,0.0044070175,0.03131565,0.0037778476],"domain_scores_gemma":[0.8109602,0.11011827,0.017356105,0.0072605163,0.047111657,0.0071932366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08672557,0.00066704454,0.0010392689,0.0052060974,0.0044192346,0.01410281,0.0014303963,0.0015182103,0.0073250043],"category_scores_gemma":[0.13578664,0.00053889246,0.0011228764,0.0048868596,0.0058586802,0.0073403628,0.006677633,0.0031955512,0.0011337866],"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":[0.0007311683,0.0008984064,0.11865821,0.0055214507,0.0005490081,0.00021148674,0.124879,0.0025949657,0.004164913,0.10115814,0.006143379,0.63448995],"study_design_scores_gemma":[0.00025911003,0.0027783609,0.4068742,0.010647636,0.00070306374,0.0005875379,0.22815287,0.007809782,0.013459167,0.08249057,0.24567759,0.0005600544],"about_ca_topic_score_codex":0.014922532,"about_ca_topic_score_gemma":0.018180503,"teacher_disagreement_score":0.08672557,"about_ca_system_score_codex":0.016053457,"about_ca_system_score_gemma":0.03233857,"threshold_uncertainty_score":0.4586541},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010399037,0.0028398533,0.000691638,0.1244457,0.8441629,0.0002522438,0.0010552029,0.00061248534,0.025835905],"genre_scores_gemma":[0.0037839606,0.0085447775,0.0050326926,0.23293284,0.38607022,0.001200564,0.0019279398,0.0015410138,0.358966],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9796141,0.002515642,0.0022930303,0.0026132092,0.011300832,0.0016631787],"domain_scores_gemma":[0.8677301,0.018846666,0.006345918,0.006819516,0.09013766,0.010120102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016112834,0.0021421167,0.0020106062,0.0043859724,0.0048245564,0.008960615,0.0069061564,0.009444512,0.2744705],"category_scores_gemma":[0.15890464,0.001048774,0.002784086,0.002913929,0.0020920876,0.0060537905,0.0038590808,0.011268904,0.18528937],"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":[0.00000728994,0.000004949414,0.000015807991,0.00008853389,0.0000018161105,0.000027391492,0.000018604864,0.00000709694,0.000018461473,0.000298882,0.993619,0.0058921813],"study_design_scores_gemma":[0.000008920866,0.00000631336,0.000069156,0.00033521687,0.000002907647,0.00006824641,0.000053059714,0.000018839495,0.00004936619,0.00045693395,0.99892175,0.000009173899],"about_ca_topic_score_codex":0.0036114962,"about_ca_topic_score_gemma":0.007934927,"teacher_disagreement_score":0.2744705,"about_ca_system_score_codex":0.0047953967,"about_ca_system_score_gemma":0.017759966,"threshold_uncertainty_score":0.9181953},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9301776,0.0020326925,0.0135534415,0.022165354,0.000105271814,0.00023512525,0.00018298603,0.000041387688,0.03150614],"genre_scores_gemma":[0.99579203,0.00031773694,0.0026765396,0.00044885976,0.00002952118,0.00006484532,0.00003444162,0.000017947901,0.00061814324],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92254585,0.044891674,0.0025811216,0.006438666,0.015579715,0.007962935],"domain_scores_gemma":[0.69689906,0.21832432,0.023981389,0.02279986,0.020871459,0.017123949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1000356,0.0004672071,0.0013162725,0.010520133,0.020104209,0.027560763,0.004822286,0.0046161776,0.006686691],"category_scores_gemma":[0.17183222,0.0019838987,0.00075655326,0.0091404,0.080263525,0.03077704,0.018543007,0.006061339,0.0006723243],"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":[0.00030244928,0.00032314894,0.13729078,0.001031926,0.00007197141,0.0003825055,0.6237518,0.00060299784,0.0005668013,0.17214055,0.0023992015,0.06113585],"study_design_scores_gemma":[0.000062078114,0.00020001066,0.154922,0.0013623955,0.000048421374,0.00032172806,0.6440088,0.004114196,0.0006064794,0.16957977,0.024681168,0.00009290898],"about_ca_topic_score_codex":0.048493464,"about_ca_topic_score_gemma":0.067155674,"teacher_disagreement_score":0.1000356,"about_ca_system_score_codex":0.027788423,"about_ca_system_score_gemma":0.033855904,"threshold_uncertainty_score":0.5290451},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9301776,0.0020326925,0.0135534415,0.022165354,0.000105271814,0.00023512525,0.00018298603,0.000041387688,0.03150614],"genre_scores_gemma":[0.99579203,0.00031773694,0.0026765396,0.00044885976,0.00002952118,0.00006484532,0.00003444162,0.000017947901,0.00061814324],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.92254585,0.044891674,0.0025811216,0.006438666,0.015579715,0.007962935],"domain_scores_gemma":[0.69689906,0.21832432,0.023981389,0.02279986,0.020871459,0.017123949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1000356,0.0004672071,0.0013162725,0.010520133,0.020104209,0.027560763,0.004822286,0.0046161776,0.006686691],"category_scores_gemma":[0.17183222,0.0019838987,0.00075655326,0.0091404,0.080263525,0.03077704,0.018543007,0.006061339,0.0006723243],"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":[0.00030244928,0.00032314894,0.13729078,0.001031926,0.00007197141,0.0003825055,0.6237518,0.00060299784,0.0005668013,0.17214055,0.0023992015,0.06113585],"study_design_scores_gemma":[0.000062078114,0.00020001066,0.154922,0.0013623955,0.000048421374,0.00032172806,0.6440088,0.004114196,0.0006064794,0.16957977,0.024681168,0.00009290898],"about_ca_topic_score_codex":0.048493464,"about_ca_topic_score_gemma":0.067155674,"teacher_disagreement_score":0.1000356,"about_ca_system_score_codex":0.027788423,"about_ca_system_score_gemma":0.033855904,"threshold_uncertainty_score":0.5290451},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009991325,0.012663718,0.10242281,0.1472046,0.0030645046,0.000307618,0.00010419557,0.00044045298,0.7238007],"genre_scores_gemma":[0.7064216,0.013147341,0.15844183,0.015410488,0.0013479899,0.00083311246,0.0002593987,0.00034572493,0.10379248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97629297,0.012306867,0.0009436636,0.0016365793,0.0076401955,0.001179728],"domain_scores_gemma":[0.96552217,0.017746985,0.0009971419,0.006013337,0.0071225353,0.0025978568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02448513,0.0008013277,0.0009413415,0.0045649367,0.0060377303,0.020586051,0.0025581294,0.005343066,0.01775609],"category_scores_gemma":[0.03065165,0.0006473242,0.00070728065,0.0029870493,0.030340154,0.011781856,0.009754,0.005831125,0.004375447],"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":[0.0000060677653,0.00007502847,0.00050778885,0.00016833114,0.000009556436,0.00004734153,0.0044262875,0.00033320527,0.00011185224,0.91780275,0.014162081,0.062349606],"study_design_scores_gemma":[0.000012538899,0.000029707962,0.0007407601,0.0012327409,0.000014439659,0.00007755622,0.008473287,0.0010333983,0.0003319048,0.7154477,0.27258584,0.000020147358],"about_ca_topic_score_codex":0.022257922,"about_ca_topic_score_gemma":0.026736476,"teacher_disagreement_score":0.02448513,"about_ca_system_score_codex":0.015347129,"about_ca_system_score_gemma":0.05795883,"threshold_uncertainty_score":0.12949127},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8187853,0.0021030088,0.001931759,0.025971465,0.00008778738,0.0006159476,0.0005252445,0.00004663482,0.14993283],"genre_scores_gemma":[0.9840904,0.0006588713,0.0011174842,0.0008278143,0.000009921202,0.0000653983,0.000075439,0.000014563334,0.013140036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99266773,0.0014249178,0.00013782848,0.0002631061,0.0014077878,0.00409855],"domain_scores_gemma":[0.9878506,0.0050884723,0.00049842004,0.00026898616,0.004094825,0.002198809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049682595,0.00046292203,0.0004956316,0.0024338122,0.026441535,0.009240077,0.0023685372,0.0033996126,0.004621257],"category_scores_gemma":[0.012858626,0.00041456622,0.0005502971,0.004280883,0.006679205,0.002230145,0.0028882695,0.0028682507,0.0001600747],"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":[0.0009627478,0.00090228906,0.1016668,0.0012206037,0.00027373162,0.012926618,0.12879916,0.028957555,0.0028745588,0.5384176,0.059737153,0.1232613],"study_design_scores_gemma":[0.00027059813,0.00041938963,0.15110578,0.0012790449,0.00041084882,0.00074986287,0.4853395,0.019553592,0.0022182558,0.039634462,0.29872423,0.00029441505],"about_ca_topic_score_codex":0.99641526,"about_ca_topic_score_gemma":0.99798465,"teacher_disagreement_score":0.30491987,"about_ca_system_score_codex":0.30491987,"about_ca_system_score_gemma":0.39179352,"threshold_uncertainty_score":0.8061944},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9077397,0.002619396,0.018456971,0.008976656,0.00035670816,0.0017193643,0.0027450062,0.0002891726,0.057097044],"genre_scores_gemma":[0.97065103,0.00063933356,0.020380434,0.0006681013,0.000041326017,0.0014748764,0.001290828,0.00007848106,0.004775652],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9705161,0.012148752,0.002027994,0.0015275305,0.01204755,0.0017321665],"domain_scores_gemma":[0.9089382,0.025231251,0.00666635,0.006096778,0.050229106,0.0028382896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03766772,0.00047092,0.0012202716,0.002067297,0.003720512,0.0036383262,0.0029592533,0.00076726783,0.0035722365],"category_scores_gemma":[0.084497735,0.00048464024,0.0010307968,0.0039998563,0.0028952044,0.0025174865,0.0022788285,0.0014667364,0.00041365944],"study_design_candidate":"bench_or_experimental","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":[0.00025499088,0.00018790718,0.84448165,0.00022163715,0.00017896609,0.00006578126,0.0046370737,0.0006883763,0.00046532226,0.005008252,0.0068511707,0.13695888],"study_design_scores_gemma":[0.000052822947,0.00024845524,0.9814904,0.0006067046,0.00012163996,0.000033609176,0.0048129777,0.002090655,0.000574004,0.0008786798,0.009039989,0.00005008164],"about_ca_topic_score_codex":0.87943864,"about_ca_topic_score_gemma":0.96902585,"teacher_disagreement_score":0.12056136,"about_ca_system_score_codex":0.028712496,"about_ca_system_score_gemma":0.05614442,"threshold_uncertainty_score":0.24254268},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8149738,0.0012761421,0.0007011486,0.09431136,0.00020448398,0.00022329565,0.00047616116,0.000056394427,0.087777205],"genre_scores_gemma":[0.98263663,0.00039412547,0.0003864692,0.0010701694,0.000020213301,0.00002463364,0.000051042818,0.000015141013,0.015401475],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9880624,0.0031251432,0.00041246973,0.00039497012,0.0036747253,0.004330314],"domain_scores_gemma":[0.9479074,0.011996386,0.0036334936,0.0007697397,0.013671315,0.022021635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007932045,0.00012180816,0.00028438724,0.0014336298,0.0151213175,0.008156835,0.0013089279,0.0015709604,0.0047401083],"category_scores_gemma":[0.0287717,0.00032662755,0.00024925437,0.0029444809,0.0048726327,0.0014034155,0.0031077983,0.0024427152,0.00030796966],"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":[0.0005048893,0.00041667593,0.56911784,0.000642989,0.0001568833,0.0013069102,0.096340835,0.005374119,0.0011838936,0.10007534,0.07892254,0.14595702],"study_design_scores_gemma":[0.00009652385,0.00018725793,0.61306053,0.00061082724,0.000077999255,0.00011249538,0.17036186,0.0037253778,0.0010448938,0.006959142,0.20363514,0.0001279863],"about_ca_topic_score_codex":0.9803083,"about_ca_topic_score_gemma":0.995195,"teacher_disagreement_score":0.82966375,"about_ca_system_score_codex":0.17033628,"about_ca_system_score_gemma":0.3808933,"threshold_uncertainty_score":0.9622923},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8142907,0.0019388392,0.12513626,0.0044876384,0.00056487747,0.008936732,0.0039304523,0.00046403627,0.04025048],"genre_scores_gemma":[0.85409373,0.00074973924,0.12348144,0.001000326,0.00011562565,0.012466927,0.0018135359,0.0001659575,0.006112708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8922613,0.056715015,0.011539639,0.008625334,0.027984228,0.0028745234],"domain_scores_gemma":[0.60211974,0.22048758,0.023822283,0.038020227,0.11163764,0.003912504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12837406,0.00094056065,0.0013232575,0.0069912546,0.004263661,0.007247659,0.0019925684,0.0016419581,0.005787889],"category_scores_gemma":[0.28547755,0.001009485,0.00212944,0.0070727575,0.0048411875,0.0057744724,0.007897945,0.0028754892,0.0012454013],"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":[0.00075858244,0.00059390714,0.46682823,0.0034243371,0.0012517519,0.00020032469,0.1501887,0.002398028,0.0059760353,0.027796851,0.006570161,0.33401302],"study_design_scores_gemma":[0.0001667532,0.0010893531,0.8390407,0.0030625027,0.0007009507,0.00020381346,0.05262028,0.006034404,0.008920079,0.016008744,0.07184615,0.00030632492],"about_ca_topic_score_codex":0.02832456,"about_ca_topic_score_gemma":0.035795864,"teacher_disagreement_score":0.12837406,"about_ca_system_score_codex":0.009800683,"about_ca_system_score_gemma":0.021804182,"threshold_uncertainty_score":0.678915},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059831548,0.011344589,0.0011546997,0.9599374,0.013231641,0.00004915595,0.000026553505,0.000037636164,0.008235116],"genre_scores_gemma":[0.13614106,0.012430394,0.004127423,0.82007444,0.0055634137,0.0003296768,0.000031414555,0.00017892981,0.021123275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9811926,0.0145024955,0.000502203,0.000917947,0.0017961495,0.0010885692],"domain_scores_gemma":[0.9686756,0.021989716,0.0009513022,0.00043857805,0.0033820397,0.004562753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025835136,0.0009661134,0.0016990991,0.0011143878,0.02146701,0.008747059,0.0024325103,0.010429085,0.0045369323],"category_scores_gemma":[0.04601885,0.00090598856,0.0008082653,0.001267047,0.011803127,0.015543357,0.0052586645,0.04100546,0.0010770649],"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":[0.0001448464,0.00028692678,0.0009780886,0.00031596143,0.000035888912,0.0030808994,0.2207611,0.00021967749,0.0005521125,0.0486572,0.6982966,0.026670642],"study_design_scores_gemma":[0.000026522708,0.00012922406,0.0007672936,0.0010171863,0.000019081614,0.0021546015,0.2192111,0.0005619906,0.00035123428,0.011729732,0.76387125,0.00016076736],"about_ca_topic_score_codex":0.010971648,"about_ca_topic_score_gemma":0.014001461,"teacher_disagreement_score":0.025835136,"about_ca_system_score_codex":0.007923569,"about_ca_system_score_gemma":0.009023438,"threshold_uncertainty_score":0.1366309},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14521761,0.76732725,0.0034195757,0.060828086,0.0012183795,0.0010089437,0.0004899379,0.00004703055,0.020443156],"genre_scores_gemma":[0.56993717,0.40094426,0.007187187,0.01786478,0.00058726966,0.0019109773,0.0003825758,0.0000977146,0.0010880562],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85250133,0.100087926,0.020245878,0.0031107324,0.021466509,0.0025876507],"domain_scores_gemma":[0.3555873,0.545127,0.043458156,0.0070139444,0.04423076,0.0045828633],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15506864,0.00045442744,0.0015485635,0.019361008,0.002823566,0.008632365,0.0020910923,0.0022836397,0.0019369038],"category_scores_gemma":[0.41246116,0.0009208109,0.0012761105,0.02335952,0.00622594,0.012051627,0.0072552767,0.002904116,0.0002746366],"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":[0.0002881301,0.00024108012,0.02778059,0.119336784,0.000990631,0.0012191118,0.2717911,0.00031910284,0.0007845974,0.011658927,0.025448585,0.5401413],"study_design_scores_gemma":[0.000121360616,0.00034260488,0.061254654,0.39541495,0.001324786,0.0017808441,0.2701246,0.0002490631,0.0008830159,0.003922897,0.2644143,0.0001669702],"about_ca_topic_score_codex":0.008817908,"about_ca_topic_score_gemma":0.024847696,"teacher_disagreement_score":0.84493136,"about_ca_system_score_codex":0.009580867,"about_ca_system_score_gemma":0.0362407,"threshold_uncertainty_score":0.8200911},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008303581,0.0025778743,0.12380374,0.037472352,0.0006239813,0.00029228991,0.000113283895,0.00021248024,0.8266005],"genre_scores_gemma":[0.59052044,0.004680966,0.11901469,0.011877596,0.0006359251,0.00079924415,0.0003415786,0.00047090198,0.27165854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9906771,0.0060446267,0.00012656604,0.00088455464,0.0015884909,0.0006786247],"domain_scores_gemma":[0.9907616,0.004952005,0.00037866438,0.0014647099,0.00094142114,0.0015015602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015662722,0.00067513087,0.0004895019,0.0010349862,0.005574081,0.013768371,0.0027091198,0.0026649425,0.022080204],"category_scores_gemma":[0.014046382,0.000333227,0.0005014844,0.0014635231,0.021222208,0.0144425975,0.011839541,0.0053375848,0.0030367856],"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":[0.0000036167382,0.000019388834,0.00020015781,0.00004835535,0.0000031280983,0.000042543372,0.0070567788,0.00027448309,0.00005691814,0.96154004,0.00938571,0.021368984],"study_design_scores_gemma":[0.000006645461,0.000024292909,0.00027774042,0.0002276265,0.000004525898,0.00014478518,0.008195711,0.000747751,0.0002827547,0.6548518,0.33522478,0.000011607334],"about_ca_topic_score_codex":0.006482985,"about_ca_topic_score_gemma":0.0116182,"teacher_disagreement_score":0.022080204,"about_ca_system_score_codex":0.008919836,"about_ca_system_score_gemma":0.011692443,"threshold_uncertainty_score":0.08283335},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8528161,0.0036818185,0.048942406,0.041791376,0.000279466,0.00031077865,0.000038108254,0.00014653665,0.05199337],"genre_scores_gemma":[0.9941732,0.0002666214,0.0042905593,0.0006233161,0.000017726743,0.00006285089,0.0000073103224,0.000028528335,0.00052993366],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.79598564,0.1666048,0.005593532,0.0072432673,0.01856906,0.0060036997],"domain_scores_gemma":[0.65157944,0.29168898,0.017562345,0.011838793,0.019082634,0.008247755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16711918,0.00052253704,0.00085493474,0.005234564,0.017715966,0.023109818,0.004172132,0.0041709812,0.0027933829],"category_scores_gemma":[0.22320993,0.0010527329,0.0006832598,0.0035682332,0.05312762,0.017526316,0.021104041,0.006638817,0.0003343742],"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":[0.000062496605,0.00007216649,0.010197583,0.00034422884,0.000028749575,0.0004887579,0.89131427,0.00031248736,0.0007002349,0.067535065,0.0009717618,0.027972246],"study_design_scores_gemma":[0.000027500831,0.000109182256,0.007428533,0.0007189318,0.000022780516,0.00043861897,0.87922645,0.0015940709,0.00078900985,0.0837586,0.025805678,0.00008058283],"about_ca_topic_score_codex":0.0050978228,"about_ca_topic_score_gemma":0.006199109,"teacher_disagreement_score":0.83288085,"about_ca_system_score_codex":0.016823968,"about_ca_system_score_gemma":0.020406641,"threshold_uncertainty_score":0.88382125},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01126296,0.0018251283,0.50790185,0.020034323,0.0054362193,0.1198019,0.049792707,0.034624718,0.24932031],"genre_scores_gemma":[0.011810497,0.0025027967,0.62534106,0.0023819802,0.0007727171,0.136142,0.024626108,0.008502382,0.18792047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9049179,0.04755722,0.019499091,0.0023223383,0.023093482,0.002609981],"domain_scores_gemma":[0.827066,0.051704917,0.009533561,0.033403784,0.07234571,0.00594605],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09887336,0.0016830043,0.0014279044,0.007873938,0.0031794095,0.008979007,0.005316788,0.0042672516,0.09251979],"category_scores_gemma":[0.15942316,0.0025517605,0.0013366777,0.0074783964,0.0016790233,0.0053062094,0.0059111896,0.005966284,0.15084535],"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":[0.00039017075,0.0009300738,0.0017298249,0.0013574199,0.00001510754,0.00030148737,0.003778386,0.0009102264,0.004117921,0.022740057,0.6537133,0.31001598],"study_design_scores_gemma":[0.0000626878,0.00017955416,0.0008238636,0.00053613324,0.0000054777397,0.00016041909,0.00059014076,0.0004035883,0.0026682059,0.0026902102,0.9918298,0.00005001073],"about_ca_topic_score_codex":0.0026246645,"about_ca_topic_score_gemma":0.004256135,"teacher_disagreement_score":0.9011266,"about_ca_system_score_codex":0.0031917868,"about_ca_system_score_gemma":0.014363732,"threshold_uncertainty_score":0.52289855},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046319594,0.014667462,0.004380356,0.23256324,0.00481609,0.00015957058,0.00083763036,0.00030524057,0.7376384],"genre_scores_gemma":[0.062964,0.013633299,0.004346762,0.022390315,0.00047698422,0.00006751199,0.00032753678,0.00012121843,0.8956725],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822205,0.00020433251,0.000029367602,0.00013870375,0.0007390718,0.00066644116],"domain_scores_gemma":[0.9982705,0.00019500387,0.000036029975,0.000048507634,0.0009820277,0.0004679283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00195159,0.00066067785,0.00041983835,0.0013381481,0.010431168,0.015810948,0.0015934707,0.0047339713,0.039598905],"category_scores_gemma":[0.0021841999,0.00021599865,0.00039705881,0.004235067,0.0051176245,0.003583761,0.0018928337,0.0040204385,0.0044596386],"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":[0.00001765243,0.000019152872,0.00062722585,0.00016428484,0.0000034433624,0.0001212515,0.0018697515,0.00044403356,0.000096812575,0.41127026,0.53409547,0.0512707],"study_design_scores_gemma":[0.000006966771,0.0000060204006,0.00085512624,0.00030539132,0.0000061074334,0.000049010883,0.0045921537,0.0003063709,0.000151685,0.03130647,0.9623939,0.000020759264],"about_ca_topic_score_codex":0.96855104,"about_ca_topic_score_gemma":0.98685235,"teacher_disagreement_score":0.92713535,"about_ca_system_score_codex":0.07286464,"about_ca_system_score_gemma":0.22667275,"threshold_uncertainty_score":0.52867246},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016752891,0.018463742,0.035688464,0.12918007,0.001869429,0.000087213426,0.00007576988,0.00018703465,0.8127729],"genre_scores_gemma":[0.27610064,0.049942512,0.07464684,0.045502897,0.0034695042,0.0008544309,0.00039187793,0.00073686294,0.54835445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918761,0.004675767,0.00023459093,0.000487277,0.002129725,0.00059647445],"domain_scores_gemma":[0.9792468,0.017471768,0.00045373596,0.0008270391,0.0012565653,0.00074414996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015059941,0.00087083614,0.0009092916,0.0017380508,0.002439812,0.017272051,0.0023107787,0.006323272,0.024034338],"category_scores_gemma":[0.024236578,0.0006090428,0.0002799394,0.0028321538,0.01363393,0.02237068,0.006763284,0.008146588,0.006086934],"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":[0.0000027597628,0.000014402374,0.000030440033,0.00006383514,0.0000014972195,0.000017700902,0.0004835481,0.00054363196,0.000034954595,0.95087254,0.025517298,0.022417404],"study_design_scores_gemma":[0.0000024409183,0.0000035334813,0.000047538648,0.00031983477,0.0000013228283,0.000014713393,0.00082690106,0.0005914608,0.000084213134,0.83013326,0.16796921,0.000005497663],"about_ca_topic_score_codex":0.005099869,"about_ca_topic_score_gemma":0.008524955,"teacher_disagreement_score":0.024034338,"about_ca_system_score_codex":0.010447472,"about_ca_system_score_gemma":0.022749253,"threshold_uncertainty_score":0.08040291},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003055298,0.007338865,0.0007027571,0.022233494,0.023618681,0.00035311026,0.00846872,0.00057570817,0.9364031],"genre_scores_gemma":[0.0011630121,0.0049782693,0.00046419768,0.0051208874,0.002519921,0.00016938556,0.0039759027,0.00020500326,0.98140347],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828315,0.00016346776,0.0001036578,0.0002377242,0.0009931499,0.00021899868],"domain_scores_gemma":[0.99606824,0.00042556392,0.0001817645,0.00029114637,0.0024976647,0.0005354896],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018769947,0.000738506,0.00063694414,0.0020675892,0.0013622708,0.006394071,0.0016797388,0.003343668,0.48377115],"category_scores_gemma":[0.0064126956,0.00036958154,0.00054571754,0.002816991,0.00046427033,0.0031913072,0.0013779616,0.0030063747,0.45764825],"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":[0.0000073918604,0.0000056108256,0.000034311855,0.00009926902,7.7086673e-7,0.000014085291,0.0000110705905,0.000016846572,0.000034267185,0.0027924248,0.9717694,0.025214551],"study_design_scores_gemma":[0.0000014595734,0.0000023756375,0.00012431167,0.000097425516,6.412083e-7,0.000010566724,0.000016227985,0.0000053077574,0.00001508404,0.00030275556,0.99942243,0.0000014830787],"about_ca_topic_score_codex":0.008935856,"about_ca_topic_score_gemma":0.009101734,"teacher_disagreement_score":0.48377115,"about_ca_system_score_codex":0.00262096,"about_ca_system_score_gemma":0.0069234557,"threshold_uncertainty_score":0.7363378},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985671,0.00062435307,0.0060043395,0.0018518846,0.000025763766,0.0008715013,0.00017490912,0.000016964004,0.0047593457],"genre_scores_gemma":[0.98868364,0.000954671,0.006474824,0.0006162106,0.000009127252,0.0012709842,0.00006852003,0.00001559406,0.001906478],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9788713,0.017001757,0.0007749481,0.00078143954,0.0010984096,0.0014721499],"domain_scores_gemma":[0.9769289,0.016692495,0.0018622265,0.0009979508,0.0021216306,0.0013968609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03649073,0.0003615144,0.00075377076,0.002363298,0.008199896,0.0041509974,0.0016779597,0.0012154429,0.001595989],"category_scores_gemma":[0.019070247,0.00059393595,0.00034072742,0.0026575336,0.0064854883,0.0035091848,0.0047552926,0.0014307186,0.00018724333],"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":[0.00002627278,0.00016232111,0.006303063,0.00020593138,0.0000066838757,0.00029981133,0.9787476,0.00007670387,0.0006801944,0.0014060795,0.0002479874,0.011837374],"study_design_scores_gemma":[0.0000064865967,0.00007549198,0.0037807093,0.0002584362,0.000005517554,0.00015960558,0.99035525,0.00018000093,0.00035693962,0.00054878654,0.004258053,0.0000147098735],"about_ca_topic_score_codex":0.008993797,"about_ca_topic_score_gemma":0.016216574,"teacher_disagreement_score":0.03649073,"about_ca_system_score_codex":0.0071623614,"about_ca_system_score_gemma":0.011031878,"threshold_uncertainty_score":0.19298369},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996436,0.00031406424,0.0002886097,0.00092692254,0.000009030556,0.00014044667,0.00015237421,0.000012034696,0.0017205534],"genre_scores_gemma":[0.99797004,0.00026631623,0.00055856834,0.0004221298,0.000013012449,0.00012389012,0.00010411235,0.000005313952,0.00053667015],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9735508,0.014325015,0.0021765695,0.0010384123,0.0061000017,0.0028092323],"domain_scores_gemma":[0.92126215,0.026673444,0.023695013,0.0015490769,0.014591093,0.0122292405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025083711,0.00021437675,0.00036338184,0.002510417,0.0020626797,0.0023147098,0.0007792342,0.0007499126,0.00250446],"category_scores_gemma":[0.04714295,0.0005440779,0.00034035344,0.002537103,0.0015194273,0.0013784702,0.0021750221,0.0011171864,0.00039948776],"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":[0.00012645588,0.00051394274,0.94617397,0.00020087563,0.000025664676,0.00009881868,0.024248356,0.0001174186,0.00047241471,0.0001985062,0.0030270861,0.024796456],"study_design_scores_gemma":[0.000026043084,0.0003440569,0.9515235,0.00014615597,0.000012543164,0.00014475647,0.0398494,0.00046852237,0.0003386714,0.00007593906,0.007045572,0.000024840343],"about_ca_topic_score_codex":0.04466046,"about_ca_topic_score_gemma":0.048887905,"teacher_disagreement_score":0.04466046,"about_ca_system_score_codex":0.008076769,"about_ca_system_score_gemma":0.010812781,"threshold_uncertainty_score":0.13265687},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32182306,0.12594403,0.018936088,0.10484011,0.000675569,0.0011969043,0.0062223636,0.00030718182,0.42005467],"genre_scores_gemma":[0.96263176,0.020291394,0.0056540295,0.0015991183,0.000055213735,0.00023050042,0.0005573681,0.000038405597,0.008942182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9742426,0.0068425033,0.00097311474,0.0012110239,0.011938593,0.0047921664],"domain_scores_gemma":[0.96836966,0.012062511,0.0020957643,0.0012026019,0.014356082,0.0019133349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028607436,0.0005040416,0.0011125809,0.006361542,0.0061537763,0.012248714,0.002105496,0.0012410897,0.003982376],"category_scores_gemma":[0.048877604,0.00037737718,0.0007205602,0.016817596,0.008006573,0.0023876557,0.0027464165,0.0021953231,0.00018646209],"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":[0.0003055119,0.000089715584,0.048319705,0.0027577295,0.00035156708,0.00008364693,0.011242789,0.014731802,0.0005118233,0.6461751,0.023311524,0.25211915],"study_design_scores_gemma":[0.00029458606,0.00017477816,0.2440421,0.010070463,0.00082583254,0.00006392067,0.030082699,0.014331055,0.0026114038,0.0923991,0.6047441,0.00036001136],"about_ca_topic_score_codex":0.98364985,"about_ca_topic_score_gemma":0.98713547,"teacher_disagreement_score":0.22118287,"about_ca_system_score_codex":0.22118287,"about_ca_system_score_gemma":0.3355288,"threshold_uncertainty_score":0.90331745},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19619277,0.003598178,0.7415481,0.026781304,0.00068065117,0.0008663289,0.00063427625,0.00089162914,0.028806787],"genre_scores_gemma":[0.77149904,0.0011028076,0.22070861,0.00039900877,0.00010918857,0.0005901091,0.00022473051,0.000080367,0.005286179],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98833394,0.007978062,0.000449351,0.00070147216,0.0021871286,0.0003499339],"domain_scores_gemma":[0.9294321,0.060603093,0.002106869,0.002294235,0.0046842624,0.0008793389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017650241,0.0010779076,0.0011205652,0.0018957648,0.0012804033,0.0065976204,0.0020246047,0.001963253,0.0065870783],"category_scores_gemma":[0.06738273,0.0005200794,0.0010331878,0.0019984143,0.0021650696,0.0068772743,0.0031043994,0.003116106,0.00059819623],"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":[0.0012672824,0.0015943424,0.029041296,0.0015149972,0.00054959196,0.00034408757,0.004294965,0.22037402,0.001273619,0.30174962,0.007367087,0.430629],"study_design_scores_gemma":[0.00014326532,0.000681608,0.004232079,0.00070740486,0.00022516414,0.00017960367,0.0018477127,0.8702338,0.0011315913,0.108331226,0.012168406,0.00011817096],"about_ca_topic_score_codex":0.028683314,"about_ca_topic_score_gemma":0.026643174,"teacher_disagreement_score":0.028683314,"about_ca_system_score_codex":0.0048040794,"about_ca_system_score_gemma":0.010649792,"threshold_uncertainty_score":0.09334457},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13171364,0.050047778,0.18312535,0.27105623,0.0018868245,0.0007982326,0.00013360755,0.0011509155,0.36008742],"genre_scores_gemma":[0.8873028,0.0088486895,0.091248035,0.0032004307,0.00029226375,0.0005289186,0.00006772172,0.00008733855,0.008423749],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9748905,0.021192916,0.0006471915,0.0005376567,0.001770107,0.0009616725],"domain_scores_gemma":[0.9442628,0.046243258,0.000890327,0.0028959084,0.0035443772,0.0021633639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046526518,0.00052868796,0.00070007803,0.00203292,0.0029246134,0.014776283,0.002962243,0.004164731,0.006922479],"category_scores_gemma":[0.032923292,0.00041457842,0.0006387548,0.0011818003,0.019585883,0.016958714,0.004686157,0.0043381043,0.0006021291],"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":[0.00022071722,0.00056694524,0.001591782,0.00052910665,0.000015033081,0.00020573774,0.007126331,0.0024066614,0.0005081817,0.8734421,0.004766324,0.10862114],"study_design_scores_gemma":[0.000217884,0.0008176088,0.0012727844,0.0028829754,0.000027876442,0.00041039713,0.014221656,0.018020123,0.0020406554,0.7973178,0.16264632,0.0001237952],"about_ca_topic_score_codex":0.0031530873,"about_ca_topic_score_gemma":0.001776822,"teacher_disagreement_score":0.046526518,"about_ca_system_score_codex":0.0053884867,"about_ca_system_score_gemma":0.005827419,"threshold_uncertainty_score":0.2460587},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079520635,0.015335052,0.017254163,0.51406157,0.04295377,0.00028555797,0.0004668916,0.0012021271,0.4076456],"genre_scores_gemma":[0.018579299,0.015848197,0.021730693,0.18953098,0.014588004,0.0004157513,0.00046913416,0.001255243,0.73758274],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949314,0.0016537211,0.00023236076,0.0004457667,0.0023771627,0.000359586],"domain_scores_gemma":[0.9876408,0.0033803089,0.00037137643,0.0015659863,0.0054887612,0.0015528486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00723698,0.0009247538,0.00071742444,0.0012003616,0.0033889685,0.011069012,0.002002122,0.0061247516,0.11523776],"category_scores_gemma":[0.025562659,0.00043802094,0.0009969501,0.00089577347,0.004854802,0.013950961,0.003227294,0.009560975,0.08364727],"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":[0.000011801451,0.000030244639,0.00010315821,0.000164855,0.000008313984,0.00008754481,0.00054685044,0.00010010668,0.0001415381,0.060838684,0.85978717,0.07817988],"study_design_scores_gemma":[0.0000044135563,0.0000108738805,0.00011253554,0.00032095378,0.0000064584506,0.00009125033,0.0004411246,0.00007205826,0.00013102694,0.038920734,0.95987535,0.000013321813],"about_ca_topic_score_codex":0.006174139,"about_ca_topic_score_gemma":0.00889091,"teacher_disagreement_score":0.11523776,"about_ca_system_score_codex":0.0037122844,"about_ca_system_score_gemma":0.007725655,"threshold_uncertainty_score":0.38550872},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016455789,0.003247858,0.03651957,0.012824021,0.0010645046,0.0000908989,0.00007983564,0.000094406845,0.94443333],"genre_scores_gemma":[0.33330345,0.0063168993,0.054830678,0.011172272,0.0025423912,0.001163001,0.00025642038,0.00038346514,0.5900314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852727,0.007539445,0.00050863717,0.001066403,0.004721232,0.0008915132],"domain_scores_gemma":[0.9873095,0.0068266843,0.00046914836,0.0027022983,0.0020651303,0.00062730367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01477377,0.0008666806,0.0007058646,0.0030113468,0.004318713,0.0089487275,0.0015030417,0.0031820359,0.013806534],"category_scores_gemma":[0.033103693,0.0007043617,0.0005153369,0.0026563331,0.043542754,0.009679874,0.0061699506,0.008751789,0.0052720606],"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":[0.0000035720086,0.0000042440665,0.00004201077,0.000009608684,0.000001038845,0.0000037578766,0.00069187704,0.000029997243,0.000016025177,0.98070586,0.0074771447,0.011014883],"study_design_scores_gemma":[0.000006476565,0.000012343713,0.00036160176,0.00007764504,0.0000025393258,0.00003674957,0.00066067296,0.00018591576,0.00010570929,0.8087602,0.18977953,0.000010673144],"about_ca_topic_score_codex":0.003410185,"about_ca_topic_score_gemma":0.0037738248,"teacher_disagreement_score":0.01477377,"about_ca_system_score_codex":0.0041732416,"about_ca_system_score_gemma":0.0074724355,"threshold_uncertainty_score":0.07813209},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6010291,0.0033774094,0.09675037,0.021859758,0.0013804031,0.06667799,0.0009822135,0.0005853666,0.20735742],"genre_scores_gemma":[0.8733098,0.0012508319,0.092743985,0.0013551209,0.000093710136,0.023727333,0.00019079857,0.00008622714,0.007242198],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.846569,0.13641821,0.0030771685,0.0028127893,0.008175826,0.0029469542],"domain_scores_gemma":[0.86380917,0.10900298,0.0048328633,0.0055610035,0.013589307,0.0032046838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11535661,0.0014656745,0.0011668546,0.0038015437,0.004898881,0.009356797,0.0033951197,0.0031765804,0.010073783],"category_scores_gemma":[0.11493279,0.0007176248,0.0015979367,0.0023402716,0.008090416,0.0077776033,0.00588848,0.0025126606,0.0006924483],"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":[0.0043147453,0.011510821,0.028006082,0.018533435,0.001147515,0.0009827232,0.13404146,0.012637331,0.0041899285,0.16842666,0.01958507,0.5966243],"study_design_scores_gemma":[0.01028433,0.059049513,0.069254786,0.024327984,0.0042360174,0.00082499103,0.30856067,0.049740776,0.030661449,0.13637786,0.3055301,0.0011515436],"about_ca_topic_score_codex":0.007163799,"about_ca_topic_score_gemma":0.016877893,"teacher_disagreement_score":0.11535661,"about_ca_system_score_codex":0.022247797,"about_ca_system_score_gemma":0.019794395,"threshold_uncertainty_score":0.61007136},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000088327666,0.00620929,0.00018013877,0.073107295,0.91181403,0.000025185052,0.0001369505,0.00009641665,0.008342387],"genre_scores_gemma":[0.0017450479,0.0106620565,0.0002690199,0.116325326,0.78663176,0.000050297393,0.00019801412,0.00009251511,0.08402603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835604,0.00027199066,0.00018372452,0.00028769064,0.0007607781,0.00013978891],"domain_scores_gemma":[0.9897573,0.0019146556,0.0005860393,0.00036131238,0.0052810633,0.0020996777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022288307,0.0014396928,0.0010979751,0.0014200866,0.0013870939,0.0050133923,0.0020278185,0.0050211283,0.09362255],"category_scores_gemma":[0.020195002,0.0005226259,0.000886664,0.0006667122,0.00085075863,0.0030730753,0.0014551786,0.0070814122,0.054965768],"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":[0.000014848722,0.000006252985,0.000036591537,0.00007493332,0.0000028330958,0.000053217933,0.0000054034986,0.000009625744,0.000028364117,0.00017204798,0.98895395,0.010641907],"study_design_scores_gemma":[0.000010407988,0.000015879792,0.0001782964,0.00020398104,0.0000051648335,0.00020566086,0.000026280792,0.00002657542,0.00005390797,0.00023143746,0.9990351,0.0000073887213],"about_ca_topic_score_codex":0.0011192332,"about_ca_topic_score_gemma":0.0029688552,"teacher_disagreement_score":0.09362255,"about_ca_system_score_codex":0.0011578613,"about_ca_system_score_gemma":0.0021940616,"threshold_uncertainty_score":0.31319863},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1907956,0.08302927,0.3523968,0.13394232,0.008387748,0.022904754,0.0025761384,0.00077711977,0.20519023],"genre_scores_gemma":[0.78842884,0.014342882,0.14201884,0.014635433,0.001441088,0.023749331,0.00077547383,0.00044081672,0.014167214],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.15776691,0.6892678,0.05692269,0.015530813,0.07736586,0.0031459348],"domain_scores_gemma":[0.10204405,0.6818993,0.04901229,0.07122479,0.0933611,0.0024583817],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6616144,0.0017287963,0.0034192528,0.009302443,0.0079143755,0.029295161,0.0074644824,0.00611157,0.0074186856],"category_scores_gemma":[0.7723161,0.0018961951,0.0038784458,0.01087794,0.019607475,0.017642885,0.013050532,0.005520645,0.0015156053],"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":[0.001955656,0.000757541,0.05622155,0.026870836,0.00497121,0.00070094975,0.1512145,0.0020290506,0.002234469,0.19830617,0.014336939,0.5404011],"study_design_scores_gemma":[0.0015419885,0.003735502,0.07392715,0.10256471,0.0044136154,0.0021972065,0.09103137,0.008712505,0.01675987,0.24496172,0.44918188,0.0009725296],"about_ca_topic_score_codex":0.015116773,"about_ca_topic_score_gemma":0.015883008,"teacher_disagreement_score":0.33838558,"about_ca_system_score_codex":0.018075526,"about_ca_system_score_gemma":0.058939002,"threshold_uncertainty_score":0.41728973},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5359586,0.018886326,0.050830435,0.14169218,0.0028740617,0.0007043869,0.00016069486,0.0003091944,0.24858406],"genre_scores_gemma":[0.9553351,0.0031808454,0.007854565,0.005246434,0.00038790042,0.0003397062,0.000045727007,0.00015155974,0.027458245],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9283371,0.058831643,0.001228341,0.0019194932,0.006843391,0.0028400782],"domain_scores_gemma":[0.93146074,0.046283554,0.0026168253,0.0032977937,0.008936097,0.007404979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041691005,0.00050791196,0.00068834494,0.0012471041,0.008872923,0.012442989,0.0014647571,0.0047121146,0.007053452],"category_scores_gemma":[0.055023015,0.0005025688,0.00090630015,0.0012150006,0.024554098,0.00789598,0.010489057,0.009390544,0.00095263234],"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":[0.00019607943,0.00048999366,0.0028706968,0.00070204854,0.000038709397,0.0011727782,0.8411065,0.00028559144,0.0023439375,0.052430198,0.011008993,0.08735463],"study_design_scores_gemma":[0.000085608146,0.00078474847,0.0074811704,0.0016205695,0.000037728143,0.0018210886,0.48551625,0.00065966934,0.0031780922,0.018586667,0.48003715,0.00019111452],"about_ca_topic_score_codex":0.008914181,"about_ca_topic_score_gemma":0.010840556,"teacher_disagreement_score":0.041691005,"about_ca_system_score_codex":0.008389556,"about_ca_system_score_gemma":0.010101128,"threshold_uncertainty_score":0.22048575},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24065925,0.23117319,0.072362415,0.07706287,0.003977198,0.008599809,0.0043121567,0.00033309672,0.36152005],"genre_scores_gemma":[0.7690815,0.077690706,0.10218888,0.0063399435,0.00049094367,0.0067224465,0.0017920303,0.0001604327,0.035533044],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.960822,0.0268797,0.0016915723,0.001276744,0.008114515,0.0012154727],"domain_scores_gemma":[0.93915725,0.033858825,0.0034174721,0.0028022535,0.018425537,0.0023386811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04556628,0.0013033616,0.001495006,0.004511908,0.002373246,0.008554254,0.0022020442,0.0024850327,0.012893111],"category_scores_gemma":[0.05201967,0.00044275247,0.0022000796,0.0043060905,0.003200954,0.0044546775,0.0048078424,0.0037755554,0.0013529513],"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":[0.0014502102,0.0010868845,0.023095604,0.016555978,0.0012277621,0.00018880793,0.019027662,0.00399113,0.0018666558,0.0794733,0.015933061,0.836103],"study_design_scores_gemma":[0.00067614106,0.0072831763,0.16430685,0.067854986,0.0032861661,0.00053765264,0.075383626,0.0053177592,0.011929884,0.09057216,0.5723063,0.00054529664],"about_ca_topic_score_codex":0.050445642,"about_ca_topic_score_gemma":0.08428383,"teacher_disagreement_score":0.9495544,"about_ca_system_score_codex":0.014577255,"about_ca_system_score_gemma":0.035785615,"threshold_uncertainty_score":0.24098039},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8940316,0.0021288902,0.0015428169,0.037810825,0.00008995658,0.00015603818,0.00020533455,0.000019258046,0.06401533],"genre_scores_gemma":[0.987169,0.00087430584,0.0006674186,0.0023947621,0.000005443162,0.00007876463,0.000055609118,0.000008805162,0.008745814],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9921808,0.0039550615,0.0002909722,0.0004885142,0.00069780374,0.0023868505],"domain_scores_gemma":[0.9908823,0.004019651,0.00065041514,0.00037018984,0.0018889236,0.0021886188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067717396,0.00034324682,0.00033506667,0.0021666493,0.020307792,0.010403811,0.0017823516,0.0017261846,0.004454237],"category_scores_gemma":[0.008170024,0.00061382016,0.0003120801,0.0045051454,0.013154564,0.0039197877,0.008762672,0.0039251572,0.00028565273],"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":[0.00015129871,0.000148776,0.114787385,0.00027355837,0.00006904891,0.0030404897,0.65269303,0.0016195144,0.0037668701,0.16490093,0.009759133,0.04878994],"study_design_scores_gemma":[0.000018867797,0.000035290584,0.06854515,0.00041159664,0.000028054175,0.00015734484,0.85518533,0.00062692474,0.0006481138,0.01045526,0.063811295,0.0000766934],"about_ca_topic_score_codex":0.9289825,"about_ca_topic_score_gemma":0.9738772,"teacher_disagreement_score":0.124744505,"about_ca_system_score_codex":0.124744505,"about_ca_system_score_gemma":0.14817974,"threshold_uncertainty_score":0.90508896},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19992271,0.008903398,0.14507635,0.17081146,0.000741631,0.00022944297,0.00033961644,0.0002122021,0.47376317],"genre_scores_gemma":[0.99005425,0.0007017124,0.006683503,0.0012287211,0.00014494153,0.00006169221,0.000020846803,0.000055854092,0.0010484896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9855239,0.009873473,0.00031600884,0.0007909995,0.0027555698,0.0007399676],"domain_scores_gemma":[0.9528589,0.035940424,0.0023018226,0.0024621866,0.0034371093,0.0029995202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015007635,0.0006376833,0.0008447333,0.005271046,0.0039393045,0.015560184,0.0016127802,0.0024623661,0.005146806],"category_scores_gemma":[0.040140666,0.0006801974,0.00059876265,0.0025394426,0.04634867,0.012614527,0.0068323333,0.004500554,0.00034840574],"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":[0.000083415376,0.000060727252,0.010264417,0.00014332384,0.00008559278,0.00014102097,0.0273501,0.0014195855,0.00017076057,0.9230513,0.0035541751,0.0336756],"study_design_scores_gemma":[0.000033880522,0.000060831997,0.008769856,0.00019894827,0.00003571936,0.00015320403,0.0146691,0.003470739,0.00013455904,0.9561224,0.016309114,0.00004160161],"about_ca_topic_score_codex":0.01968763,"about_ca_topic_score_gemma":0.022427788,"teacher_disagreement_score":0.01968763,"about_ca_system_score_codex":0.010725646,"about_ca_system_score_gemma":0.009740293,"threshold_uncertainty_score":0.07936889},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013181649,0.0073225233,0.84338546,0.07441171,0.0021151465,0.007704341,0.000667033,0.0005565584,0.0506555],"genre_scores_gemma":[0.18352705,0.0062073595,0.7751191,0.012356734,0.00047767613,0.014451695,0.00021953903,0.00053219096,0.00710867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.5884803,0.38782156,0.005413243,0.0042416723,0.012267935,0.0017752667],"domain_scores_gemma":[0.5722568,0.37389123,0.00913442,0.022802437,0.019495271,0.0024198117],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26799634,0.001494226,0.001460443,0.005706722,0.0077545615,0.019307503,0.003532986,0.003986664,0.007023266],"category_scores_gemma":[0.27662474,0.0014282844,0.0010870234,0.006723225,0.029042458,0.018162794,0.01395825,0.0068267607,0.0026189224],"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":[0.00012569936,0.00023897765,0.0028656393,0.005734277,0.00009984688,0.00049179036,0.26897913,0.001753072,0.0016697878,0.43567583,0.022557404,0.2598086],"study_design_scores_gemma":[0.00012257806,0.00017707232,0.0010131475,0.0130702015,0.00007434281,0.00039981457,0.122045435,0.004137073,0.002714679,0.61818326,0.23786257,0.00019985916],"about_ca_topic_score_codex":0.004465742,"about_ca_topic_score_gemma":0.0076062796,"teacher_disagreement_score":0.7320037,"about_ca_system_score_codex":0.00956396,"about_ca_system_score_gemma":0.019488174,"threshold_uncertainty_score":0.9026908},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1547167,0.009224373,0.72132224,0.029911134,0.0007793344,0.0027506552,0.00025500136,0.00013976781,0.08090082],"genre_scores_gemma":[0.70161045,0.0053347633,0.28253692,0.0019965796,0.00029732694,0.0058879415,0.00008873838,0.00010630525,0.0021409849],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6218949,0.34874412,0.0057999096,0.004008767,0.018091165,0.0014610466],"domain_scores_gemma":[0.42230192,0.51954365,0.018515943,0.0240667,0.014493032,0.0010786682],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20889741,0.0010444212,0.0015967345,0.0074353474,0.0053033032,0.01619759,0.0026635677,0.0024556103,0.0034314068],"category_scores_gemma":[0.40383694,0.0008625227,0.0010230026,0.010897403,0.019822692,0.013150763,0.008387118,0.0041749957,0.00037968231],"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":[0.00014174521,0.00025198402,0.021656893,0.0015229748,0.00030004483,0.00015716211,0.045669403,0.0043041604,0.00045666043,0.7878664,0.0016328486,0.13603976],"study_design_scores_gemma":[0.00012566395,0.00017873636,0.0077854595,0.0038780568,0.00016140203,0.00026353323,0.044755854,0.020608475,0.0022479785,0.89478517,0.025086155,0.00012355017],"about_ca_topic_score_codex":0.0029022552,"about_ca_topic_score_gemma":0.00245701,"teacher_disagreement_score":0.20889741,"about_ca_system_score_codex":0.009534177,"about_ca_system_score_gemma":0.016675921,"threshold_uncertainty_score":0.9755703},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42204756,0.0034030797,0.028438648,0.42333418,0.0037344038,0.005561444,0.00015536259,0.000522685,0.11280272],"genre_scores_gemma":[0.9326906,0.0006925798,0.02942227,0.019897563,0.00051808794,0.0015284208,0.00011981534,0.0001154934,0.015015161],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9359704,0.03348856,0.0038266385,0.0045195115,0.0117705995,0.01042419],"domain_scores_gemma":[0.74766624,0.04354543,0.014225333,0.014302101,0.043275505,0.1369854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11729872,0.0005252976,0.0007162999,0.0046024406,0.017981393,0.015785784,0.004901462,0.008417688,0.010266858],"category_scores_gemma":[0.10941833,0.0010552609,0.0009548723,0.0022330603,0.01256063,0.010626256,0.035098784,0.012036971,0.0013028801],"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":[0.00038836323,0.005843948,0.17500083,0.0010256012,0.00018773197,0.0025559184,0.09405858,0.0013136305,0.0042695096,0.09184067,0.060451906,0.5630634],"study_design_scores_gemma":[0.000638027,0.004454544,0.21796693,0.0035649196,0.00016033152,0.0021600998,0.24885824,0.0054651126,0.0020084826,0.06613253,0.4480303,0.00056040887],"about_ca_topic_score_codex":0.008564349,"about_ca_topic_score_gemma":0.021684848,"teacher_disagreement_score":0.11729872,"about_ca_system_score_codex":0.0102917,"about_ca_system_score_gemma":0.13659273,"threshold_uncertainty_score":0.6203424},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017375935,0.01189128,0.001406609,0.533305,0.001541925,0.0000617415,0.0002373294,0.00007327238,0.43410686],"genre_scores_gemma":[0.6559452,0.022258483,0.005630025,0.0727582,0.0010829078,0.0003188921,0.00036102344,0.00021728245,0.24142808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921038,0.0016891443,0.00011948238,0.00055433076,0.0017726559,0.003760652],"domain_scores_gemma":[0.98937654,0.0022918563,0.0004239237,0.0007028543,0.002905706,0.0042991433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0095030535,0.0005899649,0.00077649386,0.0020126882,0.026339732,0.025343003,0.0020592941,0.008651622,0.017152095],"category_scores_gemma":[0.0133676585,0.00037826158,0.0005881893,0.0051636463,0.015037868,0.011557038,0.010166696,0.009403622,0.00089003204],"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":[0.000048912156,0.00003748023,0.0016449699,0.000077586585,0.000019436124,0.00010089885,0.0089842,0.0003308363,0.000074551914,0.8039604,0.13125356,0.053467207],"study_design_scores_gemma":[0.000039977323,0.00002466375,0.0055818493,0.0006034632,0.00003217781,0.000058390757,0.03054456,0.00037174832,0.00013190298,0.12243996,0.84012175,0.000049498347],"about_ca_topic_score_codex":0.9085462,"about_ca_topic_score_gemma":0.95098096,"teacher_disagreement_score":0.09145379,"about_ca_system_score_codex":0.08170328,"about_ca_system_score_gemma":0.27892253,"threshold_uncertainty_score":0.5928016},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053217594,0.0013690024,0.019534161,0.041683607,0.00025211563,0.00028281583,0.0014374955,0.0005212809,0.8817018],"genre_scores_gemma":[0.7867589,0.0022999346,0.023359606,0.002613854,0.00006004658,0.00028984793,0.0011135523,0.00028942298,0.18321486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9926046,0.0018814814,0.00027669547,0.0006239003,0.0030172826,0.0015960534],"domain_scores_gemma":[0.98857147,0.0024206215,0.0008926795,0.0010553402,0.0041155075,0.002944406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053115706,0.00022786399,0.0002854763,0.0034305756,0.015972149,0.015782183,0.0014490065,0.0018227571,0.013861367],"category_scores_gemma":[0.011665599,0.00046367725,0.00036975878,0.0074438234,0.010892706,0.0067718676,0.005002892,0.0020484983,0.0014558967],"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":[0.00003894161,0.000045640292,0.019167714,0.00027576694,0.00002331745,0.0008072525,0.07030756,0.0017098251,0.00096860057,0.7592559,0.07420796,0.07319161],"study_design_scores_gemma":[0.000006529475,0.000009365099,0.009574414,0.0001757909,0.00001247194,0.000074694035,0.028065857,0.0008343421,0.00031494032,0.019471157,0.9414231,0.0000372381],"about_ca_topic_score_codex":0.95405143,"about_ca_topic_score_gemma":0.9752925,"teacher_disagreement_score":0.123430945,"about_ca_system_score_codex":0.123430945,"about_ca_system_score_gemma":0.18106961,"threshold_uncertainty_score":0.89555836},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010026587,0.009188234,0.8398106,0.05502558,0.00204709,0.013030737,0.00018863543,0.001250978,0.06943149],"genre_scores_gemma":[0.12209453,0.0028255077,0.85782665,0.006075115,0.00025312617,0.0086359205,0.00006414128,0.00026862498,0.0019564019],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.38394645,0.57229084,0.011257601,0.0056622783,0.02517802,0.001664875],"domain_scores_gemma":[0.40535125,0.4663618,0.016770843,0.047531303,0.05782089,0.0061639114],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.52543706,0.0019538873,0.002907426,0.009950196,0.0050263936,0.019354777,0.0039597265,0.0052506984,0.008626375],"category_scores_gemma":[0.42946357,0.0012858938,0.0023969042,0.006518277,0.020340145,0.013537739,0.011117022,0.008227253,0.0013877691],"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":[0.0006395199,0.0007018483,0.0054454505,0.007903274,0.0005223184,0.00020993191,0.020682273,0.001987081,0.00089887774,0.2652525,0.016503397,0.6792535],"study_design_scores_gemma":[0.0018310952,0.002774524,0.0100802295,0.0508893,0.00071741466,0.0010280764,0.026050897,0.01495207,0.0058751837,0.69633,0.18890849,0.0005628024],"about_ca_topic_score_codex":0.004711419,"about_ca_topic_score_gemma":0.006914593,"teacher_disagreement_score":0.52543706,"about_ca_system_score_codex":0.014155001,"about_ca_system_score_gemma":0.039661407,"threshold_uncertainty_score":0.58522063},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07030934,0.008266378,0.2707618,0.12358677,0.0031220648,0.00080867286,0.00028416244,0.0009678741,0.521893],"genre_scores_gemma":[0.8727234,0.0027856468,0.08181523,0.007993588,0.00068063784,0.00089067616,0.00020676013,0.0006969356,0.03220714],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9505979,0.041110974,0.00094602205,0.0019510905,0.0035848573,0.0018091403],"domain_scores_gemma":[0.9299617,0.050707906,0.003156988,0.0059189238,0.004066884,0.0061876057],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.056609575,0.0016415392,0.0009636001,0.0053802994,0.02114737,0.035284314,0.006288275,0.007155756,0.010777529],"category_scores_gemma":[0.05751042,0.0009083651,0.0009185572,0.0022513254,0.06537159,0.03602579,0.04016611,0.01092782,0.002808485],"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":[0.000038191978,0.00007757073,0.00054028037,0.00022551102,0.00001779802,0.00073920115,0.5218195,0.00033567895,0.00038551918,0.43762755,0.011971181,0.026222035],"study_design_scores_gemma":[0.00003570807,0.00003865834,0.00021098417,0.0012151969,0.000017682241,0.00059166754,0.27037287,0.0011432953,0.000545293,0.36276332,0.3630203,0.000045092245],"about_ca_topic_score_codex":0.0025302542,"about_ca_topic_score_gemma":0.0047933375,"teacher_disagreement_score":0.9788526,"about_ca_system_score_codex":0.00997398,"about_ca_system_score_gemma":0.014924663,"threshold_uncertainty_score":0.29938358},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71953106,0.0019806284,0.055642657,0.02062061,0.00021033341,0.002961866,0.00014518909,0.0003143984,0.19859338],"genre_scores_gemma":[0.99029046,0.00017619907,0.0059556523,0.00029427026,0.000017253229,0.00027548388,0.000041011117,0.000022373059,0.0029273499],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.90010726,0.070376344,0.0029354386,0.0031593086,0.008797896,0.014623731],"domain_scores_gemma":[0.84194916,0.086477645,0.012875489,0.013840771,0.024915027,0.01994194],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.086027876,0.000521513,0.0005251041,0.005542811,0.01179366,0.012944412,0.0029139232,0.0016949187,0.0045572924],"category_scores_gemma":[0.06629769,0.0006211604,0.0007667285,0.004582454,0.017344087,0.0063165906,0.02274171,0.0031855877,0.00037694606],"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":[0.00035685286,0.0018043553,0.15304795,0.0012458983,0.00039432323,0.002480512,0.12895456,0.027119998,0.002675376,0.3190979,0.014735778,0.3480865],"study_design_scores_gemma":[0.0001814087,0.00075104454,0.17840785,0.002724314,0.00013988304,0.0010113303,0.42908213,0.020083921,0.003892472,0.121252656,0.24203539,0.000437595],"about_ca_topic_score_codex":0.036230728,"about_ca_topic_score_gemma":0.059224103,"teacher_disagreement_score":0.91397214,"about_ca_system_score_codex":0.033459127,"about_ca_system_score_gemma":0.076312676,"threshold_uncertainty_score":0.45496434},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09173535,0.008327749,0.21467611,0.5503005,0.008504966,0.0054452885,0.00031375137,0.00282484,0.11787149],"genre_scores_gemma":[0.6220204,0.005129498,0.2675159,0.061908487,0.0020464298,0.0074216127,0.00036002434,0.0022359078,0.031361718],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6216362,0.3535085,0.0037657316,0.0047922567,0.007339312,0.008957906],"domain_scores_gemma":[0.5288424,0.3751741,0.0077060326,0.025761798,0.02534273,0.037172955],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2802973,0.0019549923,0.0015259971,0.0031920809,0.025975764,0.025988385,0.00892043,0.012260535,0.011409273],"category_scores_gemma":[0.22089799,0.0021000127,0.0021543887,0.0018326681,0.03947622,0.03557347,0.039049365,0.027058456,0.0030420725],"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":[0.00029315092,0.0019274617,0.0030989938,0.002305716,0.00007839501,0.0028458545,0.6321195,0.0019391187,0.0014111628,0.08199141,0.09152021,0.180469],"study_design_scores_gemma":[0.00027121528,0.00060894905,0.0023316504,0.006179617,0.000043084758,0.0007324503,0.35358316,0.0019152709,0.0017033927,0.072334014,0.56000966,0.00028754488],"about_ca_topic_score_codex":0.0050512273,"about_ca_topic_score_gemma":0.01134998,"teacher_disagreement_score":0.7197027,"about_ca_system_score_codex":0.017856296,"about_ca_system_score_gemma":0.055446908,"threshold_uncertainty_score":0.88752156},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062875166,0.2031723,0.032477703,0.57387424,0.14848053,0.00035778774,0.00018684533,0.00045634966,0.034706775],"genre_scores_gemma":[0.08818801,0.23843402,0.117736585,0.34421542,0.12357912,0.00144558,0.0005336111,0.001296215,0.08457154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99235076,0.0037874097,0.0007371257,0.0005717384,0.0019310918,0.000621938],"domain_scores_gemma":[0.9667626,0.0210523,0.0012080054,0.0009233489,0.00672498,0.0033287304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01836414,0.0008702795,0.0009196097,0.0021222178,0.0027813034,0.007793612,0.0023024697,0.007964644,0.0108482735],"category_scores_gemma":[0.030282,0.00055594125,0.0007624356,0.0012169622,0.0052621723,0.012785937,0.007857919,0.011345918,0.0028552902],"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":[0.00004758366,0.0002496658,0.0016940528,0.0013661726,0.000026907112,0.000307601,0.011384859,0.00023391063,0.0015995093,0.039692737,0.60571855,0.33767855],"study_design_scores_gemma":[0.000017912223,0.00011429017,0.0044379877,0.0037549338,0.000016395254,0.00083557086,0.0077181295,0.00024417593,0.0005460167,0.045954116,0.9362763,0.00008417758],"about_ca_topic_score_codex":0.0023301202,"about_ca_topic_score_gemma":0.013738451,"teacher_disagreement_score":0.01836414,"about_ca_system_score_codex":0.0033882693,"about_ca_system_score_gemma":0.008144188,"threshold_uncertainty_score":0.09712005},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004201542,0.99455345,0.00035570818,0.0030266119,0.0003487974,0.00005201035,0.000018653483,0.0000048325146,0.0012197153],"genre_scores_gemma":[0.013329615,0.9821452,0.0020808761,0.0017398613,0.00023583295,0.00014873684,0.00003736579,0.000010321134,0.00027226988],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95803916,0.021341803,0.0074897143,0.0012894645,0.011175048,0.0006648631],"domain_scores_gemma":[0.8635864,0.092117056,0.01668867,0.0020212983,0.023988657,0.0015979784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.068091564,0.00067152485,0.0017977777,0.009882781,0.0014167359,0.004974109,0.0018675703,0.0021725956,0.0015301562],"category_scores_gemma":[0.14607762,0.00089918077,0.0014095696,0.012463062,0.002349404,0.005208224,0.0025734946,0.0028291913,0.0004607719],"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":[0.00009704484,0.00005325688,0.0018551181,0.13456191,0.00045355936,0.00010444956,0.0022560286,0.00022767499,0.00031879582,0.011556938,0.021406647,0.82710856],"study_design_scores_gemma":[0.000040048773,0.00012197976,0.0072958977,0.38180426,0.00091013266,0.0005659993,0.002392001,0.00022763776,0.0003996021,0.0027166747,0.60347015,0.000055619188],"about_ca_topic_score_codex":0.009277489,"about_ca_topic_score_gemma":0.030926688,"teacher_disagreement_score":0.068091564,"about_ca_system_score_codex":0.0067525366,"about_ca_system_score_gemma":0.03459359,"threshold_uncertainty_score":0.3601069},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14371179,0.0014072172,0.35538468,0.035789087,0.00064329576,0.0019409312,0.00033820013,0.003032354,0.45775244],"genre_scores_gemma":[0.69722587,0.0008845761,0.27201036,0.0025712017,0.000052082327,0.0010631575,0.00020502906,0.0005024868,0.025485234],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.994331,0.0040491526,0.00018303374,0.00028384203,0.00063795096,0.0005149705],"domain_scores_gemma":[0.9918799,0.0034267579,0.0007515347,0.00089246535,0.0017294952,0.0013198502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008223173,0.0009331097,0.00034047136,0.0021338938,0.0026348876,0.006380647,0.0011581458,0.0019062064,0.014035964],"category_scores_gemma":[0.02382566,0.00029961436,0.0005465592,0.000813601,0.008639742,0.008489015,0.008932318,0.0025780469,0.0027830072],"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":[0.0002597539,0.00066561776,0.010892816,0.0015297519,0.000040426603,0.0004984738,0.09237829,0.005104988,0.007905474,0.3242316,0.05443518,0.50205755],"study_design_scores_gemma":[0.000170032,0.0009192755,0.025030626,0.0046702963,0.00008151816,0.0010006239,0.12228337,0.019551612,0.01729897,0.27583125,0.5328837,0.0002787703],"about_ca_topic_score_codex":0.0047200536,"about_ca_topic_score_gemma":0.008893188,"teacher_disagreement_score":0.014035964,"about_ca_system_score_codex":0.0031403794,"about_ca_system_score_gemma":0.007262193,"threshold_uncertainty_score":0.04695499},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048670787,0.020934965,0.044112246,0.826581,0.005809603,0.0001666427,0.00043759373,0.00027097217,0.05301618],"genre_scores_gemma":[0.8098461,0.0059690126,0.04191098,0.1294154,0.005022093,0.00040379117,0.0004600252,0.00027136935,0.006701321],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93473005,0.0349652,0.002993797,0.0051955595,0.013755693,0.008359661],"domain_scores_gemma":[0.6718748,0.1578377,0.014207156,0.021642035,0.07129134,0.06314688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10862827,0.0007366437,0.0023283993,0.00943604,0.013787894,0.020056676,0.004518068,0.0070320503,0.0117079755],"category_scores_gemma":[0.19526662,0.0008215056,0.0013112306,0.009712021,0.01006729,0.014685732,0.022544838,0.01423502,0.0015858352],"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":[0.00036670343,0.000581357,0.04733872,0.0010987002,0.0003589565,0.00039603614,0.012414404,0.0017896446,0.0006595052,0.41252905,0.10074058,0.42172632],"study_design_scores_gemma":[0.00017726253,0.00034983995,0.047275603,0.00565739,0.00015735428,0.0010932797,0.026250876,0.009311586,0.0008599708,0.5703454,0.33821866,0.00030288944],"about_ca_topic_score_codex":0.06443828,"about_ca_topic_score_gemma":0.112351224,"teacher_disagreement_score":0.10862827,"about_ca_system_score_codex":0.019933172,"about_ca_system_score_gemma":0.08616978,"threshold_uncertainty_score":0.57448804},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12618099,0.00989934,0.7923341,0.0067610913,0.0015316913,0.010907754,0.0018239546,0.00060081936,0.049960308],"genre_scores_gemma":[0.3933167,0.0025136296,0.57617325,0.0011200251,0.00046557136,0.021426084,0.0008930529,0.00025399897,0.0038377417],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6889658,0.23874813,0.023197496,0.008993659,0.03847578,0.0016191197],"domain_scores_gemma":[0.25213492,0.62223977,0.030118829,0.036217425,0.058219124,0.0010699545],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2476312,0.0011919768,0.002332145,0.030821659,0.0060146665,0.013776649,0.003076709,0.0027150153,0.0058843144],"category_scores_gemma":[0.50415045,0.000701426,0.0025040992,0.03755616,0.004917977,0.011504993,0.0077567147,0.0027916792,0.00059560145],"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":[0.00038077496,0.0005317583,0.0501776,0.008582706,0.0018312423,0.0004592865,0.08268506,0.004750225,0.0020005347,0.4054655,0.0066138995,0.43652138],"study_design_scores_gemma":[0.0005353122,0.0011853417,0.041602746,0.012329736,0.0022380468,0.00065789674,0.06964785,0.050228905,0.012949731,0.68998796,0.117911056,0.0007254616],"about_ca_topic_score_codex":0.0044964585,"about_ca_topic_score_gemma":0.00803627,"teacher_disagreement_score":0.9691783,"about_ca_system_score_codex":0.008115518,"about_ca_system_score_gemma":0.012962691,"threshold_uncertainty_score":0.92780465},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011061417,0.8294502,0.056110647,0.07829619,0.0026382427,0.011993276,0.0010411083,0.000088681336,0.00932033],"genre_scores_gemma":[0.29041356,0.4848204,0.14075823,0.027161263,0.0014210102,0.0530932,0.0007680722,0.00011038348,0.0014538341],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6074957,0.3076602,0.055922788,0.007294475,0.019207794,0.0024190655],"domain_scores_gemma":[0.44408044,0.48440802,0.03317902,0.011733053,0.024708102,0.0018912805],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34336,0.0018515731,0.004646402,0.024987329,0.0046408856,0.012952799,0.0038519588,0.0043970016,0.0027591623],"category_scores_gemma":[0.506155,0.0020114905,0.006513261,0.014687553,0.011677904,0.01825727,0.008315381,0.004800319,0.00033747635],"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":[0.0005089406,0.00008497132,0.00573511,0.4977213,0.0067092762,0.00070865126,0.076059006,0.0015389833,0.0006986641,0.17374495,0.012370493,0.22411954],"study_design_scores_gemma":[0.0001767906,0.00013284161,0.0018350324,0.80400586,0.007672096,0.0005276971,0.024439482,0.0011264035,0.00090135913,0.06326648,0.09579551,0.0001204844],"about_ca_topic_score_codex":0.0073636086,"about_ca_topic_score_gemma":0.018844433,"teacher_disagreement_score":0.995603,"about_ca_system_score_codex":0.02568808,"about_ca_system_score_gemma":0.062551856,"threshold_uncertainty_score":0.809754},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047360644,0.0039529474,0.24631105,0.028229222,0.0024951454,0.011547023,0.00026451002,0.00073395035,0.6591056],"genre_scores_gemma":[0.725036,0.0015736177,0.23674431,0.0043232497,0.00025179447,0.0091190385,0.00020915722,0.00029298276,0.022449784],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7447476,0.22490402,0.004109832,0.0032447777,0.019128732,0.0038650807],"domain_scores_gemma":[0.877948,0.076693036,0.0037039083,0.0063953437,0.031178838,0.0040808804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14157102,0.0009797567,0.0015005799,0.007479331,0.009482139,0.014080372,0.003664196,0.0034355514,0.012808788],"category_scores_gemma":[0.14738116,0.0006338369,0.0007927767,0.0062082843,0.0078113154,0.011687049,0.014502434,0.005359352,0.0015575665],"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":[0.000478791,0.0014787205,0.008059889,0.0025611697,0.00015455407,0.00093534833,0.059264213,0.007203913,0.0018689517,0.38958737,0.068869166,0.45953795],"study_design_scores_gemma":[0.00054398674,0.0014956448,0.008768565,0.0087213395,0.00023548998,0.0007426141,0.1623068,0.022102475,0.006105167,0.27148384,0.51711357,0.00038046247],"about_ca_topic_score_codex":0.018350193,"about_ca_topic_score_gemma":0.057957698,"teacher_disagreement_score":0.14157102,"about_ca_system_score_codex":0.014000605,"about_ca_system_score_gemma":0.025866332,"threshold_uncertainty_score":0.748708},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032420505,0.004355025,0.106200896,0.014105797,0.0054968256,0.12834051,0.008275332,0.0018449816,0.6989601],"genre_scores_gemma":[0.33206072,0.0064845304,0.24558158,0.009908572,0.0013471505,0.24400285,0.00749339,0.0016180205,0.15150316],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79908806,0.12491151,0.013199331,0.0056340946,0.05214822,0.00501876],"domain_scores_gemma":[0.73654777,0.08096803,0.009195303,0.022701982,0.14042054,0.010166422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14480875,0.0011981027,0.0015979185,0.0061436472,0.0046769367,0.008376084,0.0027474419,0.0020045359,0.07553879],"category_scores_gemma":[0.2318682,0.00061316445,0.0021890618,0.0045715137,0.0035865903,0.003958546,0.0069171865,0.0032253067,0.010247461],"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":[0.0026303064,0.0022230814,0.0058059054,0.0057632923,0.00029301425,0.00019552566,0.0118648885,0.0018664398,0.0014453398,0.055464566,0.17751451,0.7349331],"study_design_scores_gemma":[0.0011914143,0.002560633,0.014708828,0.010292799,0.00027254416,0.00017607618,0.008756045,0.0017764097,0.0039694747,0.02195301,0.93413365,0.00020910043],"about_ca_topic_score_codex":0.008315633,"about_ca_topic_score_gemma":0.014095524,"teacher_disagreement_score":0.85519123,"about_ca_system_score_codex":0.015589697,"about_ca_system_score_gemma":0.034937024,"threshold_uncertainty_score":0},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6784731,0.00030160954,0.29252642,0.001765005,0.00012433376,0.0019089844,0.0013771243,0.00053602806,0.022987356],"genre_scores_gemma":[0.9414455,0.00012278493,0.055964913,0.00005261083,0.000019786003,0.00043338875,0.0004717534,0.00005296716,0.0014364483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98369944,0.009070542,0.0006598336,0.0015269303,0.0038660634,0.0011772469],"domain_scores_gemma":[0.9633159,0.02241633,0.0035622634,0.002095573,0.007311131,0.0012988079],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01938093,0.00095410243,0.00074376207,0.0041885995,0.0016607083,0.0041971267,0.0013859338,0.00079282845,0.003684851],"category_scores_gemma":[0.052002504,0.000404602,0.001086998,0.0032165041,0.0019469274,0.0034490235,0.003964271,0.0012764327,0.00030373054],"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":[0.0009922856,0.0007770748,0.14231399,0.0012538845,0.00088450767,0.0009807663,0.009865769,0.46859947,0.0057537025,0.14009802,0.0065143825,0.22196612],"study_design_scores_gemma":[0.00009565707,0.001163555,0.06346249,0.0003588281,0.00043829807,0.00023593691,0.010518336,0.80901635,0.0050697722,0.09383502,0.015661094,0.00014469707],"about_ca_topic_score_codex":0.013340485,"about_ca_topic_score_gemma":0.009601681,"teacher_disagreement_score":0.9806191,"about_ca_system_score_codex":0.005130705,"about_ca_system_score_gemma":0.006094052,"threshold_uncertainty_score":0.10249734},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009452392,0.002946795,0.0005717141,0.030839236,0.035504896,0.000537905,0.0046721105,0.0006006295,0.91487443],"genre_scores_gemma":[0.009126254,0.00036759028,0.00042572548,0.0018936611,0.0012276198,0.00008594262,0.0011547591,0.00018291811,0.9855355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99934584,0.00010663433,0.000015145095,0.000078664496,0.00025012426,0.00020358419],"domain_scores_gemma":[0.99844414,0.00008155181,0.000042624655,0.000087334505,0.00059054414,0.0007537409],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016063268,0.00044430455,0.0003588731,0.00040598013,0.0044881245,0.0031147923,0.0006879508,0.001588467,0.4068531],"category_scores_gemma":[0.0020191264,0.00022637026,0.00036528517,0.00040122046,0.00055876025,0.0011790494,0.0027097254,0.002730476,0.10525209],"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":[0.000065517655,0.0000406585,0.00024163925,0.000026616732,0.0000021636122,0.00006491901,0.0000961125,0.000019212788,0.0002463187,0.0008723209,0.9874936,0.010830981],"study_design_scores_gemma":[0.000007069362,0.000014044136,0.0019789774,0.000024050678,6.497002e-7,0.000013035872,0.00022038435,0.000031446678,0.000055267225,0.00013672744,0.99751306,0.0000052733612],"about_ca_topic_score_codex":0.03796311,"about_ca_topic_score_gemma":0.14619173,"teacher_disagreement_score":0.4068531,"about_ca_system_score_codex":0.0019865732,"about_ca_system_score_gemma":0.004627282,"threshold_uncertainty_score":0.84605205},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006945022,0.005455902,0.005894456,0.4009907,0.18573095,0.0021400254,0.0041455003,0.0056901537,0.38300726],"genre_scores_gemma":[0.015374372,0.0018890612,0.0020275917,0.08691272,0.016450994,0.0019050533,0.00088665815,0.0011940862,0.87335944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990765,0.0003148463,0.000029165365,0.00014108393,0.00022708412,0.0002112835],"domain_scores_gemma":[0.9946302,0.00092737656,0.0001635702,0.00016688781,0.0011957544,0.0029161477],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002433517,0.0010213421,0.0007287779,0.000536168,0.0032445476,0.002603953,0.0011187573,0.00334732,0.46388936],"category_scores_gemma":[0.0112284245,0.00046049792,0.0006205424,0.00022143878,0.00071145775,0.002026898,0.004011118,0.0067879288,0.23304683],"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":[0.0000628806,0.000020450938,0.000043067932,0.000019422405,0.0000012152996,0.00008358082,0.00011112649,0.000008608856,0.00012156322,0.00019152963,0.99404377,0.0052928464],"study_design_scores_gemma":[0.000026493095,0.00005652399,0.00024860975,0.00005289796,0.000002359244,0.00017698087,0.00072889484,0.000041817126,0.00011138766,0.00030548335,0.99823666,0.000011962346],"about_ca_topic_score_codex":0.0023608138,"about_ca_topic_score_gemma":0.0041613425,"teacher_disagreement_score":0.46388936,"about_ca_system_score_codex":0.0010517797,"about_ca_system_score_gemma":0.0018125001,"threshold_uncertainty_score":0.7646967},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002417224,0.0064841136,0.003351819,0.16204374,0.15889542,0.00094570615,0.01350405,0.0021637997,0.6501942],"genre_scores_gemma":[0.013354224,0.002998559,0.0018866515,0.038122457,0.018631678,0.00072696776,0.0065889047,0.0015793227,0.91611123],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99784863,0.0005116105,0.00007140597,0.00015663903,0.00095894816,0.00045273945],"domain_scores_gemma":[0.9932255,0.002961412,0.00019272968,0.00067909533,0.0013242556,0.0016170265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003197215,0.00069427205,0.0006218736,0.0012827726,0.00665067,0.009781627,0.0019763084,0.0055797165,0.2668614],"category_scores_gemma":[0.013540109,0.00056797685,0.0007306332,0.0019273997,0.0021760457,0.005608462,0.006029583,0.009822841,0.06600496],"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":[0.000020135967,0.000013026324,0.000020590569,0.00004726511,5.1765466e-7,0.000039052757,0.00032204064,0.000011999541,0.000033524328,0.001536181,0.99186194,0.006093696],"study_design_scores_gemma":[0.000009577794,0.000008363842,0.00015932208,0.000072380695,7.001669e-7,0.000015323996,0.0005034008,0.000016965887,0.0000375086,0.0006812288,0.99849105,0.000004244555],"about_ca_topic_score_codex":0.025459783,"about_ca_topic_score_gemma":0.07683792,"teacher_disagreement_score":0.2668614,"about_ca_system_score_codex":0.0041923686,"about_ca_system_score_gemma":0.004396726,"threshold_uncertainty_score":0.89274037},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017852564,0.0041136406,0.0015022245,0.4000526,0.52869487,0.00091212464,0.00096461835,0.0009986628,0.06097599],"genre_scores_gemma":[0.020531468,0.005122056,0.0046897186,0.1953352,0.21236351,0.0015634801,0.001271913,0.0017876155,0.557335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96795166,0.006806721,0.002273875,0.0020348178,0.017038157,0.003894735],"domain_scores_gemma":[0.7565551,0.051108606,0.008089306,0.010677319,0.1186718,0.05489791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027810806,0.0015221483,0.0024112917,0.003989833,0.011375257,0.022766221,0.004273752,0.027825676,0.2681992],"category_scores_gemma":[0.15050663,0.0010344337,0.0027767746,0.0024938993,0.0043192892,0.010115637,0.010219038,0.012900371,0.08813406],"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":[0.000031164396,0.000022457494,0.00010746331,0.00009848117,0.0000051013967,0.0001130288,0.00015606663,0.000011726438,0.0000873593,0.0012465885,0.9922652,0.005855436],"study_design_scores_gemma":[0.000049292183,0.000050583785,0.0008374866,0.00021628992,0.000012509159,0.00015026696,0.0018741331,0.000117117794,0.00015755896,0.004204889,0.99227446,0.00005541314],"about_ca_topic_score_codex":0.010598428,"about_ca_topic_score_gemma":0.03870307,"teacher_disagreement_score":0.2681992,"about_ca_system_score_codex":0.008334368,"about_ca_system_score_gemma":0.026645562,"threshold_uncertainty_score":0.8972157},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842433,0.000053443364,0.004477168,0.0007585981,0.000014906346,0.0004360762,0.00011091203,0.000014868552,0.009890764],"genre_scores_gemma":[0.9947625,0.00005054111,0.0041899174,0.00007076068,0.000010781707,0.00017160008,0.00008068424,0.0000047457133,0.00065844745],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9848355,0.007065046,0.0012687676,0.00041193134,0.0054161893,0.0010026428],"domain_scores_gemma":[0.946245,0.030821526,0.0067295614,0.0017647893,0.011811796,0.0026272812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0146392435,0.00030029437,0.00029029616,0.002789539,0.0015245054,0.0030508908,0.00047016804,0.00046391197,0.002942561],"category_scores_gemma":[0.07797401,0.00017908464,0.00043399274,0.0016628379,0.0013108217,0.0022011925,0.0034085033,0.0007305371,0.00028860453],"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":[0.00090012286,0.0019753936,0.62644106,0.000499193,0.00013205165,0.0006641909,0.06783952,0.004002567,0.0077231,0.010165968,0.0039266367,0.27573022],"study_design_scores_gemma":[0.00007357714,0.0028572478,0.8773349,0.0003606463,0.000066599394,0.00049140456,0.07175418,0.011340148,0.008616276,0.0062078647,0.02074749,0.00014968152],"about_ca_topic_score_codex":0.0032294441,"about_ca_topic_score_gemma":0.00732481,"teacher_disagreement_score":0.0146392435,"about_ca_system_score_codex":0.0040620603,"about_ca_system_score_gemma":0.004690543,"threshold_uncertainty_score":0.07742065},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027974957,0.998566,0.000060856262,0.0004448038,0.000062558596,0.000016536447,0.00008079509,0.000002694444,0.00048607695],"genre_scores_gemma":[0.002418224,0.9968714,0.000274732,0.00020008063,0.000027775699,0.000016165322,0.000040587795,0.000001486035,0.0001495696],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765164,0.00076894823,0.00042625872,0.00019839437,0.0008276506,0.00012717175],"domain_scores_gemma":[0.9873798,0.0066852914,0.001860483,0.00022101251,0.003513049,0.00034044962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008233022,0.0012580766,0.0028617026,0.010588008,0.00074335857,0.00334119,0.0019844794,0.00096127467,0.0025321913],"category_scores_gemma":[0.016169166,0.00074068597,0.001703663,0.021284929,0.0015063387,0.0015548015,0.0019779578,0.0014359608,0.0003307961],"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":[0.000119409975,0.0000446271,0.0030695314,0.11969674,0.0012703874,0.00014510818,0.0007772123,0.0011246628,0.00029733204,0.0032845421,0.016233703,0.8539368],"study_design_scores_gemma":[0.000064902444,0.00023527449,0.036609173,0.33587244,0.008540562,0.00043163303,0.0018248471,0.0003438661,0.0005057711,0.0027170198,0.6127438,0.00011070643],"about_ca_topic_score_codex":0.3470826,"about_ca_topic_score_gemma":0.69750726,"teacher_disagreement_score":0.6529174,"about_ca_system_score_codex":0.015227749,"about_ca_system_score_gemma":0.05593549,"threshold_uncertainty_score":0.69012475},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0388626,0.05364159,0.011682715,0.054907862,0.00650202,0.00034901933,0.00234425,0.00018479144,0.83152515],"genre_scores_gemma":[0.30939117,0.05299797,0.01604719,0.014140219,0.0022604035,0.00046904746,0.0030342103,0.00037358652,0.6012862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99860626,0.00042015951,0.0000872497,0.00018916737,0.00043241662,0.0002648427],"domain_scores_gemma":[0.99818134,0.0010707221,0.00012216669,0.00007086228,0.00042542885,0.00012946392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010405633,0.00054695824,0.0005139945,0.0021765314,0.0038383335,0.0067232093,0.0010641539,0.0023002415,0.041396506],"category_scores_gemma":[0.0033726962,0.00031238343,0.00065112236,0.0030699521,0.002327077,0.0025039706,0.0014890047,0.0030649754,0.00322202],"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":[0.00009711527,0.00018623962,0.0074764662,0.0019786563,0.00005019225,0.004428097,0.04125494,0.0011366736,0.0013891943,0.5549274,0.24843882,0.13863614],"study_design_scores_gemma":[0.000005339706,0.000018918287,0.0070287725,0.0014080226,0.00000860862,0.0013122562,0.017221522,0.00016260246,0.00044189522,0.0103697935,0.9619998,0.000022528779],"about_ca_topic_score_codex":0.14062823,"about_ca_topic_score_gemma":0.19666861,"teacher_disagreement_score":0.99064934,"about_ca_system_score_codex":0.009350672,"about_ca_system_score_gemma":0.0072113685,"threshold_uncertainty_score":0.27961934},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019231282,0.0044317106,0.5526821,0.080122285,0.001097216,0.009436676,0.0003908023,0.0007623903,0.33184555],"genre_scores_gemma":[0.5057029,0.0030912505,0.45876843,0.0036438166,0.00041531047,0.016872255,0.00046999374,0.0003456074,0.01069042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.7036695,0.25349766,0.0096358955,0.00787804,0.018356243,0.0069626304],"domain_scores_gemma":[0.6326772,0.28961772,0.010716766,0.023068653,0.033839133,0.010080512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.27029532,0.0021858863,0.0022357544,0.007727077,0.006437639,0.026665319,0.0076869205,0.007168444,0.03309855],"category_scores_gemma":[0.35694298,0.0018071911,0.0027582531,0.004538688,0.021763343,0.03177751,0.039895266,0.0078078425,0.0028700202],"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":[0.00008544447,0.00016488272,0.0009076043,0.0015553518,0.00009921823,0.00012716798,0.0068669333,0.016892567,0.00018609683,0.9044744,0.008456455,0.06018397],"study_design_scores_gemma":[0.00017900352,0.00019177077,0.0005650051,0.005165193,0.00005284803,0.0000886715,0.006440474,0.021564772,0.00051880896,0.87610716,0.08903582,0.000090444875],"about_ca_topic_score_codex":0.006638647,"about_ca_topic_score_gemma":0.0062998165,"teacher_disagreement_score":0.27029532,"about_ca_system_score_codex":0.035857808,"about_ca_system_score_gemma":0.059427317,"threshold_uncertainty_score":0.8998558},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010446748,0.051364712,0.17722882,0.7337715,0.008715405,0.00059745146,0.00017923808,0.00074878376,0.016947305],"genre_scores_gemma":[0.30563307,0.026388189,0.4863171,0.16679859,0.009451598,0.0017051036,0.00021785832,0.00067633466,0.002812168],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5266336,0.3447516,0.037685506,0.01250353,0.07385682,0.0045689964],"domain_scores_gemma":[0.26498687,0.60383976,0.029436585,0.05231631,0.03799002,0.011430458],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38736033,0.0026967993,0.0063481065,0.01058193,0.008354641,0.033499427,0.008487827,0.017831035,0.0078043817],"category_scores_gemma":[0.6368306,0.0022255967,0.0036932477,0.0061712577,0.040427998,0.06562017,0.038000267,0.0355654,0.0022871199],"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":[0.0009139106,0.00046399617,0.0045140428,0.010242368,0.0014487697,0.0004690747,0.01602074,0.0031225665,0.0013604708,0.22702163,0.07455656,0.6598658],"study_design_scores_gemma":[0.00041510075,0.0006173507,0.0020153956,0.020726146,0.000847009,0.0006560421,0.006732002,0.0037432818,0.0011960916,0.8506929,0.11195241,0.00040621648],"about_ca_topic_score_codex":0.0050706607,"about_ca_topic_score_gemma":0.008393333,"teacher_disagreement_score":0.61263967,"about_ca_system_score_codex":0.013727542,"about_ca_system_score_gemma":0.047814183,"threshold_uncertainty_score":0.75549376},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005961243,0.0008351842,0.004252214,0.00037473105,0.00019570801,0.99135005,0.0017964522,0.00014011306,0.00045941593],"genre_scores_gemma":[0.00074718136,0.00030821117,0.01107551,0.00015825925,0.000036215555,0.9872569,0.00023193687,0.00001792039,0.00016789846],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.794893,0.09014493,0.08892756,0.008697365,0.013207493,0.0041296766],"domain_scores_gemma":[0.7280751,0.13065822,0.051096786,0.029771723,0.055315092,0.005083054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20157756,0.0061696,0.01670891,0.01504826,0.0057740454,0.007675562,0.0048898356,0.009574992,0.06104991],"category_scores_gemma":[0.26221505,0.0068732565,0.022039833,0.011799658,0.006241224,0.007291824,0.0085251285,0.011629809,0.012845559],"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":[0.045668058,0.002796998,0.005613773,0.58218896,0.009396128,0.0014312096,0.011410185,0.0045422628,0.010562169,0.023362152,0.0815477,0.22148049],"study_design_scores_gemma":[0.12270198,0.0092160115,0.023644457,0.4343711,0.014960259,0.0016094829,0.006214861,0.0102187,0.013358256,0.058119588,0.30331472,0.002270551],"about_ca_topic_score_codex":0.003811853,"about_ca_topic_score_gemma":0.008991133,"teacher_disagreement_score":0.79842246,"about_ca_system_score_codex":0.014109984,"about_ca_system_score_gemma":0.041908346,"threshold_uncertainty_score":0.984597},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16769394,0.03555708,0.3035184,0.34297997,0.001989106,0.003117883,0.00047574742,0.00076403224,0.1439038],"genre_scores_gemma":[0.9037358,0.004302751,0.07672861,0.006192417,0.00031761508,0.0022251739,0.00013469782,0.00021892617,0.0061440105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.30320624,0.5662862,0.026153166,0.012904465,0.08416196,0.0072879405],"domain_scores_gemma":[0.15365228,0.67426664,0.036033265,0.06195427,0.06386178,0.0102317305],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49835593,0.0012493369,0.0017802716,0.0079557,0.013814639,0.029830765,0.0045948233,0.007103605,0.003545181],"category_scores_gemma":[0.54726285,0.002032475,0.0018904724,0.007917607,0.066352986,0.033290464,0.025969826,0.011942196,0.001045729],"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":[0.00045012095,0.0003015657,0.015473399,0.0037140278,0.00034468438,0.0003162359,0.27434915,0.0014982112,0.0023153764,0.5272706,0.006007594,0.16795897],"study_design_scores_gemma":[0.00032840145,0.0009402934,0.023693714,0.00879694,0.00022584124,0.0009259977,0.1678243,0.0036005569,0.005012149,0.60202956,0.18610178,0.00052035885],"about_ca_topic_score_codex":0.015277928,"about_ca_topic_score_gemma":0.010132702,"teacher_disagreement_score":0.5016441,"about_ca_system_score_codex":0.028382754,"about_ca_system_score_gemma":0.08929892,"threshold_uncertainty_score":0.61861646},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021245379,0.0031295957,0.08578011,0.04481717,0.00041312122,0.000083362014,0.00015656874,0.000060226066,0.8443144],"genre_scores_gemma":[0.93234414,0.0015601744,0.016771968,0.004955851,0.00080056564,0.00025429975,0.00015133436,0.000064130596,0.043097503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99439937,0.002525165,0.00016294456,0.0011851,0.0012502768,0.0004770563],"domain_scores_gemma":[0.9965379,0.001924044,0.00024208214,0.0005809478,0.00047523525,0.00023976887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061483225,0.00046608085,0.0005601536,0.0009998393,0.004218854,0.0054538017,0.00093402545,0.0026579506,0.008283619],"category_scores_gemma":[0.0073878085,0.0002482017,0.00059259415,0.00077773497,0.025598943,0.00600039,0.0035809474,0.005135188,0.0009708715],"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":[7.8618814e-7,0.0000020289162,0.000025826579,0.0000037063535,7.18447e-7,0.00000495815,0.0001130291,0.000037557533,0.000008867546,0.9990932,0.00026782157,0.00044149827],"study_design_scores_gemma":[0.0000034937318,0.0000025569707,0.00007010184,0.0000102048125,0.0000011545512,0.000014738831,0.00007435471,0.0003046398,0.00002533551,0.9833122,0.016179485,0.0000016724864],"about_ca_topic_score_codex":0.0027578936,"about_ca_topic_score_gemma":0.001800469,"teacher_disagreement_score":0.008283619,"about_ca_system_score_codex":0.005822189,"about_ca_system_score_gemma":0.002133049,"threshold_uncertainty_score":0.042243183},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02520423,0.008923093,0.8299522,0.001549349,0.0023300822,0.11733396,0.0011289376,0.0013840161,0.012194166],"genre_scores_gemma":[0.1034984,0.0009786179,0.7281414,0.00076696806,0.0002558239,0.1649084,0.00029374374,0.00023930384,0.0009172391],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.08939035,0.8601052,0.02127399,0.00782368,0.020579182,0.0008276225],"domain_scores_gemma":[0.10678217,0.80595696,0.025174223,0.029405305,0.031237958,0.0014433922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.63799727,0.0053012664,0.009708352,0.023392236,0.0045673084,0.011461576,0.009619078,0.0046269875,0.0080109285],"category_scores_gemma":[0.6853683,0.0023141317,0.009171989,0.01482478,0.007058767,0.007814324,0.010909267,0.005785003,0.001195145],"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":[0.009928012,0.0036588972,0.02071143,0.03057441,0.023398073,0.000372569,0.011755872,0.017320888,0.00079785724,0.08787411,0.008540609,0.78506726],"study_design_scores_gemma":[0.01426885,0.045467198,0.035386756,0.038657546,0.019381717,0.0008536654,0.019836381,0.3647781,0.013298723,0.35479262,0.091438375,0.0018401438],"about_ca_topic_score_codex":0.005413967,"about_ca_topic_score_gemma":0.0050557293,"teacher_disagreement_score":0.63799727,"about_ca_system_score_codex":0.014946656,"about_ca_system_score_gemma":0.01569181,"threshold_uncertainty_score":0.44641387},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020500212,0.012723882,0.89158654,0.029825838,0.00079401076,0.0018812428,0.00023743618,0.0003495982,0.060551368],"genre_scores_gemma":[0.17751305,0.007467129,0.8040491,0.0025043339,0.00077004475,0.0053882026,0.00020318404,0.00016888994,0.001936003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6743116,0.28949872,0.011302795,0.007818219,0.014615652,0.0024530813],"domain_scores_gemma":[0.6960761,0.23678128,0.0125656305,0.026319355,0.023576574,0.0046810056],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31315196,0.004979793,0.0043097967,0.027446523,0.006877427,0.034054875,0.0067621055,0.0070973993,0.005775132],"category_scores_gemma":[0.13875812,0.0019380547,0.0038609626,0.01346227,0.081421524,0.032929063,0.019047799,0.010929454,0.00099351],"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":[0.000012050178,0.000035847683,0.00031619077,0.00087834126,0.00006003174,0.000041230458,0.0023766893,0.0019057563,0.00008420355,0.9752873,0.00096970855,0.018032614],"study_design_scores_gemma":[0.000028307626,0.00006079502,0.00027356885,0.0019392159,0.000080587335,0.0000654725,0.0020975682,0.0037390683,0.00019513328,0.9601295,0.031346466,0.00004446175],"about_ca_topic_score_codex":0.0049698935,"about_ca_topic_score_gemma":0.005062001,"teacher_disagreement_score":0.68684804,"about_ca_system_score_codex":0.025630677,"about_ca_system_score_gemma":0.033742175,"threshold_uncertainty_score":0.84700596},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865218,0.0010033767,0.0007058112,0.004827246,0.000030437974,0.00015715994,0.00007249077,0.000016805216,0.006664882],"genre_scores_gemma":[0.9961903,0.00044171512,0.0006997218,0.00041541643,0.000007604254,0.000091909795,0.000036812493,0.000006067186,0.0021104233],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99021345,0.005985871,0.00054238073,0.00062699243,0.0006413636,0.0019900214],"domain_scores_gemma":[0.9864116,0.0056451564,0.003581951,0.0006604701,0.0009369857,0.0027637866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070276638,0.00015847369,0.00025656135,0.0010994577,0.008208385,0.004185409,0.0011824269,0.0011664013,0.0039628986],"category_scores_gemma":[0.014137845,0.00050856697,0.0001223658,0.0023021104,0.005735715,0.0020641417,0.004347541,0.0011202418,0.00029661105],"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":[0.0001615531,0.00031283125,0.23203245,0.000856812,0.000029145316,0.0029453097,0.66577023,0.00048932474,0.0027157695,0.015239732,0.006082574,0.07336418],"study_design_scores_gemma":[0.000030987016,0.0001720092,0.11947046,0.00044365122,0.000012789752,0.00032559253,0.80509543,0.00020889874,0.00050145376,0.001006777,0.07269892,0.000033035336],"about_ca_topic_score_codex":0.034553554,"about_ca_topic_score_gemma":0.08051676,"teacher_disagreement_score":0.034553554,"about_ca_system_score_codex":0.016912978,"about_ca_system_score_gemma":0.015402662,"threshold_uncertainty_score":0.12271285},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03158514,0.027354691,0.6761724,0.18509844,0.0071823606,0.007847282,0.00062303763,0.0018936774,0.062243085],"genre_scores_gemma":[0.51547635,0.009356702,0.42782107,0.020984543,0.008347686,0.012684658,0.0005473841,0.0010289287,0.0037527385],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.13988146,0.7117491,0.050650418,0.019822624,0.074561834,0.0033346105],"domain_scores_gemma":[0.03047486,0.7024124,0.036886867,0.16877471,0.058894936,0.0025563259],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.76960456,0.0016180922,0.0035089098,0.0138990525,0.009161469,0.02283515,0.008437565,0.009719728,0.0046081305],"category_scores_gemma":[0.89787143,0.0024718388,0.003461668,0.011395797,0.040407028,0.032078788,0.021598449,0.013022635,0.0021467274],"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":[0.00063108245,0.00037469572,0.023842057,0.007879073,0.0010335415,0.0004533559,0.053134166,0.005975268,0.002334119,0.43490133,0.02902989,0.44041142],"study_design_scores_gemma":[0.00078928773,0.00094696775,0.012062082,0.017045757,0.0006138048,0.0008512106,0.008847037,0.009567384,0.007458949,0.709551,0.23171337,0.0005532589],"about_ca_topic_score_codex":0.0032315336,"about_ca_topic_score_gemma":0.002406621,"teacher_disagreement_score":0.23039544,"about_ca_system_score_codex":0.011682825,"about_ca_system_score_gemma":0.04717665,"threshold_uncertainty_score":0.28411865},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62619185,0.0021773002,0.26309517,0.0030206991,0.0013217592,0.043448623,0.006339947,0.0023412379,0.05206331],"genre_scores_gemma":[0.5845979,0.0014276581,0.323145,0.0011713406,0.00023606139,0.07378118,0.0028627121,0.0004522036,0.012325996],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9725779,0.01349091,0.0034239977,0.0021510979,0.0074459054,0.0009102365],"domain_scores_gemma":[0.93654823,0.03320658,0.006014831,0.005052168,0.017718324,0.0014599336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023900397,0.00092381984,0.0009698462,0.0021465558,0.0010678134,0.0030644813,0.0016088784,0.0011899003,0.0073289787],"category_scores_gemma":[0.07946669,0.00067279895,0.0019010584,0.0016074796,0.0015779532,0.002016815,0.0031306276,0.0018236232,0.0021095863],"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":[0.0031741294,0.0017656466,0.18233009,0.006785115,0.0008575091,0.00027765773,0.029539654,0.004574084,0.016231347,0.010941216,0.018527744,0.72499573],"study_design_scores_gemma":[0.0012738039,0.004783039,0.74838275,0.0049147345,0.0011937595,0.00082950067,0.017552452,0.01805535,0.028201824,0.019019512,0.1550587,0.00073453813],"about_ca_topic_score_codex":0.002662852,"about_ca_topic_score_gemma":0.003995245,"teacher_disagreement_score":0.023900397,"about_ca_system_score_codex":0.0021270744,"about_ca_system_score_gemma":0.0053368863,"threshold_uncertainty_score":0.12639892},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000654728,0.16472034,0.40818197,0.37651882,0.015836338,0.002284881,0.0003910805,0.00065219967,0.030759575],"genre_scores_gemma":[0.012311328,0.09974449,0.8215455,0.042177532,0.0062148897,0.008247557,0.00033141606,0.000728798,0.008698492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5533036,0.39923617,0.0207425,0.004452247,0.02084257,0.0014229104],"domain_scores_gemma":[0.29770514,0.6675857,0.0053238883,0.012008824,0.015536425,0.0018400144],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4108518,0.002538485,0.0076912567,0.011350863,0.004579078,0.029999224,0.006909562,0.011370363,0.012002204],"category_scores_gemma":[0.44514722,0.0032361909,0.003630387,0.010250847,0.021207834,0.030841663,0.016801275,0.023283426,0.0067430446],"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":[0.000063398686,0.0000724786,0.00025801978,0.012303786,0.00032568513,0.00030773424,0.016637385,0.0014566125,0.00042447628,0.61429965,0.11438866,0.23946217],"study_design_scores_gemma":[0.00005629988,0.00005228463,0.00013526894,0.019675491,0.00007243533,0.00021610432,0.003638375,0.0009195806,0.00029635784,0.5844054,0.39044902,0.000083440806],"about_ca_topic_score_codex":0.0023232885,"about_ca_topic_score_gemma":0.0033798926,"teacher_disagreement_score":0.99542093,"about_ca_system_score_codex":0.010641651,"about_ca_system_score_gemma":0.033822533,"threshold_uncertainty_score":0.7265246},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06137627,0.009496477,0.8014775,0.08621934,0.0039952327,0.022326892,0.0005787678,0.001840946,0.012688551],"genre_scores_gemma":[0.30325338,0.003079634,0.59634036,0.019608038,0.0010014593,0.071857326,0.00038016256,0.0011734962,0.0033061916],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.1451748,0.669874,0.08373784,0.022060405,0.074870706,0.0042822487],"domain_scores_gemma":[0.039911762,0.79636055,0.0750393,0.03952436,0.0468653,0.0022986967],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7160548,0.0033095793,0.0061580585,0.013945662,0.016501667,0.018699324,0.00907129,0.011772277,0.0044034543],"category_scores_gemma":[0.8479375,0.0061382055,0.0045384853,0.014266168,0.039438095,0.028351827,0.027514467,0.016782885,0.0016444143],"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":[0.0006891998,0.00028552618,0.015706345,0.017444622,0.00042794447,0.0017761766,0.58492666,0.0015073288,0.0026451037,0.16431193,0.02103731,0.18924184],"study_design_scores_gemma":[0.0006199082,0.0011279515,0.010817358,0.09717137,0.0008432508,0.0036240816,0.25263724,0.024446104,0.01202286,0.40810546,0.18753985,0.0010446177],"about_ca_topic_score_codex":0.003968659,"about_ca_topic_score_gemma":0.0048106615,"teacher_disagreement_score":0.2839452,"about_ca_system_score_codex":0.027917936,"about_ca_system_score_gemma":0.047321312,"threshold_uncertainty_score":0.35015506},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0091588935,0.52394205,0.008154498,0.4227225,0.0020167637,0.00007141195,0.00006666421,0.00012795541,0.03373933],"genre_scores_gemma":[0.20279023,0.7209977,0.022651287,0.042809375,0.004080075,0.00017086539,0.00016942596,0.00014089399,0.006190206],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97848356,0.013284462,0.0016343594,0.0012702883,0.0030938727,0.0022335602],"domain_scores_gemma":[0.95206636,0.027660662,0.003840574,0.0015439985,0.0089381635,0.0059502064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045545567,0.0006436758,0.0007170208,0.005164609,0.0033257422,0.01448834,0.0017928487,0.0060905726,0.0031391047],"category_scores_gemma":[0.016973237,0.00053496484,0.000833602,0.00750686,0.009720334,0.011265086,0.007543299,0.00697497,0.00063500635],"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":[0.0001087821,0.00020230084,0.014168069,0.009010432,0.000051023526,0.0006930928,0.02665759,0.0007607579,0.00095425424,0.19584905,0.07701132,0.6745334],"study_design_scores_gemma":[0.000022314165,0.0001442111,0.013626869,0.01427219,0.00003854505,0.0021385236,0.049685474,0.00070696266,0.0004183992,0.057507582,0.86135226,0.000086782464],"about_ca_topic_score_codex":0.0037974056,"about_ca_topic_score_gemma":0.0050663687,"teacher_disagreement_score":0.9544544,"about_ca_system_score_codex":0.005754733,"about_ca_system_score_gemma":0.02184845,"threshold_uncertainty_score":0.24087083},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868139,0.0005322834,0.000533056,0.0013632433,0.000012495455,0.00032819808,0.00022483617,0.0000068875484,0.010185056],"genre_scores_gemma":[0.9916829,0.0012061374,0.0017071959,0.00020824072,0.000012483413,0.00017974804,0.00010683145,0.0000067966553,0.0048896153],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.995017,0.0019974194,0.00024201159,0.00029129654,0.0010670803,0.0013853129],"domain_scores_gemma":[0.9894685,0.0050316653,0.001769597,0.00042955508,0.0016966112,0.0016040934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036876234,0.00038275906,0.00048206927,0.0019448152,0.012912569,0.0028201926,0.0018408123,0.0017133337,0.0028579796],"category_scores_gemma":[0.008410918,0.00046264107,0.00037451938,0.0056617013,0.003224447,0.0012930718,0.0021038565,0.0012114507,0.00022003897],"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":[0.00049203454,0.0014009689,0.2401668,0.0008217278,0.00008154851,0.049087092,0.6249418,0.0027744635,0.0021999364,0.010778332,0.008069569,0.059185702],"study_design_scores_gemma":[0.00006851687,0.00046004023,0.14429073,0.00048343439,0.00007312067,0.004202711,0.77275187,0.0026809725,0.0010265155,0.0010047724,0.07287341,0.00008378834],"about_ca_topic_score_codex":0.87083644,"about_ca_topic_score_gemma":0.9594959,"teacher_disagreement_score":0.9366597,"about_ca_system_score_codex":0.063340336,"about_ca_system_score_gemma":0.03485021,"threshold_uncertainty_score":0.45956844},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021573476,0.0022429293,0.8753506,0.024642164,0.00096552464,0.006586008,0.00012898946,0.001182924,0.06732744],"genre_scores_gemma":[0.33458704,0.0013318533,0.64907223,0.0023058408,0.00028192604,0.006530677,0.00016740739,0.0004964722,0.0052265967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.57203585,0.38770545,0.00769868,0.0074690115,0.022048958,0.0030421007],"domain_scores_gemma":[0.6004511,0.30964473,0.010628977,0.036201954,0.037559412,0.005513938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30612633,0.0017151737,0.0018435173,0.008159262,0.005319653,0.025721386,0.0045888536,0.00639909,0.007954432],"category_scores_gemma":[0.31512442,0.0011655516,0.0012588438,0.0051718242,0.02318176,0.019969707,0.013972822,0.005582233,0.0022022107],"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":[0.00031171023,0.00079823844,0.0043098587,0.0034137175,0.00016886777,0.00032573496,0.065847985,0.005148522,0.002855083,0.50412524,0.012761833,0.39993313],"study_design_scores_gemma":[0.0006029805,0.0013686711,0.0027146586,0.010055701,0.00020088321,0.0004876967,0.058703322,0.024030304,0.008585288,0.7061302,0.18680744,0.0003129024],"about_ca_topic_score_codex":0.0019849383,"about_ca_topic_score_gemma":0.0018600665,"teacher_disagreement_score":0.30612633,"about_ca_system_score_codex":0.013887268,"about_ca_system_score_gemma":0.023218825,"threshold_uncertainty_score":0.8556698},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012496136,0.0012877083,0.95537305,0.018988112,0.0012942199,0.0004929394,0.00026653797,0.0014317868,0.008369543],"genre_scores_gemma":[0.23313527,0.00087336317,0.7451997,0.0135005005,0.001107296,0.0016820522,0.00025587462,0.0009697084,0.0032762461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93558556,0.043852348,0.002627714,0.008365396,0.008241062,0.0013278753],"domain_scores_gemma":[0.7216764,0.21522662,0.008276427,0.039905638,0.012229212,0.0026856891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08281766,0.0019450105,0.002130718,0.0028598963,0.0034943942,0.0060211387,0.005469749,0.004716332,0.0068629235],"category_scores_gemma":[0.3776143,0.0012607668,0.0031454097,0.002414524,0.012173473,0.008608525,0.008422211,0.013066,0.0020019466],"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":[0.0013203858,0.00037446799,0.0136836115,0.0009502608,0.0007473735,0.0013693153,0.002906118,0.033109836,0.007115513,0.5944293,0.0328796,0.31111413],"study_design_scores_gemma":[0.0002572218,0.00061232055,0.0013191565,0.00046357093,0.00023768378,0.0008155574,0.00040068539,0.05706247,0.0064533716,0.9029345,0.029299052,0.00014434078],"about_ca_topic_score_codex":0.0020880438,"about_ca_topic_score_gemma":0.0021657795,"teacher_disagreement_score":0.08281766,"about_ca_system_score_codex":0.0031634427,"about_ca_system_score_gemma":0.0059373924,"threshold_uncertainty_score":0.43798685},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3296107,0.0037699898,0.47275317,0.03825319,0.00077752897,0.0021732957,0.0001410204,0.0003619554,0.15215926],"genre_scores_gemma":[0.82533854,0.0007238572,0.16604002,0.002512172,0.0001675609,0.001428524,0.000042927895,0.000076175405,0.0036702491],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8451611,0.12387083,0.0042019645,0.0031572746,0.020388383,0.0032204937],"domain_scores_gemma":[0.81460625,0.13073224,0.008396077,0.022592343,0.015933486,0.0077395397],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11637665,0.00074468687,0.0008918402,0.00419379,0.0057214866,0.01385272,0.0025337636,0.0022754916,0.0046140156],"category_scores_gemma":[0.16839266,0.0007025272,0.00090968935,0.0018319348,0.008915457,0.011033575,0.030094033,0.0035762428,0.0006836278],"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":[0.00034537556,0.0015006409,0.0188809,0.001186893,0.00023988624,0.00033833706,0.066695735,0.0016269042,0.005571523,0.34245598,0.0034977498,0.55766004],"study_design_scores_gemma":[0.00020297997,0.00094817195,0.011047287,0.0054118005,0.00031681822,0.0007989153,0.044536576,0.0067668636,0.014926373,0.85871685,0.056200463,0.00012707432],"about_ca_topic_score_codex":0.00069119595,"about_ca_topic_score_gemma":0.0016094315,"teacher_disagreement_score":0.88362336,"about_ca_system_score_codex":0.0038126172,"about_ca_system_score_gemma":0.016490951,"threshold_uncertainty_score":0.61546594},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043426147,0.98436594,0.002433128,0.0024425602,0.00049229275,0.0018890226,0.0009830904,0.000041940402,0.0030093468],"genre_scores_gemma":[0.01913995,0.9691161,0.0064622057,0.00087309896,0.00011777095,0.0028792394,0.00089088496,0.000030788437,0.00048988604],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96046853,0.014173153,0.013942092,0.0017882675,0.008797949,0.00083010265],"domain_scores_gemma":[0.85422087,0.09033804,0.017783279,0.0038753506,0.032643124,0.0011393226],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07300958,0.0016129101,0.0034232975,0.057254087,0.0022375027,0.0055958177,0.0020876583,0.0024270976,0.0029944074],"category_scores_gemma":[0.19321127,0.0018882252,0.003797541,0.055707593,0.0019734595,0.0071745752,0.00520608,0.0018124423,0.00072411634],"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":[0.00012447377,0.000048638703,0.0029488674,0.4582332,0.0012886979,0.00030688263,0.004556241,0.00040692504,0.0006188703,0.0023268482,0.012471994,0.5166683],"study_design_scores_gemma":[0.000026624515,0.00009766914,0.0059850235,0.91517305,0.0027938175,0.00026301248,0.0029338952,0.0001555871,0.00042493746,0.00086511293,0.07123532,0.000045977773],"about_ca_topic_score_codex":0.015893111,"about_ca_topic_score_gemma":0.04680869,"teacher_disagreement_score":0.9269904,"about_ca_system_score_codex":0.008754549,"about_ca_system_score_gemma":0.04775911,"threshold_uncertainty_score":0.3861162},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9749268,0.0011823435,0.0008242721,0.0018901853,0.0000274629,0.00007009094,0.0010600906,0.000030862648,0.019987797],"genre_scores_gemma":[0.998555,0.0001100201,0.00014440175,0.00002542077,0.0000029637117,0.0000087123035,0.00014324946,0.000005652587,0.0010046805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863312,0.0030739126,0.0005790475,0.0009009414,0.0057534873,0.0033612882],"domain_scores_gemma":[0.9424756,0.017666664,0.005795657,0.001889881,0.025068993,0.007103243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012083986,0.00033104658,0.00062569184,0.004126815,0.0045907227,0.006130885,0.0017204275,0.00078935886,0.0034412374],"category_scores_gemma":[0.056391988,0.00025223818,0.00045251404,0.0087578185,0.005611822,0.0027299891,0.005016609,0.0014077366,0.00018762007],"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":[0.00081769226,0.00041219065,0.829009,0.00021376778,0.00024962117,0.00012799533,0.018243881,0.004432867,0.00046793127,0.05258015,0.0056877485,0.087757155],"study_design_scores_gemma":[0.00003683202,0.00006700906,0.9785542,0.000107386455,0.000113886716,0.00001981984,0.010223744,0.0019024597,0.00062953023,0.002560613,0.005742649,0.00004174367],"about_ca_topic_score_codex":0.97287375,"about_ca_topic_score_gemma":0.9763174,"teacher_disagreement_score":0.91525084,"about_ca_system_score_codex":0.084749185,"about_ca_system_score_gemma":0.10060427,"threshold_uncertainty_score":0.61490124},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9535317,0.00073511136,0.0063617923,0.0008776623,0.000031957952,0.007416659,0.000096368174,0.00003636482,0.030912384],"genre_scores_gemma":[0.97195846,0.00048554418,0.021707518,0.000120657074,0.000014352609,0.0034867565,0.00005457867,0.000007856792,0.002164231],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9385877,0.04869414,0.0019819764,0.0013079923,0.0059728627,0.003455282],"domain_scores_gemma":[0.92610025,0.048689887,0.0058599273,0.002287773,0.013151401,0.003910793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06756291,0.00087582227,0.00110198,0.003658777,0.006876362,0.0045587095,0.0019109197,0.0013527457,0.0030901046],"category_scores_gemma":[0.084436044,0.0004457586,0.00068038283,0.0037115263,0.0040965853,0.0020391578,0.0049740076,0.0017324835,0.000281696],"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":[0.004685091,0.013793728,0.23451008,0.0040052957,0.00052178034,0.0028517176,0.23178057,0.012645904,0.005466973,0.027632529,0.0027803627,0.459326],"study_design_scores_gemma":[0.0012658036,0.026611447,0.42291683,0.0025636996,0.00074676075,0.00080789113,0.4746538,0.016411873,0.010718498,0.015133788,0.027858824,0.00031084023],"about_ca_topic_score_codex":0.07854385,"about_ca_topic_score_gemma":0.15032975,"teacher_disagreement_score":0.92145616,"about_ca_system_score_codex":0.020962713,"about_ca_system_score_gemma":0.033706605,"threshold_uncertainty_score":0.35731107},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075240806,0.0008653851,0.79819,0.0031023829,0.0012659127,0.094448805,0.0011818423,0.0011822503,0.024522537],"genre_scores_gemma":[0.15368398,0.00037488123,0.6534166,0.0016327858,0.00018621345,0.18786947,0.00046268682,0.00032188778,0.002051516],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.37072855,0.5865739,0.019741574,0.0067881653,0.0140735125,0.0020942816],"domain_scores_gemma":[0.25993875,0.60472393,0.021459563,0.05702907,0.05477795,0.0020708255],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3354897,0.0021236178,0.0017376902,0.009018115,0.0072233267,0.005892507,0.0038225313,0.002822849,0.0104448],"category_scores_gemma":[0.5783035,0.0019750325,0.0015588239,0.006613325,0.0074643833,0.006673719,0.008331609,0.003634857,0.0021435441],"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":[0.0024248469,0.0017224131,0.00865551,0.011763443,0.00030423744,0.0015421306,0.38393041,0.0058796303,0.021551669,0.12374249,0.018997831,0.41948536],"study_design_scores_gemma":[0.002730641,0.0056069307,0.020980984,0.01730446,0.00043841513,0.0028736629,0.18638399,0.053389117,0.056203485,0.17897725,0.4737391,0.0013719706],"about_ca_topic_score_codex":0.0018691472,"about_ca_topic_score_gemma":0.0047303485,"teacher_disagreement_score":0.6645103,"about_ca_system_score_codex":0.008035711,"about_ca_system_score_gemma":0.008709091,"threshold_uncertainty_score":0.81945956},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009350078,0.0005716872,0.00030014358,0.99531835,0.0022274137,0.000008511178,0.000010439298,0.0000114649865,0.001458373],"genre_scores_gemma":[0.0034623903,0.0005691979,0.0012433439,0.9857932,0.0051517165,0.000050702576,0.000012359232,0.00003811354,0.003678993],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.86638534,0.084798336,0.010099057,0.0070580384,0.028499931,0.0031593554],"domain_scores_gemma":[0.6159699,0.29526046,0.008599821,0.009348705,0.05673568,0.014085462],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12047766,0.0008096521,0.0014986193,0.0015489528,0.0070797997,0.014508454,0.0035575647,0.03631776,0.010779975],"category_scores_gemma":[0.2677021,0.0008018406,0.0017977254,0.0015829848,0.020474952,0.015015812,0.0054497374,0.05268258,0.005035934],"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":[0.00004978384,0.000025614481,0.0006585455,0.00016391695,0.000021644933,0.00016729075,0.00078943017,0.00006687792,0.00014127899,0.027561987,0.9524618,0.017891912],"study_design_scores_gemma":[0.00012381354,0.00008236654,0.0019165064,0.0017372454,0.000034289445,0.00066173373,0.002901175,0.0008598517,0.0003059629,0.09645041,0.8947809,0.00014578107],"about_ca_topic_score_codex":0.018300923,"about_ca_topic_score_gemma":0.0347243,"teacher_disagreement_score":0.8795223,"about_ca_system_score_codex":0.012586454,"about_ca_system_score_gemma":0.025621403,"threshold_uncertainty_score":0.6371544},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009047427,0.077406466,0.024832495,0.75164396,0.013647307,0.00067798747,0.00014258933,0.00043171344,0.122170016],"genre_scores_gemma":[0.37198392,0.0955696,0.07578447,0.35558063,0.024808552,0.0038593812,0.00039974067,0.0011270222,0.07088669],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9686105,0.020483274,0.0011878469,0.0027955342,0.0054323836,0.0014904438],"domain_scores_gemma":[0.75211865,0.17882355,0.005364883,0.01797892,0.03198625,0.013727781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07796585,0.0014283118,0.003172333,0.0031577072,0.0040756813,0.0103022065,0.004721474,0.0066550598,0.0571441],"category_scores_gemma":[0.13359703,0.0004479275,0.0013673544,0.0018831725,0.017155308,0.028197693,0.01305135,0.01074636,0.0048961183],"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":[0.00034157958,0.0008896541,0.003714649,0.00825295,0.00023401427,0.0002515456,0.01405508,0.00049181195,0.0012894231,0.22943628,0.14090636,0.60013676],"study_design_scores_gemma":[0.00014124665,0.000485325,0.0072617326,0.0072572157,0.00007822126,0.00032398858,0.016800271,0.00024369254,0.00073511055,0.20504874,0.76150304,0.00012147632],"about_ca_topic_score_codex":0.01158436,"about_ca_topic_score_gemma":0.010201382,"teacher_disagreement_score":0.07796585,"about_ca_system_score_codex":0.008806555,"about_ca_system_score_gemma":0.018234242,"threshold_uncertainty_score":0.41232777},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0776004,0.00049986027,0.9125821,0.00049908936,0.00009168004,0.00014937104,0.00023435624,0.006423799,0.0019193573],"genre_scores_gemma":[0.586782,0.00026988517,0.40722167,0.0002349275,0.0001235265,0.00014653767,0.0008634455,0.0005501658,0.0038078225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983381,0.00036825266,0.000117558826,0.00040223234,0.00056989165,0.00020391823],"domain_scores_gemma":[0.99268496,0.0037502302,0.0005952633,0.0017807349,0.0009986712,0.00019018448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002639955,0.0015071543,0.0015355063,0.0017256852,0.00061983155,0.0016082268,0.001388003,0.0014412084,0.004149328],"category_scores_gemma":[0.014527795,0.0005135449,0.0010540371,0.0010950628,0.00090800115,0.003145109,0.0032908502,0.0020197309,0.0015237072],"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":[0.00070782803,0.00026233256,0.0070636496,0.00031613786,0.00018899378,0.00027274262,0.00059744465,0.31876916,0.02217698,0.013956417,0.009087525,0.62660086],"study_design_scores_gemma":[0.00005333931,0.00016707774,0.001559453,0.000028219683,0.00007560172,0.00012069099,0.00011350883,0.96040726,0.012404608,0.022144608,0.0029026645,0.000023000055],"about_ca_topic_score_codex":0.0025637737,"about_ca_topic_score_gemma":0.004292406,"teacher_disagreement_score":0.004149328,"about_ca_system_score_codex":0.0010501131,"about_ca_system_score_gemma":0.0016013485,"threshold_uncertainty_score":0.013961554},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38686988,0.061364625,0.3090342,0.038698718,0.0019684436,0.020356387,0.02076739,0.0019408157,0.15899953],"genre_scores_gemma":[0.7090423,0.00593853,0.27220494,0.00092669565,0.00029779592,0.0063537494,0.0038419114,0.00013711363,0.0012568751],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.44000632,0.43459776,0.041887566,0.011029825,0.06796208,0.0045164814],"domain_scores_gemma":[0.1460358,0.718133,0.041109007,0.021943461,0.06709166,0.0056870263],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46087405,0.0022852188,0.0036911392,0.06993212,0.004282686,0.03251079,0.0043205875,0.004231043,0.007298524],"category_scores_gemma":[0.63693506,0.0009948057,0.004491198,0.07737795,0.005785411,0.014800292,0.01381382,0.0029108743,0.0011471305],"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":[0.0039130035,0.001354886,0.12895772,0.03206429,0.008349464,0.00047665407,0.013138996,0.05188225,0.002670664,0.17703666,0.012988715,0.5671667],"study_design_scores_gemma":[0.002244409,0.0058476203,0.12034841,0.028384075,0.010257193,0.00041506923,0.057174373,0.16328703,0.015244765,0.48847708,0.10753013,0.0007898745],"about_ca_topic_score_codex":0.013840141,"about_ca_topic_score_gemma":0.015925579,"teacher_disagreement_score":0.9300679,"about_ca_system_score_codex":0.027921507,"about_ca_system_score_gemma":0.028982587,"threshold_uncertainty_score":0.6648383},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051824166,0.00013923446,0.00020296552,0.00014806568,0.00004351533,0.000050653623,0.9963744,0.0010509372,0.0014719813],"genre_scores_gemma":[0.00055241695,0.00002740559,0.00060339377,0.000046316072,0.000006218435,0.0001317683,0.9979603,0.000058807986,0.0006132634],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974999,0.000619502,0.00025919848,0.00063727226,0.00070403895,0.00028000874],"domain_scores_gemma":[0.9950228,0.0019664122,0.00034522568,0.0012108639,0.00096737733,0.0004873533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024353247,0.0040410724,0.0015114385,0.0038181432,0.0012566234,0.0028940714,0.0042318124,0.004534381,0.06416584],"category_scores_gemma":[0.012932775,0.0008125783,0.0023639132,0.0035810664,0.0008315353,0.0021725956,0.0032761418,0.0031644204,0.09898188],"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":[0.00011500888,0.00007635459,0.0006866374,0.0007859374,0.000033751527,0.00003050424,0.000039582632,0.00046587884,0.00022860928,0.0006351282,0.993378,0.0035246338],"study_design_scores_gemma":[0.00082833634,0.00007044049,0.0056955866,0.00048115305,0.00006695165,0.00012678404,0.00020554841,0.0026362427,0.0014073299,0.0038307088,0.98458385,0.00006713727],"about_ca_topic_score_codex":0.02817369,"about_ca_topic_score_gemma":0.060565516,"teacher_disagreement_score":0.06416584,"about_ca_system_score_codex":0.00253948,"about_ca_system_score_gemma":0.003641474,"threshold_uncertainty_score":0.21465611},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051824166,0.00013923446,0.00020296552,0.00014806568,0.00004351533,0.000050653623,0.9963744,0.0010509372,0.0014719813],"genre_scores_gemma":[0.00055241695,0.00002740559,0.00060339377,0.000046316072,0.000006218435,0.0001317683,0.9979603,0.000058807986,0.0006132634],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974999,0.000619502,0.00025919848,0.00063727226,0.00070403895,0.00028000874],"domain_scores_gemma":[0.9950228,0.0019664122,0.00034522568,0.0012108639,0.00096737733,0.0004873533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024353247,0.0040410724,0.0015114385,0.0038181432,0.0012566234,0.0028940714,0.0042318124,0.004534381,0.06416584],"category_scores_gemma":[0.012932775,0.0008125783,0.0023639132,0.0035810664,0.0008315353,0.0021725956,0.0032761418,0.0031644204,0.09898188],"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":[0.00011500888,0.00007635459,0.0006866374,0.0007859374,0.000033751527,0.00003050424,0.000039582632,0.00046587884,0.00022860928,0.0006351282,0.993378,0.0035246338],"study_design_scores_gemma":[0.00082833634,0.00007044049,0.0056955866,0.00048115305,0.00006695165,0.00012678404,0.00020554841,0.0026362427,0.0014073299,0.0038307088,0.98458385,0.00006713727],"about_ca_topic_score_codex":0.02817369,"about_ca_topic_score_gemma":0.060565516,"teacher_disagreement_score":0.06416584,"about_ca_system_score_codex":0.00253948,"about_ca_system_score_gemma":0.003641474,"threshold_uncertainty_score":0.21465611},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051824166,0.00013923446,0.00020296552,0.00014806568,0.00004351533,0.000050653623,0.9963744,0.0010509372,0.0014719813],"genre_scores_gemma":[0.00055241695,0.00002740559,0.00060339377,0.000046316072,0.000006218435,0.0001317683,0.9979603,0.000058807986,0.0006132634],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974999,0.000619502,0.00025919848,0.00063727226,0.00070403895,0.00028000874],"domain_scores_gemma":[0.9950228,0.0019664122,0.00034522568,0.0012108639,0.00096737733,0.0004873533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024353247,0.0040410724,0.0015114385,0.0038181432,0.0012566234,0.0028940714,0.0042318124,0.004534381,0.06416584],"category_scores_gemma":[0.012932775,0.0008125783,0.0023639132,0.0035810664,0.0008315353,0.0021725956,0.0032761418,0.0031644204,0.09898188],"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":[0.00011500888,0.00007635459,0.0006866374,0.0007859374,0.000033751527,0.00003050424,0.000039582632,0.00046587884,0.00022860928,0.0006351282,0.993378,0.0035246338],"study_design_scores_gemma":[0.00082833634,0.00007044049,0.0056955866,0.00048115305,0.00006695165,0.00012678404,0.00020554841,0.0026362427,0.0014073299,0.0038307088,0.98458385,0.00006713727],"about_ca_topic_score_codex":0.02817369,"about_ca_topic_score_gemma":0.060565516,"teacher_disagreement_score":0.06416584,"about_ca_system_score_codex":0.00253948,"about_ca_system_score_gemma":0.003641474,"threshold_uncertainty_score":0.21465611},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018660055,0.0036189076,0.003089697,0.9365113,0.0018590259,0.00012381792,0.000033424574,0.0000563354,0.03604733],"genre_scores_gemma":[0.7046121,0.00541571,0.023099735,0.19781286,0.0017977699,0.0007449627,0.00011384528,0.00030768436,0.06609542],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9493087,0.029873606,0.00082292367,0.002985268,0.006194028,0.0108154],"domain_scores_gemma":[0.9159973,0.0330655,0.0015083306,0.002742958,0.0108969025,0.035789046],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07587067,0.0004503823,0.00064755743,0.001390879,0.031969804,0.020076497,0.0034332534,0.012796468,0.0077442387],"category_scores_gemma":[0.045209788,0.0010096172,0.00059354294,0.001663967,0.022109155,0.010940903,0.017377635,0.024687389,0.0008638354],"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":[0.00009990208,0.0006467568,0.0035110447,0.00017009661,0.000017239316,0.00071395887,0.035515998,0.000742666,0.000604395,0.34817812,0.5427296,0.067070186],"study_design_scores_gemma":[0.000058154503,0.00010112501,0.0031717464,0.000454933,0.0000052572072,0.000148892,0.03618359,0.0013064807,0.00073931634,0.04282874,0.9148789,0.00012279578],"about_ca_topic_score_codex":0.14345501,"about_ca_topic_score_gemma":0.31799272,"teacher_disagreement_score":0.9487244,"about_ca_system_score_codex":0.051275633,"about_ca_system_score_gemma":0.13593572,"threshold_uncertainty_score":0.40124726},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23737967,0.0016254392,0.44919023,0.023047475,0.0009818305,0.0055561108,0.00017372021,0.0023013398,0.27974415],"genre_scores_gemma":[0.69530153,0.0011903585,0.28828812,0.0013713244,0.00022205955,0.0025497412,0.00016356181,0.00016738196,0.010745951],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9738565,0.02102875,0.0005102328,0.0011135846,0.0021798147,0.0013111426],"domain_scores_gemma":[0.90747017,0.07200187,0.0019549145,0.0057757664,0.0035351529,0.009262089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0355126,0.00094934955,0.00062165677,0.0019074325,0.003678694,0.008752865,0.0043646153,0.0019570505,0.011631048],"category_scores_gemma":[0.053628396,0.00046866902,0.0007026266,0.0014688099,0.0057085506,0.0064912946,0.016592477,0.0032200164,0.0017784009],"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":[0.000292101,0.009922393,0.0041500153,0.0012246222,0.00010809511,0.00071594684,0.063868456,0.008970422,0.0032256134,0.08422958,0.031930655,0.7913622],"study_design_scores_gemma":[0.0010747619,0.003029648,0.009227813,0.004285633,0.000148082,0.0015045851,0.11526455,0.028947162,0.012035039,0.44637844,0.3776572,0.00044712925],"about_ca_topic_score_codex":0.0010324031,"about_ca_topic_score_gemma":0.002660933,"teacher_disagreement_score":0.0355126,"about_ca_system_score_codex":0.002978201,"about_ca_system_score_gemma":0.011016766,"threshold_uncertainty_score":0.18781078},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8890694,0.017466733,0.04066558,0.0031469075,0.00013547121,0.0012250056,0.00075324083,0.00009830143,0.04743936],"genre_scores_gemma":[0.9714831,0.0056928047,0.020400662,0.0003202748,0.000037693582,0.0010074602,0.00038207197,0.00006332239,0.00061261957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.92350733,0.047136445,0.008091351,0.0029315387,0.016550144,0.0017831607],"domain_scores_gemma":[0.40714118,0.5084608,0.021697149,0.014699378,0.04614264,0.0018588497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09469199,0.0006442162,0.0008044346,0.022958312,0.002309329,0.005989609,0.0019940075,0.0009337167,0.0019861157],"category_scores_gemma":[0.3468906,0.00071560714,0.0011707046,0.022799524,0.004636295,0.010230894,0.009891407,0.0018922206,0.0002411776],"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":[0.00022688675,0.0002513933,0.30129436,0.0058155423,0.00025380732,0.00042019432,0.17307746,0.0017499834,0.00079215807,0.023492865,0.0022228258,0.49040252],"study_design_scores_gemma":[0.00008768668,0.0006492882,0.55522305,0.015466968,0.0006145834,0.0018572985,0.31427592,0.0052963253,0.0044028694,0.028170887,0.07370554,0.00024961622],"about_ca_topic_score_codex":0.0078198835,"about_ca_topic_score_gemma":0.0066520968,"teacher_disagreement_score":0.09469199,"about_ca_system_score_codex":0.007494883,"about_ca_system_score_gemma":0.014041549,"threshold_uncertainty_score":0.5007851},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03928022,0.0044979304,0.009209186,0.8288305,0.002626258,0.000296552,0.00013559534,0.00042839153,0.11469541],"genre_scores_gemma":[0.6307279,0.0048648827,0.035956953,0.11046222,0.0005528259,0.00059083046,0.00023109303,0.00088865135,0.21572456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95394135,0.020372337,0.0016401722,0.0038497194,0.011503359,0.008693142],"domain_scores_gemma":[0.92178303,0.020346163,0.0020806887,0.0056152516,0.02297489,0.027199987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035549123,0.0006660542,0.00088779314,0.0016767987,0.044767626,0.042862102,0.005928787,0.014445489,0.012655211],"category_scores_gemma":[0.053152766,0.0018105496,0.0011809247,0.0027001926,0.035991635,0.013309553,0.031582236,0.015625149,0.0028979613],"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":[0.00022204341,0.00020022967,0.008403778,0.00066182093,0.0000723121,0.0027356136,0.12749113,0.0019911714,0.0011980269,0.30072582,0.44783166,0.1084664],"study_design_scores_gemma":[0.000028077562,0.000057043326,0.0025868432,0.00039634094,0.000019259276,0.00020948546,0.07144813,0.00054079096,0.00076147326,0.015510909,0.90825856,0.00018300612],"about_ca_topic_score_codex":0.6963897,"about_ca_topic_score_gemma":0.84317505,"teacher_disagreement_score":0.6963897,"about_ca_system_score_codex":0.108688965,"about_ca_system_score_gemma":0.27155668,"threshold_uncertainty_score":0.78859735},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06375046,0.22720198,0.20070234,0.21389836,0.0023862482,0.0011667088,0.0005083172,0.0005005656,0.28988498],"genre_scores_gemma":[0.73321867,0.106468804,0.13792133,0.014768368,0.0008200643,0.0013378956,0.00035268068,0.0003075385,0.004804769],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95402735,0.036795292,0.0015470268,0.0017331347,0.0039662733,0.0019308092],"domain_scores_gemma":[0.7541959,0.21387702,0.005707671,0.0081322715,0.014652942,0.0034342017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06498821,0.00081468874,0.0014777037,0.010860264,0.0042450065,0.022003818,0.0031278385,0.0036503319,0.009543638],"category_scores_gemma":[0.11811044,0.00062311476,0.0011893893,0.014129751,0.022546854,0.04080113,0.010844146,0.005259924,0.0008950419],"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":[0.000077614066,0.000091084315,0.0034584354,0.0072357645,0.00008961994,0.00019627846,0.027574584,0.0008323827,0.00030273123,0.62071896,0.007982606,0.33143997],"study_design_scores_gemma":[0.000035018376,0.00012545838,0.0031212284,0.02521388,0.0001769002,0.00018838976,0.064432204,0.0020019715,0.0008281801,0.5895485,0.31426418,0.0000640764],"about_ca_topic_score_codex":0.008546238,"about_ca_topic_score_gemma":0.012495663,"teacher_disagreement_score":0.06498821,"about_ca_system_score_codex":0.010611823,"about_ca_system_score_gemma":0.02694483,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8817055,0.0021695152,0.013040141,0.045297723,0.0000663377,0.0003842022,0.00007963174,0.000056349334,0.057200696],"genre_scores_gemma":[0.99683136,0.00032214643,0.00177202,0.00055391766,0.00001322392,0.00010654857,0.000015103444,0.000007938602,0.00037777753],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.90167356,0.07794315,0.0029768902,0.0021778482,0.008240784,0.006987865],"domain_scores_gemma":[0.6826192,0.2612278,0.014581277,0.007941375,0.021885518,0.011744775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08244675,0.0002591108,0.0006177742,0.0050114254,0.005807629,0.012858959,0.0018075376,0.0017523709,0.0032209512],"category_scores_gemma":[0.17586276,0.00047031936,0.0004536315,0.0035572099,0.016049143,0.011806732,0.010671856,0.0028137339,0.00013150644],"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":[0.00012827307,0.00094899,0.22072513,0.0007362517,0.00006788276,0.0007100408,0.4848116,0.00075195957,0.00053405616,0.079659246,0.0033371395,0.2075894],"study_design_scores_gemma":[0.000042869036,0.0002519761,0.14701208,0.0022543997,0.00004134554,0.00045491394,0.72319686,0.0034542396,0.0010892684,0.084999904,0.037050147,0.00015188554],"about_ca_topic_score_codex":0.03567411,"about_ca_topic_score_gemma":0.034812834,"teacher_disagreement_score":0.08244675,"about_ca_system_score_codex":0.015021124,"about_ca_system_score_gemma":0.03197841,"threshold_uncertainty_score":0},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006526985,0.008514686,0.009715403,0.6464462,0.0073571927,0.00008927058,0.00030688726,0.00019016623,0.32085314],"genre_scores_gemma":[0.23352946,0.012957326,0.013105295,0.3162713,0.00209581,0.00028387652,0.00044651615,0.0010447279,0.4202656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883279,0.004982323,0.00025166787,0.0011561794,0.0027729825,0.0025089923],"domain_scores_gemma":[0.99037385,0.003880501,0.0003805954,0.0007155193,0.0031899833,0.0014595146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015699582,0.0010779194,0.00090120675,0.0017819935,0.026065128,0.024928544,0.00340012,0.009084247,0.025909597],"category_scores_gemma":[0.02216519,0.0006888454,0.0010981916,0.0024721362,0.041172415,0.023160035,0.008164507,0.021255849,0.008627538],"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":[0.000018241166,0.000020773065,0.0004756129,0.00011903268,0.000007418005,0.0002830564,0.097098224,0.000161417,0.00035790916,0.7013098,0.17622386,0.0239246],"study_design_scores_gemma":[0.0000023752243,0.000004241376,0.00022144066,0.0002769693,0.0000030324697,0.00011270384,0.08527115,0.000059569942,0.00014484908,0.06906651,0.84481114,0.000026059024],"about_ca_topic_score_codex":0.3342727,"about_ca_topic_score_gemma":0.3954447,"teacher_disagreement_score":0.3342727,"about_ca_system_score_codex":0.032271724,"about_ca_system_score_gemma":0.030433584,"threshold_uncertainty_score":0.664654},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8987003,0.00071764307,0.010554799,0.062514365,0.0014201645,0.0009766342,0.00016746655,0.00012632928,0.024822326],"genre_scores_gemma":[0.9696973,0.0006756545,0.006922972,0.008464115,0.00030966123,0.00073015894,0.00010156021,0.00018748028,0.012911115],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9588882,0.03007218,0.0008589815,0.001570779,0.0037684913,0.004841317],"domain_scores_gemma":[0.9227225,0.04596205,0.0025645236,0.0023517653,0.012923058,0.013476213],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039620884,0.0012551394,0.0010285474,0.0015886198,0.018299794,0.011754838,0.004321632,0.008394639,0.0028397432],"category_scores_gemma":[0.099796444,0.0011629515,0.00084628386,0.0008236015,0.015087784,0.0070476267,0.013859469,0.016628798,0.0005804612],"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":[0.00008087114,0.00050498743,0.0030452013,0.00010399452,0.0000106211055,0.0031189835,0.96287614,0.0003442855,0.0008801348,0.0047806874,0.009930288,0.014323774],"study_design_scores_gemma":[0.000018470377,0.00023705659,0.0008856237,0.00015924685,0.000006036342,0.0009963831,0.9332724,0.00063195836,0.0007226864,0.0018529871,0.061135825,0.00008135985],"about_ca_topic_score_codex":0.014673248,"about_ca_topic_score_gemma":0.033849444,"teacher_disagreement_score":0.9603791,"about_ca_system_score_codex":0.0077572656,"about_ca_system_score_gemma":0.013095696,"threshold_uncertainty_score":0.2095378},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118403025,0.015797198,0.13590592,0.61350024,0.002334021,0.00063634716,0.00046061794,0.00018284595,0.112779796],"genre_scores_gemma":[0.8451725,0.008659849,0.11102644,0.017466674,0.0013340934,0.00092544046,0.00039377456,0.0002211419,0.014800167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.84471774,0.1231408,0.0038669691,0.0038870182,0.02062017,0.0037672978],"domain_scores_gemma":[0.5326445,0.38847512,0.010293319,0.026862841,0.033160422,0.008563727],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20144314,0.0005201411,0.0010175039,0.0031141972,0.0098073995,0.022303596,0.0041696127,0.0057409415,0.0032246339],"category_scores_gemma":[0.31297934,0.0006214331,0.00069697184,0.0037248977,0.024698595,0.02947956,0.017329773,0.0141616175,0.0005492344],"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":[0.0000991452,0.00022311011,0.010796703,0.00070177903,0.000037532966,0.001325524,0.11136183,0.0011604981,0.00045467695,0.6306852,0.044248827,0.19890504],"study_design_scores_gemma":[0.00005105589,0.00016131089,0.0052463133,0.0031261167,0.00002831587,0.0015074264,0.10258782,0.005989801,0.0018718933,0.42997128,0.44925466,0.00020395828],"about_ca_topic_score_codex":0.0073320875,"about_ca_topic_score_gemma":0.020945149,"teacher_disagreement_score":0.79855686,"about_ca_system_score_codex":0.012623997,"about_ca_system_score_gemma":0.023173643,"threshold_uncertainty_score":0.9847628},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015947787,0.008903592,0.29101887,0.083247386,0.003526687,0.0012103186,0.00017083446,0.0005424582,0.595432],"genre_scores_gemma":[0.79027253,0.004106009,0.12953854,0.011246753,0.0016635697,0.001885724,0.000122060446,0.00031609208,0.06084863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90018874,0.078230284,0.0037973323,0.0036218422,0.012133011,0.0020287891],"domain_scores_gemma":[0.9312775,0.048874162,0.0029961525,0.007824522,0.006989941,0.002037715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.075491935,0.0008329457,0.00075314863,0.0029339222,0.006052336,0.017661083,0.0016701977,0.0039083953,0.00543199],"category_scores_gemma":[0.07037806,0.00044332727,0.0006600948,0.0021421798,0.05202971,0.014692751,0.010402191,0.0069323527,0.0010689558],"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":[0.000012049151,0.000017367,0.00012276135,0.00006942284,0.0000028097995,0.00002204906,0.0048769154,0.00019351089,0.00008900409,0.9778276,0.002129348,0.014637117],"study_design_scores_gemma":[0.000020660085,0.00007237106,0.00027154852,0.0005252922,0.000009941028,0.00008892103,0.0036496301,0.0011180699,0.00072624214,0.79881513,0.19466993,0.000032255073],"about_ca_topic_score_codex":0.0022329416,"about_ca_topic_score_gemma":0.0019772744,"teacher_disagreement_score":0.075491935,"about_ca_system_score_codex":0.011840672,"about_ca_system_score_gemma":0.012852787,"threshold_uncertainty_score":0.3992443},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009843133,0.59551454,0.02187073,0.17132375,0.011360875,0.000070963244,0.00016937533,0.00023190725,0.19847345],"genre_scores_gemma":[0.03673641,0.8088446,0.038349926,0.022005703,0.016345132,0.0002748819,0.0002997708,0.00031917862,0.07682427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99160755,0.0038993035,0.00028859059,0.00043065287,0.0033824532,0.00039151823],"domain_scores_gemma":[0.96509373,0.027637754,0.0006635642,0.0011525037,0.0042258347,0.0012266033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03232209,0.0018351263,0.0024161485,0.006061784,0.0018986667,0.019966537,0.0033684499,0.0045396793,0.01299083],"category_scores_gemma":[0.024211997,0.00063331856,0.0009041822,0.0108165415,0.013767153,0.023277458,0.0056689405,0.008633397,0.003885368],"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":[0.000022051021,0.0000774002,0.0002520844,0.0013172968,0.000026761345,0.00004681848,0.0005997357,0.000719421,0.00022639325,0.67244035,0.10561095,0.21866067],"study_design_scores_gemma":[0.000009228663,0.000033651133,0.0003008024,0.0023720432,0.000020375068,0.00009297581,0.0011644504,0.00063618744,0.00021621255,0.6801615,0.31496117,0.000031337273],"about_ca_topic_score_codex":0.0039355024,"about_ca_topic_score_gemma":0.006280128,"teacher_disagreement_score":0.9676779,"about_ca_system_score_codex":0.0068220454,"about_ca_system_score_gemma":0.011820531,"threshold_uncertainty_score":0.1709376},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99791914,0.00018195107,0.00010520783,0.00039535458,0.0000029744829,0.000060803675,0.00004475897,0.0000017895206,0.0012879666],"genre_scores_gemma":[0.9995939,0.00012500261,0.000092596776,0.000033364893,0.0000013152963,0.000032981276,0.000025955776,8.1667673e-7,0.0000939757],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9961273,0.0019230531,0.00027688174,0.00019390203,0.00043612192,0.0010427358],"domain_scores_gemma":[0.9896287,0.0037072867,0.0031471855,0.0002575925,0.0014198511,0.0018394577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006575385,0.00035142154,0.00027081565,0.002666706,0.003167177,0.0022801494,0.00086909987,0.00067833526,0.002043177],"category_scores_gemma":[0.014309053,0.00061651395,0.0002957924,0.0017423658,0.002157339,0.003307112,0.0056552384,0.0005995584,0.00015852961],"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":[0.00010170108,0.0001332617,0.81729805,0.00030069877,0.000050284598,0.0007545525,0.15741064,0.00025878902,0.0007324279,0.0014550186,0.0005771531,0.020927455],"study_design_scores_gemma":[0.000009239223,0.00016732138,0.64736056,0.00037668538,0.000021226848,0.0002499614,0.3479222,0.00040105177,0.00020167304,0.00038810502,0.0028798396,0.00002217404],"about_ca_topic_score_codex":0.013218704,"about_ca_topic_score_gemma":0.017718714,"teacher_disagreement_score":0.013218704,"about_ca_system_score_codex":0.0031922404,"about_ca_system_score_gemma":0.0040878057,"threshold_uncertainty_score":0.034774423},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004324343,0.000013971663,0.000039350805,0.000039970113,0.0000080577265,0.00006470241,0.9991277,0.000025916937,0.000637092],"genre_scores_gemma":[0.0012243524,0.0000781123,0.0008278578,0.00020299702,0.000021083251,0.0023340804,0.9920128,0.00010344153,0.0031953724],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962888,0.0007145019,0.001049758,0.0007374681,0.0007083529,0.00050113286],"domain_scores_gemma":[0.9627837,0.021692473,0.0035950525,0.0030481734,0.007943571,0.0009371702],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043647853,0.0014526568,0.0014776284,0.006007712,0.0012153445,0.003408066,0.0027756116,0.0020572855,0.64214075],"category_scores_gemma":[0.047290538,0.00083638873,0.0019186639,0.009204841,0.0004480503,0.0022634002,0.0021174932,0.0021573296,0.13068779],"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":[0.00010117056,0.000036263362,0.0013343935,0.003452936,0.000039561233,0.000018073146,0.000043555967,0.00020664753,0.000021521893,0.00080854713,0.990864,0.0030732013],"study_design_scores_gemma":[0.001985724,0.00007936709,0.0148551,0.0066332608,0.00016595247,0.00010738173,0.00043136353,0.00038503297,0.00018890653,0.003503327,0.97159934,0.00006530658],"about_ca_topic_score_codex":0.02749211,"about_ca_topic_score_gemma":0.044591825,"teacher_disagreement_score":0.64214075,"about_ca_system_score_codex":0.003131144,"about_ca_system_score_gemma":0.0068372274,"threshold_uncertainty_score":0.51044273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074258096,0.000010027405,0.000052936724,0.000034110784,0.0000063911175,0.000035610366,0.9993426,0.000037615806,0.00040646023],"genre_scores_gemma":[0.0011436628,0.00003557724,0.0007603293,0.00011420362,0.000010806947,0.0010918129,0.9951315,0.000075476855,0.0016366919],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976497,0.0005235826,0.0005196111,0.000563248,0.00044868398,0.0002950899],"domain_scores_gemma":[0.9744596,0.016070228,0.0019020736,0.0023671743,0.0045604794,0.0006404486],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004110175,0.0014669787,0.0015440285,0.0038200608,0.0011065477,0.0027208028,0.002919201,0.0023385077,0.51307565],"category_scores_gemma":[0.033331808,0.00089036627,0.0014719996,0.0065942775,0.0004558075,0.0020909947,0.0017985471,0.0021178871,0.10689282],"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":[0.000095745105,0.000053315234,0.0015959033,0.0015279595,0.000033261807,0.00001534539,0.00003847906,0.00022106581,0.000022997305,0.0006698964,0.9935487,0.0021774739],"study_design_scores_gemma":[0.002887029,0.000078208795,0.015259448,0.0027898324,0.00016542299,0.000094992974,0.0004869179,0.00087269774,0.00032394857,0.00651553,0.97044283,0.00008315769],"about_ca_topic_score_codex":0.023044901,"about_ca_topic_score_gemma":0.046700932,"teacher_disagreement_score":0.51307565,"about_ca_system_score_codex":0.0027292673,"about_ca_system_score_gemma":0.004697853,"threshold_uncertainty_score":0.6945385},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072515914,0.0026538111,0.025606947,0.010010489,0.00017926384,0.0013295979,0.92655617,0.0011901658,0.025222056],"genre_scores_gemma":[0.07667362,0.004159302,0.14679408,0.0013541197,0.00006831941,0.011610889,0.7564868,0.0005070238,0.0023458924],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9745453,0.017102104,0.003514142,0.0015659513,0.0028353403,0.0004370827],"domain_scores_gemma":[0.84918886,0.12194594,0.005733227,0.012415431,0.009806903,0.00090960483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034391087,0.00077763054,0.00094058755,0.008284888,0.0009536712,0.0049561486,0.0026565038,0.0014926846,0.021526555],"category_scores_gemma":[0.17131104,0.00046285545,0.0013685941,0.017902935,0.0012574747,0.0034106113,0.0034453673,0.0021191884,0.0058448464],"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":[0.00040792068,0.00022037803,0.027527519,0.02456284,0.00067027373,0.00012620052,0.0027084958,0.013966274,0.00017877639,0.14173774,0.62012166,0.16777189],"study_design_scores_gemma":[0.00054584484,0.00007429867,0.018673303,0.017610148,0.00027184896,0.00009491641,0.0027652022,0.010955038,0.000454477,0.09167714,0.85675466,0.00012323378],"about_ca_topic_score_codex":0.030864203,"about_ca_topic_score_gemma":0.04184005,"teacher_disagreement_score":0.034391087,"about_ca_system_score_codex":0.00875208,"about_ca_system_score_gemma":0.009259317,"threshold_uncertainty_score":0.18187964},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000103857834,0.000014656886,0.00008426319,0.00006093463,0.0000070142255,0.00005387092,0.99930286,0.000038904036,0.00033375242],"genre_scores_gemma":[0.0025190173,0.00005694421,0.001763475,0.00018140358,0.000019370375,0.0025048691,0.99074566,0.00010243538,0.0021068796],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693394,0.00093481265,0.00073742855,0.0006538338,0.00047669397,0.00026326696],"domain_scores_gemma":[0.9504666,0.03650285,0.0033914156,0.0034696346,0.005388835,0.0007806045],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0063174623,0.0012181156,0.0014471222,0.0035544476,0.0011097863,0.0028753334,0.0030066648,0.0026077055,0.45023006],"category_scores_gemma":[0.06619775,0.0008516321,0.0018506963,0.005758464,0.0005565616,0.0024135376,0.0023213695,0.002290623,0.07987839],"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":[0.00029068295,0.00009894981,0.003947539,0.0045744,0.00009360948,0.000025032296,0.00011797505,0.0004733746,0.000037137364,0.0013765768,0.98477525,0.0041895155],"study_design_scores_gemma":[0.005530576,0.00018435303,0.028116893,0.005272101,0.00042471598,0.000114204624,0.0006385371,0.0015132967,0.00036358697,0.009898374,0.9478197,0.00012372417],"about_ca_topic_score_codex":0.020550212,"about_ca_topic_score_gemma":0.046731036,"teacher_disagreement_score":0.45023006,"about_ca_system_score_codex":0.0025129977,"about_ca_system_score_gemma":0.0044049406,"threshold_uncertainty_score":0.7841801},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004331857,0.0000070589285,0.000048316975,0.000030032465,0.000005746848,0.000029541627,0.99934345,0.000040005743,0.00045245892],"genre_scores_gemma":[0.00082615565,0.000029606432,0.00071697944,0.000085625594,0.0000094668185,0.0009486625,0.9956578,0.00009639326,0.0016291902],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971192,0.00070775236,0.0005875346,0.000617881,0.00057183113,0.00039581396],"domain_scores_gemma":[0.96850085,0.019209417,0.0020978993,0.003484364,0.005874946,0.0008325705],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0045370986,0.0015876234,0.0015665642,0.0049184435,0.0013082032,0.003015494,0.0029845708,0.0024387643,0.5627724],"category_scores_gemma":[0.036835242,0.0010317861,0.0016512359,0.008700635,0.0005012842,0.0025662747,0.0022963514,0.0020801518,0.13848367],"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":[0.00006834897,0.000034724755,0.0011180846,0.0013470851,0.000025203646,0.000010842446,0.000044050026,0.00016036961,0.000019154313,0.0007280423,0.9946331,0.0018109318],"study_design_scores_gemma":[0.0016075496,0.00005562188,0.012507096,0.0023506626,0.00011700208,0.00005336976,0.0004995866,0.0004933825,0.00021493723,0.0048843017,0.9771502,0.000066146036],"about_ca_topic_score_codex":0.027297126,"about_ca_topic_score_gemma":0.0540153,"teacher_disagreement_score":0.5627724,"about_ca_system_score_codex":0.0026039195,"about_ca_system_score_gemma":0.0047847833,"threshold_uncertainty_score":0.6236521},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006779853,0.000009897726,0.000113681264,0.000066991845,0.0000078067005,0.000056947436,0.9991844,0.000056838977,0.00043558519],"genre_scores_gemma":[0.0023254515,0.000049215512,0.00277152,0.00020490725,0.000021201347,0.0028741313,0.98906845,0.00020603319,0.0024790775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665314,0.0011269291,0.0007063228,0.00071318075,0.00051328575,0.00028719445],"domain_scores_gemma":[0.9277175,0.056546994,0.0035521772,0.0051620672,0.0060662366,0.00095498393],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007927258,0.0012909152,0.0013990733,0.003764709,0.0013079097,0.0032481935,0.0032762012,0.0027701897,0.5899782],"category_scores_gemma":[0.07660716,0.0010644986,0.0018223928,0.006334427,0.0006738722,0.0026865376,0.0025335117,0.002448152,0.105758645],"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":[0.00020752763,0.00007129852,0.0020730104,0.0033870349,0.00006491816,0.000020405772,0.00011246694,0.0005421897,0.000031128562,0.0017669268,0.9881494,0.0035737203],"study_design_scores_gemma":[0.0048557646,0.00013808566,0.015419076,0.004144777,0.00029758766,0.00009211831,0.00053268607,0.0015519015,0.0003249592,0.013115266,0.9594077,0.00012008226],"about_ca_topic_score_codex":0.018829376,"about_ca_topic_score_gemma":0.04262976,"teacher_disagreement_score":0.5899782,"about_ca_system_score_codex":0.0028147988,"about_ca_system_score_gemma":0.004972908,"threshold_uncertainty_score":0.58484626},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018212253,0.0006579537,0.002570849,0.0016069016,0.000042612548,0.000204456,0.9652203,0.00033677474,0.01114795],"genre_scores_gemma":[0.08949977,0.0004493306,0.009353573,0.00031082073,0.000028391962,0.0012824095,0.89668304,0.0001612117,0.0022314573],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9842143,0.009716638,0.0017815945,0.0014490698,0.00225701,0.0005814103],"domain_scores_gemma":[0.9089307,0.060125776,0.0091497945,0.009713384,0.011287275,0.0007931467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016391674,0.0005358334,0.00064993976,0.0047194352,0.0007918925,0.0035119255,0.0018155264,0.0009911612,0.013674587],"category_scores_gemma":[0.088472195,0.00039177295,0.00071937975,0.012192743,0.000825427,0.0017088881,0.0018004314,0.0015462516,0.0040270695],"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":[0.0005793548,0.00026070978,0.117665134,0.004652282,0.0005040119,0.00006900254,0.0008936262,0.014962194,0.00024964465,0.03610475,0.78471684,0.039342396],"study_design_scores_gemma":[0.0007530419,0.000089061454,0.18314995,0.0024242324,0.00029322293,0.00010362313,0.00192662,0.015798999,0.0013972276,0.020799547,0.77312744,0.0001371501],"about_ca_topic_score_codex":0.053602144,"about_ca_topic_score_gemma":0.073463716,"teacher_disagreement_score":0.053602144,"about_ca_system_score_codex":0.005800986,"about_ca_system_score_gemma":0.0042771543,"threshold_uncertainty_score":0.10658032},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99674404,0.00012240426,0.0007547803,0.0001506174,0.000014177797,0.000025755216,0.000021394018,0.000007811532,0.0021591312],"genre_scores_gemma":[0.9994423,0.000054339343,0.00023501892,0.00003118545,0.000006555679,0.000015494128,0.000022946013,0.0000032237901,0.0001889803],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99260956,0.0044518407,0.00060843327,0.00054923294,0.0013587128,0.000422101],"domain_scores_gemma":[0.9351737,0.039877657,0.011476982,0.0030055156,0.008115102,0.0023510684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010116807,0.0002988666,0.00024369641,0.00071309746,0.0005484708,0.0014420555,0.00038471582,0.0005762307,0.0015743865],"category_scores_gemma":[0.049742963,0.0003609214,0.00059840066,0.00032414866,0.0013234679,0.0009219825,0.0011327616,0.00093637477,0.00021977392],"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":[0.000559499,0.00030173123,0.9327289,0.00022277035,0.00019007061,0.00020711753,0.03929392,0.00018810344,0.0049405145,0.00022579238,0.00028822877,0.020853408],"study_design_scores_gemma":[0.000032026626,0.0004617637,0.9618666,0.00013219447,0.000111318484,0.00010859574,0.03362738,0.0007999555,0.0014660978,0.0001802119,0.001165783,0.000048123486],"about_ca_topic_score_codex":0.005669408,"about_ca_topic_score_gemma":0.0061348584,"teacher_disagreement_score":0.9898832,"about_ca_system_score_codex":0.0008650351,"about_ca_system_score_gemma":0.000618246,"threshold_uncertainty_score":0.053503394},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002226403,0.0021718128,0.000063454325,0.035809755,0.96084595,0.000027420896,0.00006511714,0.000041460782,0.0009527739],"genre_scores_gemma":[0.0005688005,0.0027940888,0.00013747945,0.045258775,0.94130385,0.000066021574,0.00006947559,0.000046616933,0.009754975],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98602295,0.002489098,0.0016646651,0.0014630769,0.0076437825,0.00071640953],"domain_scores_gemma":[0.95587367,0.017919116,0.0026137114,0.0012737057,0.01811838,0.004201384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01456821,0.004072479,0.004940174,0.0058394014,0.005966474,0.011456024,0.0055020815,0.02064543,0.017308464],"category_scores_gemma":[0.080263175,0.0015163803,0.0038770316,0.0028480564,0.0046234224,0.0058707655,0.0019316438,0.023720391,0.012430626],"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":[0.000019725758,0.00000657471,0.000014182777,0.00011858695,0.000012514442,0.000045133766,0.000008381696,0.000018970582,0.000015405201,0.00018404964,0.9980798,0.0014768664],"study_design_scores_gemma":[0.00015220766,0.000035499354,0.00037458172,0.0013239535,0.00009603848,0.00020608077,0.00005452609,0.00024387149,0.00010542031,0.0017181204,0.9956583,0.00003145782],"about_ca_topic_score_codex":0.005366064,"about_ca_topic_score_gemma":0.013984264,"teacher_disagreement_score":0.02064543,"about_ca_system_score_codex":0.008355937,"about_ca_system_score_gemma":0.010451801,"threshold_uncertainty_score":0.077044964},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60349256,0.00047853822,0.3413288,0.0027629451,0.0008244064,0.013432458,0.0018429315,0.00035454828,0.035482846],"genre_scores_gemma":[0.8459474,0.0001775841,0.12593785,0.0016557119,0.00014897498,0.024316879,0.0006544319,0.00008384,0.0010774517],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.61753666,0.35020915,0.009203374,0.0076158633,0.013609996,0.0018249638],"domain_scores_gemma":[0.18338335,0.7214379,0.03696496,0.044456072,0.012480272,0.0012775759],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2191087,0.0014725323,0.0012271134,0.0016559062,0.0019200908,0.0032745912,0.0020937866,0.0033266908,0.005308697],"category_scores_gemma":[0.51598555,0.000727609,0.0015012996,0.0025724384,0.0074248086,0.004963601,0.0033657728,0.003670177,0.0008911675],"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":[0.020173129,0.026276903,0.28658664,0.0057786726,0.0038869889,0.0005262237,0.050179802,0.020625805,0.01708411,0.27607962,0.012947657,0.27985448],"study_design_scores_gemma":[0.011199588,0.05688389,0.27152288,0.0029477777,0.002385243,0.0008310617,0.016190382,0.14954269,0.05571357,0.36425948,0.067261375,0.0012620805],"about_ca_topic_score_codex":0.0010464974,"about_ca_topic_score_gemma":0.0006246072,"teacher_disagreement_score":0.2191087,"about_ca_system_score_codex":0.0020515928,"about_ca_system_score_gemma":0.0023345216,"threshold_uncertainty_score":0.962978},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005712468,0.058722317,0.05711455,0.8455789,0.006721435,0.0006379249,0.00022432813,0.00047792675,0.024810186],"genre_scores_gemma":[0.2950303,0.07373287,0.27540433,0.32794178,0.015426524,0.0036456478,0.0010528654,0.0012756492,0.006490111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6787086,0.24518788,0.017259967,0.01568443,0.028220877,0.014938249],"domain_scores_gemma":[0.41432872,0.399054,0.01883705,0.056894384,0.053926453,0.056959428],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36078018,0.003063829,0.0063450034,0.016526503,0.017393569,0.06271239,0.008635834,0.027971378,0.015589493],"category_scores_gemma":[0.32751444,0.004332014,0.005358478,0.008090852,0.049494125,0.11529525,0.10596798,0.048789576,0.0058304397],"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":[0.0003418262,0.00054500345,0.008387991,0.009799339,0.0019193153,0.0013898107,0.044547535,0.0027168477,0.0010771035,0.41018057,0.11189755,0.4071971],"study_design_scores_gemma":[0.0002889741,0.0003481208,0.0019967756,0.020006489,0.00030289224,0.00036953264,0.017142046,0.0006422032,0.00035071935,0.61830723,0.34003145,0.00021358191],"about_ca_topic_score_codex":0.004215582,"about_ca_topic_score_gemma":0.0063569318,"teacher_disagreement_score":0.6392198,"about_ca_system_score_codex":0.013539496,"about_ca_system_score_gemma":0.107693925,"threshold_uncertainty_score":0.78827184},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041361684,0.05984837,0.050521918,0.8594462,0.0073062354,0.0006192708,0.0001820289,0.00040503926,0.017534815],"genre_scores_gemma":[0.2395097,0.077408046,0.2644761,0.3887738,0.019865816,0.0033415232,0.0008263372,0.0012393828,0.004559305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.58345336,0.32553396,0.02294112,0.017114606,0.034456063,0.016500982],"domain_scores_gemma":[0.3060974,0.5065317,0.019968651,0.06296333,0.05172853,0.052710343],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42982268,0.003164389,0.0071808477,0.018828597,0.017751642,0.07219236,0.01076438,0.032848164,0.015915098],"category_scores_gemma":[0.4043805,0.0047654808,0.005093655,0.009492709,0.06057542,0.1267324,0.118989,0.056472294,0.005524686],"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":[0.0003742327,0.0005323606,0.006770749,0.012084673,0.0021017212,0.0015742328,0.04449157,0.0027332453,0.0009405353,0.43726632,0.118531205,0.37259918],"study_design_scores_gemma":[0.0002633581,0.00034162603,0.0015351541,0.02535328,0.0002537269,0.00038067545,0.015722157,0.00065463927,0.00033630236,0.640746,0.31418502,0.00022801409],"about_ca_topic_score_codex":0.0037099924,"about_ca_topic_score_gemma":0.006472118,"teacher_disagreement_score":0.5701773,"about_ca_system_score_codex":0.015497981,"about_ca_system_score_gemma":0.12198543,"threshold_uncertainty_score":0.7031301},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024133692,0.0010972065,0.9401474,0.002500172,0.00031638582,0.00096398994,0.0005813978,0.0010036048,0.029256146],"genre_scores_gemma":[0.28408286,0.00045399825,0.70895416,0.00026703326,0.00009031292,0.0014293068,0.00081934285,0.00015330855,0.0037495585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9823982,0.012721107,0.0007418065,0.0012439364,0.002447685,0.00044722983],"domain_scores_gemma":[0.9503656,0.039292015,0.0011045358,0.00472255,0.0033831478,0.0011322101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0167777,0.0008080802,0.0012854432,0.008545806,0.0030803385,0.0058655078,0.002560184,0.0017307568,0.020071844],"category_scores_gemma":[0.06385309,0.0005123475,0.0016904386,0.007469041,0.003850927,0.00816854,0.008415027,0.0023674672,0.0023816207],"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":[0.00027936016,0.0004066974,0.0040381094,0.00086066226,0.00009973622,0.00014721164,0.0088262055,0.009684922,0.0007332208,0.41626668,0.0070565525,0.55160064],"study_design_scores_gemma":[0.000080609134,0.0001588947,0.0016904715,0.00046518657,0.000042823845,0.00016618009,0.00802624,0.04865351,0.0009923251,0.9065931,0.033082325,0.00004832152],"about_ca_topic_score_codex":0.0030448646,"about_ca_topic_score_gemma":0.0020083254,"teacher_disagreement_score":0.020071844,"about_ca_system_score_codex":0.0025634554,"about_ca_system_score_gemma":0.0060620653,"threshold_uncertainty_score":0.08872998},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016105721,0.97955245,0.0053789928,0.0063310214,0.0008024996,0.0017282632,0.00034939207,0.0000317143,0.004215138],"genre_scores_gemma":[0.021450663,0.96046364,0.011413218,0.0018751256,0.00031695128,0.0037070117,0.00034310666,0.000022656423,0.00040759423],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9306369,0.03295708,0.01824229,0.0033185184,0.013459799,0.0013855058],"domain_scores_gemma":[0.7168051,0.2308745,0.020809934,0.004476709,0.025818542,0.0012152104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09286154,0.0021570125,0.005598464,0.057996385,0.0039630495,0.014589562,0.004442443,0.005729877,0.0047840294],"category_scores_gemma":[0.2402804,0.0022200623,0.0070034675,0.045374107,0.006387319,0.015620185,0.00746148,0.0048436346,0.00092827564],"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":[0.000105505846,0.000083157465,0.0025654638,0.6229051,0.002073978,0.00044921544,0.011162603,0.00083927205,0.00031133145,0.03262954,0.011876382,0.3149984],"study_design_scores_gemma":[0.000021097727,0.00003247539,0.0009380117,0.945789,0.0021297904,0.0001893842,0.0041740765,0.00025828887,0.00013470306,0.0067401784,0.03955594,0.000037061716],"about_ca_topic_score_codex":0.013213866,"about_ca_topic_score_gemma":0.018736525,"teacher_disagreement_score":0.09286154,"about_ca_system_score_codex":0.017239142,"about_ca_system_score_gemma":0.066293865,"threshold_uncertainty_score":0.49110466},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019347718,0.043097943,0.26030576,0.6409566,0.008474006,0.00053552,0.00020744225,0.0002518912,0.026823131],"genre_scores_gemma":[0.63358796,0.019270636,0.24417673,0.089883305,0.008384794,0.0024033415,0.00011550344,0.00059602887,0.001581768],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.31307855,0.5985463,0.020804575,0.012575985,0.052646007,0.0023485613],"domain_scores_gemma":[0.045321174,0.9162769,0.009886044,0.013444039,0.013704271,0.0013674948],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59324545,0.0014097053,0.0036776473,0.008118812,0.0068421704,0.018612528,0.0058462736,0.013466724,0.003556174],"category_scores_gemma":[0.85956514,0.0017717623,0.0018099757,0.0128012225,0.09550881,0.036448885,0.010459444,0.030643549,0.00089525094],"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":[0.0002924578,0.00013040406,0.0062526623,0.0027785515,0.00034504262,0.00043720525,0.016666306,0.001400737,0.0004907675,0.8187186,0.028995436,0.123491794],"study_design_scores_gemma":[0.00007818198,0.00028118026,0.003213747,0.0037431344,0.0000945984,0.00035524895,0.0054801907,0.003760857,0.0005839257,0.9449743,0.03729019,0.0001444127],"about_ca_topic_score_codex":0.0034044515,"about_ca_topic_score_gemma":0.002173368,"teacher_disagreement_score":0.40675455,"about_ca_system_score_codex":0.009213584,"about_ca_system_score_gemma":0.020160228,"threshold_uncertainty_score":0.50160086},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006204403,0.018572418,0.007850468,0.9224487,0.038810313,0.000063692816,0.00015606728,0.00012910675,0.011348865],"genre_scores_gemma":[0.085298434,0.088239536,0.06568425,0.58763134,0.11134194,0.0007973304,0.00094311876,0.00047606142,0.059587944],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98730683,0.0064778584,0.0008415846,0.0016818028,0.002558873,0.0011331424],"domain_scores_gemma":[0.914128,0.04489955,0.0021060058,0.0037052324,0.029801255,0.005359938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025736397,0.0009618904,0.0011087275,0.0021676929,0.0040164134,0.010909965,0.0029146327,0.008466253,0.022639332],"category_scores_gemma":[0.07034361,0.00035982975,0.0012914846,0.0022153207,0.0068864184,0.013252246,0.0060981777,0.015758567,0.005911492],"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":[0.000084503,0.000051295126,0.0004946905,0.0007564777,0.00002036907,0.00018856922,0.0015288847,0.000642277,0.00016580077,0.2338003,0.7089694,0.05329748],"study_design_scores_gemma":[0.000031639524,0.00003638715,0.0004722562,0.0022722157,0.000016587404,0.00012312293,0.0045555136,0.0006965324,0.00020010072,0.2726234,0.71891946,0.000052874773],"about_ca_topic_score_codex":0.0055979993,"about_ca_topic_score_gemma":0.0076663275,"teacher_disagreement_score":0.9938481,"about_ca_system_score_codex":0.0061518867,"about_ca_system_score_gemma":0.014579263,"threshold_uncertainty_score":0.1361087},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004224902,0.09376705,0.1997741,0.43513358,0.007005127,0.0006272723,0.0002712058,0.0005097597,0.25868705],"genre_scores_gemma":[0.53504556,0.14984511,0.2168636,0.053496923,0.012169232,0.0032394852,0.00041091882,0.0007024028,0.028226865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8252289,0.12934607,0.0066937055,0.008517646,0.02689114,0.0033224558],"domain_scores_gemma":[0.65843385,0.27340668,0.00971584,0.025679559,0.026813237,0.005950893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12929353,0.0012413391,0.0020171576,0.008898812,0.006406261,0.022535581,0.0041674986,0.007301299,0.008567111],"category_scores_gemma":[0.23011988,0.0009262312,0.0012010393,0.006901446,0.062005762,0.017126124,0.012621686,0.013347994,0.0022218833],"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":[0.00001708497,0.00005105643,0.0010151058,0.001084739,0.00004411164,0.00005548882,0.002214625,0.002172962,0.00006229109,0.8393046,0.034055967,0.119921915],"study_design_scores_gemma":[0.000020823,0.000027662656,0.00051867554,0.0029785954,0.000016451044,0.00007085233,0.0019348424,0.0015079025,0.00022886095,0.8366691,0.15598121,0.00004514377],"about_ca_topic_score_codex":0.013394916,"about_ca_topic_score_gemma":0.009266643,"teacher_disagreement_score":0.12929353,"about_ca_system_score_codex":0.01922513,"about_ca_system_score_gemma":0.04646703,"threshold_uncertainty_score":0.6837777},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000117729855,0.0012976934,0.00027106417,0.27884552,0.7151528,0.000034912373,0.00016591839,0.00018330112,0.0039309715],"genre_scores_gemma":[0.0027442607,0.0022972352,0.0014049334,0.5225047,0.42751756,0.00014260804,0.00015263582,0.00022324495,0.043012783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98421025,0.0015883875,0.0018555686,0.0028716857,0.008078022,0.0013962236],"domain_scores_gemma":[0.93159527,0.015008644,0.0037959921,0.003607217,0.03964638,0.0063466257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013787447,0.0017643084,0.0020207681,0.0021483523,0.0041083978,0.009009464,0.0052717235,0.020522304,0.031075437],"category_scores_gemma":[0.1135676,0.0009338653,0.0032997192,0.00167464,0.0031355554,0.0055564684,0.003326765,0.024090575,0.030889269],"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":[0.00001582202,0.0000069029325,0.000045003504,0.000051301296,0.0000050773224,0.000089622125,0.000027517382,0.000019469026,0.000041269857,0.00049185223,0.99643564,0.0027705317],"study_design_scores_gemma":[0.000017452254,0.000014854993,0.00020683413,0.00018051494,0.000009421172,0.00018103386,0.00008806687,0.00006478415,0.00019083713,0.0009021307,0.99812084,0.000023218432],"about_ca_topic_score_codex":0.0027335433,"about_ca_topic_score_gemma":0.005247001,"teacher_disagreement_score":0.031075437,"about_ca_system_score_codex":0.0040393015,"about_ca_system_score_gemma":0.008104122,"threshold_uncertainty_score":0.10395771},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010619472,0.0048067532,0.28435305,0.008524331,0.0012299233,0.0016200569,0.008817581,0.017910698,0.6716756],"genre_scores_gemma":[0.013867763,0.0066902693,0.32555428,0.002241479,0.00063363614,0.0022237736,0.0103132175,0.0027205518,0.63575506],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968725,0.0010399342,0.00023003547,0.00012950174,0.0015766915,0.00015132564],"domain_scores_gemma":[0.98616564,0.007659531,0.0006223732,0.0010014093,0.0039501563,0.00060093804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067825657,0.0009214735,0.0005929603,0.0042975796,0.0011322907,0.0044900533,0.0022676296,0.0011476771,0.23169059],"category_scores_gemma":[0.0151877785,0.0010710321,0.0005669049,0.0032474834,0.0006947629,0.0024962435,0.0018006123,0.002035368,0.08839078],"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":[0.000047334852,0.00010371996,0.00023918864,0.0003670678,0.000005943542,0.000050358,0.00010815729,0.0023067198,0.00027655542,0.041029632,0.57384646,0.38161886],"study_design_scores_gemma":[0.000032411095,0.000044234726,0.00031239333,0.00032613327,0.00000712018,0.000095736636,0.00009827043,0.0018143477,0.0006490313,0.02481182,0.9717884,0.000020036472],"about_ca_topic_score_codex":0.0055482117,"about_ca_topic_score_gemma":0.016123844,"teacher_disagreement_score":0.23169059,"about_ca_system_score_codex":0.0025379513,"about_ca_system_score_gemma":0.011552568,"threshold_uncertainty_score":0.77508223},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13899313,0.0033238402,0.40880397,0.023539906,0.0006173172,0.00096663414,0.00017178798,0.00071608374,0.4228674],"genre_scores_gemma":[0.7838224,0.0016502672,0.123799995,0.00097292906,0.00012393457,0.00070667494,0.00012534286,0.00028906093,0.088509485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.984133,0.009781389,0.0004981878,0.0014681763,0.0032851591,0.0008341612],"domain_scores_gemma":[0.9857567,0.0064584203,0.0010670656,0.0019921728,0.0028651238,0.0018604757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016934978,0.0007673549,0.0005496956,0.0028686067,0.006168799,0.014317186,0.0015332972,0.0023447415,0.012405737],"category_scores_gemma":[0.01413276,0.00049817417,0.00062761863,0.002800084,0.01683979,0.012047704,0.010921863,0.0043131355,0.0024377157],"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":[0.000079034166,0.00015891211,0.00677276,0.00037032802,0.00002357917,0.0003899417,0.123414256,0.0016087912,0.0037205038,0.7298378,0.0034528985,0.13017116],"study_design_scores_gemma":[0.000039031765,0.00032979055,0.012943773,0.0012295287,0.00004820005,0.00060637895,0.09974537,0.0038280971,0.00593839,0.29602507,0.57915306,0.00011335101],"about_ca_topic_score_codex":0.010031351,"about_ca_topic_score_gemma":0.011044256,"teacher_disagreement_score":0.016934978,"about_ca_system_score_codex":0.0075696427,"about_ca_system_score_gemma":0.022183381,"threshold_uncertainty_score":0.08956176},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05524878,0.016236378,0.12955584,0.0666798,0.0012729521,0.00034486377,0.00023427633,0.0003110235,0.7301161],"genre_scores_gemma":[0.9604806,0.0047490676,0.021892166,0.0012649025,0.00082478265,0.00023111214,0.00006248582,0.000044914705,0.010449966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97877365,0.015727075,0.00053653057,0.00096654374,0.0033049756,0.000691268],"domain_scores_gemma":[0.9379193,0.04507675,0.0018609867,0.009468949,0.0043632267,0.0013107926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025697472,0.0007048052,0.00069226685,0.0036325888,0.0014864787,0.011551358,0.0013261839,0.0022371823,0.010125345],"category_scores_gemma":[0.036806393,0.00031571218,0.00069057994,0.0018945715,0.0163439,0.009913337,0.005174619,0.0020742686,0.0011798993],"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":[0.000041802254,0.000047296024,0.0004585756,0.00017367299,0.000033567918,0.000082989536,0.00059536344,0.0012821687,0.00029166497,0.9663843,0.0013608037,0.02924777],"study_design_scores_gemma":[0.000024240726,0.00004346332,0.0003431022,0.00014510588,0.000015989444,0.00009862415,0.0006104844,0.0024709099,0.00054450915,0.9767766,0.01891635,0.000010703942],"about_ca_topic_score_codex":0.0004816075,"about_ca_topic_score_gemma":0.0005217962,"teacher_disagreement_score":0.025697472,"about_ca_system_score_codex":0.003493632,"about_ca_system_score_gemma":0.0055462783,"threshold_uncertainty_score":0.13590282},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057035456,0.004613541,0.70100254,0.06980851,0.0011053986,0.004583326,0.00016136491,0.00056997966,0.21245179],"genre_scores_gemma":[0.21610558,0.0037725074,0.7512763,0.009890264,0.00063543365,0.009912473,0.00017926733,0.0003131346,0.007915007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5278981,0.39031994,0.020916278,0.014332482,0.0399111,0.006622035],"domain_scores_gemma":[0.6049246,0.28028914,0.014799326,0.03856373,0.050129756,0.011293435],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41498852,0.002400954,0.002624496,0.012149241,0.010574339,0.0302922,0.006481345,0.013280615,0.0040215175],"category_scores_gemma":[0.2267371,0.002181996,0.0038966509,0.0062854984,0.107879944,0.030965671,0.024159761,0.011985297,0.0019516244],"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":[0.000018071223,0.000034500375,0.00039094998,0.000558864,0.000027898039,0.00006807707,0.008972246,0.00070176437,0.0001404063,0.967744,0.0025316917,0.0188116],"study_design_scores_gemma":[0.000058141057,0.0000862276,0.00032661518,0.002619161,0.000032110438,0.0001285127,0.0042787204,0.00086813926,0.0003077566,0.92619514,0.065046355,0.000052990108],"about_ca_topic_score_codex":0.0051623606,"about_ca_topic_score_gemma":0.004785987,"teacher_disagreement_score":0.5850115,"about_ca_system_score_codex":0.022890054,"about_ca_system_score_gemma":0.12128671,"threshold_uncertainty_score":0.7214233},"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":"methods","genre_gemma":"other","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13922794,0.03398185,0.46037006,0.21836638,0.0029867073,0.0019901795,0.00018024383,0.0006198244,0.1422768],"genre_scores_gemma":[0.79022264,0.006158539,0.18288843,0.015164007,0.0006493139,0.0011966174,0.000088606284,0.00031477952,0.0033169608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.3887674,0.47616282,0.03279484,0.021173276,0.07607056,0.0050311564],"domain_scores_gemma":[0.28214166,0.5327685,0.057244334,0.07764496,0.044734158,0.0054664193],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3187442,0.0015192102,0.00256973,0.017858546,0.021440478,0.03733111,0.004362496,0.011536168,0.0025745071],"category_scores_gemma":[0.47297552,0.0022769384,0.0020180792,0.011123765,0.103089854,0.032125708,0.024300754,0.014192279,0.00074889784],"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":[0.00015527503,0.0002165714,0.012415198,0.0028864855,0.00023126551,0.00095998275,0.32040012,0.0010401373,0.0012906195,0.5073551,0.007361307,0.14568788],"study_design_scores_gemma":[0.00005310259,0.00015260627,0.005621794,0.008260314,0.00012577759,0.0013054855,0.07422704,0.003183806,0.0021952922,0.826916,0.07773522,0.00022359329],"about_ca_topic_score_codex":0.0031505313,"about_ca_topic_score_gemma":0.0039453185,"teacher_disagreement_score":0.9884638,"about_ca_system_score_codex":0.020759892,"about_ca_system_score_gemma":0.030426385,"threshold_uncertainty_score":0.8401097},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05504208,0.054187182,0.075628094,0.24453303,0.003920547,0.001424296,0.00012793987,0.0004934919,0.56464344],"genre_scores_gemma":[0.843431,0.011784866,0.050883804,0.019308673,0.00032448184,0.0011096055,0.00006223031,0.00023289825,0.07286244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9783718,0.019348172,0.00030841795,0.000361914,0.0009953371,0.0006143444],"domain_scores_gemma":[0.98891443,0.009527994,0.00016711986,0.0004616292,0.00061651017,0.00031219717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02115943,0.0004626393,0.0004686389,0.0024236112,0.0055702897,0.008613711,0.0012317572,0.0024344665,0.0029301292],"category_scores_gemma":[0.0201511,0.00043213708,0.0005096005,0.002279119,0.0255485,0.0070999702,0.0044483924,0.0039233025,0.00030636718],"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":[0.000043838612,0.0000615278,0.00059345696,0.00030846935,0.000015593661,0.0003100626,0.060935676,0.0007829509,0.00013207183,0.84872425,0.029380884,0.05871114],"study_design_scores_gemma":[0.000076829834,0.00016738201,0.0011960069,0.002192121,0.000040877636,0.00038800194,0.0630786,0.0015715975,0.0009231146,0.37793103,0.5523797,0.000054657245],"about_ca_topic_score_codex":0.0233597,"about_ca_topic_score_gemma":0.039240923,"teacher_disagreement_score":0.0233597,"about_ca_system_score_codex":0.014238018,"about_ca_system_score_gemma":0.01007969,"threshold_uncertainty_score":0.11190307},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019911667,0.0040168785,0.39506623,0.19279455,0.0010786356,0.0007830644,0.00017496121,0.00029589722,0.38587818],"genre_scores_gemma":[0.76630765,0.0028548248,0.20092879,0.01430875,0.0008181718,0.0019908338,0.00015572112,0.00023162362,0.012403609],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8608913,0.10898781,0.003409012,0.009406114,0.01326829,0.004037417],"domain_scores_gemma":[0.8312348,0.107850984,0.009539254,0.027709315,0.014762813,0.008902771],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.18989588,0.0011012801,0.0013468587,0.0062938854,0.01597176,0.02858035,0.005839576,0.008523186,0.0063913995],"category_scores_gemma":[0.122909114,0.0012204319,0.0014968193,0.004639958,0.16557284,0.03358197,0.028081425,0.010813327,0.0016083568],"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":[0.000010665345,0.000022253433,0.00045478946,0.0001360353,0.000020728085,0.00010254137,0.037954275,0.00026331627,0.00013806742,0.94835377,0.0013347426,0.011208923],"study_design_scores_gemma":[0.000015566868,0.000019234034,0.00018865045,0.00029595924,0.000014403497,0.000080497535,0.006364064,0.00037460437,0.00017286363,0.96084565,0.031608537,0.000019981966],"about_ca_topic_score_codex":0.0072269933,"about_ca_topic_score_gemma":0.009497893,"teacher_disagreement_score":0.9840282,"about_ca_system_score_codex":0.01662455,"about_ca_system_score_gemma":0.05235051,"threshold_uncertainty_score":0.9990026},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002140974,0.0000353663,0.0000861563,0.00014334242,0.000023917943,0.00010369081,0.9958164,0.00008381975,0.001566281],"genre_scores_gemma":[0.0051303157,0.00007437708,0.00041978253,0.00019652177,0.00002442062,0.0012738018,0.989829,0.000042259242,0.0030094136],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.996488,0.0008530523,0.00069922203,0.00059735175,0.000915852,0.0004465237],"domain_scores_gemma":[0.9833431,0.005675827,0.00267961,0.0016302641,0.005472528,0.00119855],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048265625,0.0012287075,0.0007320009,0.0044550872,0.00078444235,0.0015661541,0.0017304677,0.0018014018,0.052231736],"category_scores_gemma":[0.024012104,0.00059450377,0.0007512773,0.008719249,0.00032388358,0.0010717742,0.001790945,0.0016480954,0.038883008],"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":[0.00030492648,0.00012315915,0.012949109,0.0008667531,0.000045888108,0.000027318512,0.00012658651,0.00026500507,0.00012557232,0.00047023225,0.97620934,0.00848604],"study_design_scores_gemma":[0.0011436231,0.00018094142,0.19724739,0.00086107064,0.00011686077,0.00011750828,0.00085951627,0.0010295263,0.0007254926,0.0013092798,0.79631513,0.000093646915],"about_ca_topic_score_codex":0.031257678,"about_ca_topic_score_gemma":0.0446563,"teacher_disagreement_score":0.99517345,"about_ca_system_score_codex":0.0020329936,"about_ca_system_score_gemma":0.0030844016,"threshold_uncertainty_score":0.17473257},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025223347,0.005028561,0.011638558,0.11797174,0.0012774004,0.00014123676,0.00008090675,0.00009276695,0.86124647],"genre_scores_gemma":[0.50871134,0.00725298,0.0109713515,0.03017334,0.0026068839,0.0007418436,0.0001500585,0.00038479472,0.43900743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9862012,0.00932283,0.0002868215,0.0010249974,0.0018220926,0.001341898],"domain_scores_gemma":[0.98784196,0.007605402,0.00050810305,0.0012432231,0.0014442292,0.0013570901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010659836,0.0004344207,0.00046626548,0.0021818131,0.015731888,0.021135325,0.0020762337,0.008499766,0.030914614],"category_scores_gemma":[0.019952599,0.00055321114,0.0006444231,0.0023403973,0.044545654,0.01808465,0.01055647,0.009640397,0.005664926],"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":[0.000003862189,0.000011160182,0.000075263335,0.000019191646,9.387867e-7,0.00009057028,0.004764081,0.000041836458,0.000016041797,0.97261566,0.01836425,0.0039972137],"study_design_scores_gemma":[0.000007913466,0.000009406224,0.0002056906,0.00026869113,0.0000028674508,0.00015086515,0.0120962635,0.00018609827,0.000037275848,0.411344,0.5756827,0.000008278566],"about_ca_topic_score_codex":0.01173889,"about_ca_topic_score_gemma":0.01064235,"teacher_disagreement_score":0.030914614,"about_ca_system_score_codex":0.014489573,"about_ca_system_score_gemma":0.01793631,"threshold_uncertainty_score":0.10512972},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30953997,0.0014377072,0.6627698,0.002211763,0.0003609361,0.0021719995,0.0015822337,0.001083187,0.018842526],"genre_scores_gemma":[0.8313416,0.00034221992,0.16352375,0.00020592213,0.00003976707,0.0021627522,0.0014895711,0.0003623856,0.0005320222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9066186,0.068067834,0.0062041534,0.0055323993,0.012452417,0.0011246046],"domain_scores_gemma":[0.5549362,0.38353544,0.011638123,0.016398445,0.03203376,0.0014581253],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1520108,0.0027876997,0.0016965977,0.008506636,0.0019686643,0.0054805484,0.00200701,0.0019192848,0.008392957],"category_scores_gemma":[0.46613872,0.00079735805,0.0049202335,0.010343649,0.00300607,0.0074669523,0.0042162905,0.0038970932,0.00065951684],"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":[0.001170783,0.0010117055,0.26297674,0.0028988253,0.006030909,0.0010035008,0.020301657,0.09720103,0.0028410917,0.19465372,0.015108601,0.39480147],"study_design_scores_gemma":[0.00046996624,0.0020937675,0.06866207,0.002700701,0.0020675005,0.0006503725,0.015779903,0.7413699,0.00443056,0.1473105,0.014080323,0.00038440654],"about_ca_topic_score_codex":0.0035257281,"about_ca_topic_score_gemma":0.004223865,"teacher_disagreement_score":0.8479892,"about_ca_system_score_codex":0.003262237,"about_ca_system_score_gemma":0.006380671,"threshold_uncertainty_score":0.80391955},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14329208,0.00409456,0.0021817014,0.84103227,0.0011000324,0.000054972537,0.00015558398,0.000038461803,0.008050362],"genre_scores_gemma":[0.9171515,0.0047604404,0.009010845,0.06656196,0.0006883708,0.0001187131,0.00009745657,0.000076374046,0.0015343942],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.92793804,0.048812147,0.003974766,0.0025746303,0.012246013,0.004454397],"domain_scores_gemma":[0.78060865,0.117022336,0.024824549,0.009460415,0.03753917,0.030544825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11076454,0.00037141077,0.0010724314,0.002225221,0.010674867,0.011333624,0.0032321343,0.004624173,0.0037080667],"category_scores_gemma":[0.26109424,0.00071376405,0.0010666547,0.0025062382,0.0097226985,0.01268181,0.009911953,0.013877971,0.0005859408],"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":[0.00030167014,0.00072965404,0.3601417,0.0010358683,0.00038488294,0.00075788057,0.12776153,0.00049851584,0.00038843043,0.01828462,0.07921415,0.41050115],"study_design_scores_gemma":[0.00014293008,0.0007117454,0.33897427,0.009476026,0.0005259884,0.0015652428,0.47327206,0.0039203125,0.0010935433,0.09504868,0.07471808,0.00055117515],"about_ca_topic_score_codex":0.16838367,"about_ca_topic_score_gemma":0.318386,"teacher_disagreement_score":0.16838367,"about_ca_system_score_codex":0.01417855,"about_ca_system_score_gemma":0.07461387,"threshold_uncertainty_score":0.58578587},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039647156,0.005636693,0.006507223,0.93379843,0.002766542,0.000026698306,0.00006127831,0.000033549128,0.047204975],"genre_scores_gemma":[0.61133057,0.011261285,0.033825275,0.2937635,0.0057533584,0.00033777542,0.00020404944,0.0005456248,0.04297858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94203585,0.03165659,0.0026560836,0.006283401,0.013320749,0.004047289],"domain_scores_gemma":[0.8536578,0.06638119,0.0071556014,0.007038432,0.033900876,0.031866185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059269965,0.0007988757,0.0022086587,0.0034364413,0.016313693,0.028171629,0.0038071044,0.017116511,0.0137179],"category_scores_gemma":[0.11403728,0.0005806914,0.0007042449,0.002658311,0.056207404,0.03386222,0.009839547,0.02547922,0.0056675565],"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":[0.000053057203,0.00013828391,0.0010459397,0.00018643927,0.00005887433,0.00013381237,0.0043013347,0.00029551674,0.00016326772,0.80730414,0.14126538,0.045053992],"study_design_scores_gemma":[0.000038324266,0.00002211385,0.0003914208,0.0004280452,0.000018447956,0.00008366622,0.009271979,0.00037700325,0.00013086907,0.83735055,0.15182506,0.00006249571],"about_ca_topic_score_codex":0.021889929,"about_ca_topic_score_gemma":0.029360324,"teacher_disagreement_score":0.059269965,"about_ca_system_score_codex":0.014883358,"about_ca_system_score_gemma":0.040866327,"threshold_uncertainty_score":0.31345326},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008669734,0.031388402,0.11695797,0.10154293,0.002587047,0.00048396556,0.00046980576,0.00030824248,0.7375919],"genre_scores_gemma":[0.7464558,0.04426287,0.0954624,0.020640977,0.0027971645,0.0023923146,0.0009784246,0.00037849808,0.086631656],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9837964,0.009572564,0.00065625703,0.0020902688,0.0028709613,0.0010134941],"domain_scores_gemma":[0.9852144,0.009883084,0.00095164,0.0019253213,0.0014977927,0.0005277394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015124704,0.0015525292,0.0014484554,0.0033334012,0.0048703332,0.014820547,0.003832338,0.0049575763,0.008265338],"category_scores_gemma":[0.015970862,0.00064422534,0.0014690575,0.0033027064,0.048006438,0.016105179,0.0062960773,0.007686913,0.0023317933],"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":[0.0000024835117,0.000009399144,0.00016257519,0.00010300071,0.000008981882,0.00003076739,0.0024363266,0.00048377484,0.00001564445,0.9890702,0.0032442622,0.004432543],"study_design_scores_gemma":[0.0000071277414,0.000010892767,0.00016884868,0.00030735484,0.00000724277,0.000055452674,0.0019427184,0.00070116343,0.000029885789,0.90512246,0.09163477,0.000012092916],"about_ca_topic_score_codex":0.006283009,"about_ca_topic_score_gemma":0.003837752,"teacher_disagreement_score":0.015124704,"about_ca_system_score_codex":0.012020736,"about_ca_system_score_gemma":0.008269748,"threshold_uncertainty_score":0.08721697},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011487135,0.0024242871,0.0013807784,0.009630649,0.004794484,0.00014860375,0.00283091,0.0013606074,0.9762809],"genre_scores_gemma":[0.0048621628,0.001930722,0.0009091138,0.003113917,0.00089007686,0.00008302337,0.0021392333,0.00042191826,0.98564976],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977182,0.00022016454,0.00014543788,0.00053965964,0.0010796164,0.0002969333],"domain_scores_gemma":[0.99390656,0.0007024999,0.00027293133,0.0008364133,0.002747423,0.0015341953],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015651784,0.0009792118,0.00089088816,0.0020575712,0.0029294968,0.009161784,0.0019705137,0.0050424086,0.84570533],"category_scores_gemma":[0.0085818665,0.0003667098,0.00064785406,0.0017141984,0.0015295787,0.0042626406,0.0038908934,0.0024630025,0.74988586],"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":[0.00006169108,0.00004789688,0.0008997713,0.0003656601,0.000008571768,0.0002196011,0.00024343166,0.00006892475,0.00042604614,0.010612928,0.7579983,0.22904709],"study_design_scores_gemma":[0.000006505567,0.000008989307,0.00056077616,0.00017062575,0.0000024418175,0.00014149593,0.00013843439,0.00004660944,0.00009194049,0.0010909518,0.99773645,0.0000048173783],"about_ca_topic_score_codex":0.00838709,"about_ca_topic_score_gemma":0.012453827,"teacher_disagreement_score":0.15429467,"about_ca_system_score_codex":0.0033926195,"about_ca_system_score_gemma":0.007125182,"threshold_uncertainty_score":0.22008264},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911574,0.0002390716,0.0034016927,0.0004236734,0.000038144208,0.000121548495,0.0004318986,0.00008471723,0.0041019125],"genre_scores_gemma":[0.99481106,0.00016614427,0.003018269,0.000044198805,0.000016562606,0.00020787926,0.00021038948,0.000017012373,0.0015084201],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98980075,0.005796605,0.00085933675,0.0009298644,0.0018118512,0.00080147584],"domain_scores_gemma":[0.8305934,0.1221429,0.016202226,0.00513825,0.021143906,0.0047793216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019129546,0.00076234515,0.00074617757,0.0026093854,0.0010517456,0.004678311,0.0013480323,0.0012498326,0.0029241045],"category_scores_gemma":[0.09845453,0.00031060164,0.0012913223,0.0025948826,0.0011428435,0.0029328691,0.001579937,0.002173702,0.0008009574],"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":[0.00048951036,0.0006303127,0.92421204,0.00015843575,0.00017595789,0.000065990374,0.008765091,0.0017396838,0.0004055657,0.001121623,0.0007639778,0.061471857],"study_design_scores_gemma":[0.000032456377,0.0015224103,0.9659747,0.00026474963,0.00026576553,0.000114731774,0.010951694,0.014604313,0.001457617,0.0008864327,0.003860005,0.00006512293],"about_ca_topic_score_codex":0.046063688,"about_ca_topic_score_gemma":0.02915425,"teacher_disagreement_score":0.046063688,"about_ca_system_score_codex":0.004505753,"about_ca_system_score_gemma":0.005709969,"threshold_uncertainty_score":0.10116792},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060222987,0.044663552,0.011487194,0.21384993,0.024853975,0.003738282,0.13678318,0.0035931445,0.50080764],"genre_scores_gemma":[0.3013636,0.11791117,0.037771806,0.19336611,0.026243247,0.008114349,0.12180724,0.0041475007,0.18927498],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9520669,0.013089646,0.0117541235,0.0039040153,0.016138533,0.0030467252],"domain_scores_gemma":[0.79177153,0.031114394,0.04101641,0.018556472,0.09545945,0.02208179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016535487,0.0007922925,0.0009331075,0.0113334255,0.0030210859,0.006460192,0.0036565096,0.0024070803,0.06462538],"category_scores_gemma":[0.13722709,0.0006704505,0.0013266128,0.013116018,0.001414096,0.006063758,0.008295089,0.0042006955,0.03058176],"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":[0.00008819856,0.00010245273,0.056223787,0.0014870256,0.00007644248,0.0005330139,0.0054649008,0.000079982245,0.00038556513,0.003635806,0.7338941,0.1980287],"study_design_scores_gemma":[0.000031556236,0.000073596944,0.0414457,0.0045485334,0.0000388731,0.0014386938,0.010582421,0.00017278393,0.0002594244,0.0017779218,0.939523,0.00010761322],"about_ca_topic_score_codex":0.035823066,"about_ca_topic_score_gemma":0.027309516,"teacher_disagreement_score":0.06462538,"about_ca_system_score_codex":0.0062631676,"about_ca_system_score_gemma":0.016001968,"threshold_uncertainty_score":0.21619344},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018465715,0.04064112,0.24853516,0.44481653,0.063850656,0.0050225235,0.0011209255,0.0038419664,0.17370543],"genre_scores_gemma":[0.12476857,0.06691487,0.5903976,0.086641245,0.014912188,0.010014614,0.0011376342,0.0049916725,0.10022159],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9380372,0.045618895,0.003492745,0.0028380451,0.008824851,0.0011881739],"domain_scores_gemma":[0.8509757,0.08192561,0.00718814,0.012684555,0.024764666,0.02246133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07791314,0.0010972912,0.0022865434,0.0021399895,0.009397991,0.019545255,0.0022906295,0.010185717,0.015190653],"category_scores_gemma":[0.16311541,0.0015489697,0.0012603087,0.0027866806,0.014977853,0.024945438,0.007844702,0.016091796,0.030557929],"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":[0.00029469337,0.00042451324,0.0029342873,0.0037846193,0.00008805753,0.0015927174,0.09426985,0.00015260739,0.008089906,0.086470515,0.47527006,0.32662815],"study_design_scores_gemma":[0.00004275813,0.00020755653,0.0015585057,0.0033217773,0.000042131775,0.00082784874,0.04150484,0.000102711005,0.0017801103,0.046621986,0.90381306,0.0001767345],"about_ca_topic_score_codex":0.00080484746,"about_ca_topic_score_gemma":0.001468691,"teacher_disagreement_score":0.92208683,"about_ca_system_score_codex":0.0024067734,"about_ca_system_score_gemma":0.020594845,"threshold_uncertainty_score":0.412049},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033246272,0.048055068,0.008683986,0.21914937,0.017889772,0.00005154508,0.00010130861,0.00021082071,0.70552564],"genre_scores_gemma":[0.008180523,0.015492943,0.004339058,0.044831324,0.0057367207,0.000080048,0.000054758388,0.00045402406,0.92083055],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954839,0.0015023544,0.00011062148,0.0003633005,0.002289086,0.00025089495],"domain_scores_gemma":[0.9958931,0.0024831193,0.00009552397,0.0002313973,0.000979448,0.00031735154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048774257,0.00090542756,0.0007267382,0.0019918005,0.002805431,0.011062025,0.0017163705,0.006599606,0.03729005],"category_scores_gemma":[0.012985816,0.00046748266,0.0003943094,0.0021767614,0.005669403,0.012408898,0.0041253786,0.009675158,0.015834797],"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":[0.0000065164495,0.000014098679,0.0000263023,0.00006410355,0.0000021919116,0.000022996956,0.00043541385,0.00009330623,0.000045184323,0.3133085,0.6506246,0.035356782],"study_design_scores_gemma":[0.0000019777685,0.0000032523353,0.000033273278,0.00013089793,0.000001235585,0.000029441067,0.00012904023,0.00007455558,0.000049556715,0.0501981,0.9493432,0.0000056105678],"about_ca_topic_score_codex":0.0077644587,"about_ca_topic_score_gemma":0.016860748,"teacher_disagreement_score":0.03729005,"about_ca_system_score_codex":0.0053744903,"about_ca_system_score_gemma":0.004666367,"threshold_uncertainty_score":0.12474769},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71848905,0.014279684,0.0028389115,0.09192209,0.0013197596,0.00073835585,0.0024670304,0.0003465307,0.16759855],"genre_scores_gemma":[0.8963027,0.010679937,0.0029626403,0.017106473,0.00010023351,0.00027607247,0.00078104466,0.00011426936,0.07167661],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99461585,0.00063282094,0.00014845177,0.00057267625,0.0015262705,0.0025039057],"domain_scores_gemma":[0.97836816,0.0014473434,0.0008718207,0.0002784032,0.007397833,0.011636354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033906696,0.00038658103,0.00046829839,0.0018958298,0.023632389,0.0049536233,0.002303826,0.0019247166,0.015071099],"category_scores_gemma":[0.010221397,0.00059868785,0.00036377783,0.005713384,0.0039814096,0.0019495265,0.005946679,0.003179975,0.0011159722],"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":[0.00016609483,0.00027292923,0.1067242,0.0013037904,0.000044538523,0.0051569357,0.47113046,0.0003680838,0.0016191696,0.029524848,0.17179568,0.21189322],"study_design_scores_gemma":[0.00002275215,0.00008105619,0.09076364,0.0011099697,0.000018031833,0.0008471935,0.45460004,0.00035292006,0.00021464578,0.0015465893,0.45035845,0.00008467553],"about_ca_topic_score_codex":0.97914267,"about_ca_topic_score_gemma":0.9892001,"teacher_disagreement_score":0.084927425,"about_ca_system_score_codex":0.084927425,"about_ca_system_score_gemma":0.34416968,"threshold_uncertainty_score":0.6161945},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28658223,0.0025121258,0.14933307,0.075695,0.0006476896,0.0018482325,0.00013498025,0.00070537603,0.48254123],"genre_scores_gemma":[0.9538256,0.00036096343,0.023498159,0.0018530841,0.000055863322,0.00048121368,0.00004833005,0.00009840374,0.019778546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94785804,0.036589507,0.002477091,0.0038095608,0.0058629923,0.003402809],"domain_scores_gemma":[0.9260508,0.04123847,0.0047162147,0.0122391265,0.01303676,0.0027186712],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.082932815,0.0004674354,0.00046995544,0.0027915915,0.011704069,0.011788542,0.0026198456,0.0025835214,0.0069841207],"category_scores_gemma":[0.07249631,0.00051031506,0.00060321274,0.0018287958,0.03249899,0.012466579,0.018791493,0.0044052233,0.00065390434],"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":[0.000058579804,0.0000915196,0.006324961,0.00037930312,0.000027046488,0.0005364469,0.0875471,0.002729657,0.0010344493,0.79961216,0.008329626,0.0933291],"study_design_scores_gemma":[0.00006231096,0.000284437,0.009086646,0.0020747406,0.000041883777,0.00070049847,0.09503922,0.010363755,0.0030410977,0.31177178,0.5673906,0.00014292506],"about_ca_topic_score_codex":0.010621549,"about_ca_topic_score_gemma":0.014394528,"teacher_disagreement_score":0.91706717,"about_ca_system_score_codex":0.027474234,"about_ca_system_score_gemma":0.031143183,"threshold_uncertainty_score":0.4385959},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4712344,0.00142621,0.26527977,0.009980146,0.00015722738,0.00094600493,0.00014689848,0.00058216066,0.25024712],"genre_scores_gemma":[0.98881966,0.000069452675,0.008840716,0.000084131,0.0000122231695,0.00017301936,0.000026785945,0.000053081563,0.0019209347],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.90678567,0.07702588,0.0016518312,0.0030354687,0.0075470037,0.003954074],"domain_scores_gemma":[0.9195343,0.0639544,0.0032096808,0.005250768,0.0055105216,0.0025402945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033929475,0.0007586722,0.00083217537,0.0037955139,0.009222964,0.01684335,0.00280209,0.004052396,0.003932543],"category_scores_gemma":[0.06495881,0.0009485313,0.00072017853,0.0025079434,0.03836104,0.01378191,0.016913828,0.0051321457,0.00048984383],"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":[0.0001308589,0.000070522685,0.0036813298,0.00020377246,0.000025115154,0.0004595128,0.5411972,0.0009222474,0.0023006785,0.4289553,0.0005858515,0.021467688],"study_design_scores_gemma":[0.0001004225,0.00023769142,0.01032107,0.0009406982,0.00006471316,0.0008165448,0.45884314,0.01336763,0.005071732,0.41122478,0.09879887,0.0002126793],"about_ca_topic_score_codex":0.007363803,"about_ca_topic_score_gemma":0.004960249,"teacher_disagreement_score":0.033929475,"about_ca_system_score_codex":0.009227117,"about_ca_system_score_gemma":0.0055453503,"threshold_uncertainty_score":0.17943841},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018595919,0.027322633,0.012153622,0.9368031,0.0010063457,0.00009975363,0.00004957996,0.00004638373,0.02065898],"genre_scores_gemma":[0.6815271,0.07046704,0.08581635,0.13924141,0.009804582,0.0022362985,0.00016816346,0.00031708291,0.010421989],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55362403,0.38022846,0.00948214,0.009111862,0.038575597,0.008977912],"domain_scores_gemma":[0.2206347,0.6890702,0.0071625654,0.009282777,0.06372111,0.010128636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.45787686,0.0015397796,0.004998111,0.012157943,0.020722352,0.054883122,0.008214241,0.023194602,0.0071015507],"category_scores_gemma":[0.4282086,0.0016041396,0.001580805,0.008763181,0.07482752,0.03379374,0.018777713,0.028612465,0.0011548244],"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":[0.000052091957,0.000075993696,0.0008924983,0.0009938721,0.000064343265,0.00015483682,0.0050088465,0.002696456,0.000062871455,0.8779298,0.044027608,0.06804078],"study_design_scores_gemma":[0.000051469804,0.000039290673,0.00056718546,0.0038841243,0.000024606146,0.00008952598,0.01143257,0.0032009985,0.00013429063,0.8806577,0.09983067,0.00008758147],"about_ca_topic_score_codex":0.06497923,"about_ca_topic_score_gemma":0.05332094,"teacher_disagreement_score":0.93502074,"about_ca_system_score_codex":0.06870581,"about_ca_system_score_gemma":0.1510955,"threshold_uncertainty_score":0.6685344},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039086486,0.059477836,0.038926475,0.80746776,0.052085355,0.002330642,0.00041367597,0.0006527424,0.034736924],"genre_scores_gemma":[0.08695901,0.077235356,0.12885137,0.4697452,0.019253261,0.016843345,0.0005941049,0.00202076,0.19849771],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9414938,0.04223386,0.001823635,0.0033044622,0.00971291,0.001431324],"domain_scores_gemma":[0.8575056,0.09707601,0.004012686,0.005498622,0.022882743,0.013024371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069502756,0.0010061973,0.0015941071,0.0017900979,0.011384076,0.011212294,0.0022773393,0.005905,0.007655446],"category_scores_gemma":[0.117147446,0.0019564144,0.0009601086,0.0017791917,0.018002708,0.008450508,0.009247165,0.021197448,0.005829387],"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":[0.000047375408,0.000100246594,0.00028758822,0.001363846,0.000017211156,0.00062619575,0.07410804,0.0001913447,0.0005641682,0.03647152,0.8125376,0.073684864],"study_design_scores_gemma":[0.000025756297,0.00006115186,0.0003386226,0.0033141454,0.0000051428847,0.0007626147,0.020045381,0.00018378139,0.0002681133,0.017619878,0.9573205,0.000055043947],"about_ca_topic_score_codex":0.007073752,"about_ca_topic_score_gemma":0.011868479,"teacher_disagreement_score":0.069502756,"about_ca_system_score_codex":0.01133028,"about_ca_system_score_gemma":0.028795186,"threshold_uncertainty_score":0.3675701},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10673776,0.051084816,0.050035164,0.50761557,0.0044918978,0.0056733713,0.0010323905,0.00032858414,0.27300054],"genre_scores_gemma":[0.8326249,0.023302948,0.08396889,0.028677758,0.0011128301,0.005030527,0.0004972676,0.00011457361,0.024670234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88465804,0.07967998,0.0041606175,0.0018789767,0.02697332,0.002649083],"domain_scores_gemma":[0.8113192,0.1085115,0.011151925,0.0064496184,0.051840432,0.010727341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.097292885,0.00065950805,0.0016079182,0.0022723079,0.004130734,0.009323705,0.0028510168,0.0025625315,0.008328848],"category_scores_gemma":[0.12959555,0.00036605596,0.0012292501,0.0026949008,0.0066113835,0.0041058036,0.0050744275,0.004346218,0.00074909476],"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":[0.0008113796,0.0008795926,0.0339642,0.004654911,0.00036696208,0.00011037335,0.017692609,0.003097888,0.0004861643,0.14471468,0.050614186,0.74260706],"study_design_scores_gemma":[0.00056386006,0.0032622658,0.18000554,0.04057858,0.001256338,0.00029842407,0.03175015,0.010726723,0.003480573,0.08701454,0.640591,0.00047194163],"about_ca_topic_score_codex":0.25749898,"about_ca_topic_score_gemma":0.43205613,"teacher_disagreement_score":0.742501,"about_ca_system_score_codex":0.041686397,"about_ca_system_score_gemma":0.15451665,"threshold_uncertainty_score":0.5145401},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1563801,0.061206054,0.045316637,0.64094454,0.001355772,0.0006077748,0.00013107702,0.0001135338,0.09394449],"genre_scores_gemma":[0.93952996,0.0143420985,0.0355831,0.008213714,0.00049898715,0.00036566213,0.00004524059,0.000020136384,0.0014011033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.90315205,0.07712506,0.005559898,0.0021205994,0.010169533,0.0018728658],"domain_scores_gemma":[0.6579293,0.27692583,0.024582462,0.010395304,0.019280365,0.010886661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12084838,0.00045675502,0.0011291874,0.0067132525,0.0063554468,0.022703923,0.002041995,0.0077644982,0.0036239093],"category_scores_gemma":[0.20876299,0.00071980455,0.00054647616,0.0045054983,0.020887015,0.025021171,0.009658583,0.007832684,0.00042389202],"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":[0.0004080157,0.0011400613,0.048736826,0.0044623753,0.00027347016,0.0016417241,0.04489498,0.0019443149,0.00074971037,0.45261818,0.011749519,0.43138084],"study_design_scores_gemma":[0.00019405219,0.00091537397,0.026384661,0.016819157,0.00023485601,0.0017149717,0.073712,0.0034829571,0.0026457813,0.7678183,0.105838604,0.00023939335],"about_ca_topic_score_codex":0.0038414397,"about_ca_topic_score_gemma":0.005204028,"teacher_disagreement_score":0.12084838,"about_ca_system_score_codex":0.008526474,"about_ca_system_score_gemma":0.035853654,"threshold_uncertainty_score":0.639115},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13670883,0.022580361,0.14100909,0.12640934,0.0011011765,0.0010089552,0.001010414,0.00026017474,0.56991166],"genre_scores_gemma":[0.87735355,0.005129778,0.05096838,0.0038040432,0.00032471784,0.00053793145,0.0005170884,0.00015573848,0.061208762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9076038,0.052829966,0.0035113622,0.0033939534,0.02974818,0.002912721],"domain_scores_gemma":[0.73753554,0.21063435,0.0042509576,0.0054922206,0.04107558,0.0010113803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.081149034,0.0009798169,0.0012329926,0.006857608,0.007351893,0.019521695,0.0027508512,0.005033173,0.007738496],"category_scores_gemma":[0.15050758,0.0008487502,0.0011730667,0.0063925143,0.017613867,0.00812439,0.003723677,0.0067148465,0.0007117551],"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":[0.0001689635,0.000071240116,0.0048826463,0.0010194068,0.00014896931,0.00074084755,0.087648205,0.0039991406,0.0013170295,0.76219004,0.020115547,0.117697954],"study_design_scores_gemma":[0.00014791593,0.00013733463,0.03160115,0.0073634856,0.00034196625,0.0003974311,0.0790403,0.017692577,0.0069079837,0.44577107,0.4103075,0.00029129247],"about_ca_topic_score_codex":0.45050487,"about_ca_topic_score_gemma":0.44300532,"teacher_disagreement_score":0.5494951,"about_ca_system_score_codex":0.06810803,"about_ca_system_score_gemma":0.051037166,"threshold_uncertainty_score":0.8957653},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096502795,0.015764907,0.070555136,0.03298665,0.0020937356,0.00007435524,0.00007780236,0.000113421134,0.877369],"genre_scores_gemma":[0.20172028,0.03605364,0.08096901,0.023637364,0.004390967,0.00078535767,0.0004994613,0.00084430556,0.6510997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99356776,0.0039892127,0.00016452082,0.00057321694,0.0013629794,0.00034232996],"domain_scores_gemma":[0.99503565,0.0036741956,0.00012191742,0.00053671765,0.00039970802,0.0002317833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005936917,0.0013519324,0.0011109869,0.0015560915,0.002598999,0.013641948,0.0023237648,0.004996068,0.028708223],"category_scores_gemma":[0.010144039,0.0007293542,0.00069732,0.0022146967,0.020908054,0.014470411,0.006425709,0.008872436,0.009098733],"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":[0.0000031554996,0.000009967422,0.000014271029,0.000048138318,0.000003927416,0.000013908543,0.00048825933,0.000461134,0.000035031862,0.9719296,0.013519796,0.01347288],"study_design_scores_gemma":[0.0000018919769,0.0000029867513,0.000015501972,0.00012958443,0.000001490994,0.000010553949,0.00021420169,0.00033184068,0.000049399107,0.86788154,0.13135661,0.0000043937625],"about_ca_topic_score_codex":0.0025423006,"about_ca_topic_score_gemma":0.002560173,"teacher_disagreement_score":0.028708223,"about_ca_system_score_codex":0.005287179,"about_ca_system_score_gemma":0.0046118153,"threshold_uncertainty_score":0.09603858},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010876436,0.006085954,0.93703717,0.0077381236,0.00044299042,0.00149802,0.0021377283,0.0008360812,0.033347517],"genre_scores_gemma":[0.12872396,0.004003942,0.85152453,0.00080886437,0.000290725,0.0032124491,0.0036323355,0.00018763209,0.007615615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9666166,0.01877659,0.0027000043,0.0024134454,0.008652897,0.0008403453],"domain_scores_gemma":[0.9701329,0.017122284,0.0017413546,0.0029046321,0.007634514,0.00046437272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028172309,0.0017182154,0.0021601757,0.004681636,0.0017457844,0.010240919,0.0022834928,0.0023429885,0.0077877995],"category_scores_gemma":[0.05338859,0.0010358948,0.003766185,0.0052767093,0.003374721,0.0065337503,0.0029427412,0.004362024,0.0022198004],"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":[0.00030443544,0.00019861947,0.00587847,0.0021985425,0.0006279449,0.00006880221,0.001584334,0.040915668,0.00077732344,0.6680947,0.018535366,0.2608158],"study_design_scores_gemma":[0.00028478462,0.00042552943,0.008796803,0.0028542075,0.00066191086,0.00017474721,0.0010292054,0.18148375,0.0018765195,0.6921601,0.110061236,0.00019106593],"about_ca_topic_score_codex":0.022975342,"about_ca_topic_score_gemma":0.016659265,"teacher_disagreement_score":0.028172309,"about_ca_system_score_codex":0.0090046665,"about_ca_system_score_gemma":0.01151896,"threshold_uncertainty_score":0.14899123},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019624826,0.082210734,0.40796542,0.20482856,0.0049958085,0.00051636,0.00042676125,0.00042470242,0.2790068],"genre_scores_gemma":[0.518219,0.045380317,0.3347215,0.026964612,0.006746674,0.0034285318,0.00051927887,0.001183196,0.06283689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73076516,0.2023668,0.0098505365,0.007680258,0.046896163,0.0024411916],"domain_scores_gemma":[0.3754997,0.5573624,0.0070629218,0.035926167,0.022398993,0.0017498345],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23509452,0.0012799517,0.0016628617,0.0062839915,0.004518495,0.022118486,0.004285981,0.0046039396,0.00768764],"category_scores_gemma":[0.30206695,0.001695369,0.00170607,0.008332437,0.05616501,0.026492562,0.011481226,0.018200114,0.001324075],"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":[0.000039035247,0.000025786703,0.0005675548,0.00044593835,0.00004193798,0.00003885845,0.006024056,0.00045377368,0.000094275536,0.9371111,0.005783455,0.049374167],"study_design_scores_gemma":[0.000053931955,0.000044780634,0.0014510027,0.0020485183,0.000034501412,0.00020459811,0.0023165497,0.0030468565,0.00079955335,0.879516,0.11041574,0.00006798822],"about_ca_topic_score_codex":0.013676518,"about_ca_topic_score_gemma":0.011220666,"teacher_disagreement_score":0.76490545,"about_ca_system_score_codex":0.017567417,"about_ca_system_score_gemma":0.017273493,"threshold_uncertainty_score":0.94326466},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035577707,0.027333502,0.17202403,0.021282734,0.0010570635,0.0016730581,0.00060261466,0.0007729893,0.73967636],"genre_scores_gemma":[0.38811764,0.024698427,0.19389388,0.0033664617,0.00059629243,0.0014766685,0.0011334239,0.00063438807,0.38608283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9804991,0.008690278,0.00046096943,0.0006345561,0.008860385,0.0008546797],"domain_scores_gemma":[0.98740256,0.005721624,0.0004593503,0.0012301994,0.00480882,0.0003775141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024683775,0.00096375064,0.0007514373,0.0041352757,0.0015601142,0.008980882,0.0019605425,0.0021517393,0.010903253],"category_scores_gemma":[0.021752123,0.0005525566,0.00061323424,0.0037246551,0.0038890196,0.004215762,0.0018203668,0.0018934023,0.0018579448],"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":[0.00008130767,0.00017930106,0.0011540793,0.0009291576,0.000033463475,0.00009917708,0.0033655534,0.0061924355,0.0015847207,0.20625794,0.030025473,0.7500974],"study_design_scores_gemma":[0.00007341915,0.0003005263,0.008216544,0.0019323486,0.000038302594,0.00021048194,0.0019238874,0.009565583,0.006562827,0.05257876,0.91854084,0.000056473844],"about_ca_topic_score_codex":0.18749338,"about_ca_topic_score_gemma":0.1496749,"teacher_disagreement_score":0.18749338,"about_ca_system_score_codex":0.026241455,"about_ca_system_score_gemma":0.028957533,"threshold_uncertainty_score":0.3728041},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025007399,0.068855435,0.58165413,0.07667956,0.0029123377,0.0046096775,0.0014527047,0.0005644949,0.23826417],"genre_scores_gemma":[0.25611767,0.039526135,0.509783,0.017101571,0.00062717195,0.014739795,0.0008212072,0.00060636795,0.16067708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.80683935,0.1534606,0.0031509541,0.0025318228,0.03249027,0.00152698],"domain_scores_gemma":[0.78096735,0.18926401,0.0028011142,0.0067459256,0.01911298,0.0011085379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13762642,0.001323214,0.0018834351,0.004417558,0.0062093786,0.011366686,0.0031312108,0.0027209737,0.009644978],"category_scores_gemma":[0.102752805,0.001003447,0.0014482333,0.0048125014,0.017484842,0.0065072225,0.0051641725,0.004010541,0.0011779992],"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":[0.0001477888,0.0002813698,0.0012879549,0.0065207914,0.000107897875,0.00026101142,0.10066617,0.0021786296,0.0040316856,0.3042415,0.043924022,0.5363512],"study_design_scores_gemma":[0.00015243546,0.0003244471,0.005206831,0.014384084,0.00014939517,0.00048123405,0.06167424,0.0030358757,0.008569485,0.15073353,0.7551216,0.00016687438],"about_ca_topic_score_codex":0.12307871,"about_ca_topic_score_gemma":0.19601913,"teacher_disagreement_score":0.13762642,"about_ca_system_score_codex":0.03760867,"about_ca_system_score_gemma":0.039474104,"threshold_uncertainty_score":0.7278468},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111687735,0.03008816,0.070669316,0.005522054,0.0011166388,0.0013115766,0.0008481498,0.0012159009,0.7775405],"genre_scores_gemma":[0.39220446,0.022066113,0.05962387,0.0012444541,0.000645871,0.0010404185,0.0015425695,0.0008661307,0.520766],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97128874,0.009696865,0.0006708749,0.0006456056,0.016796956,0.0009009766],"domain_scores_gemma":[0.9785428,0.012651575,0.000675624,0.0015766354,0.0061875647,0.0003658289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02557261,0.0012936188,0.0012483905,0.005593417,0.002431822,0.010328898,0.0021349073,0.0023209564,0.019338787],"category_scores_gemma":[0.036796696,0.00056135835,0.00093725347,0.0063019185,0.0025133695,0.0043429015,0.002060199,0.0019532915,0.003785416],"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":[0.0005039999,0.00042076723,0.0011234434,0.0013206957,0.00003983818,0.00032245993,0.005767192,0.0041656955,0.006315561,0.055366207,0.016927559,0.9077266],"study_design_scores_gemma":[0.00028741604,0.0019100198,0.023482837,0.004444789,0.00028801284,0.0007405869,0.0073347236,0.011228218,0.053544056,0.05849032,0.83802384,0.00022519947],"about_ca_topic_score_codex":0.044648603,"about_ca_topic_score_gemma":0.044162612,"teacher_disagreement_score":0.044648603,"about_ca_system_score_codex":0.0088744,"about_ca_system_score_gemma":0.008899641,"threshold_uncertainty_score":0.13524252},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042047995,0.015331426,0.0013364883,0.69311816,0.09167037,0.00026169853,0.0008331873,0.00045838678,0.19656985],"genre_scores_gemma":[0.010221066,0.0126122115,0.0021702682,0.20547207,0.011730815,0.00030916277,0.00090457726,0.00060869724,0.7559711],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9625604,0.0032727858,0.001420663,0.0028573596,0.026178734,0.0037100203],"domain_scores_gemma":[0.8481794,0.007973531,0.0016195845,0.0036371837,0.11978698,0.018803302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014736616,0.00097429025,0.0015926469,0.0037665567,0.014843986,0.010480384,0.0026716893,0.0082400525,0.10121721],"category_scores_gemma":[0.07777416,0.0008681017,0.000993787,0.0043399725,0.003749743,0.0026697132,0.0035173898,0.012145716,0.048876204],"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":[0.000004447674,0.0000031176912,0.000042964417,0.000012884262,0.000001256876,0.00002464067,0.00002819893,0.000007898745,0.000011955515,0.0010729004,0.9936103,0.005179401],"study_design_scores_gemma":[0.000005819159,0.0000032970468,0.00027144756,0.000104684696,0.0000028916254,0.00008045292,0.00012789277,0.000028524815,0.000032174947,0.00043379428,0.9988952,0.000013775348],"about_ca_topic_score_codex":0.59506494,"about_ca_topic_score_gemma":0.7922861,"teacher_disagreement_score":0.9668682,"about_ca_system_score_codex":0.03313177,"about_ca_system_score_gemma":0.18809235,"threshold_uncertainty_score":0.81463957},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15880209,0.0032553973,0.5356301,0.006573995,0.00036593596,0.00059977133,0.00008791584,0.00057947263,0.29410538],"genre_scores_gemma":[0.9342152,0.00045015552,0.058140177,0.00025405787,0.00015886896,0.00033721427,0.000045213612,0.000107140564,0.006291856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93933076,0.042155407,0.00212254,0.003131653,0.011822788,0.0014368974],"domain_scores_gemma":[0.91855246,0.05925124,0.007993301,0.0059654256,0.0070005376,0.0012370029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024834368,0.0011069587,0.0010111588,0.0060104085,0.0020383825,0.010143096,0.0012540102,0.00246289,0.0072144694],"category_scores_gemma":[0.078969054,0.00045518854,0.0008682535,0.0027325372,0.014495315,0.009388798,0.004813006,0.0026835063,0.0008216696],"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":[0.00011501289,0.00009053433,0.0033152266,0.00039853062,0.00007765243,0.0001607367,0.008570524,0.002738127,0.0018684982,0.9048015,0.0010252023,0.07683852],"study_design_scores_gemma":[0.000064912936,0.00024566296,0.004035848,0.00034886572,0.000055979217,0.00033209048,0.0036971206,0.011214308,0.003656603,0.95462644,0.021650147,0.00007199564],"about_ca_topic_score_codex":0.0005793568,"about_ca_topic_score_gemma":0.0006239827,"teacher_disagreement_score":0.024834368,"about_ca_system_score_codex":0.004037552,"about_ca_system_score_gemma":0.0028989536,"threshold_uncertainty_score":0.13133824},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07261708,0.012877289,0.14550446,0.27777985,0.010966288,0.00067146803,0.00020509292,0.0007923281,0.4785862],"genre_scores_gemma":[0.8164818,0.0042402665,0.0781424,0.019190501,0.0019820402,0.00048941735,0.00023051028,0.00073839445,0.07850464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9783165,0.015524355,0.0007697535,0.0008239754,0.0038418514,0.0007236735],"domain_scores_gemma":[0.9570434,0.02800828,0.001840508,0.0019192969,0.009656691,0.0015318504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025321836,0.0006067236,0.000633455,0.0012741952,0.0037223503,0.011935716,0.0012652436,0.004434799,0.017174471],"category_scores_gemma":[0.08581251,0.00026018347,0.0004889421,0.0011101791,0.009257721,0.014306444,0.0039157276,0.0049447445,0.0038913111],"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":[0.00081733987,0.0002343409,0.002833388,0.0009834848,0.00007629398,0.00046496975,0.016505422,0.0010418812,0.0020588015,0.6174418,0.13306713,0.22447518],"study_design_scores_gemma":[0.00011772642,0.0002788151,0.002348161,0.0033836358,0.000077971155,0.0002657853,0.019747734,0.0039482107,0.0036032924,0.50103354,0.46510348,0.00009172461],"about_ca_topic_score_codex":0.001525726,"about_ca_topic_score_gemma":0.0020276343,"teacher_disagreement_score":0.025321836,"about_ca_system_score_codex":0.0036100976,"about_ca_system_score_gemma":0.0035645121,"threshold_uncertainty_score":0.13391632},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030835934,0.32877687,0.023642682,0.4766605,0.0056274235,0.00009247752,0.00024147463,0.00007886972,0.13404372],"genre_scores_gemma":[0.73622423,0.21105321,0.015242401,0.01710453,0.011610611,0.00024411464,0.00021744559,0.00010459265,0.008198935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930332,0.004126905,0.00022295202,0.00053935713,0.0014513985,0.0006261998],"domain_scores_gemma":[0.979302,0.01367385,0.0011221209,0.0009751495,0.0022679823,0.0026589546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014582922,0.0005860212,0.0011512685,0.0044090166,0.004825447,0.014193941,0.0014635538,0.0028647576,0.008037608],"category_scores_gemma":[0.016852213,0.00033852796,0.000598729,0.008360778,0.02645019,0.019193148,0.0060184705,0.0067398897,0.0008154627],"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":[0.000034826247,0.00007141916,0.0036491505,0.00046141088,0.000015974601,0.0000587366,0.008773569,0.00021711962,0.00014762577,0.87008655,0.013797701,0.10268595],"study_design_scores_gemma":[0.000008709047,0.000060146143,0.0072567062,0.0022668038,0.000017756563,0.00010415221,0.014624891,0.0011434144,0.0001015538,0.860516,0.1138648,0.000035047087],"about_ca_topic_score_codex":0.008730536,"about_ca_topic_score_gemma":0.006689692,"teacher_disagreement_score":0.014582922,"about_ca_system_score_codex":0.00844752,"about_ca_system_score_gemma":0.010139084,"threshold_uncertainty_score":0.07712275},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11435596,0.002454308,0.54822516,0.014183563,0.0006189268,0.00055491703,0.00024833038,0.00015985793,0.3191989],"genre_scores_gemma":[0.9429884,0.0005396847,0.046495475,0.0011212903,0.00022168859,0.0005348614,0.00008199905,0.00006003002,0.007956448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98383385,0.008842292,0.00069457584,0.0020779946,0.0033803873,0.0011709444],"domain_scores_gemma":[0.965376,0.021727566,0.0038389747,0.0029667264,0.0046092346,0.0014814144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011890246,0.00081709377,0.0006446664,0.0029793025,0.0022984783,0.006444196,0.0014699531,0.0016915625,0.008557999],"category_scores_gemma":[0.040736757,0.0003839936,0.0014689855,0.0021580225,0.011492987,0.00799396,0.0032419653,0.0025888383,0.0008547332],"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":[0.00008230593,0.00012199589,0.01150431,0.00016817283,0.00004851213,0.00012029503,0.009164713,0.0020968134,0.00054721395,0.93396497,0.0015475242,0.04063315],"study_design_scores_gemma":[0.00004918385,0.00016671879,0.0111207515,0.00023692375,0.000050961407,0.00023252856,0.002999246,0.010833819,0.0005216438,0.96128124,0.012440691,0.00006643605],"about_ca_topic_score_codex":0.0034156865,"about_ca_topic_score_gemma":0.002594811,"teacher_disagreement_score":0.011890246,"about_ca_system_score_codex":0.006636066,"about_ca_system_score_gemma":0.0031534052,"threshold_uncertainty_score":0.062882364},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08257183,0.03462763,0.31420246,0.50228935,0.008466091,0.0027615346,0.0007071932,0.00026377285,0.05411024],"genre_scores_gemma":[0.65451247,0.015658781,0.21804854,0.08434114,0.006198894,0.0110371625,0.0004058748,0.0007438623,0.009053304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60685676,0.3335748,0.013726253,0.016568992,0.024430735,0.004842378],"domain_scores_gemma":[0.37781328,0.51366234,0.024175968,0.040799826,0.03634907,0.007199563],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38967773,0.001404296,0.0031624234,0.009875868,0.016457574,0.029010864,0.008433883,0.0076541677,0.008593505],"category_scores_gemma":[0.5310688,0.001306758,0.0017722102,0.010124159,0.036444027,0.030437486,0.035281435,0.012774616,0.0016953237],"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":[0.00018264729,0.0002276299,0.01862115,0.004843605,0.0002760219,0.0005508621,0.31529516,0.0010701964,0.0017164057,0.35871908,0.033816256,0.26468095],"study_design_scores_gemma":[0.00004846878,0.00020439453,0.008909741,0.011278899,0.00016072752,0.000516985,0.26005027,0.00267638,0.002034977,0.54445577,0.16945587,0.00020754864],"about_ca_topic_score_codex":0.0066088154,"about_ca_topic_score_gemma":0.009794437,"teacher_disagreement_score":0.61032224,"about_ca_system_score_codex":0.0095011685,"about_ca_system_score_gemma":0.026490629,"threshold_uncertainty_score":0.752636},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050127845,0.008615726,0.83963585,0.006795862,0.0029537834,0.0074179014,0.0013869992,0.0018216224,0.08124435],"genre_scores_gemma":[0.10442652,0.0031622178,0.8718413,0.0008980434,0.00034994129,0.011393466,0.0022818788,0.00036320204,0.0052833916],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8044224,0.08447719,0.028340336,0.00552948,0.07408735,0.0031433853],"domain_scores_gemma":[0.76722556,0.093707725,0.013075505,0.010589166,0.11274477,0.0026572356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15954815,0.0017005694,0.0020247453,0.020086063,0.0029116578,0.00920282,0.0043282663,0.003021593,0.0036622083],"category_scores_gemma":[0.31035686,0.0011580355,0.0018392858,0.010611316,0.0033373353,0.006736294,0.0047484054,0.0040531135,0.0034967195],"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":[0.00045550073,0.0006974636,0.040481273,0.0021948237,0.0002284775,0.00015470594,0.005190131,0.0031161222,0.0024935245,0.12878512,0.042502925,0.7736999],"study_design_scores_gemma":[0.00053448515,0.0030912103,0.12963063,0.011763301,0.0005681773,0.0013588923,0.019218333,0.02573971,0.038283736,0.30280948,0.46582836,0.001173709],"about_ca_topic_score_codex":0.0032244422,"about_ca_topic_score_gemma":0.0041813464,"teacher_disagreement_score":0.15954815,"about_ca_system_score_codex":0.0069445483,"about_ca_system_score_gemma":0.012287966,"threshold_uncertainty_score":0.84378135},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8446935,0.0010738435,0.08536285,0.012523903,0.0002515035,0.010611554,0.0014399686,0.00016158634,0.04388132],"genre_scores_gemma":[0.9249886,0.0006245599,0.053594403,0.002184616,0.000023977816,0.008846809,0.00027599995,0.00005825045,0.009402774],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97333187,0.02294974,0.0005592426,0.0007055536,0.0011182565,0.0013352848],"domain_scores_gemma":[0.95800096,0.034926362,0.0015143643,0.0011389204,0.0032974286,0.0011220718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037689723,0.00046563783,0.00042523892,0.0013725772,0.005751967,0.003608311,0.0016691881,0.0013892051,0.0053983834],"category_scores_gemma":[0.023630073,0.0005698818,0.00082259724,0.001551607,0.007367084,0.0026424194,0.0040628165,0.0014862615,0.0005248227],"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":[0.00010008648,0.00016857739,0.003916648,0.0011757247,0.00001628034,0.00065994426,0.94676346,0.00038552404,0.0022137875,0.014999577,0.002441476,0.027158875],"study_design_scores_gemma":[0.00006200192,0.00018896152,0.003751809,0.0017546559,0.000024087125,0.00033599083,0.9349816,0.0012491124,0.0031726386,0.00658788,0.04783924,0.000052053154],"about_ca_topic_score_codex":0.011628346,"about_ca_topic_score_gemma":0.017337255,"teacher_disagreement_score":0.037689723,"about_ca_system_score_codex":0.009800816,"about_ca_system_score_gemma":0.017235046,"threshold_uncertainty_score":0.19932473},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020731745,0.2895697,0.17428744,0.15634434,0.0048302263,0.001097585,0.002750346,0.0012352755,0.3491533],"genre_scores_gemma":[0.3163858,0.27556768,0.29050997,0.01635366,0.004214066,0.0024235547,0.0029466092,0.0011398226,0.090458766],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.90691644,0.041933455,0.005497904,0.0036698193,0.03989315,0.0020893638],"domain_scores_gemma":[0.84273094,0.07556519,0.0074041025,0.011740306,0.06035982,0.0021996258],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.06504385,0.0019868636,0.0022734876,0.015581687,0.0035617983,0.02605149,0.003031061,0.0056720106,0.018059783],"category_scores_gemma":[0.10914931,0.0010550056,0.0024698128,0.019642778,0.0073019415,0.016266478,0.0044322372,0.006603414,0.0061468654],"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":[0.00035794437,0.0002055778,0.0032468094,0.0104236575,0.00025845712,0.0000982745,0.0029358505,0.0044049164,0.0019352006,0.33098748,0.039015796,0.60613],"study_design_scores_gemma":[0.00014454228,0.0006362002,0.012550976,0.02103932,0.0004324284,0.00038279756,0.005300385,0.005779699,0.009148829,0.14833392,0.7959352,0.00031572863],"about_ca_topic_score_codex":0.042781297,"about_ca_topic_score_gemma":0.027153993,"teacher_disagreement_score":0.97394854,"about_ca_system_score_codex":0.022831613,"about_ca_system_score_gemma":0.038576856,"threshold_uncertainty_score":0.3439889},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006981552,0.004509738,0.16884345,0.016636893,0.005506701,0.003187239,0.00067082694,0.0019820181,0.7916816],"genre_scores_gemma":[0.2294338,0.006290239,0.30738246,0.010186539,0.0025298852,0.005561054,0.0018415322,0.0028739495,0.43390054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9155671,0.041088115,0.005604264,0.004415735,0.030907253,0.0024176524],"domain_scores_gemma":[0.81426543,0.06171716,0.007705321,0.03833712,0.06939778,0.008577131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08028155,0.0014124662,0.0010352372,0.0054769833,0.0045687524,0.02008176,0.0039045506,0.0024357047,0.0657231],"category_scores_gemma":[0.16146155,0.0005963939,0.0015850993,0.0036425139,0.006786091,0.01013529,0.01225784,0.00394456,0.016298082],"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":[0.00023728247,0.000172674,0.0016884697,0.0014366286,0.000057182595,0.00015096946,0.007598563,0.00049392943,0.0011427399,0.3066901,0.14367196,0.5366596],"study_design_scores_gemma":[0.00006585267,0.00013305712,0.0012439752,0.0015196067,0.000039795395,0.00033472932,0.0038323693,0.0009416148,0.0018126221,0.080581725,0.9094251,0.000069537695],"about_ca_topic_score_codex":0.0027451196,"about_ca_topic_score_gemma":0.0051927366,"teacher_disagreement_score":0.08028155,"about_ca_system_score_codex":0.008900727,"about_ca_system_score_gemma":0.018491386,"threshold_uncertainty_score":0.4245745},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99567896,0.00025251997,0.0015883286,0.0011361546,0.000028437906,0.00017502542,0.000019960842,0.00000895255,0.001111568],"genre_scores_gemma":[0.99642986,0.00034165167,0.0012119577,0.00070274697,0.00002948681,0.00048611406,0.000020927453,0.000010171368,0.0007672493],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97301733,0.020223532,0.001250519,0.0012052319,0.0020790657,0.002224362],"domain_scores_gemma":[0.9509107,0.03903643,0.0025118,0.00085384824,0.0040260167,0.0026613038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03100484,0.0006823813,0.0012147323,0.0027640134,0.0058678803,0.003580672,0.0015647925,0.002881692,0.0020504938],"category_scores_gemma":[0.038607348,0.00076681474,0.0007442502,0.0011479323,0.00402394,0.0047946274,0.0056769126,0.003041336,0.00046955064],"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":[0.00006524762,0.00024239751,0.007064023,0.00012360894,0.000011252173,0.00070838234,0.9807562,0.000028486125,0.0013574654,0.00023717269,0.00017693723,0.009228854],"study_design_scores_gemma":[0.000030695068,0.00047425745,0.010637188,0.00021821648,0.000023530256,0.0005239231,0.980753,0.00017259693,0.0008760412,0.0004263427,0.0058183265,0.00004582951],"about_ca_topic_score_codex":0.0020478317,"about_ca_topic_score_gemma":0.0032428224,"teacher_disagreement_score":0.03100484,"about_ca_system_score_codex":0.0026430804,"about_ca_system_score_gemma":0.0027050904,"threshold_uncertainty_score":0.16397125},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023144163,0.90240926,0.0014640877,0.026640823,0.027478179,0.0001084166,0.000167856,0.0001227364,0.041377246],"genre_scores_gemma":[0.0032124487,0.8429819,0.002549875,0.010215119,0.030267201,0.00018706487,0.0003914586,0.00017062169,0.110024214],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777395,0.0005741222,0.00014809587,0.00019782901,0.0012017861,0.000104189814],"domain_scores_gemma":[0.9886014,0.006503941,0.0005186746,0.00041548454,0.003073088,0.0008874192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027097422,0.00089554815,0.001402986,0.004387316,0.00064647716,0.0036284039,0.0011608497,0.0022266654,0.03660985],"category_scores_gemma":[0.010474334,0.0003855796,0.000592619,0.005805536,0.0013752045,0.0032236606,0.001378081,0.0028210643,0.01826061],"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":[0.0000110949795,0.00003751437,0.000063937565,0.0018718684,0.000009247969,0.000046554273,0.000112248286,0.000083351035,0.00008350642,0.0028721767,0.6100344,0.38477412],"study_design_scores_gemma":[0.000009653132,0.000026861735,0.00041711613,0.002764763,0.000008473371,0.00032518656,0.00010238949,0.000051133535,0.000041908068,0.0023677936,0.99387264,0.000012065576],"about_ca_topic_score_codex":0.007860759,"about_ca_topic_score_gemma":0.02070182,"teacher_disagreement_score":0.03660985,"about_ca_system_score_codex":0.003018872,"about_ca_system_score_gemma":0.0037017865,"threshold_uncertainty_score":0.12247217},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028531216,0.00036623437,0.00011846093,0.97615767,0.02144608,0.000014731393,0.000022937844,0.00001207229,0.0015764588],"genre_scores_gemma":[0.0043203533,0.0005076205,0.00040576985,0.95336574,0.03388068,0.000075389515,0.0000135197415,0.00003649801,0.0073943734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99207664,0.0026743044,0.0010007956,0.000889387,0.0026735787,0.00068527606],"domain_scores_gemma":[0.96166205,0.023834035,0.001685883,0.0009320889,0.008493382,0.0033925204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009623799,0.0008151818,0.0015667374,0.00069631764,0.0055343173,0.0048320163,0.0022278172,0.04724192,0.007890372],"category_scores_gemma":[0.08273216,0.00081483315,0.0010703641,0.0008017833,0.0036550036,0.0033073763,0.0018526053,0.03793511,0.0047512366],"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":[0.000041237225,0.000022998904,0.00030826093,0.000044937136,0.000010357051,0.0007610913,0.00025357844,0.000042297666,0.0000776744,0.0021630821,0.9908065,0.0054680067],"study_design_scores_gemma":[0.000108225024,0.000049615322,0.00091146084,0.00036331278,0.00003099629,0.0016303589,0.001053719,0.0005543555,0.00026334406,0.0067653647,0.9882123,0.000057011224],"about_ca_topic_score_codex":0.007315081,"about_ca_topic_score_gemma":0.012207333,"teacher_disagreement_score":0.04724192,"about_ca_system_score_codex":0.005048309,"about_ca_system_score_gemma":0.0099876765,"threshold_uncertainty_score":0.05089611},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001221665,0.024392253,0.0016079209,0.47046167,0.17558536,0.00026775996,0.001469259,0.0010427881,0.3239514],"genre_scores_gemma":[0.027290387,0.01382294,0.0015867384,0.10366273,0.026847117,0.00030267378,0.0014150445,0.0010608326,0.82401156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98422575,0.002307353,0.00037132454,0.0014471187,0.009266472,0.0023819953],"domain_scores_gemma":[0.9316413,0.0018939616,0.00083419355,0.0032539743,0.014550827,0.04782581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015786612,0.0015147568,0.0014229307,0.0026633397,0.008872902,0.044079993,0.0020074674,0.005985222,0.16268541],"category_scores_gemma":[0.036272593,0.0005612543,0.00084543467,0.0022332177,0.006972084,0.012804361,0.013770787,0.0108018005,0.10372025],"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":[0.000020753443,0.00001864785,0.00020566142,0.00006340671,0.0000056728154,0.00002997264,0.00046836655,0.000017170965,0.000072995295,0.008494804,0.95802766,0.032574873],"study_design_scores_gemma":[0.000007374698,0.000015272892,0.00025518914,0.00010278852,0.0000037797683,0.000021962067,0.0009065819,0.000010916636,0.000025623765,0.0023542703,0.99628735,0.000008787906],"about_ca_topic_score_codex":0.025443755,"about_ca_topic_score_gemma":0.032695618,"teacher_disagreement_score":0.16268541,"about_ca_system_score_codex":0.014767553,"about_ca_system_score_gemma":0.03142339,"threshold_uncertainty_score":0.5442369},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32345223,0.16169827,0.3126026,0.05098722,0.0030856254,0.075379156,0.007989015,0.00070476544,0.064101174],"genre_scores_gemma":[0.6217084,0.013175326,0.3226069,0.006912503,0.000348633,0.031497624,0.0011829033,0.0002557475,0.0023119564],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.16845864,0.715949,0.050047148,0.010552319,0.051963728,0.0030291774],"domain_scores_gemma":[0.047426943,0.8350161,0.023593612,0.038650285,0.053947195,0.0013659578],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.74105644,0.0017801793,0.0030742546,0.0125734415,0.006469509,0.017934578,0.0068634627,0.0058920435,0.0025821247],"category_scores_gemma":[0.84780276,0.003112652,0.0053985217,0.008688564,0.007564769,0.011316992,0.016683757,0.0070485105,0.00054245995],"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":[0.007310497,0.0019414861,0.07493604,0.061760955,0.020591663,0.0003291569,0.099111885,0.0032534802,0.0050492366,0.035893407,0.009967591,0.6798546],"study_design_scores_gemma":[0.0040163025,0.011836641,0.13194185,0.3353165,0.049631976,0.0011942493,0.08329232,0.020614056,0.071657784,0.08751454,0.20113619,0.0018475279],"about_ca_topic_score_codex":0.013788139,"about_ca_topic_score_gemma":0.030176682,"teacher_disagreement_score":0.74105644,"about_ca_system_score_codex":0.018875664,"about_ca_system_score_gemma":0.052280784,"threshold_uncertainty_score":0.31932354},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96225387,0.00090805994,0.001565426,0.0069737546,0.00031353385,0.003137727,0.003273101,0.00013772387,0.02143677],"genre_scores_gemma":[0.99382174,0.00029698567,0.0014063625,0.00047478362,0.000032675696,0.00065202086,0.0010341571,0.000006675833,0.0022745896],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98857284,0.0021942265,0.00031170415,0.0003998328,0.003202896,0.0053185504],"domain_scores_gemma":[0.9760163,0.0032822746,0.002294452,0.00065285567,0.011122127,0.0066319965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010633482,0.00078669155,0.00062707183,0.0018606846,0.004591971,0.0023459864,0.002579358,0.0011168651,0.0028712186],"category_scores_gemma":[0.029198196,0.00030059688,0.0008391309,0.0017484972,0.0017483244,0.0012456516,0.0028113094,0.00265271,0.0003716073],"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":[0.008090071,0.010897979,0.5033848,0.0009536803,0.00085081,0.00032180647,0.008042573,0.016229736,0.0018090192,0.004519706,0.043680016,0.4012198],"study_design_scores_gemma":[0.0003342881,0.003104718,0.9657828,0.00042269425,0.00025468896,0.00002242812,0.010288123,0.0048084063,0.0016536324,0.0007487324,0.01245117,0.00012823785],"about_ca_topic_score_codex":0.9506689,"about_ca_topic_score_gemma":0.97457564,"teacher_disagreement_score":0.08621412,"about_ca_system_score_codex":0.08621412,"about_ca_system_score_gemma":0.17923708,"threshold_uncertainty_score":0.6255301},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46002522,0.0067880736,0.2753781,0.0655281,0.0010149473,0.0050306586,0.00020122009,0.0006199233,0.18541375],"genre_scores_gemma":[0.8424639,0.002167612,0.1483191,0.0018776327,0.00010831694,0.0013251704,0.00007493707,0.000083118575,0.0035800645],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86210513,0.112077594,0.0044123884,0.0061180983,0.011250973,0.0040358948],"domain_scores_gemma":[0.8289158,0.12181454,0.01000331,0.0149758225,0.016329363,0.007961226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0854036,0.00148697,0.0011508858,0.011150868,0.014039455,0.028458837,0.0045808605,0.0049106893,0.003508363],"category_scores_gemma":[0.10951145,0.0011635366,0.0014717572,0.004300717,0.02076856,0.018959075,0.0190328,0.006542577,0.0007384201],"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":[0.00006838446,0.0007329945,0.034959193,0.0013277873,0.00020344422,0.0011867945,0.6979085,0.00071853295,0.0013091493,0.034284215,0.003016428,0.2242846],"study_design_scores_gemma":[0.00006531969,0.00046053046,0.03657808,0.0036932814,0.0002940783,0.0014832338,0.8023328,0.0038094884,0.0015498351,0.06494641,0.08455243,0.00023444365],"about_ca_topic_score_codex":0.025039066,"about_ca_topic_score_gemma":0.04567552,"teacher_disagreement_score":0.0854036,"about_ca_system_score_codex":0.014048668,"about_ca_system_score_gemma":0.04463333,"threshold_uncertainty_score":0.45166278},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23725235,0.00044098604,0.48858842,0.009006384,0.0005438372,0.10424005,0.017560758,0.008401746,0.13396539],"genre_scores_gemma":[0.21954414,0.00027370904,0.720896,0.0005303046,0.000037291742,0.026302522,0.0072459723,0.00033959004,0.024830488],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99160016,0.0035597973,0.000893764,0.000732944,0.0022943493,0.0009189979],"domain_scores_gemma":[0.964656,0.0049918606,0.002378035,0.0021686382,0.022978304,0.0028272187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027637837,0.0009909596,0.0006680555,0.005115605,0.0031140596,0.0032662412,0.002346394,0.0010003614,0.01687442],"category_scores_gemma":[0.03140152,0.00080131966,0.00091837475,0.0021440845,0.00048763744,0.002842619,0.0031000152,0.0015276726,0.0033594843],"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":[0.0011302715,0.0030967223,0.14239235,0.000736011,0.00017195835,0.0008155754,0.003422027,0.035099182,0.007151201,0.012492229,0.08616829,0.70732415],"study_design_scores_gemma":[0.000945273,0.010929012,0.3838721,0.0026929118,0.0005651377,0.00069552514,0.037794862,0.23741582,0.046380885,0.01998961,0.25812864,0.00059023895],"about_ca_topic_score_codex":0.04811448,"about_ca_topic_score_gemma":0.10794279,"teacher_disagreement_score":0.04811448,"about_ca_system_score_codex":0.009257135,"about_ca_system_score_gemma":0.04299197,"threshold_uncertainty_score":0.1461646},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98467064,0.00015163221,0.010920232,0.000092835995,0.000058578295,0.00081948854,0.00017883857,0.000087027816,0.003020863],"genre_scores_gemma":[0.98586816,0.000089193076,0.011025667,0.00010073403,0.000030377225,0.0011482217,0.00027601374,0.000033488897,0.0014282902],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95206934,0.027684027,0.0061901296,0.0028989103,0.009965669,0.0011918293],"domain_scores_gemma":[0.69915926,0.21346234,0.02095737,0.017655289,0.047124173,0.001641634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.077737056,0.00069828756,0.0007735216,0.0013652568,0.00092315866,0.0014071454,0.0009820631,0.0010525204,0.0014681051],"category_scores_gemma":[0.17570345,0.0007524126,0.0011669769,0.0009875703,0.00096333254,0.0023487213,0.0014663676,0.0012252668,0.0007159799],"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":[0.0039301505,0.0039853784,0.83070123,0.00034126823,0.00040859924,0.0001176335,0.008302113,0.001202278,0.0048788805,0.00045022136,0.0007624196,0.14491972],"study_design_scores_gemma":[0.00025524534,0.012051608,0.95178246,0.00019097076,0.00032583266,0.00025174723,0.0030440886,0.0074071074,0.021298932,0.0007174875,0.0025788357,0.000095746494],"about_ca_topic_score_codex":0.0017350056,"about_ca_topic_score_gemma":0.0038109766,"teacher_disagreement_score":0.077737056,"about_ca_system_score_codex":0.0010032014,"about_ca_system_score_gemma":0.0017404974,"threshold_uncertainty_score":0.41111773},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936253,0.00011333267,0.0009891121,0.00025132566,0.000021714059,0.00091148564,0.00092719,0.000020514195,0.0031401122],"genre_scores_gemma":[0.9852669,0.00046293123,0.004200811,0.0008973091,0.000044837903,0.003933066,0.0022258037,0.000022070693,0.0029462962],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98687184,0.0076896534,0.0013675424,0.00054058625,0.0024090046,0.0011214585],"domain_scores_gemma":[0.93209565,0.042709477,0.0089432625,0.0020888015,0.012694851,0.0014680214],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023821188,0.00042656474,0.00046979147,0.0030851774,0.0022036175,0.0015227912,0.0006848736,0.0005948775,0.00076390494],"category_scores_gemma":[0.08258331,0.0005323229,0.00070282514,0.002839307,0.0014001229,0.0010355213,0.003048055,0.0015161104,0.00045316824],"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":[0.00047690544,0.0016838878,0.7271806,0.0002932128,0.00006966454,0.00028408915,0.21580191,0.00015866155,0.0009742018,0.00039699415,0.0026835734,0.049996324],"study_design_scores_gemma":[0.00010972432,0.0013469784,0.81346816,0.00015112138,0.00007082944,0.0002395825,0.17400844,0.00036195738,0.0010292215,0.00027972698,0.008868346,0.00006594271],"about_ca_topic_score_codex":0.046973485,"about_ca_topic_score_gemma":0.07373904,"teacher_disagreement_score":0.9761788,"about_ca_system_score_codex":0.0036284332,"about_ca_system_score_gemma":0.004734086,"threshold_uncertainty_score":0.12598002},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011303669,0.0085727135,0.009732161,0.8985923,0.0050343713,0.00009686953,0.000014295507,0.00011628069,0.06653729],"genre_scores_gemma":[0.7460185,0.00637482,0.0282598,0.18690795,0.0057032323,0.00033181757,0.000020501833,0.000559947,0.025823466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8077952,0.15205006,0.0032096219,0.0038737496,0.025387574,0.007683639],"domain_scores_gemma":[0.7225865,0.19285914,0.008611209,0.012989411,0.031533178,0.031420562],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20288971,0.00083768845,0.0013638657,0.0036540087,0.030951979,0.034882836,0.0033698573,0.012713026,0.007898909],"category_scores_gemma":[0.20618215,0.00091556803,0.00083801453,0.0022061823,0.09621005,0.02563544,0.027199326,0.03419904,0.0008567333],"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":[0.00017078596,0.00024140363,0.002012983,0.00079341244,0.000144006,0.00036704514,0.14290832,0.00044305835,0.0006248738,0.5803258,0.116099074,0.15586926],"study_design_scores_gemma":[0.00013526018,0.00018155218,0.0028237298,0.0030441668,0.00014907253,0.0004130247,0.088457406,0.0008538334,0.0011159221,0.3614156,0.5412124,0.0001981135],"about_ca_topic_score_codex":0.03746832,"about_ca_topic_score_gemma":0.12080796,"teacher_disagreement_score":0.20288971,"about_ca_system_score_codex":0.028442614,"about_ca_system_score_gemma":0.07181547,"threshold_uncertainty_score":0.9829789},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06614591,0.020524682,0.19444998,0.16429174,0.0011171341,0.00050491816,0.00015545345,0.00031080507,0.5524995],"genre_scores_gemma":[0.9308405,0.0056894403,0.040820207,0.01232349,0.000244786,0.00044115004,0.00006490639,0.00011276388,0.009462711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9801601,0.014165964,0.00065112,0.0010666891,0.0024172831,0.0015387615],"domain_scores_gemma":[0.96814805,0.021328434,0.0019888913,0.0019298426,0.0045112413,0.0020935482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025766736,0.0008074378,0.00061692717,0.0062123425,0.004324614,0.011685484,0.0025635348,0.00446967,0.0051899147],"category_scores_gemma":[0.02947758,0.00037806242,0.0008564236,0.0031663447,0.04693924,0.019488167,0.0062551806,0.00651124,0.0006193305],"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":[0.0000141636265,0.00004309234,0.0019477776,0.00013988893,0.000008733217,0.00008225521,0.017193593,0.0006698922,0.00011344617,0.96305424,0.0020397804,0.014693255],"study_design_scores_gemma":[0.00003355373,0.0001237302,0.005549936,0.0022140224,0.000034862383,0.00039442233,0.029177882,0.0051866444,0.00050913607,0.7863842,0.17030206,0.000089590256],"about_ca_topic_score_codex":0.02317343,"about_ca_topic_score_gemma":0.017417831,"teacher_disagreement_score":0.97423327,"about_ca_system_score_codex":0.012207822,"about_ca_system_score_gemma":0.017915733,"threshold_uncertainty_score":0.13626915},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005771068,0.06904334,0.0051694037,0.49662334,0.047356408,0.00021296862,0.0018431462,0.0016758406,0.37749848],"genre_scores_gemma":[0.0048448923,0.02478462,0.0038071454,0.035241496,0.0030387922,0.00012761979,0.0004916347,0.00042822497,0.92723554],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729484,0.0003873268,0.00011052076,0.0002853268,0.0017220215,0.00019980819],"domain_scores_gemma":[0.9867775,0.0019268172,0.0006355738,0.00031032308,0.0071090837,0.0032407385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049182405,0.0007720411,0.0004093134,0.0018844994,0.0024090689,0.00501148,0.0011535535,0.003194001,0.21097259],"category_scores_gemma":[0.014730925,0.0004543967,0.000339399,0.0010354394,0.0010142298,0.0020606597,0.0020438002,0.0030641218,0.13558045],"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":[0.0000056163717,0.000004911869,0.00006562169,0.000041196763,5.8823355e-7,0.000014906541,0.000031502783,0.000010170788,0.00003498642,0.001017239,0.96055406,0.038219165],"study_design_scores_gemma":[0.00000273229,0.0000041425055,0.00022495042,0.00016535821,0.0000015151404,0.000046132078,0.000091467824,0.000027576842,0.000053258358,0.0007837006,0.99859446,0.0000047068042],"about_ca_topic_score_codex":0.03528408,"about_ca_topic_score_gemma":0.11383477,"teacher_disagreement_score":0.21097259,"about_ca_system_score_codex":0.0029435782,"about_ca_system_score_gemma":0.014666342,"threshold_uncertainty_score":0.7057736},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006329949,0.881645,0.0055580046,0.06968524,0.009042106,0.000034982157,0.0009402979,0.00033023002,0.032131057],"genre_scores_gemma":[0.0049157985,0.9379292,0.0042087855,0.0024656653,0.00238978,0.000057075154,0.0008264421,0.00021005998,0.046997305],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982717,0.00040306264,0.00013657486,0.00018000703,0.00085789943,0.00015067843],"domain_scores_gemma":[0.99651897,0.0016519852,0.00040009816,0.000090711306,0.00083881174,0.00049947685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00428438,0.002093399,0.0012942188,0.0030633758,0.00068381935,0.004656281,0.0011389203,0.0025174555,0.02927123],"category_scores_gemma":[0.005615013,0.00096385635,0.0005638868,0.0043357424,0.0011913106,0.005678961,0.0017524577,0.0026055523,0.028853627],"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":[0.00003231346,0.000012725121,0.0002820885,0.0005403519,0.000010689253,0.000033779157,0.000099630466,0.00025830782,0.00006547855,0.0036088158,0.70587313,0.28918278],"study_design_scores_gemma":[0.000010254008,0.000010886621,0.0010128699,0.0014782009,0.00002577105,0.0001364778,0.0002639036,0.0003638315,0.00022722116,0.004236377,0.99221295,0.000021235312],"about_ca_topic_score_codex":0.032824017,"about_ca_topic_score_gemma":0.068855554,"teacher_disagreement_score":0.032824017,"about_ca_system_score_codex":0.0034385677,"about_ca_system_score_gemma":0.008445871,"threshold_uncertainty_score":0},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12771551,0.003181993,0.25991455,0.22004232,0.0023368266,0.0045655537,0.00048457473,0.005309656,0.37644908],"genre_scores_gemma":[0.45205992,0.0027596396,0.47591445,0.014444303,0.0005224096,0.0017926791,0.00072550523,0.00087335677,0.050907712],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97755903,0.015379541,0.000502741,0.00085723883,0.0036180427,0.0020834252],"domain_scores_gemma":[0.92873055,0.03701036,0.0015020637,0.006025978,0.007265002,0.019466124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051616725,0.0007639679,0.00048751058,0.0021495833,0.006810698,0.011186235,0.004356618,0.0025447384,0.009014778],"category_scores_gemma":[0.04871233,0.0004864262,0.0005985584,0.0014481139,0.0114187915,0.0066231624,0.018558946,0.005902904,0.002013147],"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":[0.00018325774,0.0034610035,0.0051214704,0.00059561647,0.00003605642,0.0007314919,0.043614473,0.0017924535,0.0021327466,0.0681294,0.120068155,0.75413394],"study_design_scores_gemma":[0.00027287204,0.0010361095,0.007920133,0.0024408838,0.000052445514,0.0007759136,0.07232662,0.0067688297,0.0055871857,0.11923619,0.7833171,0.00026577222],"about_ca_topic_score_codex":0.021559758,"about_ca_topic_score_gemma":0.09229816,"teacher_disagreement_score":0.051616725,"about_ca_system_score_codex":0.010022248,"about_ca_system_score_gemma":0.037131857,"threshold_uncertainty_score":0.2729786},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25755304,0.0006591489,0.5581634,0.014281086,0.00067085365,0.09211191,0.0003906835,0.0014071603,0.07476268],"genre_scores_gemma":[0.22218822,0.00045419656,0.73954827,0.0008105942,0.00006756363,0.027211696,0.00022589958,0.000081423714,0.009412191],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9827574,0.012136254,0.0006178157,0.00083791954,0.002358785,0.0012917059],"domain_scores_gemma":[0.97331595,0.012131163,0.0013954521,0.001745312,0.0057857656,0.005626409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048630133,0.0005862885,0.0004519549,0.0019831792,0.004055655,0.003362257,0.003279817,0.001189728,0.0038707],"category_scores_gemma":[0.032046735,0.00048115067,0.00047547414,0.0015200647,0.0020418358,0.001830257,0.0062394673,0.0024922856,0.00065542985],"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":[0.00021347946,0.0136443395,0.0060508233,0.0014971398,0.000035293295,0.00044719572,0.027431112,0.010095748,0.006682014,0.028414812,0.01856223,0.8869259],"study_design_scores_gemma":[0.0020045023,0.014097571,0.036973305,0.0063636275,0.00019615938,0.0011994547,0.09436358,0.049067732,0.036080852,0.07577614,0.68349034,0.00038686825],"about_ca_topic_score_codex":0.0030500104,"about_ca_topic_score_gemma":0.0068719904,"teacher_disagreement_score":0.048630133,"about_ca_system_score_codex":0.0075842002,"about_ca_system_score_gemma":0.041008055,"threshold_uncertainty_score":0.2571838},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00503366,0.2774172,0.22550593,0.42705095,0.014845936,0.00062068994,0.00020309247,0.00044881596,0.04887371],"genre_scores_gemma":[0.14956503,0.34798592,0.38132223,0.092614904,0.01025962,0.0025385043,0.00028066392,0.0011694655,0.014263591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7291032,0.19784197,0.020256942,0.010642719,0.039835233,0.0023199592],"domain_scores_gemma":[0.44598296,0.44122025,0.01023254,0.030342268,0.067476355,0.0047455416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30023992,0.0016037204,0.0033427814,0.010289632,0.0060179657,0.023763029,0.006758878,0.01438147,0.0030016503],"category_scores_gemma":[0.2507205,0.0024672437,0.0021249612,0.017749256,0.03490743,0.03573415,0.012350663,0.020360379,0.002289358],"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":[0.0001392231,0.00014504677,0.0025302721,0.004032015,0.00011671775,0.00036692785,0.017305864,0.0027695836,0.00027478195,0.41000316,0.0741525,0.48816392],"study_design_scores_gemma":[0.000044007073,0.000091893984,0.001053423,0.015425316,0.00008357576,0.0005706418,0.006682848,0.0034664304,0.00049398403,0.13010608,0.84176826,0.00021352507],"about_ca_topic_score_codex":0.02274985,"about_ca_topic_score_gemma":0.023731139,"teacher_disagreement_score":0.30023992,"about_ca_system_score_codex":0.024763832,"about_ca_system_score_gemma":0.028807197,"threshold_uncertainty_score":0.86292875},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023230925,0.67721105,0.004967244,0.232201,0.029362861,0.000052204392,0.0008826858,0.0003260339,0.054764524],"genre_scores_gemma":[0.004352564,0.79683447,0.007989452,0.021183936,0.011143982,0.00012692543,0.0008400927,0.00044874474,0.15707986],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995765,0.0010762672,0.0003213179,0.00029411472,0.0023361177,0.00020718202],"domain_scores_gemma":[0.98700434,0.0062310006,0.0009255966,0.00034287162,0.003997851,0.0014982801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008763719,0.0020250732,0.0014498159,0.0025296912,0.0016762513,0.0072230836,0.0016925008,0.005513163,0.04374592],"category_scores_gemma":[0.015186624,0.0012228779,0.00084882986,0.0039214245,0.0024221232,0.0061338954,0.0024726642,0.0060855467,0.0462999],"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":[0.000012463754,0.0000072829575,0.00009656742,0.0002836672,0.0000053063877,0.000029018503,0.0000954532,0.000094327195,0.000034354794,0.0026280882,0.879915,0.1167984],"study_design_scores_gemma":[0.0000066403095,0.000007120005,0.00032854962,0.0016730923,0.000011176606,0.000118207616,0.0002523552,0.00015845738,0.00010464378,0.005253489,0.9920684,0.000017927436],"about_ca_topic_score_codex":0.043770935,"about_ca_topic_score_gemma":0.12042789,"teacher_disagreement_score":0.043770935,"about_ca_system_score_codex":0.004791787,"about_ca_system_score_gemma":0.018513247,"threshold_uncertainty_score":0.1463446},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010011447,0.74044997,0.00071640935,0.14175227,0.09835622,0.00026269557,0.00026418277,0.00006424716,0.018033916],"genre_scores_gemma":[0.0026296577,0.80575776,0.0015709181,0.098989874,0.06479497,0.00078866904,0.00035999282,0.00010690753,0.025001232],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798956,0.009790711,0.0015761484,0.0010442882,0.0071694134,0.0005238094],"domain_scores_gemma":[0.8685938,0.10393359,0.005002861,0.0015121903,0.019239927,0.0017177084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012246823,0.0017230462,0.003013502,0.006110852,0.0019451336,0.011444765,0.003307348,0.009930486,0.020036612],"category_scores_gemma":[0.08859364,0.0011100644,0.0017890502,0.008729793,0.004203593,0.0064840596,0.002433288,0.009020424,0.008775885],"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":[0.000017308143,0.000013963008,0.000033754004,0.004749216,0.000026120711,0.000025460473,0.000108072476,0.00011964745,0.000019753403,0.003234267,0.9561863,0.035466157],"study_design_scores_gemma":[0.000035064186,0.0000317278,0.00026454878,0.02130105,0.00004187283,0.00015198106,0.00013779826,0.000076111115,0.000037746493,0.0041282116,0.97376674,0.00002718371],"about_ca_topic_score_codex":0.009165893,"about_ca_topic_score_gemma":0.017892467,"teacher_disagreement_score":0.020036612,"about_ca_system_score_codex":0.012007848,"about_ca_system_score_gemma":0.019826882,"threshold_uncertainty_score":0.08712345},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028196706,0.0045823087,0.051899053,0.015472486,0.0009585577,0.0001557508,0.00003176318,0.00038848422,0.92369205],"genre_scores_gemma":[0.13103619,0.010220095,0.10588331,0.0063922913,0.0006678014,0.0005205768,0.00017260807,0.0006090037,0.74449813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99533683,0.0026442944,0.00010837878,0.0003147949,0.0013526595,0.0002430974],"domain_scores_gemma":[0.9955818,0.002755632,0.00017515245,0.00064281357,0.00050954014,0.00033502968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061340034,0.00069447025,0.00039782835,0.000780411,0.001762498,0.009419999,0.0015707413,0.0033117128,0.0270417],"category_scores_gemma":[0.008804723,0.0003820023,0.00023039093,0.0014452884,0.0061671156,0.011339679,0.0050278725,0.003403012,0.010175529],"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":[0.000015058417,0.00010407594,0.00022509557,0.00033749526,0.000006159392,0.0001448837,0.008438283,0.0005776436,0.0007977713,0.49612457,0.10009736,0.39313152],"study_design_scores_gemma":[0.0000073549563,0.00002704173,0.0004535512,0.00070000044,0.0000046581167,0.00016770628,0.004154574,0.00060334516,0.00079591566,0.20552607,0.7875454,0.0000143963525],"about_ca_topic_score_codex":0.0023724264,"about_ca_topic_score_gemma":0.004442528,"teacher_disagreement_score":0.0270417,"about_ca_system_score_codex":0.0027971286,"about_ca_system_score_gemma":0.006617427,"threshold_uncertainty_score":0.09046352},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9153122,0.0023215006,0.0062834006,0.021978667,0.0000872026,0.0001714136,0.00019124338,0.00014954852,0.05350494],"genre_scores_gemma":[0.99601185,0.00025391686,0.0013282549,0.0006463792,0.000022101056,0.00004502814,0.00003485207,0.00001777325,0.0016399828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.96806705,0.01900629,0.0022200951,0.0020568066,0.004553522,0.0040961457],"domain_scores_gemma":[0.9503773,0.032712083,0.0073811663,0.0032082768,0.0039656605,0.0023555318],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.036079943,0.00032228004,0.00060592557,0.005303213,0.0047384487,0.013076452,0.0011547441,0.0020535637,0.0030327255],"category_scores_gemma":[0.04835791,0.00043066626,0.0003380223,0.0066244584,0.009783105,0.005135193,0.0107145775,0.0017889309,0.00028486783],"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":[0.0007575322,0.00029924998,0.16397673,0.0013644873,0.00022674799,0.0029108468,0.12068795,0.008028686,0.005331684,0.43941393,0.0066982554,0.25030395],"study_design_scores_gemma":[0.00021348722,0.00061788893,0.4094728,0.0020613,0.00020577166,0.0008834836,0.121979795,0.009887506,0.014505561,0.19213432,0.24768238,0.00035568635],"about_ca_topic_score_codex":0.009321943,"about_ca_topic_score_gemma":0.009400064,"teacher_disagreement_score":0.96392006,"about_ca_system_score_codex":0.017358625,"about_ca_system_score_gemma":0.022153983,"threshold_uncertainty_score":0.19081128},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17334716,0.008071651,0.014787451,0.031945966,0.00042040015,0.0001563646,0.00012469028,0.000105998115,0.7710403],"genre_scores_gemma":[0.9747372,0.0015085962,0.0017286775,0.001425452,0.00015768672,0.00008250441,0.00004589107,0.000027278487,0.020286707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968362,0.0013085074,0.00009509789,0.00041742713,0.0008423499,0.00050041504],"domain_scores_gemma":[0.9957171,0.0012995021,0.00045051728,0.00021686364,0.0005087582,0.0018073065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043250863,0.00022859646,0.00022028791,0.0014805187,0.0015313472,0.007786845,0.00052992784,0.0007235411,0.005654774],"category_scores_gemma":[0.009916685,0.00011197177,0.00009558476,0.00088456884,0.010709907,0.0025028226,0.0028188415,0.0015000348,0.00039788848],"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":[0.00004376062,0.00016871507,0.012190435,0.00006914412,0.000014904217,0.00007875658,0.006633285,0.0005667038,0.000281901,0.881177,0.005043356,0.093732044],"study_design_scores_gemma":[0.00008039842,0.00022678249,0.055021558,0.00052412855,0.000021767142,0.00015477941,0.0075232876,0.0017508782,0.00048350607,0.7603439,0.17381531,0.00005367291],"about_ca_topic_score_codex":0.012184292,"about_ca_topic_score_gemma":0.008616839,"teacher_disagreement_score":0.012184292,"about_ca_system_score_codex":0.0048237573,"about_ca_system_score_gemma":0.0059647937,"threshold_uncertainty_score":0.034999013},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34634408,0.012145333,0.00192221,0.48592192,0.0031389783,0.00035913973,0.0021261775,0.00024106006,0.14780125],"genre_scores_gemma":[0.9087648,0.0054286686,0.0023103468,0.027362833,0.00045572678,0.00011599357,0.00075528974,0.00022166123,0.05458462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9722102,0.004736922,0.0009179545,0.0015426774,0.011008182,0.009584093],"domain_scores_gemma":[0.85176486,0.01733788,0.0029843547,0.0018361404,0.06836364,0.057713244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018591074,0.00043835677,0.0009541738,0.0052298065,0.02777068,0.0143646905,0.002790473,0.0036894178,0.0155755365],"category_scores_gemma":[0.043856543,0.0007357292,0.00089485047,0.008849743,0.007835889,0.00365425,0.0071625686,0.0073107365,0.0008924059],"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":[0.000755782,0.00078229775,0.12639198,0.000686782,0.0002435592,0.001359365,0.05747433,0.0018767279,0.0011350145,0.100567654,0.355907,0.35281962],"study_design_scores_gemma":[0.00011990687,0.00019202672,0.34791446,0.0012500949,0.000085588305,0.00012098903,0.08228291,0.0014845965,0.0006158868,0.009821582,0.55582803,0.00028400624],"about_ca_topic_score_codex":0.99776256,"about_ca_topic_score_gemma":0.99880195,"teacher_disagreement_score":0.31820804,"about_ca_system_score_codex":0.31820804,"about_ca_system_score_gemma":0.6195173,"threshold_uncertainty_score":0.79078203},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005131492,0.1118925,0.0012241866,0.68635666,0.19877104,0.000044197343,0.000070048394,0.000034331555,0.0010938765],"genre_scores_gemma":[0.029792586,0.29711342,0.008518989,0.3002792,0.3403533,0.00042968115,0.0001680813,0.00018728501,0.023157476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99052864,0.0047098156,0.0012739967,0.00057741185,0.0026628003,0.00024734216],"domain_scores_gemma":[0.9325866,0.04085597,0.002855929,0.00087884115,0.02059147,0.0022312438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029177777,0.0008743131,0.0010660269,0.0026923877,0.0022819627,0.0065362174,0.00270323,0.005396164,0.0020219656],"category_scores_gemma":[0.078256026,0.0006196715,0.0007114917,0.0022069728,0.006756961,0.0034044178,0.0022785857,0.007832294,0.00063170807],"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":[0.000055075987,0.000020323328,0.0007618647,0.0010112433,0.000031263808,0.0002729502,0.0019446076,0.000090088164,0.000100405196,0.0019378864,0.91001505,0.0837592],"study_design_scores_gemma":[0.000042757547,0.000044269407,0.0035279172,0.0038091675,0.00006789966,0.00047998267,0.0036112487,0.00031254612,0.00037144133,0.0049471534,0.9827146,0.00007105509],"about_ca_topic_score_codex":0.07636054,"about_ca_topic_score_gemma":0.27832615,"teacher_disagreement_score":0.9236395,"about_ca_system_score_codex":0.0070832563,"about_ca_system_score_gemma":0.014292081,"threshold_uncertainty_score":0.15430862},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00100476,0.90039206,0.019171713,0.029368574,0.0044870283,0.00023155236,0.0012835399,0.00041395793,0.043646913],"genre_scores_gemma":[0.0232234,0.79635096,0.04556148,0.005506243,0.0022787347,0.00049814786,0.0010479635,0.0003809448,0.12515217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978377,0.00056564994,0.0003291305,0.00014448697,0.001026184,0.0000968084],"domain_scores_gemma":[0.99049664,0.005533689,0.00070324045,0.0004223203,0.0024726496,0.00037143726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075655854,0.0020499406,0.0011433145,0.0051072994,0.00180068,0.0046817493,0.0021617848,0.00419786,0.045197748],"category_scores_gemma":[0.01722669,0.0016306319,0.0006061716,0.0047831764,0.0038220084,0.009835649,0.0017709909,0.0035098086,0.023723738],"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":[0.000027493472,0.00002570597,0.00040132343,0.001218898,0.00001284113,0.00008202409,0.00086719263,0.00017228546,0.000314974,0.0061711427,0.48658377,0.5041224],"study_design_scores_gemma":[0.000010618836,0.000047731042,0.0026477599,0.0042655035,0.000021711649,0.0005211646,0.00067183137,0.00012284321,0.0006080734,0.015621882,0.9754292,0.00003165383],"about_ca_topic_score_codex":0.026224447,"about_ca_topic_score_gemma":0.065725386,"teacher_disagreement_score":0.045197748,"about_ca_system_score_codex":0.0032874814,"about_ca_system_score_gemma":0.0048097637,"threshold_uncertainty_score":0.15120155},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7473263,0.00051290286,0.008475789,0.005732009,0.0005259117,0.037068754,0.0023828077,0.0004171868,0.19755839],"genre_scores_gemma":[0.91351986,0.0004576236,0.026408693,0.001320097,0.00015679841,0.023365248,0.0014622526,0.00010043255,0.0332091],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96614957,0.01733922,0.00086344226,0.0012134794,0.01188884,0.0025454222],"domain_scores_gemma":[0.96009475,0.015134819,0.0016840417,0.0017870568,0.013625079,0.0076742694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033271533,0.0006283832,0.0005053354,0.0020109506,0.0052871937,0.0025577254,0.0015652991,0.0010366496,0.01469489],"category_scores_gemma":[0.034747098,0.00032022165,0.0005646486,0.0018168273,0.0027042339,0.0014140354,0.0036333655,0.0018648604,0.0010294346],"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":[0.01191054,0.05013871,0.04755364,0.00439563,0.0003880249,0.00084946636,0.053426854,0.010401822,0.008254869,0.023492878,0.057602134,0.73158544],"study_design_scores_gemma":[0.009517056,0.06403426,0.3802653,0.004091102,0.0006458844,0.00029728463,0.10192907,0.009173993,0.035733823,0.012321885,0.38138252,0.0006078405],"about_ca_topic_score_codex":0.053805776,"about_ca_topic_score_gemma":0.12441629,"teacher_disagreement_score":0.053805776,"about_ca_system_score_codex":0.018683022,"about_ca_system_score_gemma":0.030564077,"threshold_uncertainty_score":0.17595881},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9114542,0.0010935483,0.0009067865,0.0011990999,0.00003069902,0.00057710195,0.07979376,0.000050247694,0.004894505],"genre_scores_gemma":[0.9197429,0.0019997526,0.0028111977,0.00055719283,0.000018369907,0.00081155903,0.065289974,0.00005011186,0.008718826],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9961094,0.00040963502,0.00035622664,0.00042195845,0.0014313281,0.0012713771],"domain_scores_gemma":[0.9859583,0.0017392111,0.0026736774,0.00077088684,0.007203775,0.0016541557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030740702,0.000579094,0.0007285852,0.005773151,0.004931282,0.0030528186,0.0031731292,0.00073676126,0.0026989228],"category_scores_gemma":[0.008849894,0.0007157974,0.0009695363,0.019014323,0.001252582,0.00072010956,0.0027450323,0.0014253849,0.0006149087],"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":[0.00008454851,0.00006648533,0.98404515,0.00012858647,0.00010598065,0.00016176279,0.0021211007,0.0008180055,0.00011434068,0.0004939395,0.004143235,0.00771687],"study_design_scores_gemma":[0.000016217791,0.000021217527,0.98289055,0.0001567911,0.00004786955,0.000035738278,0.008207388,0.0017306412,0.000108913664,0.00006548029,0.006686217,0.000033107648],"about_ca_topic_score_codex":0.99913067,"about_ca_topic_score_gemma":0.999479,"teacher_disagreement_score":0.07403027,"about_ca_system_score_codex":0.07403027,"about_ca_system_score_gemma":0.1204735,"threshold_uncertainty_score":0.53712976},"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":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14582984,0.018428361,0.22524184,0.35702422,0.004219852,0.04443619,0.014333545,0.0030524647,0.18743369],"genre_scores_gemma":[0.42294872,0.0068810345,0.51413554,0.017984208,0.0005188913,0.025785886,0.004692256,0.0008865585,0.0061669312],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.3498274,0.51837516,0.023724617,0.008179787,0.083366096,0.016526911],"domain_scores_gemma":[0.24588782,0.42228913,0.013514996,0.069430925,0.2293768,0.01950034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.57735384,0.001848075,0.0024563335,0.009376609,0.017324138,0.030634122,0.009845239,0.0040495563,0.0043558446],"category_scores_gemma":[0.5375974,0.0016565867,0.003129333,0.017365409,0.016245933,0.018108698,0.0270868,0.009000017,0.0007915756],"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":[0.0023259064,0.0024164354,0.048126183,0.0096031865,0.0021051536,0.0008593508,0.12784582,0.011307359,0.0020186012,0.13527767,0.08367932,0.57443494],"study_design_scores_gemma":[0.003313029,0.0035405988,0.08916482,0.043491133,0.0024300471,0.00035737417,0.14187166,0.020628346,0.008047517,0.13572527,0.5501188,0.001311404],"about_ca_topic_score_codex":0.79530287,"about_ca_topic_score_gemma":0.86288035,"teacher_disagreement_score":0.57735384,"about_ca_system_score_codex":0.16396216,"about_ca_system_score_gemma":0.40916675,"threshold_uncertainty_score":0.9696854},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040722705,0.008073819,0.0043782284,0.8857409,0.08956393,0.000060785856,0.0000817499,0.00023105278,0.0114623755],"genre_scores_gemma":[0.026522322,0.0300679,0.033894002,0.70518214,0.11564337,0.00045889846,0.00035159942,0.0011544487,0.08672535],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96822023,0.010661214,0.004042515,0.002483835,0.011263096,0.003329079],"domain_scores_gemma":[0.8853421,0.018961236,0.003775093,0.0041846125,0.054030217,0.033706676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027234929,0.0012046392,0.001690095,0.0028987648,0.008954167,0.023177927,0.0050614965,0.01832804,0.01583216],"category_scores_gemma":[0.080784924,0.0007450446,0.0015437779,0.004760095,0.015979098,0.018497571,0.009882934,0.04475452,0.00999796],"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":[0.000024983132,0.00003591291,0.00025560532,0.00017123536,0.00001003457,0.00016258268,0.0006776437,0.00007374784,0.00018261837,0.021195563,0.9314285,0.045781616],"study_design_scores_gemma":[0.000016383505,0.00004892741,0.0004924752,0.00044388082,0.000008409659,0.00041162854,0.0010999475,0.00016595174,0.000098934725,0.009447408,0.98770905,0.000056882127],"about_ca_topic_score_codex":0.017823545,"about_ca_topic_score_gemma":0.028457824,"teacher_disagreement_score":0.027234929,"about_ca_system_score_codex":0.012551962,"about_ca_system_score_gemma":0.049225926,"threshold_uncertainty_score":0.14403379},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7939222,0.0088151125,0.065842465,0.020831866,0.0016789522,0.0024504105,0.00038663216,0.00040288133,0.105669424],"genre_scores_gemma":[0.953278,0.0023956776,0.025074111,0.00171524,0.0002001863,0.0026275888,0.00014405533,0.0001294949,0.014435507],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.85213727,0.11377536,0.0059251804,0.0038569714,0.020915324,0.003389839],"domain_scores_gemma":[0.7224395,0.1867267,0.020383561,0.013998083,0.04842825,0.008023871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14724055,0.00084574334,0.0012332357,0.0040287185,0.0059071365,0.013067076,0.0019554445,0.0017655098,0.0086093955],"category_scores_gemma":[0.25104052,0.0007125041,0.0011715702,0.0029020705,0.0070582987,0.007855658,0.007567899,0.0041597267,0.0014530947],"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":[0.0009556984,0.00097539724,0.07940477,0.0025937853,0.00024781685,0.00022446345,0.35236287,0.0005707612,0.002217017,0.026812296,0.008644567,0.5249905],"study_design_scores_gemma":[0.000527435,0.0043196944,0.33190617,0.012941298,0.000553327,0.00063424825,0.3776432,0.003139288,0.010347856,0.03674438,0.2205976,0.0006454751],"about_ca_topic_score_codex":0.014428494,"about_ca_topic_score_gemma":0.019803166,"teacher_disagreement_score":0.14724055,"about_ca_system_score_codex":0.012954183,"about_ca_system_score_gemma":0.024536768,"threshold_uncertainty_score":0.77869177},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056386914,0.7715507,0.010105082,0.15073076,0.00564232,0.000139277,0.0006571669,0.00013380147,0.060477],"genre_scores_gemma":[0.024850491,0.8110858,0.033836056,0.02917871,0.0010256071,0.0002959568,0.00057037565,0.00027703794,0.09887999],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927402,0.0014201447,0.00043805837,0.00044674857,0.004466248,0.0004884772],"domain_scores_gemma":[0.9852829,0.007202377,0.00090121024,0.00028474937,0.0052266503,0.0011021608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008629056,0.001323589,0.0010145289,0.004238402,0.0057824804,0.0110855345,0.0029287487,0.005383485,0.008896546],"category_scores_gemma":[0.017023265,0.0014737359,0.0006907208,0.009645534,0.012701796,0.008690951,0.0029176902,0.0075105103,0.0036740324],"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":[0.000021336271,0.000011414601,0.0008257139,0.0016535807,0.000020420619,0.00011821462,0.005055625,0.0002666902,0.00019603824,0.05723777,0.68832576,0.24626747],"study_design_scores_gemma":[0.000007955824,0.000007962048,0.0020138728,0.0024749145,0.000019009572,0.00014644818,0.0019056104,0.00010430825,0.00015847076,0.019687677,0.9734291,0.00004463624],"about_ca_topic_score_codex":0.7172932,"about_ca_topic_score_gemma":0.8755735,"teacher_disagreement_score":0.9597691,"about_ca_system_score_codex":0.040230855,"about_ca_system_score_gemma":0.0854474,"threshold_uncertainty_score":0.5687434},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059851386,0.0016306251,0.889499,0.010552539,0.0002862195,0.007957001,0.0011262472,0.0020732556,0.02702382],"genre_scores_gemma":[0.10852221,0.00085677695,0.88249964,0.00040847185,0.000029882758,0.004527691,0.00074690016,0.00018405642,0.0022243978],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9178982,0.054360032,0.010761471,0.0056510568,0.010239805,0.0010895367],"domain_scores_gemma":[0.82150626,0.12780263,0.009744803,0.010876526,0.028817069,0.0012527505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07772031,0.0014981506,0.0014359888,0.015747638,0.004798846,0.0107824765,0.0033182714,0.0025458508,0.0028549754],"category_scores_gemma":[0.1525188,0.0018464801,0.0018364219,0.010930634,0.009136608,0.02560909,0.011460761,0.0026841469,0.001124051],"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":[0.00019942033,0.00013987353,0.011503724,0.0056899413,0.00012691242,0.0007653149,0.38610741,0.0023006801,0.0054378393,0.1050211,0.0071078334,0.4756],"study_design_scores_gemma":[0.00024083612,0.00077280187,0.013936234,0.015559629,0.00054509536,0.0018011398,0.30615154,0.03885729,0.016333878,0.26862806,0.3367162,0.0004573214],"about_ca_topic_score_codex":0.007016724,"about_ca_topic_score_gemma":0.008556057,"teacher_disagreement_score":0.07772031,"about_ca_system_score_codex":0.0068522,"about_ca_system_score_gemma":0.019497657,"threshold_uncertainty_score":0.41102916},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002765958,0.45801756,0.003691223,0.3739178,0.14407231,0.0006786612,0.0011200879,0.00017421567,0.018051613],"genre_scores_gemma":[0.0074040145,0.74705493,0.006316731,0.11697569,0.08822676,0.0012599915,0.0022701933,0.00030229418,0.030189456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9669052,0.015230329,0.0039782245,0.0014728145,0.0117948605,0.00061867817],"domain_scores_gemma":[0.82397306,0.09442708,0.009616725,0.0039857873,0.064276546,0.0037207184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033262756,0.0013434336,0.0035868015,0.010311307,0.0022015152,0.008414513,0.004400625,0.0077426936,0.027551817],"category_scores_gemma":[0.16042773,0.0008516691,0.0016883701,0.011237968,0.005325179,0.00828521,0.0041888305,0.0052578812,0.013652475],"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":[0.00003779217,0.000013865623,0.0000618392,0.018345209,0.000065416825,0.00005546213,0.00017938428,0.00012129046,0.00012255926,0.009532141,0.87435114,0.0971139],"study_design_scores_gemma":[0.000020951098,0.000018281436,0.0003796613,0.025232997,0.00009405808,0.00011302846,0.00015730267,0.00012685767,0.00009560453,0.0061646686,0.9675688,0.000027659775],"about_ca_topic_score_codex":0.0052475315,"about_ca_topic_score_gemma":0.012947338,"teacher_disagreement_score":0.033262756,"about_ca_system_score_codex":0.008947108,"about_ca_system_score_gemma":0.03976953,"threshold_uncertainty_score":0.17591238},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62432384,0.0015359995,0.026708454,0.061082512,0.0008263148,0.005725728,0.0003626584,0.0004911574,0.27894327],"genre_scores_gemma":[0.94761634,0.00047665747,0.034817252,0.0021537468,0.000049874656,0.00077481446,0.00012024934,0.000054842872,0.013936138],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97767115,0.012376045,0.00035409792,0.00088327867,0.0044277273,0.004287722],"domain_scores_gemma":[0.9470644,0.008584857,0.0021969005,0.003428329,0.007939308,0.030786267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03082205,0.0003476254,0.0004238587,0.0029510274,0.025786463,0.015948446,0.0027665275,0.0015270596,0.008253714],"category_scores_gemma":[0.026299128,0.0004142689,0.0005097412,0.0019486053,0.0124339275,0.0056612883,0.025216801,0.0025317182,0.0008310922],"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":[0.00029879026,0.002559092,0.06349776,0.0006408233,0.000083817176,0.0012255377,0.1936881,0.0014785063,0.0025581843,0.12614411,0.061877903,0.5459475],"study_design_scores_gemma":[0.00027546773,0.0010891065,0.056305163,0.0016089879,0.00006974447,0.00044030158,0.39831215,0.0027710504,0.0017376556,0.033687968,0.5035296,0.00017276085],"about_ca_topic_score_codex":0.27951944,"about_ca_topic_score_gemma":0.6312812,"teacher_disagreement_score":0.27951944,"about_ca_system_score_codex":0.036610994,"about_ca_system_score_gemma":0.1969186,"threshold_uncertainty_score":0.55578494},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08471866,0.0067173294,0.041690182,0.40355232,0.005762599,0.0013881017,0.000092607515,0.0006947763,0.45538336],"genre_scores_gemma":[0.70480335,0.0073703015,0.09053561,0.049287036,0.0015581656,0.0008951864,0.00016908269,0.00035075916,0.14503054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97914255,0.009448569,0.0006110335,0.001209411,0.0073272367,0.0022611865],"domain_scores_gemma":[0.96359766,0.0064687813,0.0027486421,0.003071681,0.007542917,0.016570311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020220077,0.0003920569,0.00032452805,0.0012964545,0.0099032195,0.010931356,0.0019077921,0.0024696928,0.008507715],"category_scores_gemma":[0.039956238,0.00042759965,0.00045228912,0.0007388326,0.0220918,0.0040694247,0.008030498,0.0056019532,0.0032499107],"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":[0.00007183986,0.00039970112,0.008896982,0.0005847927,0.000049009363,0.0010203699,0.2118642,0.00043262282,0.0023569977,0.12315939,0.31608918,0.33507496],"study_design_scores_gemma":[0.00004209104,0.00012304376,0.0071779354,0.00063271134,0.000011841543,0.00045594826,0.04157164,0.00020735113,0.00045702924,0.03950248,0.9097625,0.00005549832],"about_ca_topic_score_codex":0.04306722,"about_ca_topic_score_gemma":0.108223625,"teacher_disagreement_score":0.04306722,"about_ca_system_score_codex":0.015366237,"about_ca_system_score_gemma":0.07691942,"threshold_uncertainty_score":0.11149037},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011700655,0.0062366785,0.12771139,0.024729112,0.0017588866,0.0016470735,0.0004901702,0.0012837886,0.8244422],"genre_scores_gemma":[0.51256585,0.00927129,0.20065159,0.010759897,0.0014310433,0.0033245715,0.0015250223,0.0011169619,0.25935382],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9701923,0.014622373,0.0019831418,0.0044955253,0.006680821,0.0020257523],"domain_scores_gemma":[0.97148657,0.010319139,0.0028212478,0.005160018,0.005776174,0.00443685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012422539,0.0010824832,0.0010056722,0.004798397,0.0075952914,0.016917776,0.0045355223,0.006631962,0.044120476],"category_scores_gemma":[0.036757942,0.00067239255,0.0012561699,0.003445981,0.015123126,0.012883125,0.017389331,0.0038418213,0.014750925],"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":[0.00004937468,0.00011209053,0.0020160975,0.0008814475,0.000040863037,0.00066203676,0.022145487,0.00074235775,0.0008352599,0.79849243,0.050466374,0.123556115],"study_design_scores_gemma":[0.00002020593,0.000036311823,0.0004262979,0.0008295577,0.0000116569045,0.00050698995,0.005843463,0.0005860861,0.00020445524,0.18639542,0.8051101,0.000029416],"about_ca_topic_score_codex":0.0032584297,"about_ca_topic_score_gemma":0.0031070672,"teacher_disagreement_score":0.044120476,"about_ca_system_score_codex":0.0054099346,"about_ca_system_score_gemma":0.015064603,"threshold_uncertainty_score":0.14759767},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4074558,0.025621513,0.081559,0.13322432,0.0019141163,0.00043448946,0.0003861838,0.0010180173,0.34838656],"genre_scores_gemma":[0.94344443,0.003773615,0.03361622,0.0026858228,0.00023750463,0.00019299104,0.00015990717,0.00024791955,0.015641654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95387936,0.029982772,0.0023553786,0.0012090662,0.011284354,0.0012889741],"domain_scores_gemma":[0.9070606,0.06547419,0.0026566195,0.0017769284,0.018993992,0.004037634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.077367924,0.0005009429,0.00061227236,0.004410861,0.0022859874,0.016617035,0.001821464,0.001524925,0.003604699],"category_scores_gemma":[0.09136476,0.00035255318,0.0004501175,0.005389468,0.0042544357,0.010579115,0.004806396,0.0033963104,0.00065169047],"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":[0.00014938177,0.00017362717,0.016321562,0.000273019,0.000029913817,0.000042492597,0.017992478,0.00082610536,0.00022760348,0.024914673,0.019024126,0.92002505],"study_design_scores_gemma":[0.00022284266,0.0023317013,0.23647447,0.007694285,0.0002456118,0.00046372192,0.23400351,0.023273157,0.008034223,0.19889945,0.2878334,0.00052371476],"about_ca_topic_score_codex":0.0072250674,"about_ca_topic_score_gemma":0.017585004,"teacher_disagreement_score":0.077367924,"about_ca_system_score_codex":0.012897293,"about_ca_system_score_gemma":0.012023029,"threshold_uncertainty_score":0.40916556},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6867262,0.004287769,0.004045944,0.14756943,0.00026386656,0.0014981957,0.0011128555,0.00012148023,0.15437427],"genre_scores_gemma":[0.9637606,0.0027900275,0.0033733235,0.004999537,0.00005341479,0.00024013894,0.00028918535,0.000025015535,0.024468636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98707145,0.003373822,0.00031920229,0.0004060515,0.0032233677,0.0056059957],"domain_scores_gemma":[0.9829061,0.0053873803,0.0011542467,0.0003567755,0.0063209427,0.0038746125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008325954,0.00019067294,0.00030485154,0.0012179636,0.01900598,0.005489009,0.0022927052,0.0025311366,0.0020189332],"category_scores_gemma":[0.014832631,0.00033933658,0.00034931133,0.002663541,0.0044207787,0.0015689654,0.002801072,0.0026898817,0.00014776771],"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":[0.000544106,0.0010494511,0.14161065,0.0021206068,0.00013446008,0.01745893,0.16720639,0.016463479,0.005899643,0.338226,0.104804285,0.20448205],"study_design_scores_gemma":[0.0001918867,0.00040277163,0.19931476,0.0014558382,0.00015829597,0.0007006408,0.25496516,0.0069341417,0.0025884148,0.015107738,0.5179717,0.0002086327],"about_ca_topic_score_codex":0.9795768,"about_ca_topic_score_gemma":0.9919646,"teacher_disagreement_score":0.76023865,"about_ca_system_score_codex":0.23976135,"about_ca_system_score_gemma":0.3524438,"threshold_uncertainty_score":0.88176906},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027059482,0.024219079,0.0040970067,0.07679046,0.00246526,0.0021132124,0.0030790425,0.00071905146,0.8594574],"genre_scores_gemma":[0.24991395,0.024757175,0.022229187,0.015116602,0.00052840024,0.0010906376,0.0030587148,0.00042955767,0.6828758],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.98979294,0.002254484,0.00025362917,0.00040302958,0.0059826784,0.0013131695],"domain_scores_gemma":[0.9848033,0.0034340813,0.0006631079,0.00035614028,0.0091098165,0.0016336001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0098851975,0.00060397695,0.0006189033,0.0022401784,0.0054601314,0.011821328,0.0019849213,0.002700295,0.018485121],"category_scores_gemma":[0.015693584,0.00046574645,0.00044624473,0.003858931,0.0021670589,0.0026881578,0.0014195532,0.0026403894,0.0026378226],"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":[0.00005586013,0.000240091,0.010956813,0.00045694463,0.000033667206,0.00014679394,0.004967235,0.0012001459,0.00063984713,0.016870564,0.71817565,0.24625657],"study_design_scores_gemma":[0.000041442712,0.00020230097,0.07960271,0.002672248,0.000063018786,0.000121235105,0.013555255,0.0010560805,0.0020129331,0.004011896,0.89650327,0.00015758477],"about_ca_topic_score_codex":0.87843305,"about_ca_topic_score_gemma":0.95023394,"teacher_disagreement_score":0.12156695,"about_ca_system_score_codex":0.07468609,"about_ca_system_score_gemma":0.11002415,"threshold_uncertainty_score":0.541888},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8480289,0.0011874138,0.069081105,0.0018862208,0.0001464547,0.008467887,0.0015620174,0.00039064194,0.06924925],"genre_scores_gemma":[0.97142935,0.0002005192,0.022594295,0.00008135007,0.000016042322,0.0044452115,0.00035036998,0.000028736758,0.0008540196],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8738123,0.10086641,0.005151742,0.0023979542,0.015225028,0.0025465616],"domain_scores_gemma":[0.602225,0.29099613,0.03155084,0.012605991,0.058516942,0.004105104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13317563,0.0008381415,0.0009471989,0.015749885,0.0026837473,0.00612035,0.001894073,0.00076184544,0.004338236],"category_scores_gemma":[0.2660719,0.00042069794,0.001299594,0.009617411,0.0027481357,0.0059542125,0.0074004564,0.0013524764,0.00044820513],"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":[0.0022679449,0.0028857838,0.3183703,0.0055185803,0.0010845758,0.0002499357,0.04496251,0.012517179,0.0017672378,0.047735617,0.0068593863,0.555781],"study_design_scores_gemma":[0.00092973065,0.010256867,0.60570526,0.007188572,0.0020102207,0.0003805595,0.13280606,0.07195381,0.023073833,0.08735606,0.057627086,0.0007119321],"about_ca_topic_score_codex":0.005603034,"about_ca_topic_score_gemma":0.0060074213,"teacher_disagreement_score":0.13317563,"about_ca_system_score_codex":0.008764398,"about_ca_system_score_gemma":0.009895675,"threshold_uncertainty_score":0.70430845},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050418574,0.030578222,0.15747787,0.5319723,0.004835871,0.0019296205,0.00009695452,0.00043998178,0.2222506],"genre_scores_gemma":[0.8520308,0.012867243,0.09394965,0.024897391,0.0016961468,0.0024285163,0.000079689744,0.00030603007,0.011744586],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.55901355,0.39679697,0.0066314572,0.0107424585,0.019326746,0.0074888067],"domain_scores_gemma":[0.67484635,0.21999939,0.015778307,0.029444987,0.025494456,0.03443652],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.28828102,0.00081647467,0.0020402963,0.0044564074,0.03570384,0.037362937,0.0045219213,0.009793305,0.0044163526],"category_scores_gemma":[0.18368533,0.0016557572,0.00095418567,0.004302849,0.15079069,0.035399884,0.03531152,0.021054102,0.0015831882],"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":[0.000040421946,0.00017822791,0.0018315539,0.00068952155,0.000062126164,0.0006411828,0.497181,0.00027557788,0.00057468895,0.45038095,0.0078923125,0.04025248],"study_design_scores_gemma":[0.00005679603,0.00035825692,0.0023760186,0.003893364,0.00005679137,0.0007391414,0.33164215,0.00053046865,0.00071477867,0.3692995,0.29017222,0.00016048123],"about_ca_topic_score_codex":0.007328243,"about_ca_topic_score_gemma":0.006364885,"teacher_disagreement_score":0.96429616,"about_ca_system_score_codex":0.016140457,"about_ca_system_score_gemma":0.062911384,"threshold_uncertainty_score":0.8776762},"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":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7858182,0.0072895642,0.11376147,0.008770616,0.0027820352,0.0023120467,0.039129265,0.0014492357,0.038687587],"genre_scores_gemma":[0.9751372,0.00011686065,0.009917045,0.0010286664,0.00018976207,0.0012136233,0.010434874,0.0002692966,0.0016927631],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8870554,0.06839355,0.0059739687,0.018219788,0.015475691,0.0048815985],"domain_scores_gemma":[0.61752635,0.2733639,0.025416445,0.047271922,0.033162296,0.0032591566],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09800271,0.0010635732,0.0013474296,0.004431598,0.004294422,0.00620541,0.0040577436,0.0027544964,0.007436608],"category_scores_gemma":[0.35306165,0.00034654373,0.0026777121,0.008213095,0.004432456,0.004125167,0.0036214185,0.002384279,0.0022950636],"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":[0.0024127841,0.00085121003,0.83906937,0.0021532257,0.0068652495,0.0012918097,0.015477582,0.006008212,0.0034476784,0.029003609,0.04338879,0.050030585],"study_design_scores_gemma":[0.0006344294,0.0019719438,0.75991434,0.0013553894,0.0040218458,0.0007126473,0.023717264,0.023574915,0.009101412,0.042250186,0.13240017,0.0003454396],"about_ca_topic_score_codex":0.09098172,"about_ca_topic_score_gemma":0.050769474,"teacher_disagreement_score":0.90199727,"about_ca_system_score_codex":0.0038977854,"about_ca_system_score_gemma":0.004110183,"threshold_uncertainty_score":0.5182941},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024713941,0.062268555,0.061885644,0.035555616,0.0044850204,0.00011354479,0.000117661104,0.00015232158,0.8329503],"genre_scores_gemma":[0.17508341,0.09562703,0.074829936,0.009857583,0.006597119,0.00029278154,0.00020697633,0.00030885354,0.63719624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971311,0.0014557398,0.000071128045,0.00012210674,0.0010992677,0.00012063134],"domain_scores_gemma":[0.9939773,0.0048418143,0.00014415711,0.00016747558,0.00070382474,0.00016532013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049397335,0.00069932616,0.00072312297,0.0014667196,0.0010054465,0.0074213124,0.00086859823,0.0022682273,0.0111044],"category_scores_gemma":[0.009953329,0.0002527589,0.0002217445,0.0020885,0.003731561,0.004917839,0.0015390062,0.0025427057,0.0030419233],"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":[0.000018248707,0.00004952109,0.00016204591,0.00019348005,0.000009604771,0.00006340262,0.0004561507,0.0031496994,0.00017123687,0.62620956,0.14498977,0.22452734],"study_design_scores_gemma":[0.0000049276764,0.000014328755,0.0002722892,0.00039126872,0.0000048189054,0.000050016188,0.00044027614,0.0028176114,0.00015495511,0.7325904,0.26324666,0.000012447923],"about_ca_topic_score_codex":0.0026314813,"about_ca_topic_score_gemma":0.004888657,"teacher_disagreement_score":0.0111044,"about_ca_system_score_codex":0.0026877157,"about_ca_system_score_gemma":0.003314654,"threshold_uncertainty_score":0.03714794},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035943373,0.0071951905,0.03277836,0.014837237,0.001820155,0.00019481087,0.0003226151,0.00041317122,0.942079],"genre_scores_gemma":[0.013558307,0.0071065514,0.022243876,0.0034376853,0.0015369018,0.0003152518,0.00035236793,0.0003696911,0.9510793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99399626,0.0024295112,0.00013321855,0.0003517384,0.0028453814,0.00024384941],"domain_scores_gemma":[0.99419266,0.0035430824,0.000116163836,0.0006735452,0.0013170803,0.0001574972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006827614,0.0009911399,0.0013064892,0.0028489733,0.0015147288,0.009207242,0.0012344633,0.0028574362,0.049033463],"category_scores_gemma":[0.013838508,0.0006722349,0.00056532875,0.0027162784,0.0036399139,0.0047330456,0.0023789757,0.0033820968,0.026624002],"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":[0.00001138663,0.000035522342,0.00005916397,0.00007935814,0.000008551288,0.00001465881,0.00009954168,0.0011078111,0.00007195103,0.43948662,0.42934355,0.12968187],"study_design_scores_gemma":[0.000004810387,0.000006291561,0.00014730533,0.00017403187,0.000006465316,0.000018766623,0.000110009205,0.0015810829,0.00015646289,0.45422688,0.54355884,0.000008953375],"about_ca_topic_score_codex":0.00841223,"about_ca_topic_score_gemma":0.011789226,"teacher_disagreement_score":0.049033463,"about_ca_system_score_codex":0.0065662926,"about_ca_system_score_gemma":0.009087553,"threshold_uncertainty_score":0.1640333},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033386286,0.055391047,0.06505774,0.6537371,0.002353054,0.00050848816,0.00018450274,0.00031387695,0.18906784],"genre_scores_gemma":[0.79333824,0.06586553,0.051319893,0.07197372,0.0018955867,0.0009887683,0.0002734831,0.0005008875,0.013843837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.85385275,0.10490812,0.0037348082,0.0059580896,0.025920432,0.0056258077],"domain_scores_gemma":[0.83924335,0.12266659,0.00491482,0.009958085,0.016261809,0.0069553284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09157161,0.00088974077,0.0016618195,0.0023245488,0.017051887,0.027540807,0.0034195615,0.010309127,0.006721512],"category_scores_gemma":[0.07757472,0.0010422157,0.0012934709,0.004184024,0.06363002,0.028015807,0.018659031,0.021805665,0.0014213237],"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":[0.000034779034,0.000106440384,0.0017337761,0.0020189688,0.000047947487,0.0003551027,0.20841601,0.00057202094,0.0009481962,0.61845857,0.020018678,0.14728951],"study_design_scores_gemma":[0.000016274635,0.00006844184,0.003106851,0.0063223275,0.000027490767,0.00024896584,0.11283157,0.00029296274,0.0006902119,0.23650892,0.63979316,0.00009290716],"about_ca_topic_score_codex":0.0596795,"about_ca_topic_score_gemma":0.071119614,"teacher_disagreement_score":0.09157161,"about_ca_system_score_codex":0.032718986,"about_ca_system_score_gemma":0.08360488,"threshold_uncertainty_score":0.48428273},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008273981,0.0021909778,0.9488872,0.010129921,0.00020075108,0.009500217,0.00021284985,0.00040931624,0.020194825],"genre_scores_gemma":[0.0927222,0.00089120434,0.8957034,0.00038808887,0.000041549167,0.009399041,0.00010276538,0.00008325337,0.0006685572],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6436016,0.3174325,0.009578758,0.007576405,0.01946743,0.002343336],"domain_scores_gemma":[0.7191433,0.22260612,0.01403035,0.020755922,0.01981633,0.0036479787],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2689332,0.0038350457,0.0033518393,0.018636068,0.008576431,0.016697757,0.0055311793,0.0044948384,0.0038796898],"category_scores_gemma":[0.1951218,0.0018825774,0.0026626457,0.008783014,0.03001605,0.018692387,0.020903345,0.006251897,0.0006536679],"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":[0.0001749896,0.00051598507,0.0052095824,0.0066943197,0.0004139565,0.0002675993,0.06809263,0.011691395,0.0015725098,0.5300408,0.0036154722,0.37171087],"study_design_scores_gemma":[0.00030173914,0.000638507,0.003366583,0.012001891,0.00033246793,0.00026144617,0.03142241,0.029005326,0.0035785607,0.8515329,0.06725599,0.000302093],"about_ca_topic_score_codex":0.0063801715,"about_ca_topic_score_gemma":0.008800229,"teacher_disagreement_score":0.7310668,"about_ca_system_score_codex":0.02068201,"about_ca_system_score_gemma":0.060063012,"threshold_uncertainty_score":0.9015355},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82389444,0.0040771416,0.13731807,0.007192099,0.00019512599,0.0037255508,0.005329943,0.000492042,0.017775483],"genre_scores_gemma":[0.96220654,0.00049920776,0.0316036,0.00019012626,0.00014286142,0.0028918847,0.0016078274,0.00008384625,0.0007743023],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7504991,0.17611074,0.022550859,0.016355155,0.03091258,0.0035715688],"domain_scores_gemma":[0.112182945,0.8161656,0.04429819,0.01503182,0.008836665,0.003484781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15440908,0.0008032225,0.0018065168,0.021867352,0.004215938,0.011827202,0.004319308,0.0024903812,0.007600332],"category_scores_gemma":[0.54468364,0.00068615447,0.0050834534,0.020199541,0.00649826,0.011018366,0.011547624,0.0038521492,0.0010657975],"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":[0.00048255787,0.00029952358,0.8879905,0.0013377083,0.0019866095,0.000902966,0.033535633,0.0038793872,0.00022806379,0.01784459,0.0024115138,0.049101003],"study_design_scores_gemma":[0.00026934012,0.001665519,0.6054597,0.0023276613,0.002457169,0.0049623493,0.070021346,0.1633259,0.0011535579,0.10520573,0.042644277,0.00050738326],"about_ca_topic_score_codex":0.0029072466,"about_ca_topic_score_gemma":0.0016841334,"teacher_disagreement_score":0.15440908,"about_ca_system_score_codex":0.0049352353,"about_ca_system_score_gemma":0.0044516097,"threshold_uncertainty_score":0.81660306},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87387216,0.0041237553,0.0067232074,0.06460337,0.0005100241,0.0007014754,0.00023693575,0.0001997924,0.049029257],"genre_scores_gemma":[0.9758158,0.0016598905,0.010469652,0.00255903,0.000036187186,0.00008802553,0.00013627888,0.000036705,0.00919854],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97857463,0.0059714722,0.0005847508,0.0012184753,0.008626289,0.0050243326],"domain_scores_gemma":[0.96196455,0.005545413,0.0019860629,0.0011533431,0.012617234,0.016733414],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01837159,0.0003844907,0.00046378686,0.0017944007,0.027282797,0.010345826,0.0030678906,0.0022920629,0.0024549505],"category_scores_gemma":[0.032039035,0.0005297612,0.00046280562,0.0030272233,0.006826127,0.0028094398,0.01008931,0.004258609,0.00027795887],"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":[0.00017673636,0.0011696324,0.09206079,0.0004980518,0.000059842157,0.002464204,0.33788502,0.0018649651,0.0028095753,0.01841382,0.029205635,0.5133918],"study_design_scores_gemma":[0.00007676652,0.0010536459,0.12507845,0.00094548066,0.00007059557,0.0012158165,0.5225282,0.0031827458,0.002232636,0.0047593242,0.33857054,0.00028580328],"about_ca_topic_score_codex":0.9424104,"about_ca_topic_score_gemma":0.9742663,"teacher_disagreement_score":0.9816284,"about_ca_system_score_codex":0.106795415,"about_ca_system_score_gemma":0.36067563,"threshold_uncertainty_score":0.7748586},"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":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041911654,0.038483478,0.0049015554,0.42223608,0.004117879,0.00051348,0.00033945235,0.00024296566,0.48725346],"genre_scores_gemma":[0.7585087,0.033175748,0.012744048,0.05684742,0.0009652523,0.0005264003,0.0003648366,0.0005954684,0.13627209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.93856096,0.028591476,0.002256375,0.0021968295,0.019756304,0.008637988],"domain_scores_gemma":[0.8810554,0.055823445,0.0025120564,0.0045697256,0.037446048,0.01859328],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052313875,0.0005324792,0.0009189029,0.0021155756,0.019303482,0.02293469,0.004248398,0.005113938,0.0116919745],"category_scores_gemma":[0.09055993,0.0008280275,0.0008618893,0.0048034065,0.018845107,0.007596273,0.010753698,0.010708089,0.0009548854],"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":[0.00015900392,0.00020439828,0.004038144,0.0011219276,0.0000565026,0.0014781802,0.05540703,0.0020763285,0.00020239399,0.53536123,0.22363082,0.17626403],"study_design_scores_gemma":[0.00008868872,0.00011241197,0.008424649,0.002817303,0.000029711051,0.00037877145,0.040125422,0.001059354,0.0004078656,0.06028816,0.8860859,0.00018184177],"about_ca_topic_score_codex":0.91678315,"about_ca_topic_score_gemma":0.94726753,"teacher_disagreement_score":0.94768614,"about_ca_system_score_codex":0.20366405,"about_ca_system_score_gemma":0.32927492,"threshold_uncertainty_score":0.92363685},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030949346,0.00786077,0.038641743,0.022102833,0.008220147,0.009973393,0.010380147,0.002299799,0.8974262],"genre_scores_gemma":[0.11176305,0.023708062,0.1236905,0.023963096,0.0034176598,0.043453258,0.025077067,0.0046819416,0.6402454],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9387695,0.033820834,0.0062437975,0.0041953307,0.014537207,0.0024332507],"domain_scores_gemma":[0.9153101,0.019848794,0.003591358,0.013566368,0.04434747,0.0033359756],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051495805,0.00093260006,0.0013314608,0.005021181,0.0036886309,0.008960923,0.004632156,0.0028415637,0.21659088],"category_scores_gemma":[0.13532083,0.00067354826,0.0016381558,0.004883206,0.0033875369,0.0071661263,0.009823421,0.0036244981,0.07093727],"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":[0.00037282225,0.0001356398,0.001219147,0.008511248,0.00009388491,0.00021838704,0.0056682494,0.00037775552,0.00054112164,0.11289412,0.44165304,0.4283146],"study_design_scores_gemma":[0.000040725405,0.00005131028,0.000715019,0.0036928183,0.000028087252,0.0000903748,0.0011846864,0.00012294548,0.00020738713,0.008981897,0.9848621,0.000022618902],"about_ca_topic_score_codex":0.00889708,"about_ca_topic_score_gemma":0.0089516295,"teacher_disagreement_score":0.9485042,"about_ca_system_score_codex":0.008060943,"about_ca_system_score_gemma":0.036057703,"threshold_uncertainty_score":0.7245687},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038250186,0.006128717,0.4904015,0.05436258,0.001770895,0.0019258318,0.000217848,0.00041172758,0.4065307],"genre_scores_gemma":[0.6102303,0.00318379,0.36223966,0.0047049373,0.0002768797,0.0038011083,0.0001855466,0.00033060415,0.015047155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9428346,0.04778209,0.00176135,0.0023475185,0.0039968444,0.0012775902],"domain_scores_gemma":[0.9397618,0.04680463,0.0025032447,0.004393876,0.005196226,0.0013402615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04292611,0.0015126264,0.0008703749,0.0071703307,0.010044481,0.020853218,0.005091401,0.0040133093,0.0040870276],"category_scores_gemma":[0.045262024,0.000938945,0.0010078168,0.004809659,0.09253835,0.020303177,0.010892038,0.009903607,0.0006040746],"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":[0.000013127831,0.00003006742,0.00043069286,0.00018712897,0.000010230813,0.00018949177,0.09253151,0.00044571463,0.00034523365,0.89049983,0.0017679351,0.01354909],"study_design_scores_gemma":[0.00002154349,0.00006614588,0.0008385833,0.0009830733,0.000021129705,0.0003630499,0.1890778,0.0015125157,0.0009675618,0.6326444,0.17345902,0.000045224606],"about_ca_topic_score_codex":0.008359616,"about_ca_topic_score_gemma":0.012082427,"teacher_disagreement_score":0.04292611,"about_ca_system_score_codex":0.019847851,"about_ca_system_score_gemma":0.019146303,"threshold_uncertainty_score":0.2270177},"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":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035821877,0.04162067,0.15565374,0.76364857,0.007151241,0.0009037007,0.00070075784,0.0010771351,0.025662053],"genre_scores_gemma":[0.12812644,0.049751613,0.6786183,0.1173948,0.005739761,0.0028862348,0.0007333219,0.0015324,0.015217072],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7704054,0.14644255,0.01232475,0.0069480552,0.060297865,0.0035813663],"domain_scores_gemma":[0.28888583,0.41332802,0.02091875,0.044059217,0.20980789,0.023000268],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35598794,0.00119131,0.0019077383,0.0079455525,0.0077907178,0.019595718,0.00511818,0.0051116454,0.008717695],"category_scores_gemma":[0.5564971,0.0014950102,0.0012960685,0.009205216,0.030583208,0.016471567,0.011818872,0.014014923,0.002615216],"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":[0.00013466217,0.0001761267,0.008376289,0.0055919043,0.0001430617,0.0001613339,0.02913131,0.0009127958,0.0011353234,0.14350225,0.21990813,0.5908268],"study_design_scores_gemma":[0.00009159373,0.00012192126,0.01714692,0.012898963,0.00010442529,0.0003174232,0.01895812,0.0037986853,0.0012479284,0.25286192,0.69210356,0.0003485542],"about_ca_topic_score_codex":0.4588955,"about_ca_topic_score_gemma":0.4518865,"teacher_disagreement_score":0.94900423,"about_ca_system_score_codex":0.050995775,"about_ca_system_score_gemma":0.20762144,"threshold_uncertainty_score":0.9124489},"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":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035821877,0.04162067,0.15565374,0.76364857,0.007151241,0.0009037007,0.00070075784,0.0010771351,0.025662053],"genre_scores_gemma":[0.12812644,0.049751613,0.6786183,0.1173948,0.005739761,0.0028862348,0.0007333219,0.0015324,0.015217072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7704054,0.14644255,0.01232475,0.0069480552,0.060297865,0.0035813663],"domain_scores_gemma":[0.28888583,0.41332802,0.02091875,0.044059217,0.20980789,0.023000268],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35598794,0.00119131,0.0019077383,0.0079455525,0.0077907178,0.019595718,0.00511818,0.0051116454,0.008717695],"category_scores_gemma":[0.5564971,0.0014950102,0.0012960685,0.009205216,0.030583208,0.016471567,0.011818872,0.014014923,0.002615216],"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":[0.00013466217,0.0001761267,0.008376289,0.0055919043,0.0001430617,0.0001613339,0.02913131,0.0009127958,0.0011353234,0.14350225,0.21990813,0.5908268],"study_design_scores_gemma":[0.00009159373,0.00012192126,0.01714692,0.012898963,0.00010442529,0.0003174232,0.01895812,0.0037986853,0.0012479284,0.25286192,0.69210356,0.0003485542],"about_ca_topic_score_codex":0.4588955,"about_ca_topic_score_gemma":0.4518865,"teacher_disagreement_score":0.94900423,"about_ca_system_score_codex":0.050995775,"about_ca_system_score_gemma":0.20762144,"threshold_uncertainty_score":0.9124489},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001497182,0.36922505,0.3482653,0.04730038,0.018643064,0.013810621,0.016120402,0.019469894,0.16566813],"genre_scores_gemma":[0.0053764866,0.28986436,0.53119344,0.012516584,0.0046693934,0.023334578,0.008806702,0.0062344284,0.11800406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9755351,0.0136517305,0.0024585444,0.00074739417,0.007226092,0.0003811645],"domain_scores_gemma":[0.91934294,0.055323716,0.0033335693,0.0039702654,0.016377833,0.0016516527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03523486,0.0022251075,0.0026950277,0.0087189395,0.0020842697,0.006336723,0.0048538577,0.0030611735,0.059566755],"category_scores_gemma":[0.05135415,0.0032239212,0.0017263086,0.007858376,0.0025433663,0.005041916,0.0036399725,0.0073281354,0.07512664],"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":[0.000038877217,0.0001210856,0.0001102581,0.003759118,0.000026649961,0.00007401765,0.0012794269,0.00022134994,0.0012558472,0.0029540174,0.52765375,0.4625056],"study_design_scores_gemma":[0.000016572292,0.000045610264,0.0003447049,0.003794467,0.000017364267,0.00020780257,0.00036972974,0.00013538125,0.000505001,0.004130093,0.99037814,0.00005497772],"about_ca_topic_score_codex":0.0062427972,"about_ca_topic_score_gemma":0.014617744,"teacher_disagreement_score":0.059566755,"about_ca_system_score_codex":0.003317073,"about_ca_system_score_gemma":0.01501154,"threshold_uncertainty_score":0.1992706},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15302905,0.55905443,0.054543063,0.08944048,0.0060769157,0.0025911697,0.0022019837,0.00026403627,0.13279893],"genre_scores_gemma":[0.69321746,0.2076629,0.049659263,0.0178126,0.0024313375,0.006041686,0.0018652302,0.00043349393,0.020875907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81547856,0.12304221,0.015434861,0.007020946,0.03605896,0.0029644696],"domain_scores_gemma":[0.5073333,0.34897783,0.031585883,0.016049936,0.091008976,0.0050440487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17113172,0.00100035,0.002614338,0.010297997,0.0047914023,0.017952131,0.002498044,0.0027275705,0.012031449],"category_scores_gemma":[0.27116784,0.00070440094,0.001838437,0.011279929,0.0070159864,0.013613292,0.0070329155,0.0035880136,0.002344843],"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":[0.0006043911,0.0002900979,0.0418008,0.038337875,0.0012407008,0.00028136163,0.07866207,0.00044091788,0.0010785001,0.06656982,0.027952328,0.74274105],"study_design_scores_gemma":[0.00014769264,0.00095493224,0.116649166,0.14014253,0.0016629816,0.0008379695,0.13462435,0.0010048252,0.0031995738,0.03273125,0.5676308,0.00041401855],"about_ca_topic_score_codex":0.02636297,"about_ca_topic_score_gemma":0.04639354,"teacher_disagreement_score":0.17113172,"about_ca_system_score_codex":0.014642959,"about_ca_system_score_gemma":0.037412826,"threshold_uncertainty_score":0.9050418},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2939538,0.027674315,0.07515775,0.20207135,0.0032530401,0.0006288358,0.00012930227,0.00020153138,0.3969301],"genre_scores_gemma":[0.95401704,0.0039886707,0.013315447,0.007291964,0.00033400135,0.0003500256,0.00004211132,0.00014310212,0.02051764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.796967,0.14816846,0.0053223195,0.0065048346,0.038577255,0.004460095],"domain_scores_gemma":[0.76441616,0.16555382,0.0105672665,0.012149378,0.038969103,0.008344271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11401462,0.0006440028,0.0009938868,0.0030811555,0.009857314,0.025916085,0.0023335668,0.0041729207,0.009050969],"category_scores_gemma":[0.22699723,0.0006110604,0.0008917595,0.0028558986,0.024085319,0.01811198,0.01343492,0.009315895,0.0011443518],"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":[0.0004207011,0.000191505,0.013213432,0.001111294,0.00019330438,0.00042962102,0.30223453,0.00079259445,0.0012649007,0.3996724,0.012026863,0.26844883],"study_design_scores_gemma":[0.00011422461,0.0006075598,0.03125994,0.0071254866,0.00022198627,0.0009845843,0.32490164,0.0024039713,0.0036207659,0.26117507,0.3672822,0.00030255012],"about_ca_topic_score_codex":0.011844574,"about_ca_topic_score_gemma":0.01690635,"teacher_disagreement_score":0.11401462,"about_ca_system_score_codex":0.012575383,"about_ca_system_score_gemma":0.023139844,"threshold_uncertainty_score":0.6029742},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22389627,0.08172827,0.32972762,0.26357487,0.003913144,0.022094417,0.000679584,0.000560709,0.07382514],"genre_scores_gemma":[0.71448106,0.008655936,0.258077,0.008000887,0.00026318082,0.0094309775,0.000108586224,0.000101505895,0.0008807761],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.33118746,0.6152956,0.020180514,0.0042476226,0.025819138,0.0032696116],"domain_scores_gemma":[0.26581094,0.6123998,0.033842526,0.032020282,0.047346443,0.008580032],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4451979,0.0015195169,0.0031265644,0.010044741,0.0052656056,0.021754466,0.004440198,0.0054720016,0.0051563373],"category_scores_gemma":[0.5600744,0.0009180261,0.0032919277,0.0064308993,0.017445704,0.023179634,0.01569265,0.008436005,0.0006867903],"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":[0.001529446,0.0016560882,0.030146305,0.042137608,0.0023236505,0.00058440276,0.083780326,0.003304191,0.0014042169,0.1415842,0.009689775,0.6818598],"study_design_scores_gemma":[0.001931821,0.013213838,0.067184255,0.28295743,0.0042256843,0.0013793309,0.16549057,0.017052474,0.009210953,0.31805304,0.11843045,0.0008701141],"about_ca_topic_score_codex":0.0050343024,"about_ca_topic_score_gemma":0.0092139,"teacher_disagreement_score":0.4451979,"about_ca_system_score_codex":0.028157976,"about_ca_system_score_gemma":0.0492145,"threshold_uncertainty_score":0.68416977},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863891,0.00021510161,0.000600886,0.0020248122,0.000015431026,0.00013689455,0.00008707799,0.000011771436,0.010518974],"genre_scores_gemma":[0.9961253,0.00025747073,0.0006243715,0.00031127234,0.0000050599997,0.000051072228,0.000037464502,0.000010338457,0.0025776492],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9880554,0.0033971397,0.00052228256,0.0008609892,0.005338924,0.0018252633],"domain_scores_gemma":[0.97161126,0.011131579,0.003751953,0.0007829972,0.007542861,0.005179394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011300475,0.00030971807,0.0004640909,0.0014524063,0.017238075,0.0049203457,0.0012774743,0.0009491222,0.004435106],"category_scores_gemma":[0.021096075,0.0004716192,0.00034494884,0.0018234443,0.007899481,0.001873941,0.0043785414,0.0012387689,0.00019727736],"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":[0.00023327467,0.00018623036,0.17978016,0.00042284597,0.00003678105,0.0010239828,0.7750403,0.00016494044,0.0035139944,0.0019801566,0.0026272323,0.03499008],"study_design_scores_gemma":[0.000019193181,0.00017017496,0.21109417,0.0002766906,0.00003792556,0.00015196363,0.7497621,0.0006042044,0.0007195443,0.0006167591,0.036459193,0.000088032706],"about_ca_topic_score_codex":0.91659623,"about_ca_topic_score_gemma":0.95946246,"teacher_disagreement_score":0.083403766,"about_ca_system_score_codex":0.06562292,"about_ca_system_score_gemma":0.08296305,"threshold_uncertainty_score":0.47612983},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078064683,0.010842702,0.3071872,0.2157053,0.017185412,0.0046628467,0.008117176,0.0949294,0.33356348],"genre_scores_gemma":[0.11371718,0.013982984,0.55476874,0.031776212,0.012115248,0.00884839,0.008900847,0.03442359,0.22146685],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9087288,0.06322731,0.007095991,0.0018675833,0.017422142,0.0016582536],"domain_scores_gemma":[0.6321906,0.24604374,0.011540977,0.053576414,0.031502075,0.025146183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13269666,0.0010121525,0.0018181794,0.00711479,0.0026351833,0.019321084,0.0027531795,0.00506044,0.099488035],"category_scores_gemma":[0.2713856,0.0011799115,0.0012625284,0.0063267536,0.0035581447,0.016797455,0.015447112,0.006665344,0.03834667],"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":[0.00024713975,0.00046914027,0.0014546356,0.0007967406,0.000044894492,0.00013607647,0.0017676243,0.00038167086,0.00031478866,0.026111554,0.42379922,0.54447657],"study_design_scores_gemma":[0.00039229257,0.00035126586,0.0019174897,0.0024326174,0.000039163482,0.00019795852,0.0011376429,0.0017909227,0.0009472857,0.061460447,0.9292343,0.00009849981],"about_ca_topic_score_codex":0.0010291385,"about_ca_topic_score_gemma":0.0021420717,"teacher_disagreement_score":0.13269666,"about_ca_system_score_codex":0.0039017475,"about_ca_system_score_gemma":0.019621624,"threshold_uncertainty_score":0.70177543},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0078064683,0.010842702,0.3071872,0.2157053,0.017185412,0.0046628467,0.008117176,0.0949294,0.33356348],"genre_scores_gemma":[0.11371718,0.013982984,0.55476874,0.031776212,0.012115248,0.00884839,0.008900847,0.03442359,0.22146685],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9087288,0.06322731,0.007095991,0.0018675833,0.017422142,0.0016582536],"domain_scores_gemma":[0.6321906,0.24604374,0.011540977,0.053576414,0.031502075,0.025146183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13269666,0.0010121525,0.0018181794,0.00711479,0.0026351833,0.019321084,0.0027531795,0.00506044,0.099488035],"category_scores_gemma":[0.2713856,0.0011799115,0.0012625284,0.0063267536,0.0035581447,0.016797455,0.015447112,0.006665344,0.03834667],"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":[0.00024713975,0.00046914027,0.0014546356,0.0007967406,0.000044894492,0.00013607647,0.0017676243,0.00038167086,0.00031478866,0.026111554,0.42379922,0.54447657],"study_design_scores_gemma":[0.00039229257,0.00035126586,0.0019174897,0.0024326174,0.000039163482,0.00019795852,0.0011376429,0.0017909227,0.0009472857,0.061460447,0.9292343,0.00009849981],"about_ca_topic_score_codex":0.0010291385,"about_ca_topic_score_gemma":0.0021420717,"teacher_disagreement_score":0.13269666,"about_ca_system_score_codex":0.0039017475,"about_ca_system_score_gemma":0.019621624,"threshold_uncertainty_score":0.70177543},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15400931,0.00517981,0.70777136,0.036285542,0.0011078063,0.0064528724,0.0005167866,0.0003621572,0.08831435],"genre_scores_gemma":[0.69872296,0.004639043,0.2818024,0.004490816,0.00018949363,0.006281526,0.0001689047,0.00018983312,0.0035150985],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9018168,0.09028702,0.001572704,0.0017902638,0.0032528404,0.0012803429],"domain_scores_gemma":[0.886408,0.09994034,0.0032062777,0.0052040746,0.004061651,0.0011796644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08074217,0.0012345298,0.0009900508,0.005566791,0.008357983,0.013220962,0.0023128365,0.0028578844,0.0038727378],"category_scores_gemma":[0.06677608,0.0008088933,0.0011440215,0.0038911744,0.030321544,0.018518306,0.014206124,0.0047231163,0.000533052],"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":[0.00005662849,0.000095235104,0.0010292034,0.0010518628,0.000028755645,0.00039013915,0.8873386,0.0005174958,0.0011497164,0.069582686,0.0015165833,0.03724314],"study_design_scores_gemma":[0.00005612845,0.00020320635,0.00092963036,0.0037825552,0.00005291954,0.0005100122,0.7691265,0.0018218175,0.0017278579,0.13616508,0.08555334,0.00007092527],"about_ca_topic_score_codex":0.0022030827,"about_ca_topic_score_gemma":0.004009621,"teacher_disagreement_score":0.08074217,"about_ca_system_score_codex":0.0061186794,"about_ca_system_score_gemma":0.011548359,"threshold_uncertainty_score":0.42701054},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005449078,0.8001272,0.06001022,0.1217845,0.006758958,0.0006001383,0.0002937747,0.00025126422,0.009629016],"genre_scores_gemma":[0.024778433,0.76400256,0.15999377,0.026838241,0.013907475,0.0054151146,0.000410986,0.00040406015,0.0042494317],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.72501063,0.22743008,0.014227266,0.0047641285,0.027403524,0.0011643525],"domain_scores_gemma":[0.39912915,0.5513461,0.011218072,0.012592173,0.022781624,0.0029327741],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24504404,0.003038917,0.0055552726,0.019692844,0.0071364916,0.025296686,0.005672584,0.013170394,0.006688573],"category_scores_gemma":[0.27577576,0.0044141244,0.0032450333,0.0162205,0.035509497,0.023498021,0.011905443,0.015554919,0.0034269404],"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":[0.00012820234,0.000106962114,0.0011949014,0.021186687,0.0006517716,0.00035587524,0.02257373,0.0006903027,0.00087054836,0.20418766,0.1724539,0.57559943],"study_design_scores_gemma":[0.000118387,0.00015177781,0.0020039554,0.051808853,0.0005346371,0.0007438255,0.006248008,0.00088575255,0.0011033119,0.3960859,0.5400216,0.0002939883],"about_ca_topic_score_codex":0.008972377,"about_ca_topic_score_gemma":0.011929801,"teacher_disagreement_score":0.24504404,"about_ca_system_score_codex":0.0105171995,"about_ca_system_score_gemma":0.02762418,"threshold_uncertainty_score":0.9309951},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016310202,0.000888038,0.97583973,0.0014897689,0.00009585105,0.00019517823,0.00013962587,0.00033522342,0.004706353],"genre_scores_gemma":[0.6328493,0.0015657836,0.354604,0.0005996363,0.00041105866,0.0014402474,0.0002774159,0.00038253615,0.0078699505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9365229,0.053205013,0.0011672528,0.0023047072,0.0043800604,0.0024201013],"domain_scores_gemma":[0.81928855,0.1659138,0.003472783,0.0059908875,0.0038327053,0.001501267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.062384047,0.0020451585,0.0048759454,0.00462639,0.0014767234,0.0063171447,0.0033264218,0.0035380793,0.0127348965],"category_scores_gemma":[0.14162436,0.002242359,0.0046300916,0.0034336203,0.0056975945,0.014795885,0.005531675,0.007834762,0.00095631124],"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":[0.000688704,0.00025839682,0.0026581145,0.0004795652,0.00068616105,0.00009130666,0.00039137856,0.14828339,0.00058448856,0.7781118,0.0018683267,0.06589831],"study_design_scores_gemma":[0.0000683704,0.0001541937,0.000750782,0.00008496379,0.00022172977,0.000028297167,0.00008371047,0.3335028,0.00070110674,0.66342187,0.0009314833,0.00005068482],"about_ca_topic_score_codex":0.004556319,"about_ca_topic_score_gemma":0.002819596,"teacher_disagreement_score":0.062384047,"about_ca_system_score_codex":0.0049314927,"about_ca_system_score_gemma":0.006951033,"threshold_uncertainty_score":0.32992238},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9202025,0.004112881,0.0023901945,0.011683417,0.000106693326,0.0003956724,0.0013848888,0.00010531232,0.05961843],"genre_scores_gemma":[0.9908573,0.0014811332,0.0013570632,0.00030939266,0.000013502882,0.00005831229,0.00024399422,0.000014227164,0.0056649502],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99193573,0.0012751727,0.00029770937,0.0006005032,0.0034852505,0.002405636],"domain_scores_gemma":[0.97604966,0.0036337685,0.0032811572,0.00070036866,0.010975459,0.0053595477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004873498,0.00033224234,0.0004606856,0.0018114911,0.009900737,0.0044365213,0.0017515793,0.000632111,0.0024073208],"category_scores_gemma":[0.012685757,0.00042586733,0.00031381924,0.008014666,0.0041460292,0.0011704686,0.0020333563,0.0009617323,0.00019763412],"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":[0.00039536474,0.00034273756,0.55294424,0.0018990117,0.00011827919,0.0017602812,0.12839453,0.0027379536,0.003918636,0.033295877,0.025499417,0.24869363],"study_design_scores_gemma":[0.000027179227,0.00015201746,0.80861014,0.00060054666,0.00003781647,0.00020016497,0.099206336,0.0016241148,0.0008837969,0.0012876042,0.08724797,0.00012226985],"about_ca_topic_score_codex":0.9931023,"about_ca_topic_score_gemma":0.9959304,"teacher_disagreement_score":0.83445764,"about_ca_system_score_codex":0.16554235,"about_ca_system_score_gemma":0.27131426,"threshold_uncertainty_score":0.9678526},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018468328,0.02115487,0.0006360184,0.94136894,0.018760022,0.000024336448,0.00006398551,0.000042919757,0.016102187],"genre_scores_gemma":[0.04508051,0.02393071,0.00213436,0.84580415,0.008318255,0.000136323,0.00007795508,0.00019181422,0.07432588],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99598205,0.0019914338,0.00013099803,0.00057247555,0.00089595764,0.00042710252],"domain_scores_gemma":[0.9836774,0.008046834,0.00045371352,0.0002404636,0.0030629123,0.004518737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008075185,0.0006898551,0.0009393597,0.001065995,0.009979508,0.005670763,0.0015691208,0.006610666,0.013911443],"category_scores_gemma":[0.028679714,0.0005843291,0.00046485424,0.0011102638,0.004149976,0.0061690533,0.0032165179,0.017627569,0.0033469207],"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":[0.0000146995935,0.000025259797,0.00023047492,0.00005147944,0.0000057827774,0.0002187337,0.0049053165,0.000028591126,0.00007419044,0.0052975323,0.9824112,0.006736768],"study_design_scores_gemma":[0.0000073492106,0.000017510569,0.00039249187,0.0003230902,0.0000043202217,0.00043753366,0.010347009,0.000055134435,0.0000839289,0.0014614069,0.9868385,0.00003171901],"about_ca_topic_score_codex":0.040266544,"about_ca_topic_score_gemma":0.07882243,"teacher_disagreement_score":0.040266544,"about_ca_system_score_codex":0.0072440715,"about_ca_system_score_gemma":0.009134939,"threshold_uncertainty_score":0.08006436},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30126682,0.022837922,0.00091512053,0.09657567,0.00044882472,0.00016812647,0.00097310037,0.00008091297,0.5767335],"genre_scores_gemma":[0.9056069,0.014432068,0.001570748,0.0036397465,0.000042967466,0.000044892993,0.0003147359,0.00004245671,0.074305445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978896,0.00023094424,0.000038413993,0.00011041648,0.00084301014,0.00088759325],"domain_scores_gemma":[0.99800366,0.00047031025,0.00010308271,0.00002705121,0.00085779914,0.00053815125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001361612,0.00026088918,0.00020974306,0.0015038435,0.019054022,0.01007432,0.001622413,0.0014169139,0.005655681],"category_scores_gemma":[0.0034805818,0.00019883418,0.00025644738,0.0052818577,0.005813328,0.001906445,0.0029377746,0.0016846257,0.00028913797],"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":[0.00006893046,0.000108966764,0.051225502,0.00082775933,0.00003501163,0.005006791,0.13317256,0.004168144,0.0008833605,0.43900448,0.18867508,0.17682348],"study_design_scores_gemma":[0.000007421842,0.00001966076,0.052327994,0.0007370827,0.000028450208,0.00047079517,0.2420986,0.0016048067,0.00053395424,0.02232191,0.6797394,0.000109946144],"about_ca_topic_score_codex":0.99469143,"about_ca_topic_score_gemma":0.99823016,"teacher_disagreement_score":0.18246947,"about_ca_system_score_codex":0.18246947,"about_ca_system_score_gemma":0.24571131,"threshold_uncertainty_score":0.94821954},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034464535,0.091317646,0.004329474,0.8082964,0.067567766,0.00012475421,0.0005430198,0.0003693695,0.027107101],"genre_scores_gemma":[0.0144632645,0.16524069,0.014885659,0.4052234,0.033675317,0.00044956553,0.0010943309,0.0008783893,0.36408943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99199355,0.001722513,0.0005037431,0.0005108032,0.004938164,0.00033111192],"domain_scores_gemma":[0.9557156,0.008940619,0.0016903151,0.0006342095,0.028093582,0.0049257353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013393101,0.0010896495,0.000636806,0.0037545946,0.0031192002,0.006663633,0.0019427533,0.0067827296,0.021878788],"category_scores_gemma":[0.04430683,0.000712149,0.0005744844,0.0027305163,0.0026689922,0.0044501033,0.0025724738,0.009164117,0.020428058],"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":[0.000009046163,0.0000060376346,0.00019856535,0.00009808281,0.0000022278593,0.00002448488,0.0001535568,0.000021907996,0.00006290094,0.001241395,0.96347505,0.03470678],"study_design_scores_gemma":[0.0000080052205,0.0000113937385,0.0008241705,0.00083489297,0.000007791017,0.00009483873,0.00033921914,0.000056945337,0.00014405062,0.002260371,0.99539655,0.000021697324],"about_ca_topic_score_codex":0.087425664,"about_ca_topic_score_gemma":0.21460631,"teacher_disagreement_score":0.087425664,"about_ca_system_score_codex":0.004695218,"about_ca_system_score_gemma":0.020613506,"threshold_uncertainty_score":0.17383355},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067039224,0.03231973,0.010417665,0.1415208,0.01123694,0.00034533752,0.0050231298,0.006212419,0.79225355],"genre_scores_gemma":[0.0021355464,0.007523026,0.004113244,0.011704055,0.00046603804,0.00014272,0.00069876446,0.0010896315,0.97212696],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998607,0.0002507186,0.00006213744,0.00018752826,0.0007663155,0.00012642633],"domain_scores_gemma":[0.9949477,0.00078818854,0.00021931398,0.0001873732,0.0026102252,0.0012472002],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002427078,0.0009765672,0.00058962003,0.0016405352,0.0020900925,0.0038320683,0.0013078669,0.0025500352,0.4066858],"category_scores_gemma":[0.0077409237,0.0007345291,0.00039027559,0.0012585992,0.00083619356,0.002543273,0.0020530792,0.0034857122,0.29929104],"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":[0.0000073712463,0.0000045220354,0.000037837668,0.000025639167,6.0585637e-7,0.000014641269,0.000024957873,0.000014790718,0.000036945337,0.00043833084,0.96858907,0.030805258],"study_design_scores_gemma":[0.0000035986097,0.000003796075,0.00018301455,0.00009756531,0.0000013400281,0.00002967322,0.000074312804,0.000043861324,0.00005152728,0.0003620213,0.9991437,0.000005467704],"about_ca_topic_score_codex":0.048329853,"about_ca_topic_score_gemma":0.14751734,"teacher_disagreement_score":0.4066858,"about_ca_system_score_codex":0.002044566,"about_ca_system_score_gemma":0.0064940234,"threshold_uncertainty_score":0.8462907},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025130128,0.019081129,0.01829192,0.87380034,0.029828642,0.00009830744,0.00019938636,0.00040436914,0.055783],"genre_scores_gemma":[0.22159886,0.020883197,0.05062499,0.6335914,0.018909879,0.00046013514,0.00031545045,0.001454995,0.052161038],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8496429,0.07492574,0.00746906,0.006093839,0.055280983,0.006587491],"domain_scores_gemma":[0.756927,0.09090502,0.008659824,0.015332735,0.109731495,0.018443905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066145055,0.0010173013,0.0026423,0.0039058528,0.008180827,0.02217061,0.0024649492,0.009255661,0.012111769],"category_scores_gemma":[0.22431158,0.00074818474,0.0016376129,0.0038990595,0.030261738,0.018341405,0.005145923,0.021999374,0.004564168],"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":[0.00017688863,0.00019022245,0.004435049,0.0021024153,0.0004211408,0.00015754873,0.0059138555,0.0005338745,0.0009776347,0.197485,0.64918,0.13842641],"study_design_scores_gemma":[0.00010910455,0.00018752957,0.004178975,0.005497089,0.00025644942,0.0004889585,0.011765316,0.00060572446,0.0017847439,0.17053318,0.80430573,0.00028722425],"about_ca_topic_score_codex":0.047212634,"about_ca_topic_score_gemma":0.048095886,"teacher_disagreement_score":0.066145055,"about_ca_system_score_codex":0.013835319,"about_ca_system_score_gemma":0.026914103,"threshold_uncertainty_score":0.3498127},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99568343,0.000041256248,0.0003790722,0.0006125177,0.000014887872,0.000052481377,0.000024274237,0.000009273104,0.0031829518],"genre_scores_gemma":[0.99812275,0.00007687419,0.00035481644,0.00013278046,0.000008120194,0.00003513758,0.00003696292,0.0000062775835,0.0012263057],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9914657,0.004836141,0.00023605481,0.00024325665,0.0012241598,0.0019947882],"domain_scores_gemma":[0.9858796,0.003956203,0.0018975018,0.00043302847,0.0022379218,0.005595733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0117739085,0.00023253335,0.00031224883,0.0007839358,0.0048004836,0.0037468798,0.000747078,0.00078543427,0.0034231674],"category_scores_gemma":[0.019629885,0.00034022055,0.0003693357,0.0006280554,0.0020608343,0.0016190499,0.005496688,0.0017911956,0.00039083313],"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":[0.00032827203,0.0016168985,0.34672916,0.00019400401,0.000024222361,0.0023683456,0.5648835,0.00033876137,0.0034473308,0.0020261535,0.0047509125,0.07329241],"study_design_scores_gemma":[0.00002072819,0.00092073344,0.14268845,0.00021183825,0.000017135311,0.0006805037,0.8312362,0.0005366674,0.0012590168,0.00040012613,0.021979962,0.00004858416],"about_ca_topic_score_codex":0.015711583,"about_ca_topic_score_gemma":0.03500631,"teacher_disagreement_score":0.015711583,"about_ca_system_score_codex":0.0039807423,"about_ca_system_score_gemma":0.0064201313,"threshold_uncertainty_score":0},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17317499,0.02290503,0.13818865,0.046679344,0.0060449513,0.0080099935,0.002794748,0.0015645974,0.6006376],"genre_scores_gemma":[0.7519388,0.0067866403,0.11219072,0.0062436764,0.0006595573,0.0074643297,0.0017307509,0.0007326741,0.11225277],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8817662,0.058970343,0.0068616755,0.0045099254,0.04475892,0.0031329384],"domain_scores_gemma":[0.841842,0.04115028,0.0055773626,0.01095633,0.09594628,0.0045277565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06363234,0.0015939759,0.0016063137,0.005607579,0.0059378934,0.013941879,0.0019711496,0.0025802453,0.021885937],"category_scores_gemma":[0.13035497,0.00060735916,0.0012904918,0.005795821,0.004766675,0.0067371996,0.007541589,0.002918023,0.0035834596],"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":[0.0012383693,0.00064003334,0.013685136,0.004836875,0.0005196655,0.0004508941,0.037037082,0.0027628276,0.004423242,0.11084255,0.06360438,0.7599589],"study_design_scores_gemma":[0.00047052433,0.0020078814,0.063046545,0.010506891,0.0007608133,0.000453736,0.042061284,0.006334572,0.0094901845,0.052270014,0.8122071,0.00039044349],"about_ca_topic_score_codex":0.18549114,"about_ca_topic_score_gemma":0.26914138,"teacher_disagreement_score":0.18549114,"about_ca_system_score_codex":0.028207606,"about_ca_system_score_gemma":0.036934823,"threshold_uncertainty_score":0.36882293},"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":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008745589,0.064217925,0.16333479,0.19157916,0.55359185,0.0018301137,0.00009303404,0.00053701206,0.023941575],"genre_scores_gemma":[0.020959554,0.09362974,0.4002954,0.17137206,0.28247163,0.010298084,0.00016717543,0.001515184,0.019291181],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.70223916,0.21742615,0.021817388,0.006185408,0.050774205,0.0015576391],"domain_scores_gemma":[0.47733575,0.45390725,0.009623264,0.008362356,0.04474378,0.0060275174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16965105,0.0024234348,0.0039569614,0.0103154825,0.009563002,0.023952736,0.0076420764,0.014589022,0.00483284],"category_scores_gemma":[0.3172198,0.0013405113,0.0026479734,0.0067684245,0.024680018,0.020252462,0.009534518,0.024400705,0.004131093],"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":[0.00013462252,0.00013238077,0.00034949573,0.009795426,0.00021528419,0.0009629882,0.014560921,0.00053644646,0.0009319811,0.19278796,0.5428495,0.23674299],"study_design_scores_gemma":[0.00009116592,0.00009217004,0.00014822604,0.0088963285,0.00010403713,0.00060330075,0.0042754984,0.00076760695,0.0004097659,0.110725395,0.87376773,0.00011878988],"about_ca_topic_score_codex":0.0008302555,"about_ca_topic_score_gemma":0.002313773,"teacher_disagreement_score":0.83034897,"about_ca_system_score_codex":0.006423971,"about_ca_system_score_gemma":0.009866146,"threshold_uncertainty_score":0.8972112},"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":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004484983,0.99008757,0.0008171338,0.0017456325,0.0002098535,0.00073535205,0.00057878403,0.000021163793,0.0013195759],"genre_scores_gemma":[0.08812271,0.90119106,0.0045229886,0.001989154,0.00020305124,0.0028822394,0.0007104973,0.000016588934,0.00036171108],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.97257304,0.015787954,0.005587078,0.0013220678,0.0038516861,0.00087827316],"domain_scores_gemma":[0.89482075,0.080716856,0.009754522,0.0017526697,0.011984316,0.0009708953],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037148472,0.0011312383,0.004214413,0.032542564,0.0019658473,0.0041466,0.001351236,0.0020468847,0.005648],"category_scores_gemma":[0.09543888,0.0007186277,0.0035937375,0.024051707,0.0018453756,0.0039925817,0.0029621485,0.00094006566,0.00041905488],"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":[0.00018857367,0.00008363327,0.006392855,0.7442174,0.0028872003,0.00043102706,0.0044489345,0.00030194223,0.00030705918,0.0045780316,0.007537525,0.22862591],"study_design_scores_gemma":[0.00008605536,0.00016312789,0.008852986,0.9167592,0.0069937073,0.0003924463,0.004872173,0.00013159661,0.00020570659,0.0012130429,0.060281634,0.000048451915],"about_ca_topic_score_codex":0.028818231,"about_ca_topic_score_gemma":0.06132983,"teacher_disagreement_score":0.9628515,"about_ca_system_score_codex":0.013030255,"about_ca_system_score_gemma":0.059201445,"threshold_uncertainty_score":0.19646227},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007668818,0.0043222453,0.8151517,0.06072768,0.00043342068,0.001222219,0.00025117918,0.00017299897,0.11004977],"genre_scores_gemma":[0.2906523,0.0045245015,0.6921419,0.0036294665,0.00027799024,0.0039490005,0.00023888263,0.0000983382,0.004487667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.970018,0.02485176,0.00086121244,0.0011174994,0.0021470652,0.0010043343],"domain_scores_gemma":[0.9798346,0.014840137,0.0011616048,0.00094221486,0.0021626574,0.0010587552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040195048,0.0017511578,0.0021265168,0.012422743,0.0071021426,0.019853633,0.006014686,0.006346522,0.004277524],"category_scores_gemma":[0.016828528,0.0010001684,0.002417175,0.011010516,0.030015923,0.021557335,0.008208866,0.009360864,0.0007203927],"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":[0.0000031015177,0.000023206523,0.00013387471,0.0000794148,0.0000068012605,0.000053538977,0.004170404,0.0007181631,0.000037809452,0.99126047,0.0005207797,0.0029925064],"study_design_scores_gemma":[0.000021346907,0.000027360036,0.00018347379,0.0005642866,0.000013630058,0.00007667255,0.016624348,0.0045180502,0.0000808164,0.9425528,0.035318878,0.0000183466],"about_ca_topic_score_codex":0.007646905,"about_ca_topic_score_gemma":0.00747501,"teacher_disagreement_score":0.040195048,"about_ca_system_score_codex":0.018384963,"about_ca_system_score_gemma":0.022544038,"threshold_uncertainty_score":0.21257424},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007305775,0.0040855524,0.026009087,0.023014575,0.00055705645,0.00005006379,0.000049735532,0.00011754366,0.9453858],"genre_scores_gemma":[0.10096107,0.008457814,0.036872298,0.008048083,0.0009681342,0.0004061224,0.0001659731,0.00028906856,0.84383136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806684,0.0012495009,0.000036648813,0.00012335801,0.00040859779,0.00011505614],"domain_scores_gemma":[0.99687356,0.0025333206,0.00007618056,0.00017677477,0.00019519788,0.00014497201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040023797,0.00082028686,0.0005377592,0.0006311457,0.0015385045,0.006550511,0.001232787,0.0033702818,0.028450832],"category_scores_gemma":[0.0071543227,0.0003285965,0.00029103135,0.00087688357,0.0079252105,0.00762165,0.0022832355,0.0040319264,0.006111979],"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":[0.000005892413,0.000017031181,0.000036020818,0.00006918691,0.0000025210272,0.000017869237,0.00051522895,0.0011335751,0.00005907151,0.89080924,0.057299584,0.050034776],"study_design_scores_gemma":[0.0000057732645,0.0000068535546,0.00007478692,0.00016536092,0.0000019761537,0.000012139154,0.00042431804,0.0012574581,0.000111817426,0.8465148,0.15141906,0.0000057184084],"about_ca_topic_score_codex":0.0055887033,"about_ca_topic_score_gemma":0.01050003,"teacher_disagreement_score":0.028450832,"about_ca_system_score_codex":0.005621177,"about_ca_system_score_gemma":0.005903567,"threshold_uncertainty_score":0.09517747},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9764265,0.00053176377,0.0021158438,0.0123914955,0.00006831151,0.00024024036,0.000018486378,0.00001830816,0.008189021],"genre_scores_gemma":[0.9944963,0.00052422285,0.0018578207,0.0013407568,0.000023716202,0.00010788895,0.000015032784,0.000020863987,0.001613447],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95157546,0.037088603,0.00081667944,0.0013221065,0.0029428964,0.006254227],"domain_scores_gemma":[0.933415,0.041064702,0.0050540934,0.0018212121,0.005603088,0.01304189],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03580789,0.00071348454,0.00075966807,0.002040878,0.02886072,0.009085402,0.004197743,0.0046900357,0.0032429134],"category_scores_gemma":[0.046192553,0.0010807764,0.0006510287,0.0020348344,0.016525185,0.007611245,0.012230682,0.008552369,0.00031413295],"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":[0.000028827897,0.0006044846,0.0067175077,0.00010682371,0.000008561686,0.0046727858,0.9756354,0.00014354195,0.00023108872,0.00265204,0.0012984746,0.007900521],"study_design_scores_gemma":[0.000005875126,0.00010204533,0.0023438216,0.00018268947,0.0000039926417,0.00060530263,0.989666,0.00022555976,0.00012058719,0.00037325989,0.00635685,0.00001391452],"about_ca_topic_score_codex":0.034095384,"about_ca_topic_score_gemma":0.08644643,"teacher_disagreement_score":0.9641921,"about_ca_system_score_codex":0.023443323,"about_ca_system_score_gemma":0.0247579,"threshold_uncertainty_score":0.18937248},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006135747,0.0035594746,0.00047242903,0.76860505,0.22294642,0.000035573787,0.00018532168,0.000050551484,0.0040837214],"genre_scores_gemma":[0.0018108827,0.0030228565,0.00081534655,0.7620864,0.21007876,0.00016628914,0.00013967698,0.0002192692,0.021660525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.976441,0.0094345845,0.00469829,0.0021250036,0.0053746286,0.0019265485],"domain_scores_gemma":[0.8542799,0.093619645,0.007994081,0.003231623,0.026144275,0.014730522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022687858,0.0017988664,0.0024754182,0.003425024,0.0074122525,0.016405055,0.0028244494,0.040128827,0.080145955],"category_scores_gemma":[0.18207294,0.0014066455,0.0019692462,0.0030301777,0.007107235,0.024636205,0.008175029,0.05926612,0.044078324],"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":[0.0000351164,0.0000075378916,0.000060918526,0.00017904027,0.000009022699,0.000065754146,0.00019275345,0.000011976765,0.000084857355,0.0039759725,0.9909314,0.004445565],"study_design_scores_gemma":[0.000037940656,0.000026297295,0.0003331974,0.0010423283,0.000023817607,0.00021829903,0.0010930401,0.000043263604,0.000087171386,0.0105909305,0.9864559,0.000047949496],"about_ca_topic_score_codex":0.003909242,"about_ca_topic_score_gemma":0.004988628,"teacher_disagreement_score":0.97731215,"about_ca_system_score_codex":0.006448084,"about_ca_system_score_gemma":0.008280325,"threshold_uncertainty_score":0.26811492},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16341142,0.0060869395,0.030437823,0.23845571,0.0014426792,0.0013580321,0.0012306395,0.0014906966,0.55608606],"genre_scores_gemma":[0.92823434,0.0043953354,0.042625193,0.009287044,0.00020065925,0.0002492674,0.000523281,0.00025767199,0.0142272785],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94305074,0.02013586,0.0019722306,0.0019028111,0.018409494,0.014528837],"domain_scores_gemma":[0.8786251,0.021098504,0.0044559552,0.0063192886,0.06394302,0.025558157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.064959735,0.0011836434,0.0005767522,0.006155567,0.017813973,0.02410142,0.0032212194,0.0022190635,0.008048314],"category_scores_gemma":[0.08143169,0.0007042932,0.00090215914,0.005643864,0.009008808,0.005747731,0.014641975,0.0034378164,0.0010564005],"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":[0.00032478914,0.000430128,0.068621464,0.0013858186,0.00015997732,0.00075701484,0.023546798,0.0053587225,0.0022700757,0.3151894,0.10602465,0.47593114],"study_design_scores_gemma":[0.00012535283,0.00042122998,0.13381639,0.0043676663,0.00035767056,0.0003890765,0.05983275,0.0060895192,0.005275221,0.050504304,0.73829573,0.0005250562],"about_ca_topic_score_codex":0.9123325,"about_ca_topic_score_gemma":0.9380662,"teacher_disagreement_score":0.88512427,"about_ca_system_score_codex":0.11487572,"about_ca_system_score_gemma":0.49100888,"threshold_uncertainty_score":0.8334856},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96837866,0.00006765692,0.01623716,0.00091743533,0.000058979855,0.007414923,0.00012759771,0.000029893843,0.0067677577],"genre_scores_gemma":[0.9318659,0.0003028115,0.049059156,0.0008677834,0.0000231376,0.012866672,0.00019153237,0.000027509144,0.0047956444],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9811948,0.013370067,0.0010881008,0.0005928508,0.0015903017,0.0021638575],"domain_scores_gemma":[0.9732289,0.018111497,0.00076081627,0.0005826908,0.005890272,0.0014258769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0389739,0.0007218778,0.0005399063,0.0031336558,0.0048641916,0.002439999,0.0012293883,0.0015351336,0.0033942792],"category_scores_gemma":[0.037611034,0.00087863795,0.00056226976,0.0015098231,0.002066833,0.002335648,0.0050180894,0.0022963206,0.0008033017],"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":[0.00059540215,0.004601466,0.03673979,0.0015351822,0.000031970354,0.0020371948,0.7426869,0.0044411365,0.017398203,0.014848645,0.0077620763,0.16732202],"study_design_scores_gemma":[0.000079073,0.0012394503,0.018921923,0.0005822773,0.000018746498,0.0003279223,0.93124586,0.010299931,0.005743452,0.003151752,0.028260812,0.00012879937],"about_ca_topic_score_codex":0.005106292,"about_ca_topic_score_gemma":0.0075319125,"teacher_disagreement_score":0.0389739,"about_ca_system_score_codex":0.0051959176,"about_ca_system_score_gemma":0.010290578,"threshold_uncertainty_score":0.20611614},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06549321,0.018172653,0.082564235,0.233978,0.018133301,0.006367106,0.01889494,0.0005222475,0.5558743],"genre_scores_gemma":[0.8280108,0.0025267666,0.055532012,0.0724001,0.0015325776,0.004405417,0.0029221023,0.00017401665,0.032496154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81378895,0.104786955,0.010212436,0.015776476,0.04810536,0.0073298193],"domain_scores_gemma":[0.7208041,0.17608908,0.018902998,0.029178966,0.052754853,0.0022699777],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15834777,0.0012418086,0.0025791533,0.0039968486,0.008019842,0.013070539,0.006457432,0.00715476,0.016809896],"category_scores_gemma":[0.33016643,0.00064108026,0.0026589395,0.0075818077,0.012882792,0.0061556194,0.005917026,0.009071161,0.00092970417],"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":[0.002078635,0.00013172415,0.008235466,0.0011732142,0.0009437159,0.00034074349,0.0018172276,0.0031942388,0.00020688916,0.9082682,0.049914055,0.023695901],"study_design_scores_gemma":[0.00393901,0.0005076253,0.023535894,0.0040099756,0.0042950003,0.00035720228,0.0063706837,0.023718588,0.0026852111,0.38737142,0.5425094,0.00070007873],"about_ca_topic_score_codex":0.7918331,"about_ca_topic_score_gemma":0.7220132,"teacher_disagreement_score":0.94698364,"about_ca_system_score_codex":0.05301638,"about_ca_system_score_gemma":0.07098635,"threshold_uncertainty_score":0.83743304},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046968638,0.00038167177,0.0010421879,0.001540799,0.0005152996,0.000057530306,0.00022596036,0.00014204274,0.99562484],"genre_scores_gemma":[0.02426613,0.0013289775,0.0015696705,0.0023107256,0.0005404227,0.00011430599,0.0008808173,0.00026382896,0.9687251],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596006,0.00043656278,0.00008023632,0.0003174183,0.0027872978,0.00041844908],"domain_scores_gemma":[0.9967012,0.00046610812,0.00012645609,0.00049913867,0.0016612309,0.00054586044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021834206,0.001052553,0.00045866362,0.0027736062,0.0020605617,0.007552426,0.001534478,0.0017607112,0.397377],"category_scores_gemma":[0.008624684,0.00028393345,0.00072131975,0.0017693773,0.0011360229,0.003943022,0.0040576723,0.002033934,0.16062625],"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":[0.000098994904,0.00010891745,0.0008848891,0.00029849718,0.000014243218,0.00013441355,0.0003067288,0.00040190865,0.0010222655,0.19015162,0.4497133,0.3568643],"study_design_scores_gemma":[0.000007721693,0.000020749078,0.00071274536,0.00014010203,0.000007731139,0.00010935815,0.00023906118,0.00013700139,0.00047838665,0.021301849,0.97683674,0.000008461279],"about_ca_topic_score_codex":0.0046024057,"about_ca_topic_score_gemma":0.0058898907,"teacher_disagreement_score":0.397377,"about_ca_system_score_codex":0.0029539804,"about_ca_system_score_gemma":0.0043013114,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04289404,0.010931687,0.6361092,0.2110438,0.004247466,0.007873851,0.000998773,0.0027021489,0.08319902],"genre_scores_gemma":[0.27538952,0.0057102945,0.68598145,0.012157073,0.000991657,0.011494432,0.00068562553,0.0011651777,0.006424734],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.30931938,0.55766237,0.059537664,0.009514831,0.059001345,0.0049644704],"domain_scores_gemma":[0.13670272,0.5087624,0.07417081,0.07213219,0.20082092,0.0074109808],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52772695,0.0022004617,0.0020927757,0.0182822,0.012343835,0.035002906,0.0069723614,0.007804138,0.0034235173],"category_scores_gemma":[0.76572984,0.0024793702,0.0017233808,0.012792211,0.02316189,0.042575423,0.020424476,0.013308338,0.0022000796],"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":[0.00024579896,0.00022541147,0.012460104,0.0038935095,0.00019273837,0.0004802304,0.24021716,0.0018400154,0.0021602057,0.19644538,0.07074088,0.47109857],"study_design_scores_gemma":[0.00022317572,0.0004037292,0.008800494,0.025434272,0.0002427992,0.00047296658,0.16120853,0.0056480756,0.0073435213,0.31960765,0.46982452,0.0007902253],"about_ca_topic_score_codex":0.014511304,"about_ca_topic_score_gemma":0.018539991,"teacher_disagreement_score":0.47227305,"about_ca_system_score_codex":0.03052623,"about_ca_system_score_gemma":0.07475299,"threshold_uncertainty_score":0.5823968},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040019017,0.003994293,0.7238265,0.036270794,0.0024629994,0.0012713876,0.0007098267,0.0037349146,0.18771024],"genre_scores_gemma":[0.4730385,0.002457308,0.4999357,0.0032721933,0.0003220011,0.0020273565,0.00048410016,0.0010122213,0.017450554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98497677,0.012426271,0.00032738317,0.0006184738,0.0013255149,0.0003255329],"domain_scores_gemma":[0.9670933,0.024667336,0.0014653695,0.0035576385,0.0023086201,0.0009077495],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015514692,0.0022198511,0.0005494381,0.005753631,0.0027971177,0.014228209,0.002833268,0.0031267519,0.011491616],"category_scores_gemma":[0.043959953,0.0007870327,0.0016450516,0.0025525568,0.014071286,0.01812332,0.0078556845,0.0039056763,0.0022256477],"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":[0.00023125975,0.00025529723,0.0022246165,0.0024243337,0.000098221346,0.00069402077,0.167818,0.0045840507,0.004075405,0.5755515,0.042313688,0.19972965],"study_design_scores_gemma":[0.00018097168,0.0003174208,0.0015344908,0.0028724466,0.000119476346,0.0011329482,0.06239934,0.011565631,0.0034637402,0.39279175,0.5233902,0.00023166143],"about_ca_topic_score_codex":0.0021770846,"about_ca_topic_score_gemma":0.0031064467,"teacher_disagreement_score":0.9844853,"about_ca_system_score_codex":0.004433618,"about_ca_system_score_gemma":0.0037095994,"threshold_uncertainty_score":0.0820505},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1979797,0.002056442,0.67305887,0.018658884,0.00035467482,0.0026086508,0.00036137403,0.00052025646,0.10440121],"genre_scores_gemma":[0.58410686,0.0016244734,0.40525228,0.00079598074,0.00009245344,0.0020068449,0.000108795786,0.00012786432,0.005884444],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94905865,0.04504607,0.0010026976,0.001165686,0.0029481014,0.000778742],"domain_scores_gemma":[0.93292576,0.055108204,0.0023683514,0.0037851457,0.004683628,0.0011288244],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.055932824,0.00069470354,0.0006490926,0.0073656305,0.007049325,0.009958641,0.0020148484,0.0008490458,0.0033821177],"category_scores_gemma":[0.05687179,0.00059922907,0.00056925317,0.0043328777,0.011048298,0.009799142,0.008472531,0.0026257082,0.00028148017],"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":[0.00006164993,0.00022043439,0.018008543,0.0008826437,0.0001658712,0.000420098,0.51832783,0.0017492202,0.0009384611,0.21509874,0.0025602987,0.24156627],"study_design_scores_gemma":[0.000046943955,0.00024626634,0.018829668,0.001877111,0.00017116123,0.00037276556,0.5660007,0.018056097,0.0015802775,0.29653153,0.096144654,0.0001428786],"about_ca_topic_score_codex":0.039683636,"about_ca_topic_score_gemma":0.06866172,"teacher_disagreement_score":0.9929507,"about_ca_system_score_codex":0.00838345,"about_ca_system_score_gemma":0.011238921,"threshold_uncertainty_score":0.29580456},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97630185,0.00033670024,0.0008886218,0.0047214488,0.000015188192,0.000035704154,0.00001617521,0.0000036005451,0.017680738],"genre_scores_gemma":[0.9982331,0.00022723043,0.0003997145,0.00030667233,0.000005497443,0.000019892399,0.00000809942,0.000003462013,0.0007962885],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99524975,0.0034322736,0.00007113514,0.00023988065,0.00040833413,0.0005984775],"domain_scores_gemma":[0.99371284,0.004841353,0.00038625157,0.00014237344,0.00028249095,0.0006345545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005966802,0.00026744278,0.00032108402,0.0017253179,0.01042599,0.006007948,0.0011358475,0.0012756098,0.002234828],"category_scores_gemma":[0.005837771,0.0002732617,0.00017508307,0.0017208437,0.015732236,0.0049026925,0.0074725137,0.0019124155,0.00010422347],"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":[0.000012462018,0.000026558602,0.004855667,0.00006537319,0.000004079447,0.00095457496,0.9793244,0.000047978174,0.0003552385,0.0063109407,0.0003446511,0.007698095],"study_design_scores_gemma":[0.0000021496887,0.000012922488,0.003834807,0.000052291125,0.00000242801,0.00017377165,0.9871889,0.00006830144,0.000051545518,0.0017916143,0.0068168757,0.000004399025],"about_ca_topic_score_codex":0.018757807,"about_ca_topic_score_gemma":0.05021747,"teacher_disagreement_score":0.018757807,"about_ca_system_score_codex":0.0051665003,"about_ca_system_score_gemma":0.0054081874,"threshold_uncertainty_score":0.03748578},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000605704,0.00038672664,0.00096161704,0.0005230084,0.00027807604,0.00011843166,0.0009406514,0.0010268351,0.995159],"genre_scores_gemma":[0.00076806935,0.0001826034,0.0005123198,0.0002264745,0.00005709797,0.00005999684,0.0004721224,0.0001630692,0.99755824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992912,0.000070572634,0.00005991913,0.00020928498,0.00022727007,0.00014173344],"domain_scores_gemma":[0.9977481,0.00068155414,0.00015781132,0.00027697012,0.00041063284,0.0007249462],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012864855,0.0021566204,0.0013077591,0.0023869073,0.0016255265,0.003282462,0.0026235364,0.004834296,0.987944],"category_scores_gemma":[0.0022079675,0.00076474296,0.0010133923,0.002718227,0.0014238477,0.004821661,0.0026757952,0.0021565773,0.9905681],"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":[0.00026378297,0.00023100869,0.0009375189,0.00042793833,0.000026692656,0.00017464542,0.00009072644,0.00042278532,0.001471826,0.0044356775,0.33121726,0.6603002],"study_design_scores_gemma":[0.000056810382,0.0001120128,0.0010079517,0.00029224702,0.000015108826,0.00026154792,0.00011547989,0.00032611185,0.00044519512,0.0007326295,0.99661237,0.000022506547],"about_ca_topic_score_codex":0.0043231524,"about_ca_topic_score_gemma":0.0034616746,"teacher_disagreement_score":0.012055993,"about_ca_system_score_codex":0.0010066135,"about_ca_system_score_gemma":0.0012993427,"threshold_uncertainty_score":0.017196298},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005563722,0.0003621027,0.0009211595,0.0004673109,0.00024886386,0.000115208255,0.00082866254,0.0010490186,0.9954513],"genre_scores_gemma":[0.0007152515,0.00017108195,0.00046781843,0.00019859069,0.000052933658,0.000057182177,0.00040158376,0.00015076807,0.9977849],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992957,0.000070065704,0.00005793349,0.00020954554,0.00022389316,0.00014290937],"domain_scores_gemma":[0.9976562,0.0007120804,0.00015870623,0.0002840307,0.0004402213,0.0007487224],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012410915,0.0022449892,0.0013047495,0.0025372982,0.0016588618,0.0032593792,0.0026631954,0.004792153,0.9885102],"category_scores_gemma":[0.002206477,0.0007527963,0.0010184272,0.0028076903,0.0014506171,0.00461785,0.00266959,0.002116497,0.99072367],"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":[0.00026510868,0.00022913516,0.00089658255,0.00042002246,0.000026965126,0.00017561953,0.00009038033,0.00043238237,0.0014331661,0.0042170077,0.33612794,0.6556856],"study_design_scores_gemma":[0.000056663222,0.00011240952,0.0009839247,0.00028933582,0.000015537336,0.00025482368,0.000119332246,0.00032793236,0.00043118332,0.0006689248,0.9967181,0.000021744207],"about_ca_topic_score_codex":0.0048125563,"about_ca_topic_score_gemma":0.0037815843,"teacher_disagreement_score":0.011489809,"about_ca_system_score_codex":0.0010447352,"about_ca_system_score_gemma":0.0012544004,"threshold_uncertainty_score":0.016388834},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03570582,0.021200782,0.051813424,0.73556894,0.0035997839,0.0014619216,0.00006792151,0.0001565887,0.15042472],"genre_scores_gemma":[0.8854755,0.011164039,0.05183281,0.04201609,0.00083281455,0.0015589629,0.00006471175,0.00018384852,0.0068712644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.634052,0.32869932,0.0054996596,0.0037008016,0.01924721,0.008801058],"domain_scores_gemma":[0.6656628,0.23825292,0.01474239,0.015629625,0.04659794,0.019114347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3260036,0.0008437125,0.0017864098,0.006003351,0.014618038,0.030058142,0.002807123,0.005854269,0.0052344673],"category_scores_gemma":[0.29076907,0.00078170793,0.0014351535,0.0040627085,0.063989244,0.033211738,0.018000454,0.009864269,0.0008186451],"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":[0.00029610324,0.00035229878,0.008084489,0.0031094365,0.00014201953,0.00044014843,0.101890646,0.00077174895,0.00064085756,0.5798726,0.03513248,0.2692672],"study_design_scores_gemma":[0.00015253898,0.0004062705,0.006394986,0.01424446,0.0001457946,0.0003745367,0.18136269,0.0016934598,0.001626009,0.5591308,0.23422477,0.00024379484],"about_ca_topic_score_codex":0.017247329,"about_ca_topic_score_gemma":0.022877675,"teacher_disagreement_score":0.3260036,"about_ca_system_score_codex":0.03553464,"about_ca_system_score_gemma":0.11164228,"threshold_uncertainty_score":0.83115757},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39015317,0.004363143,0.05871363,0.042250354,0.0005848372,0.0005953453,0.0007596927,0.000528565,0.50205135],"genre_scores_gemma":[0.88439626,0.0027156407,0.023615953,0.0025404936,0.00009779565,0.00030834152,0.00041713114,0.00012813357,0.08578023],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99468225,0.0023586743,0.00018547942,0.0005176786,0.001384963,0.00087102136],"domain_scores_gemma":[0.9881384,0.0036467826,0.0014149338,0.0010304191,0.003963866,0.0018056809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054335203,0.0006109748,0.00030069548,0.0014936123,0.0074301865,0.0071428735,0.0011285659,0.0016230852,0.017363653],"category_scores_gemma":[0.009451358,0.00040980979,0.00044383065,0.0020269048,0.0053593875,0.004482112,0.0034499196,0.002303253,0.0024815376],"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":[0.0002797251,0.00033222898,0.1097384,0.0017200994,0.00015384331,0.0013518712,0.20167975,0.0037402436,0.009086417,0.18542969,0.05102222,0.43546563],"study_design_scores_gemma":[0.000033534176,0.00025482677,0.08009293,0.0013098726,0.00007262605,0.0003418578,0.13053784,0.0015865399,0.0022578016,0.016590534,0.7667637,0.00015798701],"about_ca_topic_score_codex":0.2986928,"about_ca_topic_score_gemma":0.5448148,"teacher_disagreement_score":0.98419327,"about_ca_system_score_codex":0.015806763,"about_ca_system_score_gemma":0.030657958,"threshold_uncertainty_score":0.5939084},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021582725,0.00047711655,0.0017590655,0.00044674493,0.00017402512,0.000052232786,0.00088270236,0.0012159488,0.99477637],"genre_scores_gemma":[0.00059033337,0.00026190374,0.0005868064,0.00012746471,0.000033753244,0.000037853606,0.0004892285,0.0003021692,0.9975706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941444,0.000046323967,0.00004203606,0.00018209948,0.00021728604,0.00009783282],"domain_scores_gemma":[0.9976538,0.00088194176,0.00017316965,0.0003677494,0.00041910054,0.0005042988],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001375646,0.001966263,0.0014160986,0.0018548948,0.0011481309,0.005360888,0.0028680665,0.0042811385,0.977849],"category_scores_gemma":[0.0025032845,0.0008546098,0.00086983806,0.0024463756,0.0012221279,0.005169884,0.003150069,0.0023081165,0.98928154],"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":[0.00011344309,0.00010637964,0.00038196417,0.00039078173,0.000016364269,0.00009779425,0.000085257074,0.00040891737,0.0017588114,0.0075539565,0.33358034,0.6555061],"study_design_scores_gemma":[0.000016419935,0.000040979805,0.0005259752,0.00027827176,0.000008860004,0.00017476073,0.00008090543,0.00018059614,0.0003382729,0.0016797626,0.9966613,0.000013896242],"about_ca_topic_score_codex":0.0032773896,"about_ca_topic_score_gemma":0.0032147726,"teacher_disagreement_score":0.022150993,"about_ca_system_score_codex":0.0010201222,"about_ca_system_score_gemma":0.0009938868,"threshold_uncertainty_score":0.031595647},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94974935,0.0048650117,0.0053250985,0.0029537138,0.0006186171,0.0028549843,0.013228939,0.00017684826,0.020227514],"genre_scores_gemma":[0.91070443,0.007969314,0.022444313,0.0012868166,0.00021268698,0.007588714,0.018297194,0.0001592027,0.031337388],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971449,0.00086655945,0.00051664404,0.00022120259,0.0009492467,0.0003014357],"domain_scores_gemma":[0.99056643,0.0027008746,0.0014890432,0.0005737645,0.0039810687,0.00068874395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056967246,0.0004976044,0.000600099,0.0017821438,0.0007757428,0.0010072187,0.00069983583,0.0006677999,0.0061135725],"category_scores_gemma":[0.012898124,0.00041768374,0.0014987263,0.0010479045,0.0005222223,0.0010190625,0.0014922019,0.0016357836,0.001522347],"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":[0.0009177187,0.00086399645,0.6225612,0.00110831,0.0005944929,0.00052300905,0.009791333,0.00074747484,0.0036088228,0.0016904311,0.034638662,0.32295445],"study_design_scores_gemma":[0.00009785637,0.00032357077,0.9589122,0.00042323853,0.00005682124,0.00044554804,0.0019344229,0.00023768996,0.0005782066,0.00037089293,0.036567584,0.000052037583],"about_ca_topic_score_codex":0.020540591,"about_ca_topic_score_gemma":0.031373937,"teacher_disagreement_score":0.020540591,"about_ca_system_score_codex":0.0014134747,"about_ca_system_score_gemma":0.0021672754,"threshold_uncertainty_score":0.040842056},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018546929,0.0044547096,0.041987278,0.015485999,0.0013871006,0.000044057124,0.000084044375,0.00037450803,0.9343276],"genre_scores_gemma":[0.048597243,0.0050631566,0.021883734,0.0066854195,0.0007701544,0.00009692609,0.00024939,0.00048176054,0.91617215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768317,0.0007409846,0.00006358943,0.00024916482,0.0011122884,0.00015078807],"domain_scores_gemma":[0.99590296,0.0019687375,0.00014934965,0.00070463127,0.0009986546,0.00027562026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026168048,0.00096492306,0.0005773792,0.0010973065,0.0017751887,0.0064656273,0.0015435714,0.0022137265,0.037297137],"category_scores_gemma":[0.012155011,0.0003857529,0.00037665566,0.0007358866,0.005459311,0.012325635,0.0040985704,0.0048918105,0.020748772],"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":[0.000016030248,0.00004322561,0.00031477262,0.00012518403,0.000009002192,0.00010813851,0.0022248793,0.0007852737,0.00023691633,0.45613444,0.25287423,0.28712794],"study_design_scores_gemma":[0.0000033281588,0.000015839281,0.00023727484,0.00038589208,0.0000049118935,0.0001639877,0.0011292114,0.0008627954,0.0003731608,0.46324104,0.53357,0.000012526784],"about_ca_topic_score_codex":0.002124217,"about_ca_topic_score_gemma":0.0047782734,"teacher_disagreement_score":0.037297137,"about_ca_system_score_codex":0.002090388,"about_ca_system_score_gemma":0.0027709524,"threshold_uncertainty_score":0.12477136},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06691878,0.0064182864,0.4186742,0.24340934,0.0027096379,0.020097949,0.00019722014,0.0007613839,0.2408132],"genre_scores_gemma":[0.4855354,0.0029517405,0.46222988,0.018526211,0.000475657,0.008166457,0.00015770008,0.00034111558,0.021615867],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.83222646,0.1256193,0.004505072,0.009927964,0.019512776,0.0082084],"domain_scores_gemma":[0.82277,0.09087933,0.007755242,0.014215822,0.036194507,0.028185116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20985156,0.0009683555,0.0009608032,0.007183861,0.023570688,0.018793741,0.0060168137,0.0105988635,0.0056823012],"category_scores_gemma":[0.13172023,0.0013729315,0.0011384988,0.0038994316,0.03864786,0.015598496,0.03460039,0.011599363,0.001088626],"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":[0.00006666984,0.0008107817,0.004061303,0.0014442255,0.000060686154,0.0011744035,0.23699981,0.0025234432,0.0016680388,0.331918,0.034031518,0.3852411],"study_design_scores_gemma":[0.00014687185,0.0005327503,0.004611596,0.0068158545,0.00003403807,0.00080772134,0.1331752,0.0032620796,0.0019194866,0.11834056,0.7301085,0.0002453373],"about_ca_topic_score_codex":0.03668919,"about_ca_topic_score_gemma":0.064752586,"teacher_disagreement_score":0.20985156,"about_ca_system_score_codex":0.038570613,"about_ca_system_score_gemma":0.21983981,"threshold_uncertainty_score":0.9743937},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003090498,0.10740177,0.033971917,0.7245491,0.0034140316,0.00011231905,0.000052505202,0.00010202462,0.12730585],"genre_scores_gemma":[0.6635388,0.13429588,0.074366495,0.09258004,0.010695062,0.0014352358,0.00015860233,0.00040031277,0.022529583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6963693,0.27214104,0.003918134,0.005080234,0.018975416,0.0035157986],"domain_scores_gemma":[0.6868746,0.2787906,0.002535697,0.0075210086,0.020078015,0.0042000916],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20339262,0.001420307,0.0018855311,0.00654622,0.007800883,0.025984038,0.0024872618,0.010226912,0.0051428233],"category_scores_gemma":[0.15337706,0.0007048892,0.0011414613,0.0040072454,0.079594456,0.05124135,0.013861896,0.015872227,0.0010323485],"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":[0.000024192097,0.00001634626,0.00009930192,0.00028501192,0.000007632444,0.000024425357,0.0028585333,0.0002796025,0.00002302762,0.9607498,0.008809375,0.026822807],"study_design_scores_gemma":[0.000024646744,0.000041457984,0.00014130892,0.0019817017,0.000009673449,0.000057222336,0.0035113809,0.0008623821,0.0001271514,0.87656665,0.116650514,0.000025748921],"about_ca_topic_score_codex":0.0056268782,"about_ca_topic_score_gemma":0.0030326305,"teacher_disagreement_score":0.7966074,"about_ca_system_score_codex":0.023433385,"about_ca_system_score_gemma":0.025334377,"threshold_uncertainty_score":0.9823587},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008198074,0.60124356,0.14233775,0.15439251,0.05434443,0.009940823,0.0066121262,0.0010451099,0.029263852],"genre_scores_gemma":[0.008979707,0.47662807,0.40589863,0.040940344,0.018096711,0.026256332,0.0045345556,0.00091581716,0.017749878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.78063947,0.12532786,0.050911967,0.007876851,0.0337627,0.001481112],"domain_scores_gemma":[0.7389357,0.14488956,0.026600046,0.014562556,0.07199532,0.0030168227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19058871,0.0023305567,0.0044037364,0.029146308,0.0023123303,0.012656491,0.005741486,0.0066833575,0.014625288],"category_scores_gemma":[0.29740873,0.0024487388,0.0060524596,0.029094312,0.007462617,0.0123061575,0.008738285,0.012778674,0.01040332],"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":[0.0003037965,0.000089820154,0.0006598716,0.096906126,0.0005108321,0.00017372315,0.0032528022,0.0009826622,0.0011094979,0.11822625,0.2473238,0.53046083],"study_design_scores_gemma":[0.0000712806,0.00011259073,0.0008880232,0.05435978,0.0002674472,0.0003121287,0.00042306934,0.0002846722,0.0004533996,0.025075307,0.91764194,0.0001104244],"about_ca_topic_score_codex":0.0061231065,"about_ca_topic_score_gemma":0.0056189015,"teacher_disagreement_score":0.8094113,"about_ca_system_score_codex":0.015065409,"about_ca_system_score_gemma":0.029490065,"threshold_uncertainty_score":0.9981482},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026585988,0.4032337,0.275973,0.07986498,0.034345422,0.12720129,0.0040332093,0.0014712613,0.071218506],"genre_scores_gemma":[0.026048569,0.30917117,0.4866138,0.01595768,0.010445141,0.13334855,0.0036169821,0.0009589672,0.01383918],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4963802,0.3626519,0.073180325,0.008488768,0.056628592,0.0026702292],"domain_scores_gemma":[0.42338705,0.41338345,0.043909818,0.025790365,0.08819395,0.00533542],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29521206,0.0032557421,0.0063701677,0.032133326,0.0042053,0.015574507,0.0059419423,0.009160399,0.020757385],"category_scores_gemma":[0.4953099,0.0031617621,0.007105146,0.021804709,0.010354041,0.0118035665,0.011728865,0.010339852,0.009172249],"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":[0.0007477699,0.00017131631,0.00049816706,0.26473835,0.0015939529,0.00032288922,0.009586384,0.0012908439,0.0021568988,0.071804196,0.12967095,0.51741815],"study_design_scores_gemma":[0.0006988631,0.00049497443,0.001458577,0.37088004,0.0013454794,0.00054506987,0.002807692,0.0010591577,0.002476211,0.07383471,0.54411775,0.0002814465],"about_ca_topic_score_codex":0.0034163664,"about_ca_topic_score_gemma":0.0042621084,"teacher_disagreement_score":0.70478797,"about_ca_system_score_codex":0.018767528,"about_ca_system_score_gemma":0.07816031,"threshold_uncertainty_score":0.869129},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015301842,0.06305168,0.0020331345,0.009022763,0.0018990781,0.000119013486,0.0005975646,0.00008471211,0.9216618],"genre_scores_gemma":[0.010364887,0.04672545,0.0022657753,0.00082969834,0.00012957146,0.000054791642,0.0003655207,0.000087006345,0.93917733],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99963915,0.000037332982,0.000022613987,0.000038770726,0.00018750741,0.000074620584],"domain_scores_gemma":[0.9996518,0.00010075361,0.00002027088,0.000018655543,0.000143084,0.000065414795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005396303,0.00088552845,0.0003980159,0.0022913446,0.0023821897,0.006485731,0.0011774253,0.0011375498,0.06953274],"category_scores_gemma":[0.0011697698,0.0004943937,0.00034104977,0.0057124333,0.001323993,0.0024364428,0.0012500337,0.0024665804,0.009649848],"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":[0.000031330896,0.000045957877,0.00067948585,0.0004952339,0.000010447392,0.00027952206,0.003071456,0.0015144494,0.000571605,0.16321702,0.5572175,0.27286607],"study_design_scores_gemma":[0.0000019369336,0.0000024899484,0.00039014217,0.0002273045,0.0000034439595,0.000034375826,0.00075382815,0.00008313592,0.00010513616,0.005996843,0.99239326,0.000008064863],"about_ca_topic_score_codex":0.5908298,"about_ca_topic_score_gemma":0.8947002,"teacher_disagreement_score":0.4091702,"about_ca_system_score_codex":0.028692603,"about_ca_system_score_gemma":0.030572826,"threshold_uncertainty_score":0.8231598},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008664024,0.021761846,0.0015752972,0.0208895,0.0035096023,0.0004361402,0.0015147044,0.00030518323,0.94134367],"genre_scores_gemma":[0.033006933,0.019668058,0.0035017526,0.0020515893,0.00017670925,0.00015208656,0.0008843218,0.00010680929,0.9404518],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999311,0.00006671577,0.000015109554,0.00003341193,0.00038727536,0.00018645775],"domain_scores_gemma":[0.99923384,0.00012055978,0.000015434123,0.000017743268,0.0004751051,0.00013717821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010403795,0.0006160822,0.00031018912,0.0014761251,0.004232986,0.0032328335,0.0011868475,0.0008944405,0.05124413],"category_scores_gemma":[0.0019776225,0.00025359652,0.00034439174,0.002525523,0.0010856666,0.0006430939,0.0008526613,0.00116079,0.0042672334],"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":[0.00002141592,0.000099523735,0.00083924644,0.0002495997,0.000004596264,0.00006842802,0.004655376,0.0002734028,0.0003393918,0.026177928,0.7158201,0.25145108],"study_design_scores_gemma":[0.000010740244,0.000031003798,0.008644831,0.00057775393,0.000013521378,0.00004516239,0.0053829,0.00015368054,0.00033343132,0.0030233827,0.9817647,0.000018854067],"about_ca_topic_score_codex":0.9620999,"about_ca_topic_score_gemma":0.9887111,"teacher_disagreement_score":0.05124413,"about_ca_system_score_codex":0.040861934,"about_ca_system_score_gemma":0.09216591,"threshold_uncertainty_score":0.29647547},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92581195,0.0004999386,0.0038935756,0.031744525,0.00028895208,0.000058044992,0.000031085423,0.0000337829,0.037638076],"genre_scores_gemma":[0.99564785,0.00017512465,0.0006237129,0.0021987935,0.000038037913,0.000014897338,0.000009951098,0.000013905299,0.0012777038],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95449096,0.031847168,0.0011839139,0.0014697508,0.0066562807,0.0043518883],"domain_scores_gemma":[0.9431847,0.030827802,0.0106715895,0.0036650212,0.008498256,0.0031526391],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.035779987,0.00026610747,0.00040226735,0.0019407434,0.010333857,0.012632542,0.0018149042,0.0024871046,0.0017800056],"category_scores_gemma":[0.060312804,0.00033722323,0.00054340437,0.002061464,0.021057943,0.007255386,0.012746105,0.0069567463,0.00015367284],"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":[0.00007125897,0.00014145262,0.083900936,0.00016031678,0.000029206856,0.00052633544,0.83681256,0.00028051567,0.0007244968,0.03597585,0.0033721917,0.038004894],"study_design_scores_gemma":[0.0000030808794,0.00010050343,0.025549367,0.0001894803,0.000009789241,0.00015123725,0.9487919,0.0002832704,0.0005566216,0.0039429315,0.020389216,0.000032640608],"about_ca_topic_score_codex":0.012538413,"about_ca_topic_score_gemma":0.014549622,"teacher_disagreement_score":0.98966616,"about_ca_system_score_codex":0.01206338,"about_ca_system_score_gemma":0.009836736,"threshold_uncertainty_score":0.1892249},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24040976,0.00030749186,0.7526846,0.00042004397,0.00012329804,0.00067309337,0.0004583506,0.00052530615,0.0043980973],"genre_scores_gemma":[0.8510234,0.00008711847,0.1467111,0.00015691872,0.000041404186,0.0009957476,0.000584026,0.00008596345,0.00031443103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.925528,0.054402776,0.0039645634,0.0061715567,0.008901368,0.0010318286],"domain_scores_gemma":[0.6174127,0.31985688,0.021450035,0.024031855,0.015388444,0.0018601737],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.086781956,0.0015520989,0.0013441797,0.0066227573,0.0012598154,0.003982796,0.0016229546,0.0015401616,0.0019020884],"category_scores_gemma":[0.32573524,0.0006535383,0.0017578554,0.0044121905,0.002406415,0.0045409487,0.003004587,0.0019722718,0.00031325157],"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":[0.0018013965,0.000871915,0.28368098,0.000968746,0.0023350508,0.0004151219,0.0061263167,0.17202629,0.0034674963,0.13461542,0.004865272,0.38882592],"study_design_scores_gemma":[0.00018894287,0.0011855069,0.051018275,0.00023887145,0.00025477933,0.00026773885,0.0011958594,0.74121976,0.002291772,0.19841456,0.0035261612,0.00019781468],"about_ca_topic_score_codex":0.001616493,"about_ca_topic_score_gemma":0.0019008822,"teacher_disagreement_score":0.913218,"about_ca_system_score_codex":0.0017572775,"about_ca_system_score_gemma":0.0015904095,"threshold_uncertainty_score":0.4589523},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25842592,0.00027108405,0.7352723,0.00034548846,0.00010200136,0.00061515253,0.0004099957,0.0004908441,0.004067165],"genre_scores_gemma":[0.858065,0.000078458535,0.13996795,0.00012679695,0.00003319898,0.00085794285,0.0005074432,0.000073129166,0.00029010858],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93665427,0.045270186,0.0035504946,0.0054065487,0.008188987,0.0009295374],"domain_scores_gemma":[0.6454983,0.29612532,0.01964886,0.02179967,0.015103085,0.0018247684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07730279,0.0013821207,0.0012193234,0.006432273,0.0011546055,0.0036370542,0.0015203209,0.0013589017,0.0016943305],"category_scores_gemma":[0.3026259,0.0006056227,0.0016049395,0.0039861756,0.002191736,0.0043428726,0.0028071895,0.0018378008,0.00027555772],"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":[0.0017848558,0.00083899475,0.29236966,0.0009328091,0.0020804775,0.00040588202,0.0062551023,0.1673346,0.0038305728,0.12026812,0.0042121396,0.39968684],"study_design_scores_gemma":[0.00018620036,0.0012940258,0.054880705,0.00022919118,0.00025378924,0.0002886156,0.0012403323,0.7525221,0.0026019416,0.18301573,0.003292806,0.00019450701],"about_ca_topic_score_codex":0.0016510715,"about_ca_topic_score_gemma":0.0019471482,"teacher_disagreement_score":0.07730279,"about_ca_system_score_codex":0.001670208,"about_ca_system_score_gemma":0.0015551028,"threshold_uncertainty_score":0.4088211},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2049144,0.054854292,0.17676288,0.020890372,0.004901779,0.018745229,0.0037092164,0.0014560645,0.5137658],"genre_scores_gemma":[0.89263415,0.010078995,0.0704834,0.0011451552,0.0009027836,0.005097579,0.0015440198,0.00022348425,0.017890483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.70041126,0.18779196,0.017189987,0.0034638112,0.08860051,0.0025424357],"domain_scores_gemma":[0.6997418,0.1313014,0.023263635,0.016948918,0.12136421,0.007380067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15405518,0.0006892912,0.0014527051,0.0078752125,0.0013913825,0.009206198,0.0014510349,0.0012337303,0.006449062],"category_scores_gemma":[0.22902489,0.0002681981,0.0009884146,0.009603831,0.0029464092,0.004365177,0.004648308,0.0011134826,0.0022079821],"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":[0.0004817092,0.0005523297,0.023443535,0.003972394,0.00031963037,0.00006440079,0.0033743829,0.002139809,0.0007734561,0.033528306,0.019976763,0.9113733],"study_design_scores_gemma":[0.0006249348,0.006678799,0.22364111,0.019661661,0.0009034885,0.0008980658,0.021002581,0.02127835,0.016815646,0.10506101,0.5828551,0.00057921006],"about_ca_topic_score_codex":0.0012283822,"about_ca_topic_score_gemma":0.0013139341,"teacher_disagreement_score":0.15405518,"about_ca_system_score_codex":0.007360744,"about_ca_system_score_gemma":0.007964718,"threshold_uncertainty_score":0.81473136},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03583379,0.012044185,0.25716445,0.64655894,0.005518157,0.008415304,0.00021638129,0.00023326372,0.03401565],"genre_scores_gemma":[0.48668954,0.0072586606,0.34823328,0.10859287,0.0019897572,0.039860226,0.00014081965,0.00051988,0.006714989],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.26524308,0.698918,0.008828618,0.00862083,0.013235286,0.0051542176],"domain_scores_gemma":[0.37978876,0.5488909,0.013477137,0.025658589,0.026148632,0.006035922],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.56967276,0.0021768329,0.0023607027,0.0067155613,0.029413326,0.0379529,0.013692607,0.012668522,0.0057028807],"category_scores_gemma":[0.43722776,0.0022194192,0.002623707,0.0058219186,0.13617785,0.03304797,0.03471912,0.030364055,0.0012514944],"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":[0.000084519714,0.00007748934,0.0010100947,0.0014044265,0.00004515966,0.00033854894,0.71139705,0.00022750982,0.00022137779,0.26273826,0.006858308,0.0155972345],"study_design_scores_gemma":[0.0001538977,0.00019795807,0.0007130454,0.0072957305,0.000087756365,0.00047288553,0.57024604,0.00149839,0.0008462501,0.28192788,0.13645193,0.00010827767],"about_ca_topic_score_codex":0.017453963,"about_ca_topic_score_gemma":0.024132015,"teacher_disagreement_score":0.43032724,"about_ca_system_score_codex":0.038070917,"about_ca_system_score_gemma":0.08475878,"threshold_uncertainty_score":0.53067017},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553889,0.0015309241,0.0039807237,0.01442669,0.00013502543,0.0010808028,0.00018254349,0.000044126176,0.023230111],"genre_scores_gemma":[0.9833003,0.0011862691,0.0040225917,0.003084222,0.00002348909,0.0005277652,0.000110523775,0.000090579284,0.007654215],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9540001,0.028999742,0.0008366414,0.0024338171,0.004896559,0.008833017],"domain_scores_gemma":[0.96106213,0.020152623,0.0016413757,0.0012571566,0.006688946,0.009197748],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03021161,0.0009751493,0.0009938835,0.0030478192,0.07010895,0.016366329,0.0076385764,0.0038662583,0.0022949772],"category_scores_gemma":[0.028178532,0.0011613148,0.000608142,0.0048848423,0.038054463,0.0048117456,0.0145890685,0.007026668,0.00033744675],"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":[0.000018956413,0.000042325177,0.0026507394,0.00007195527,0.0000057773614,0.0011483362,0.9895824,0.00007476023,0.00036216143,0.0019520011,0.0006535907,0.003436877],"study_design_scores_gemma":[0.0000026213384,0.000014316384,0.001354428,0.00007245306,0.0000034186744,0.00008044627,0.9904371,0.000072128205,0.00008552174,0.00026200167,0.0076046404,0.0000109918365],"about_ca_topic_score_codex":0.926841,"about_ca_topic_score_gemma":0.9739193,"teacher_disagreement_score":0.9697884,"about_ca_system_score_codex":0.11785448,"about_ca_system_score_gemma":0.17090394,"threshold_uncertainty_score":0.8550981},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031339172,0.05468802,0.64754933,0.22224407,0.006070459,0.0151668,0.00061892223,0.001444138,0.020879127],"genre_scores_gemma":[0.28275737,0.0084713865,0.6654702,0.013004063,0.0010174179,0.02767684,0.00045412782,0.0004153478,0.0007333118],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.12294315,0.7276754,0.07307808,0.017394915,0.055648103,0.0032604013],"domain_scores_gemma":[0.029292403,0.8071167,0.01973854,0.06616147,0.07463354,0.0030574447],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8819278,0.0049338634,0.013157671,0.023306334,0.01697509,0.0384502,0.01605861,0.008299793,0.0028469288],"category_scores_gemma":[0.8914865,0.005631053,0.006914468,0.026850834,0.07540442,0.04503667,0.033533055,0.024479643,0.0009778249],"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":[0.00044960517,0.00094591413,0.07672139,0.027899995,0.0029306535,0.0005134613,0.12024501,0.003742605,0.00095882657,0.27582556,0.015418067,0.4743489],"study_design_scores_gemma":[0.0005665596,0.0013108269,0.05232512,0.10356304,0.0018986759,0.0006814155,0.09101199,0.022357013,0.0030707126,0.6459905,0.07611197,0.0011121479],"about_ca_topic_score_codex":0.04194655,"about_ca_topic_score_gemma":0.04222233,"teacher_disagreement_score":0.11807221,"about_ca_system_score_codex":0.045925193,"about_ca_system_score_gemma":0.119796105,"threshold_uncertainty_score":0.33321214},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931132,0.00019640566,0.00017182379,0.0019747936,0.000007789665,0.00008009928,0.00017278871,0.000008452294,0.004274488],"genre_scores_gemma":[0.99740964,0.00023883567,0.00026488685,0.0003046684,0.0000022408306,0.000053782656,0.000094755786,0.000003875617,0.0016272326],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9974554,0.0006386194,0.00011241331,0.00015389803,0.0006221237,0.0010175577],"domain_scores_gemma":[0.9912152,0.0020412288,0.00085860223,0.00011433191,0.0031011945,0.0026694988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033880856,0.0002219596,0.00028424113,0.0008997914,0.008841327,0.003546753,0.001056407,0.00086430385,0.004093039],"category_scores_gemma":[0.008899238,0.0002912659,0.00022990751,0.0019513088,0.0023367438,0.0010729694,0.0021633315,0.00095528405,0.0002011938],"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":[0.00023382985,0.00027932695,0.4060973,0.00055835274,0.00003613196,0.001859915,0.5233899,0.0010225208,0.00247001,0.0029842604,0.008732664,0.052335773],"study_design_scores_gemma":[0.000010801222,0.000107110405,0.27424476,0.00034664723,0.000018545454,0.00010943994,0.70459026,0.0008756895,0.00024034014,0.00020846473,0.019188073,0.000059783415],"about_ca_topic_score_codex":0.9822525,"about_ca_topic_score_gemma":0.99226075,"teacher_disagreement_score":0.057702642,"about_ca_system_score_codex":0.057702642,"about_ca_system_score_gemma":0.05755043,"threshold_uncertainty_score":0.41866398},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008206568,0.92333853,0.002282086,0.044677455,0.0037899115,0.0005226224,0.0027173269,0.00018484553,0.021666614],"genre_scores_gemma":[0.009933949,0.9448181,0.00990632,0.023205267,0.0017175542,0.0006979249,0.002537197,0.00008332734,0.0071003437],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9722943,0.004510661,0.0025773072,0.00091610884,0.018835826,0.0008658111],"domain_scores_gemma":[0.93692154,0.016676644,0.007925402,0.00093356555,0.03636422,0.0011786369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041421518,0.0014556859,0.0021750624,0.015506143,0.002002136,0.005036785,0.00436446,0.005222779,0.0038448058],"category_scores_gemma":[0.05145106,0.0010716808,0.0025125758,0.0139926085,0.0017141667,0.0033926102,0.0021815111,0.0048668813,0.0016719407],"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":[0.000110858615,0.00021890744,0.0012995906,0.021848034,0.00034235878,0.00014164667,0.00018381313,0.0010008105,0.0008702447,0.021168401,0.39847526,0.55434],"study_design_scores_gemma":[0.000027069924,0.00007791927,0.0058263056,0.024341887,0.0004717602,0.00010607122,0.00011755455,0.00020882925,0.00050292106,0.0021119176,0.9661627,0.00004503012],"about_ca_topic_score_codex":0.085037865,"about_ca_topic_score_gemma":0.122515775,"teacher_disagreement_score":0.085037865,"about_ca_system_score_codex":0.014622821,"about_ca_system_score_gemma":0.103826866,"threshold_uncertainty_score":0.21906054},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.130563,0.0061718207,0.15848416,0.12633044,0.0009472618,0.001004911,0.0002674553,0.00048354926,0.57574743],"genre_scores_gemma":[0.8429084,0.0031589142,0.08702873,0.005110335,0.00029926441,0.0005726776,0.00024819523,0.0002467551,0.06042689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9574952,0.025091095,0.0021249186,0.0024132438,0.008385762,0.0044897567],"domain_scores_gemma":[0.94374484,0.021396412,0.0038628585,0.0045962017,0.016007194,0.010392445],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.038291883,0.00095428195,0.0007962639,0.004158763,0.008703852,0.026471421,0.0025443186,0.0053029787,0.014029149],"category_scores_gemma":[0.045959808,0.0007039037,0.0007779322,0.003131229,0.013106541,0.016607968,0.011356386,0.008259012,0.0033391325],"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":[0.00016181814,0.00033756383,0.025281359,0.00078112655,0.00011123063,0.00044554457,0.04972825,0.0024553516,0.004128565,0.6396662,0.016364949,0.26053798],"study_design_scores_gemma":[0.00006252126,0.0002684088,0.033912003,0.0031580792,0.000093395516,0.0006448385,0.08493637,0.0059699784,0.004634038,0.28999543,0.5760147,0.0003102067],"about_ca_topic_score_codex":0.03005056,"about_ca_topic_score_gemma":0.034451354,"teacher_disagreement_score":0.99469703,"about_ca_system_score_codex":0.01955846,"about_ca_system_score_gemma":0.05376914,"threshold_uncertainty_score":0.20250928},"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":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009727666,0.15547393,0.048794225,0.66338795,0.025416072,0.00017580314,0.0001097117,0.00033883037,0.105330676],"genre_scores_gemma":[0.11016881,0.28207055,0.19910717,0.22059697,0.065321,0.0014016302,0.0005204642,0.0016385859,0.11917486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.96775293,0.022275211,0.0012106062,0.0011437117,0.0062331143,0.0013844484],"domain_scores_gemma":[0.91213846,0.066462606,0.0019127146,0.0032785786,0.01201828,0.004189279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025956912,0.001729445,0.0020424235,0.0038543197,0.006465036,0.038793433,0.004415382,0.009501043,0.017314369],"category_scores_gemma":[0.043679982,0.0009943367,0.0015667358,0.0051461714,0.029560082,0.043003898,0.008066099,0.023691505,0.0053941375],"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":[0.000035492456,0.00010238857,0.0002879981,0.0009818575,0.000022582186,0.000046461435,0.0051222886,0.0002730362,0.00017828145,0.436808,0.40387866,0.15226305],"study_design_scores_gemma":[0.000014768688,0.00003137565,0.00027892552,0.0026875602,0.000015167066,0.0001075285,0.006423852,0.0006212355,0.00016438302,0.42538205,0.5642208,0.00005244725],"about_ca_topic_score_codex":0.009439045,"about_ca_topic_score_gemma":0.014643453,"teacher_disagreement_score":0.038793433,"about_ca_system_score_codex":0.013471849,"about_ca_system_score_gemma":0.027650137,"threshold_uncertainty_score":0.13727492},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006830772,0.03037917,0.41641465,0.34528482,0.12159894,0.04344271,0.0047725094,0.0033993511,0.027877148],"genre_scores_gemma":[0.061267007,0.026494717,0.69799197,0.058860518,0.041755255,0.095740534,0.0024938807,0.0025338046,0.012862287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.13484085,0.5857807,0.20221506,0.007470629,0.06593191,0.0037608612],"domain_scores_gemma":[0.040898327,0.55376565,0.09784779,0.14064498,0.16154818,0.005295035],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.64663917,0.003991715,0.011820594,0.013228324,0.007799236,0.036356196,0.008290195,0.02607543,0.011001139],"category_scores_gemma":[0.8885537,0.006796978,0.005720713,0.01655046,0.02571111,0.024306143,0.0119952895,0.037321728,0.018730469],"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":[0.0012861461,0.00044713574,0.002128279,0.02628699,0.0013287736,0.0017447352,0.04243886,0.0011682005,0.004531472,0.104608245,0.538215,0.27581617],"study_design_scores_gemma":[0.0007250791,0.00038847383,0.003027817,0.049614448,0.0005499171,0.0028548336,0.0068585626,0.004171569,0.0054022535,0.16288269,0.76271486,0.00080945593],"about_ca_topic_score_codex":0.0011804028,"about_ca_topic_score_gemma":0.0016294307,"teacher_disagreement_score":0.35336083,"about_ca_system_score_codex":0.008201885,"about_ca_system_score_gemma":0.06097233,"threshold_uncertainty_score":0.43575686},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6012891,0.009937799,0.010155572,0.052276816,0.00045419412,0.0005540871,0.0020115369,0.0002586072,0.32306242],"genre_scores_gemma":[0.94896376,0.0035849204,0.0026690392,0.000742185,0.000060648697,0.00014340665,0.00019718023,0.000076871984,0.043561976],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9919493,0.0014108224,0.00033590055,0.00065149687,0.0035620932,0.002090221],"domain_scores_gemma":[0.9840651,0.004696979,0.0020097778,0.00086323515,0.005833395,0.002531567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008181194,0.00031545883,0.00045814365,0.0032447388,0.009398675,0.010455496,0.0011590376,0.0014400135,0.010360957],"category_scores_gemma":[0.016997447,0.00061587675,0.00043447537,0.007961946,0.013951425,0.0053402814,0.005663841,0.0023700036,0.0007663833],"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":[0.00018753299,0.000093343995,0.08431616,0.0011891648,0.000060817012,0.0007126553,0.37616688,0.0013331027,0.0017008578,0.3667582,0.015871828,0.15160945],"study_design_scores_gemma":[0.0000384073,0.00011039429,0.22944346,0.000986805,0.00005865457,0.00017184959,0.13769722,0.00066739804,0.0008227332,0.008213327,0.62168205,0.00010769929],"about_ca_topic_score_codex":0.85290515,"about_ca_topic_score_gemma":0.9303455,"teacher_disagreement_score":0.8645888,"about_ca_system_score_codex":0.13541119,"about_ca_system_score_gemma":0.16872106,"threshold_uncertainty_score":0.98248154},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8525393,0.0036671308,0.0021767756,0.08363247,0.00035568431,0.00014326336,0.00020385707,0.000085901025,0.05719571],"genre_scores_gemma":[0.9906675,0.00040973496,0.00066722766,0.0024998216,0.000027550874,0.00003169632,0.000019273215,0.000016596148,0.0056606494],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9859212,0.006126933,0.00025546056,0.00066513853,0.0015538074,0.005477402],"domain_scores_gemma":[0.9734524,0.008512329,0.001638392,0.0005656421,0.0026701987,0.013161051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008065962,0.00043865567,0.000484756,0.0016238858,0.03894872,0.013542599,0.003571081,0.0030815967,0.009590809],"category_scores_gemma":[0.010083945,0.00043796084,0.00036918573,0.0022196674,0.020692382,0.003758314,0.01063455,0.0034727543,0.00047918124],"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":[0.00008797916,0.00014268937,0.021808412,0.00038672757,0.000018399434,0.0037415922,0.8916741,0.0003627174,0.0018213869,0.033693377,0.020353556,0.025909021],"study_design_scores_gemma":[0.0000070511633,0.00006684894,0.008843859,0.00035645507,0.000009444475,0.00040614622,0.88908106,0.00012894247,0.00059503276,0.0014004664,0.09904479,0.000059873422],"about_ca_topic_score_codex":0.547479,"about_ca_topic_score_gemma":0.76527625,"teacher_disagreement_score":0.99193406,"about_ca_system_score_codex":0.054906823,"about_ca_system_score_gemma":0.10356784,"threshold_uncertainty_score":0.910372},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001711733,0.005256822,0.00023040002,0.051962074,0.94192755,0.000019837371,0.00003472988,0.00002800598,0.0005235378],"genre_scores_gemma":[0.00036279348,0.0044295248,0.00035488006,0.02226168,0.9701301,0.00004238426,0.000016768952,0.000029953273,0.002371951],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97658384,0.0076668686,0.0038552922,0.0017091947,0.009406302,0.00077844516],"domain_scores_gemma":[0.8069336,0.10274208,0.006380573,0.003429974,0.06679275,0.013721073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03906909,0.005104095,0.008190486,0.008503476,0.005174749,0.018826418,0.0049526244,0.027795386,0.010724594],"category_scores_gemma":[0.13871056,0.0019418567,0.0033416313,0.0040491484,0.0068416,0.0069524776,0.0023305758,0.038149744,0.008754475],"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":[0.000034956716,0.000020614358,0.00004841961,0.00034950703,0.00003906843,0.00004060166,0.000019854167,0.000029349832,0.000022715336,0.0005457908,0.99162805,0.007221027],"study_design_scores_gemma":[0.00031586832,0.000073655545,0.00085085415,0.0034874254,0.00039806496,0.0003138768,0.000252096,0.0008416317,0.00019345064,0.009828634,0.983352,0.00009234529],"about_ca_topic_score_codex":0.0039542504,"about_ca_topic_score_gemma":0.012436223,"teacher_disagreement_score":0.03906909,"about_ca_system_score_codex":0.0067314967,"about_ca_system_score_gemma":0.009028851,"threshold_uncertainty_score":0.20661956},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009072094,0.015852505,0.0670422,0.030899758,0.002079803,0.000071701346,0.000076547585,0.00011013069,0.88296014],"genre_scores_gemma":[0.18475835,0.036647763,0.07721328,0.022371495,0.0042734663,0.00072196487,0.00048877735,0.00080625695,0.6727186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939645,0.003701991,0.00015741603,0.00053990853,0.0013157349,0.00032049045],"domain_scores_gemma":[0.9952349,0.003521077,0.00011553251,0.0005159191,0.00039026004,0.00022231406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057109226,0.001350018,0.0010855751,0.0015514075,0.002500514,0.013411348,0.002274405,0.004781499,0.029086165],"category_scores_gemma":[0.00962604,0.00070558477,0.00068051537,0.0022033637,0.019968955,0.014089695,0.006241712,0.008627599,0.009338515],"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":[0.0000031370307,0.000009977339,0.0000137522575,0.00004990254,0.000003839555,0.000014032058,0.0004758089,0.00046373348,0.00003591333,0.97033554,0.014364964,0.0142294895],"study_design_scores_gemma":[0.000001848112,0.000002988004,0.000015557238,0.00013565249,0.0000014616633,0.000010862755,0.00021158681,0.0003356189,0.000051083345,0.8562484,0.14298058,0.000004446894],"about_ca_topic_score_codex":0.0025310344,"about_ca_topic_score_gemma":0.0026049477,"teacher_disagreement_score":0.029086165,"about_ca_system_score_codex":0.0052060257,"about_ca_system_score_gemma":0.004504515,"threshold_uncertainty_score":0.09730291},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9662868,0.0001288626,0.030845772,0.00012264091,0.000035097855,0.00004711578,0.00060161646,0.00019537851,0.0017366217],"genre_scores_gemma":[0.9916435,0.000052551783,0.007131707,0.000023033925,0.000014892485,0.000019976827,0.00087767467,0.000015815003,0.0002207905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996902,0.00010936547,0.000034190012,0.00007241802,0.000053438358,0.00004044536],"domain_scores_gemma":[0.9975666,0.0014325399,0.00022392605,0.00025302713,0.0004075825,0.00011636402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023301302,0.0005380766,0.0005690123,0.000501401,0.00034764662,0.0006977451,0.00058384385,0.0005202881,0.0008204835],"category_scores_gemma":[0.0054249824,0.00027207003,0.00055757124,0.00040757837,0.00029972807,0.00091090886,0.00070086267,0.0006460496,0.00013005067],"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":[0.00020661525,0.00007276302,0.037060622,0.000026340505,0.00020741345,0.00010252289,0.00007221921,0.9458194,0.0011545712,0.0005560346,0.00038983635,0.014331729],"study_design_scores_gemma":[0.000010462254,0.000049313534,0.011074065,0.0000067379665,0.000025328258,0.000010279112,0.000020233352,0.987703,0.0006830039,0.0002462852,0.00015963649,0.000011609998],"about_ca_topic_score_codex":0.014397952,"about_ca_topic_score_gemma":0.011204699,"teacher_disagreement_score":0.014397952,"about_ca_system_score_codex":0.00047925636,"about_ca_system_score_gemma":0.0007656198,"threshold_uncertainty_score":0.02862829},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9331713,0.0025063881,0.0007092884,0.012102528,0.000086617954,0.00035833564,0.0010744048,0.000027106837,0.049963944],"genre_scores_gemma":[0.991662,0.0014610868,0.00092416344,0.00074668083,0.000009190473,0.00012139902,0.0003549378,0.000019255946,0.004701144],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99452597,0.0011235698,0.00038485424,0.00046956414,0.0016919785,0.0018041187],"domain_scores_gemma":[0.981398,0.008003735,0.00093719835,0.00030334125,0.006931486,0.0024262012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074785706,0.00067490345,0.0006765814,0.0067752614,0.0428739,0.010887421,0.0024565905,0.0018384587,0.0024386551],"category_scores_gemma":[0.014477056,0.0004885221,0.0005641102,0.0154923275,0.013425039,0.0026992771,0.0050130878,0.0032436347,0.00015552687],"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":[0.000060494913,0.00004786007,0.020399032,0.00021824046,0.000012098706,0.00071586546,0.9513576,0.00022881066,0.00043871044,0.012579428,0.002646333,0.011295537],"study_design_scores_gemma":[0.0000037688264,0.000008188449,0.012969559,0.00023208107,0.000014935409,0.00004230087,0.9604366,0.00021383289,0.00019836925,0.0004682599,0.025389398,0.000022679002],"about_ca_topic_score_codex":0.99669087,"about_ca_topic_score_gemma":0.9972957,"teacher_disagreement_score":0.37415588,"about_ca_system_score_codex":0.37415588,"about_ca_system_score_gemma":0.44069758,"threshold_uncertainty_score":0.7258905},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008142145,0.024169372,0.57602847,0.3302623,0.007796332,0.004852422,0.00017842885,0.00042233523,0.048148185],"genre_scores_gemma":[0.1545658,0.008716178,0.78157413,0.034757804,0.0018848655,0.015488657,0.00009345067,0.00021915394,0.0026999812],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2548748,0.67789984,0.015355765,0.009890511,0.03913875,0.0028403993],"domain_scores_gemma":[0.33421886,0.58381855,0.012906536,0.030053332,0.031060912,0.007941779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.48693842,0.0028835149,0.0041747736,0.012552449,0.016509531,0.05371047,0.009374147,0.012388224,0.005647133],"category_scores_gemma":[0.43623096,0.0025791223,0.0037713551,0.0087915575,0.07874806,0.03152326,0.028042434,0.021840483,0.0019517202],"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":[0.00017406426,0.00034727235,0.0022708029,0.005131533,0.00045225536,0.00055665406,0.06957367,0.0019748705,0.00034812302,0.80902344,0.010676679,0.09947053],"study_design_scores_gemma":[0.00019305269,0.00031705434,0.0005220472,0.011422836,0.00014206441,0.00044316388,0.030756759,0.0025902577,0.0005985969,0.86028665,0.09258191,0.00014550719],"about_ca_topic_score_codex":0.0028015878,"about_ca_topic_score_gemma":0.003544162,"teacher_disagreement_score":0.48693842,"about_ca_system_score_codex":0.021767212,"about_ca_system_score_gemma":0.04793575,"threshold_uncertainty_score":0.6326963},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016520636,0.003497759,0.0005200492,0.914025,0.012354432,0.000094107694,0.0007624304,0.00020923374,0.0668849],"genre_scores_gemma":[0.04322081,0.0053728516,0.004729541,0.5098063,0.0035772908,0.00019333893,0.0011879388,0.0004432609,0.4314686],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9769936,0.0018974178,0.0006130787,0.0015663293,0.011076959,0.007852632],"domain_scores_gemma":[0.89512485,0.004750962,0.0009370848,0.0027569504,0.04319221,0.053237904],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0155208325,0.0010586663,0.0011953629,0.0029530916,0.02446664,0.016350025,0.0034652275,0.018301979,0.099139914],"category_scores_gemma":[0.04307246,0.00069395255,0.001651975,0.0033693174,0.008735114,0.008605836,0.01085717,0.016275384,0.012037448],"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":[0.00004345685,0.00002809137,0.0005860918,0.00008230122,0.000013435216,0.00010507099,0.00036494088,0.00006943298,0.00014699355,0.021367816,0.9656416,0.011550863],"study_design_scores_gemma":[0.000037902064,0.00001864311,0.002118113,0.00019150297,0.000016932514,0.00005818873,0.0014379369,0.000078683035,0.00011121894,0.0033378685,0.9925396,0.000053475662],"about_ca_topic_score_codex":0.9623048,"about_ca_topic_score_gemma":0.9726193,"teacher_disagreement_score":0.99653476,"about_ca_system_score_codex":0.06976633,"about_ca_system_score_gemma":0.41769853,"threshold_uncertainty_score":0.5061925},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11660365,0.13950779,0.0018913281,0.26949316,0.001878902,0.00036059026,0.0021354072,0.00030028992,0.46782893],"genre_scores_gemma":[0.75344193,0.085584596,0.0048212917,0.020561041,0.00037829383,0.00020327453,0.001175556,0.0002857391,0.1335482],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98565996,0.0016744818,0.0004093453,0.00057502754,0.0074878354,0.0041934163],"domain_scores_gemma":[0.9709565,0.0044489903,0.0011535473,0.0005461997,0.012834617,0.010060176],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0075427564,0.00048814624,0.00072430546,0.0074779014,0.024369681,0.019779908,0.0025277415,0.0029518101,0.013931925],"category_scores_gemma":[0.01643361,0.00058213295,0.00056555995,0.0205828,0.010719198,0.004144474,0.0077874376,0.0034262289,0.00077705045],"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":[0.00015628197,0.00018726994,0.024902338,0.0012037572,0.00009674016,0.00062067196,0.04888017,0.0010998815,0.0004121481,0.3066202,0.28321308,0.33260748],"study_design_scores_gemma":[0.00003845539,0.000048718543,0.034868363,0.0012244862,0.000052744916,0.000117721414,0.055678055,0.00059915317,0.00038367676,0.01302525,0.89385134,0.00011206178],"about_ca_topic_score_codex":0.99541867,"about_ca_topic_score_gemma":0.99800986,"teacher_disagreement_score":0.9974723,"about_ca_system_score_codex":0.227759,"about_ca_system_score_gemma":0.4772765,"threshold_uncertainty_score":0.8956901},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025269624,0.012138607,0.00030938792,0.020132113,0.006540308,0.00009769158,0.0256582,0.00059659436,0.9320002],"genre_scores_gemma":[0.0052729947,0.0040309723,0.00025605733,0.0005250088,0.00030341832,0.000031319934,0.0026553026,0.00021002688,0.9867148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987907,0.00008139367,0.000044121873,0.00015438825,0.00072167837,0.00020771704],"domain_scores_gemma":[0.9955787,0.00024258645,0.00010581588,0.00023567106,0.0026372795,0.0011998661],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012435972,0.0007973676,0.0010009983,0.0034610084,0.006564511,0.007206799,0.0007525947,0.0011032079,0.44539034],"category_scores_gemma":[0.005317908,0.0003049149,0.00048795642,0.004077952,0.0008166933,0.0012629938,0.0014481823,0.0016332173,0.18859722],"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":[0.000017234861,0.00001821983,0.00023292864,0.00006306969,0.0000027022743,0.00003221745,0.00017045389,0.000029213357,0.0000681693,0.002659904,0.9726465,0.024059406],"study_design_scores_gemma":[0.000002931777,0.0000047815442,0.0016935284,0.00014442245,0.0000032114294,0.000016095722,0.000319159,0.000027905975,0.00007660255,0.0005936815,0.99711156,0.0000062154395],"about_ca_topic_score_codex":0.37954074,"about_ca_topic_score_gemma":0.66797185,"teacher_disagreement_score":0.99924743,"about_ca_system_score_codex":0.013882221,"about_ca_system_score_gemma":0.024875768,"threshold_uncertainty_score":0.79108334},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004018133,0.0014349066,0.0072111567,0.20600113,0.014253059,0.0023713203,0.007662121,0.002159505,0.7548888],"genre_scores_gemma":[0.051368926,0.0014235207,0.020289754,0.33320075,0.004255031,0.0028313734,0.0091007585,0.0015232285,0.57600665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8389452,0.016296227,0.008370657,0.008053005,0.109164834,0.01917018],"domain_scores_gemma":[0.65047395,0.039155822,0.0054805507,0.03481679,0.2440147,0.02605817],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.08822596,0.00091464503,0.0016669591,0.00447875,0.014921566,0.023574771,0.007107353,0.023288954,0.03484975],"category_scores_gemma":[0.1873144,0.0018082003,0.001984811,0.008006152,0.0075806235,0.0074872607,0.008564248,0.019110387,0.029490277],"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":[0.000051753097,0.00009221677,0.00094979187,0.000116933006,0.000015152553,0.00009836526,0.0005509276,0.0001493253,0.00064258784,0.10402066,0.8804525,0.012859831],"study_design_scores_gemma":[0.000029826853,0.000031762997,0.002077889,0.0001935932,0.000019368283,0.000037717262,0.00026091063,0.00013642067,0.00035337804,0.002560137,0.9942334,0.00006546535],"about_ca_topic_score_codex":0.71773285,"about_ca_topic_score_gemma":0.7482592,"teacher_disagreement_score":0.9928926,"about_ca_system_score_codex":0.04811172,"about_ca_system_score_gemma":0.27862158,"threshold_uncertainty_score":0.56785893},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13309436,0.010428377,0.31468382,0.10453323,0.019209532,0.0028226534,0.00037442325,0.0020958052,0.41275787],"genre_scores_gemma":[0.8067606,0.0033896973,0.14345744,0.0052222917,0.0023611614,0.00172975,0.00061530905,0.002330096,0.03413375],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8810594,0.081872374,0.0052399444,0.010948361,0.015906615,0.004973207],"domain_scores_gemma":[0.87043786,0.05921123,0.009502133,0.018573333,0.02710164,0.01517387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.084335424,0.0015131487,0.0011928554,0.00985993,0.023591053,0.034032956,0.004714067,0.0054973345,0.010445737],"category_scores_gemma":[0.1619484,0.0017847508,0.0013876753,0.005506033,0.047394786,0.036978472,0.035733897,0.010332964,0.0034692644],"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":[0.00009190142,0.00009884382,0.0054879156,0.0005889097,0.000042873948,0.0017663611,0.6138776,0.00032266928,0.0015105014,0.26928255,0.02480397,0.08212594],"study_design_scores_gemma":[0.000031794134,0.0000966784,0.0030612245,0.0015880832,0.00006008718,0.00093944307,0.2932541,0.0010251186,0.0011528995,0.13469018,0.5639407,0.00015960292],"about_ca_topic_score_codex":0.0036123297,"about_ca_topic_score_gemma":0.0039285105,"teacher_disagreement_score":0.084335424,"about_ca_system_score_codex":0.009175577,"about_ca_system_score_gemma":0.020492608,"threshold_uncertainty_score":0.4460137},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00223522,0.0028017552,0.004834429,0.07169173,0.004370728,0.00033875628,0.004211072,0.0017102384,0.90780604],"genre_scores_gemma":[0.022773517,0.002608718,0.009975695,0.020234652,0.00036773697,0.0002050948,0.0031017826,0.0011633065,0.9395695],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875579,0.000664046,0.00014511563,0.0008330472,0.008814018,0.001985775],"domain_scores_gemma":[0.9812362,0.00096210634,0.00024756792,0.0010222251,0.010051154,0.0064807306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039164247,0.0007965675,0.0004635577,0.0027752738,0.015670296,0.0137660215,0.0017448639,0.004155877,0.1081572],"category_scores_gemma":[0.012296152,0.0006822896,0.0008916032,0.0033472597,0.004406292,0.0036867247,0.0063510463,0.004968332,0.019744687],"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":[0.000031501764,0.00003769383,0.0009887932,0.000094606345,0.000009228237,0.000105735126,0.0006660902,0.00013524348,0.00036087533,0.084568106,0.8521977,0.060804427],"study_design_scores_gemma":[0.000007803221,0.00000365948,0.0003531933,0.000024292927,0.0000022755405,0.000019113108,0.00021190336,0.000043915454,0.000121208555,0.0011792426,0.99802303,0.000010420882],"about_ca_topic_score_codex":0.8808597,"about_ca_topic_score_gemma":0.95526564,"teacher_disagreement_score":0.11914033,"about_ca_system_score_codex":0.054581888,"about_ca_system_score_gemma":0.2011788,"threshold_uncertainty_score":0.3960212},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002730828,0.004674461,0.00017128026,0.08910517,0.90488833,0.000030321753,0.000050735132,0.00003326961,0.0010191553],"genre_scores_gemma":[0.00068926555,0.0034274666,0.00023420817,0.035312,0.95615286,0.0000777317,0.000021204383,0.000037967133,0.004047272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9607555,0.014413476,0.00548552,0.0026295264,0.01524982,0.0014660719],"domain_scores_gemma":[0.6745857,0.23552606,0.009790724,0.005891681,0.061021812,0.013184112],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.076927766,0.003645786,0.005217979,0.006013706,0.0062032235,0.016909372,0.005797418,0.04585286,0.016663134],"category_scores_gemma":[0.25531352,0.002167064,0.0040315893,0.0035474133,0.006072849,0.0074453275,0.0031430211,0.03662642,0.008167864],"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":[0.000045516044,0.000014658435,0.000035341505,0.0003898252,0.000043821936,0.000049113773,0.000029509196,0.00003077544,0.00002038675,0.00082737306,0.992332,0.006181699],"study_design_scores_gemma":[0.0003913715,0.000060599752,0.00078916503,0.002819926,0.00037487465,0.00014855021,0.00018309438,0.00064253085,0.00016595269,0.009308605,0.98503184,0.00008343599],"about_ca_topic_score_codex":0.0049168193,"about_ca_topic_score_gemma":0.01590566,"teacher_disagreement_score":0.9230722,"about_ca_system_score_codex":0.008073107,"about_ca_system_score_gemma":0.0119955605,"threshold_uncertainty_score":0.40683776},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015102148,0.0792226,0.215638,0.4362875,0.0060797986,0.009134169,0.0008512414,0.0016806213,0.23600392],"genre_scores_gemma":[0.19915606,0.08612309,0.6260036,0.04369681,0.0010877246,0.019408057,0.0012746889,0.0008871072,0.022362892],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.77142614,0.17387193,0.017199099,0.008165416,0.021339992,0.0079974625],"domain_scores_gemma":[0.7587117,0.15787277,0.012146461,0.020565664,0.035259955,0.015443419],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.15839481,0.0025595836,0.002146943,0.015669046,0.014046889,0.043406986,0.008551811,0.012447701,0.018475931],"category_scores_gemma":[0.15456097,0.0018973796,0.004079862,0.013115351,0.019632643,0.038883746,0.03743227,0.012045339,0.008416722],"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":[0.000099019824,0.00053600257,0.003388106,0.02707566,0.00028548075,0.001767946,0.16370457,0.0010924331,0.0018098354,0.30109218,0.05862807,0.44052067],"study_design_scores_gemma":[0.00010025455,0.00012582776,0.0017519674,0.050201144,0.00017012403,0.00079435844,0.12396852,0.0005186588,0.0013056992,0.1922516,0.6286648,0.00014708987],"about_ca_topic_score_codex":0.006740021,"about_ca_topic_score_gemma":0.012581246,"teacher_disagreement_score":0.99144816,"about_ca_system_score_codex":0.018642439,"about_ca_system_score_gemma":0.08074535,"threshold_uncertainty_score":0.83768183},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98909736,0.00022980402,0.0019468634,0.0003834833,0.000092491566,0.0037457745,0.0005817903,0.000091322596,0.003831061],"genre_scores_gemma":[0.9566048,0.00033325795,0.012487874,0.00062787405,0.000076671466,0.024306392,0.0007123069,0.000038511018,0.004812462],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965772,0.0023563951,0.0002214493,0.000401214,0.0002492411,0.00019444451],"domain_scores_gemma":[0.97947913,0.015368311,0.0019744448,0.0013343819,0.00085610495,0.0009876475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005502864,0.0007627364,0.0009863672,0.0005042494,0.001086822,0.00066251174,0.00093227223,0.0014037804,0.012445848],"category_scores_gemma":[0.017904436,0.0005040464,0.0009315711,0.00043194104,0.00085803727,0.0006825855,0.0010876501,0.0017142401,0.0009100765],"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":[0.23587221,0.21278955,0.028927961,0.005478029,0.0025733004,0.00027314472,0.008456569,0.008829192,0.029614124,0.0051136017,0.014689118,0.44738317],"study_design_scores_gemma":[0.14996563,0.61469865,0.14056507,0.0007681992,0.0033555112,0.00018857981,0.004294833,0.010274299,0.029756548,0.00853461,0.037379283,0.00021879835],"about_ca_topic_score_codex":0.0010844992,"about_ca_topic_score_gemma":0.003048925,"teacher_disagreement_score":0.012445848,"about_ca_system_score_codex":0.0008928044,"about_ca_system_score_gemma":0.0011716562,"threshold_uncertainty_score":0.041635454},"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":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054408057,0.011053299,0.008183019,0.014358722,0.014165841,0.0003217629,0.054714926,0.0072716195,0.88938665],"genre_scores_gemma":[0.0057674237,0.017102798,0.005771325,0.0028992093,0.0065416084,0.00028187502,0.061760765,0.004974726,0.89490014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951748,0.00050284574,0.0006628869,0.0006123024,0.0026455019,0.00040153108],"domain_scores_gemma":[0.97995865,0.0025378235,0.00089253846,0.0064185476,0.0069975527,0.0031948755],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035187907,0.001667629,0.0027663999,0.018964963,0.0027887379,0.02874144,0.0024509856,0.0031188724,0.69582826],"category_scores_gemma":[0.027633764,0.0009860035,0.0012044648,0.045695633,0.0023237804,0.011183044,0.00786766,0.0033839683,0.48018593],"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":[0.000014614935,0.00002657057,0.00021001029,0.0003765487,0.000015016469,0.00004722229,0.00014055884,0.00009916674,0.00017625322,0.025707098,0.9273485,0.04583849],"study_design_scores_gemma":[0.0000054400143,0.0000058500973,0.00030218696,0.00033046782,0.0000057132934,0.000025660845,0.00007841965,0.00004224235,0.000039621755,0.0052637677,0.9938933,0.0000071715726],"about_ca_topic_score_codex":0.008886562,"about_ca_topic_score_gemma":0.016099686,"teacher_disagreement_score":0.997549,"about_ca_system_score_codex":0.0057420274,"about_ca_system_score_gemma":0.0094004115,"threshold_uncertainty_score":0.43386406},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016203752,0.7077273,0.05928292,0.12099359,0.009856594,0.0010309382,0.0037926335,0.00078063994,0.09491493],"genre_scores_gemma":[0.03255976,0.7079705,0.12350208,0.016540915,0.001230842,0.002187964,0.0023927705,0.0011412613,0.112473845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920374,0.0036055092,0.00076336134,0.00049599976,0.002815706,0.00028205986],"domain_scores_gemma":[0.9506915,0.031846594,0.0021781798,0.00090303697,0.013072381,0.0013081777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022284733,0.0013459251,0.0010114503,0.005069396,0.0051693935,0.007810595,0.0029411092,0.0035530273,0.026823327],"category_scores_gemma":[0.051324863,0.0029446897,0.00095836807,0.0076831058,0.0071114562,0.00800697,0.0031390588,0.0065126834,0.012445187],"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":[0.000031079948,0.000023182763,0.0007283228,0.0032969392,0.000021923228,0.0001453278,0.009096297,0.00018222399,0.00044914635,0.014193144,0.6324476,0.3393848],"study_design_scores_gemma":[0.000016715368,0.000023621777,0.0017855346,0.0071545998,0.00004120607,0.0002499707,0.0044323583,0.00012618849,0.00042903327,0.012870722,0.97280574,0.00006422424],"about_ca_topic_score_codex":0.26813415,"about_ca_topic_score_gemma":0.48675674,"teacher_disagreement_score":0.7318659,"about_ca_system_score_codex":0.00969266,"about_ca_system_score_gemma":0.039253246,"threshold_uncertainty_score":0.53314686},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019700557,0.0347237,0.040223643,0.6538499,0.0035647685,0.00032351047,0.000076575794,0.00018289065,0.24735454],"genre_scores_gemma":[0.89035803,0.018754683,0.02494467,0.051349103,0.0029330954,0.00089868,0.000055915934,0.00032425515,0.01038155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7794468,0.18732125,0.0030315134,0.008666636,0.015132903,0.0064009414],"domain_scores_gemma":[0.63115066,0.3065518,0.009978756,0.0129855005,0.011563176,0.027770136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14584704,0.0012360475,0.0022995532,0.009381323,0.018476099,0.039307844,0.004118023,0.010694075,0.010247117],"category_scores_gemma":[0.11705373,0.00162681,0.0011094185,0.0051903604,0.1436176,0.032852095,0.036782447,0.01823915,0.00155304],"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":[0.00006535899,0.00022812809,0.0026057581,0.0005027698,0.00011287152,0.00039231215,0.08677902,0.0003626765,0.00016157556,0.84244573,0.01678926,0.049554497],"study_design_scores_gemma":[0.000095330994,0.00012534154,0.0015730012,0.0015959763,0.000035989055,0.00028086247,0.060763374,0.00047293302,0.00011138957,0.7875651,0.14728509,0.000095599484],"about_ca_topic_score_codex":0.0076942085,"about_ca_topic_score_gemma":0.008723544,"teacher_disagreement_score":0.14584704,"about_ca_system_score_codex":0.017768975,"about_ca_system_score_gemma":0.03542409,"threshold_uncertainty_score":0.7713221},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007424458,0.02051372,0.25026864,0.6918397,0.014969317,0.002460383,0.00008825384,0.00029745945,0.012138076],"genre_scores_gemma":[0.2958269,0.014926763,0.42995572,0.235182,0.006831939,0.012620247,0.000077770084,0.0006904249,0.0038882284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.18528564,0.69849735,0.042196184,0.016552178,0.054011576,0.0034570668],"domain_scores_gemma":[0.11112911,0.7448978,0.01748067,0.059275325,0.06471221,0.002504895],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6921039,0.0025856576,0.004043718,0.007271818,0.014548474,0.024782516,0.0086423475,0.020153148,0.0025001515],"category_scores_gemma":[0.74565065,0.0028861389,0.004632846,0.0047865687,0.08621913,0.046384405,0.023427853,0.061030217,0.00087157905],"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":[0.00027802808,0.00013995003,0.001515746,0.009278689,0.00031047908,0.0010717083,0.2569403,0.0011910805,0.0018313229,0.5890148,0.04048135,0.097946495],"study_design_scores_gemma":[0.00022177427,0.00042550114,0.0011905641,0.02987457,0.00031447515,0.001922274,0.057337984,0.0041868766,0.007962887,0.49186245,0.40432933,0.00037134375],"about_ca_topic_score_codex":0.0039021797,"about_ca_topic_score_gemma":0.0029338875,"teacher_disagreement_score":0.30789608,"about_ca_system_score_codex":0.027901195,"about_ca_system_score_gemma":0.047659997,"threshold_uncertainty_score":0.3796907},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25869545,0.006859187,0.02854218,0.42919773,0.006892452,0.0007015238,0.0019003947,0.0011263804,0.2660847],"genre_scores_gemma":[0.7529055,0.0047541764,0.025937516,0.055271503,0.0013731342,0.00075346633,0.0024716225,0.0013080726,0.15522496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97743213,0.014273599,0.00028566882,0.00082520425,0.0036065085,0.0035768116],"domain_scores_gemma":[0.97403157,0.0027918646,0.00041634438,0.0005788727,0.0031749418,0.019006412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023332529,0.00045466534,0.00031213547,0.00072619645,0.0070985453,0.009585245,0.001961837,0.0030762148,0.01140266],"category_scores_gemma":[0.018201813,0.00033172962,0.00047972184,0.0020693166,0.004527297,0.005059415,0.011587085,0.006877382,0.0031915058],"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":[0.00068525696,0.0033510304,0.015877472,0.0006503311,0.00006130273,0.0024386987,0.10224169,0.0017866999,0.0015802027,0.122971356,0.36674628,0.38160968],"study_design_scores_gemma":[0.000048532573,0.00035449144,0.005827103,0.00022078402,0.000008786492,0.0003044356,0.05117409,0.00071761385,0.00061358843,0.009154159,0.93153274,0.000043651722],"about_ca_topic_score_codex":0.026851982,"about_ca_topic_score_gemma":0.04876115,"teacher_disagreement_score":0.026851982,"about_ca_system_score_codex":0.008713617,"about_ca_system_score_gemma":0.018425828,"threshold_uncertainty_score":0},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019658236,0.004300476,0.42664567,0.3564267,0.0072471667,0.0038719068,0.00040485105,0.00032894575,0.18111613],"genre_scores_gemma":[0.60783046,0.0044561755,0.2874415,0.05184654,0.0019448132,0.013250242,0.0002523672,0.00027588248,0.03270196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8903934,0.09081513,0.0021279631,0.0023424444,0.012041978,0.0022791424],"domain_scores_gemma":[0.60399485,0.33807382,0.0061178794,0.024526425,0.02174881,0.005538325],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10691485,0.0009445975,0.00089586223,0.00809479,0.012321816,0.015846172,0.005114986,0.0066408804,0.022327114],"category_scores_gemma":[0.16477105,0.0009861826,0.0010922899,0.0037622992,0.047549408,0.023181383,0.019940704,0.007474427,0.0030633016],"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":[0.000036578353,0.000166089,0.0007378612,0.0008703594,0.00002043293,0.00029349505,0.07384783,0.00027212512,0.00040429257,0.874265,0.017255234,0.031830564],"study_design_scores_gemma":[0.000062342544,0.00003496859,0.0003797027,0.0029234942,0.000028524857,0.00036965965,0.09806226,0.0010474083,0.00093122723,0.76409626,0.13202332,0.000040902472],"about_ca_topic_score_codex":0.003842219,"about_ca_topic_score_gemma":0.0064604036,"teacher_disagreement_score":0.8930851,"about_ca_system_score_codex":0.0123439105,"about_ca_system_score_gemma":0.019462435,"threshold_uncertainty_score":0.5654265},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14381218,0.007769066,0.011409528,0.6931765,0.0057775304,0.00032016163,0.0012745732,0.0005614373,0.13589905],"genre_scores_gemma":[0.7443038,0.007651285,0.019200575,0.119200885,0.0019231144,0.0005806959,0.0021915769,0.0009809019,0.103967175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9693671,0.01836822,0.00041573177,0.0009767466,0.0052448004,0.005627375],"domain_scores_gemma":[0.9561039,0.0047828923,0.00074606616,0.0007237896,0.004848571,0.032794755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0359153,0.00046096515,0.00037179922,0.0007897722,0.007598685,0.012550356,0.0022343113,0.0045455117,0.011437609],"category_scores_gemma":[0.027913898,0.0003658796,0.00055901834,0.0023228652,0.0054753134,0.0063024885,0.013120809,0.009433393,0.0028848876],"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":[0.0006457397,0.0026056068,0.018700859,0.0005958235,0.000060400507,0.0018353673,0.0780481,0.0013937773,0.0012291499,0.11447127,0.4695544,0.31085962],"study_design_scores_gemma":[0.00004597421,0.00035398398,0.0069398307,0.0002992168,0.000009422555,0.0002972002,0.05618465,0.00058773736,0.0005194858,0.009348432,0.92536557,0.00004857572],"about_ca_topic_score_codex":0.033443768,"about_ca_topic_score_gemma":0.061698332,"teacher_disagreement_score":0.0359153,"about_ca_system_score_codex":0.0111914,"about_ca_system_score_gemma":0.028603705,"threshold_uncertainty_score":0.18994051},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010642296,0.011228532,0.76467663,0.028815234,0.002197141,0.052902155,0.00602494,0.012624529,0.110888645],"genre_scores_gemma":[0.016188363,0.0067682154,0.93347335,0.0017910519,0.0002050233,0.032728266,0.0021403113,0.0013257356,0.0053796545],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8789893,0.08926863,0.01433613,0.0021955078,0.013251579,0.0019589232],"domain_scores_gemma":[0.8173057,0.15232962,0.004280025,0.008751533,0.012954006,0.004379205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09079083,0.0024878003,0.002196233,0.009638976,0.0034747499,0.012219741,0.0053454763,0.0037538386,0.016325044],"category_scores_gemma":[0.10973473,0.002561206,0.004224651,0.009392635,0.00802509,0.011510667,0.019861072,0.009193212,0.007152403],"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":[0.00029005608,0.001207107,0.0043802382,0.021921972,0.00027491685,0.0008030685,0.050995976,0.005732383,0.002632588,0.08482244,0.1183148,0.70862454],"study_design_scores_gemma":[0.00027308465,0.0005627619,0.005409304,0.018887268,0.00015710822,0.0010905825,0.014050305,0.0032356603,0.0021292493,0.124834485,0.82891196,0.00045826018],"about_ca_topic_score_codex":0.0042488477,"about_ca_topic_score_gemma":0.009548051,"teacher_disagreement_score":0.09079083,"about_ca_system_score_codex":0.008786896,"about_ca_system_score_gemma":0.017433457,"threshold_uncertainty_score":0.48015356},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86856675,0.017388254,0.006583044,0.046675228,0.0003591864,0.004668333,0.002455886,0.00025961985,0.053043675],"genre_scores_gemma":[0.97262496,0.005681091,0.01309032,0.0032353662,0.00004251823,0.0010175465,0.00067045726,0.00009887067,0.003538742],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9302349,0.02721508,0.00419472,0.0023795802,0.02346071,0.012515027],"domain_scores_gemma":[0.8850903,0.021724096,0.0047480217,0.003668663,0.06358312,0.02118576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.066571824,0.000807885,0.0012808993,0.0030160777,0.025812702,0.010920833,0.004762768,0.0022023364,0.002005029],"category_scores_gemma":[0.059012495,0.0007630723,0.0010982868,0.013366419,0.011094294,0.0029749635,0.012256222,0.0038140845,0.00021941318],"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":true,"study_design_scores_codex":[0.00084615604,0.002057912,0.11476391,0.0037087894,0.00042079002,0.0020049582,0.5339356,0.0030532146,0.002413432,0.019342443,0.029532177,0.28792065],"study_design_scores_gemma":[0.00032382802,0.002247701,0.21112533,0.005697219,0.00050990947,0.00053511694,0.5893126,0.003565198,0.0033765852,0.0044383723,0.17839177,0.00047640514],"about_ca_topic_score_codex":0.9890326,"about_ca_topic_score_gemma":0.99127114,"teacher_disagreement_score":0.93342817,"about_ca_system_score_codex":0.30022034,"about_ca_system_score_gemma":0.5144444,"threshold_uncertainty_score":0.8116452},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08635107,0.017165804,0.08102229,0.7334419,0.0027581132,0.026360843,0.00052518444,0.0011733255,0.051201444],"genre_scores_gemma":[0.29728913,0.013482275,0.62769794,0.03265237,0.00026517003,0.024833882,0.00044857422,0.00013690164,0.0031937636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8720765,0.09779697,0.007867103,0.0027318755,0.009911377,0.009616023],"domain_scores_gemma":[0.8152,0.09833333,0.008715262,0.0049126353,0.025271192,0.047567695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16316873,0.0017751686,0.0015261939,0.0040504774,0.01082245,0.017030025,0.006882549,0.008606466,0.007065976],"category_scores_gemma":[0.12789007,0.0014023782,0.00223356,0.003526956,0.008739847,0.012783247,0.017805073,0.011911441,0.00093500805],"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":[0.00039852894,0.0026181834,0.024198504,0.010709514,0.0002087964,0.00093954674,0.06886114,0.0022559315,0.0013819059,0.035783872,0.038348705,0.81429535],"study_design_scores_gemma":[0.00107406,0.0028158023,0.050631907,0.066199,0.000807476,0.0010887206,0.49291745,0.0114414655,0.0034586438,0.09064399,0.27834988,0.00057172246],"about_ca_topic_score_codex":0.036845386,"about_ca_topic_score_gemma":0.087217145,"teacher_disagreement_score":0.16316873,"about_ca_system_score_codex":0.027536718,"about_ca_system_score_gemma":0.24964419,"threshold_uncertainty_score":0.86292905},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.973881,0.00013417426,0.0010314566,0.0003353152,0.000015066199,0.000018290233,0.00044112728,0.000016329268,0.02412723],"genre_scores_gemma":[0.9990314,0.000054817203,0.00012479973,0.000036178026,0.000005065357,0.000008103987,0.00016213249,0.000006300856,0.0005711778],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99838793,0.00059018435,0.000075114855,0.00019807424,0.0002882722,0.00046051003],"domain_scores_gemma":[0.9929844,0.0023113252,0.0018421526,0.0005397217,0.0016152179,0.0007072533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013070357,0.00014920879,0.00026868796,0.0016538374,0.0010742587,0.0028428393,0.0001679167,0.0003447117,0.0037112266],"category_scores_gemma":[0.007589378,0.00011998375,0.00019821992,0.0021562285,0.0016113904,0.001305731,0.0018379557,0.0004995796,0.00047967955],"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":[0.00051697664,0.0000732416,0.92958194,0.00010784407,0.00015868644,0.00016932921,0.013095466,0.0013179119,0.0029790506,0.010304488,0.0025836558,0.039111502],"study_design_scores_gemma":[0.000008781792,0.00004157899,0.9676096,0.00004915775,0.000037161568,0.000061955114,0.019972367,0.0009715721,0.0008636019,0.0034650434,0.0068946774,0.00002454361],"about_ca_topic_score_codex":0.0117998915,"about_ca_topic_score_gemma":0.012968499,"teacher_disagreement_score":0.0117998915,"about_ca_system_score_codex":0.0010687592,"about_ca_system_score_gemma":0.0005314727,"threshold_uncertainty_score":0.023462415},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20439348,0.031096688,0.1851681,0.38150904,0.001411306,0.0013201331,0.00006295594,0.0004877738,0.1945505],"genre_scores_gemma":[0.9195484,0.0074838996,0.06388923,0.0050216857,0.00025136617,0.0003668048,0.000016552476,0.000088786495,0.0033332459],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9053203,0.08204155,0.0022514062,0.0026630175,0.0044145556,0.0033091777],"domain_scores_gemma":[0.871446,0.10909789,0.0035012325,0.0061827544,0.005520952,0.004251246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.100890435,0.0009541666,0.0009580353,0.0042737317,0.0061513474,0.011399768,0.0028704526,0.004150292,0.002480328],"category_scores_gemma":[0.08824658,0.0005716444,0.00078253815,0.0033243597,0.034563567,0.015227148,0.016345961,0.0064179506,0.0003387084],"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":[0.00019992015,0.0006744221,0.011522393,0.0018804742,0.00008999599,0.0015787673,0.16917111,0.0040908796,0.000889551,0.2788141,0.013453563,0.51763475],"study_design_scores_gemma":[0.00016119641,0.00062024366,0.007914078,0.010095417,0.00006114633,0.0010600236,0.21149276,0.004397448,0.0035906453,0.51385653,0.24650748,0.00024301591],"about_ca_topic_score_codex":0.0063882964,"about_ca_topic_score_gemma":0.0069888085,"teacher_disagreement_score":0.100890435,"about_ca_system_score_codex":0.011815776,"about_ca_system_score_gemma":0.019007742,"threshold_uncertainty_score":0.533566},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019197645,0.032701507,0.0032339515,0.66928506,0.0021236518,0.00005287698,0.0005855753,0.00009624806,0.2727235],"genre_scores_gemma":[0.6455084,0.036662683,0.004986658,0.17511013,0.0018049157,0.00009094171,0.00034908912,0.00036197735,0.13512513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99229324,0.0009784581,0.00011684043,0.0007679251,0.0019758292,0.003867665],"domain_scores_gemma":[0.98067564,0.0043703243,0.00070656056,0.000733775,0.00846863,0.0050450144],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004698361,0.00052088825,0.00076634175,0.0025978817,0.015661428,0.021570545,0.0019129007,0.0067458237,0.021243645],"category_scores_gemma":[0.01978708,0.00031580913,0.00062294403,0.0061209304,0.016679447,0.013092801,0.004862281,0.007996524,0.0012044545],"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":[0.0000885458,0.00003808257,0.004780785,0.00044307095,0.000039200637,0.00050851575,0.0084742,0.00066151144,0.00049497216,0.6761118,0.2531669,0.05519238],"study_design_scores_gemma":[0.00001890693,0.000017288135,0.00854835,0.0012246825,0.0000564489,0.00013645315,0.018739078,0.0003521028,0.00037317188,0.09074081,0.8796974,0.000095292446],"about_ca_topic_score_codex":0.9828342,"about_ca_topic_score_gemma":0.98810416,"teacher_disagreement_score":0.9980871,"about_ca_system_score_codex":0.06750039,"about_ca_system_score_gemma":0.16673017,"threshold_uncertainty_score":0.48975188},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15195735,0.0041594636,0.0011080405,0.041609693,0.000698995,0.00024307688,0.006555529,0.0003716288,0.79329634],"genre_scores_gemma":[0.62477964,0.0025491633,0.0015172446,0.0050828527,0.00009851844,0.00008067471,0.0026186225,0.00014808931,0.36312518],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956636,0.00027302533,0.00008947584,0.00038290286,0.0016768412,0.0019141437],"domain_scores_gemma":[0.98940456,0.0005684658,0.00025691307,0.00029590883,0.004857266,0.0046169464],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0018514055,0.00025301208,0.00047629452,0.003648215,0.019808734,0.0113563435,0.0011473508,0.0012333896,0.043592285],"category_scores_gemma":[0.0076771933,0.00042380678,0.0004940802,0.006975984,0.0024719457,0.0017873998,0.0034568664,0.0021756825,0.0031267088],"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":[0.00024746236,0.0002748448,0.0715785,0.0003797368,0.00006467532,0.0010379634,0.013474116,0.0010834883,0.0008153473,0.27507514,0.451999,0.18396974],"study_design_scores_gemma":[0.000037510465,0.000026921887,0.09738603,0.00026637933,0.000025146952,0.0001239085,0.012149074,0.0010284878,0.0003793947,0.005375689,0.88314414,0.000057323476],"about_ca_topic_score_codex":0.9975666,"about_ca_topic_score_gemma":0.99880195,"teacher_disagreement_score":0.99885267,"about_ca_system_score_codex":0.14437339,"about_ca_system_score_gemma":0.25017935,"threshold_uncertainty_score":0.9924056},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028298944,0.0029926891,0.9114058,0.0093885865,0.00033282302,0.0004089813,0.004053362,0.00080183696,0.042316996],"genre_scores_gemma":[0.76045614,0.0022953919,0.2182996,0.0020152663,0.0005848788,0.00088780955,0.005634923,0.00024350887,0.009582476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9879566,0.007903708,0.00051959197,0.0019799995,0.0013412886,0.00029877745],"domain_scores_gemma":[0.90619195,0.082423985,0.0035583056,0.0046564043,0.0024529663,0.00071639847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014626704,0.0016118537,0.0015464482,0.0042916015,0.0013792857,0.0054424643,0.002485761,0.0025571247,0.0231285],"category_scores_gemma":[0.12027611,0.0010956138,0.0024862695,0.0029826632,0.0033939404,0.007775123,0.0029805012,0.0037256537,0.0027781443],"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":[0.00030908384,0.00018970722,0.020115972,0.0009324343,0.0007788462,0.00063206564,0.0021132,0.04459828,0.00045676867,0.73312277,0.018415578,0.17833534],"study_design_scores_gemma":[0.000042419837,0.000021445256,0.0018579768,0.000146401,0.0000725079,0.00014030818,0.00017590853,0.11270562,0.00019761128,0.87822145,0.006388154,0.00003021288],"about_ca_topic_score_codex":0.0094075315,"about_ca_topic_score_gemma":0.009377385,"teacher_disagreement_score":0.0231285,"about_ca_system_score_codex":0.0030469901,"about_ca_system_score_gemma":0.0018497929,"threshold_uncertainty_score":0.07737255},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016246377,0.016668916,0.012688762,0.009245428,0.0008369082,0.00004511968,0.000026791582,0.000050856383,0.9588126],"genre_scores_gemma":[0.124930516,0.03375972,0.017179282,0.004203002,0.0013835243,0.00043018692,0.00016089044,0.00024794368,0.8177049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99395025,0.004004412,0.00011067881,0.00027974715,0.0012756123,0.0003792393],"domain_scores_gemma":[0.99729615,0.0017876066,0.00011779259,0.00025414437,0.00039073205,0.00015350369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005492506,0.0007898667,0.0006635933,0.0018562645,0.0025736035,0.010946327,0.0009415106,0.003035775,0.01202771],"category_scores_gemma":[0.005768795,0.00038433183,0.00035824036,0.0046211365,0.0069593517,0.008610336,0.0059749326,0.0028039906,0.003259641],"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":[0.00000283736,0.0000113809265,0.00005576904,0.000061916246,0.0000029266123,0.000025138204,0.0006864549,0.0004349592,0.000048305017,0.937024,0.01967519,0.041971095],"study_design_scores_gemma":[0.0000018929044,0.0000066441016,0.0001157659,0.00030205,0.0000027931594,0.00004992052,0.0010168584,0.00033517307,0.000119937,0.62635875,0.37168452,0.000005556932],"about_ca_topic_score_codex":0.002253605,"about_ca_topic_score_gemma":0.0049754973,"teacher_disagreement_score":0.01202771,"about_ca_system_score_codex":0.005389095,"about_ca_system_score_gemma":0.0054320754,"threshold_uncertainty_score":0.04023671},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516615,0.0007454492,0.00817365,0.0034829106,0.000062240055,0.0002230065,0.00013059599,0.000089569956,0.035431035],"genre_scores_gemma":[0.9718411,0.0005536731,0.0077644796,0.00034288593,0.000009525962,0.00017268326,0.00011988795,0.000031159747,0.019164626],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99138665,0.004345561,0.00026161384,0.000643509,0.0024741443,0.0008884693],"domain_scores_gemma":[0.96956795,0.011622576,0.002086797,0.0012618749,0.012844607,0.0026161321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012872245,0.0005145057,0.00047727273,0.0015173055,0.0046572713,0.005407731,0.00096036436,0.0011303751,0.005235143],"category_scores_gemma":[0.026466157,0.00030168094,0.00045368623,0.001327198,0.0036438259,0.001692368,0.0027610955,0.002006561,0.0006472101],"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":[0.00030823998,0.0005726525,0.15108728,0.00057544204,0.000104182196,0.00079061097,0.6058719,0.0010384023,0.008147284,0.009191203,0.0054714377,0.2168413],"study_design_scores_gemma":[0.000037879803,0.0005653159,0.4187381,0.0008110456,0.000104103274,0.00032586924,0.4852559,0.0032423297,0.004717467,0.0034961884,0.08250033,0.00020547875],"about_ca_topic_score_codex":0.48510903,"about_ca_topic_score_gemma":0.6882014,"teacher_disagreement_score":0.51489097,"about_ca_system_score_codex":0.020005457,"about_ca_system_score_gemma":0.034621228,"threshold_uncertainty_score":0.96457076},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5471875,0.003198226,0.02277453,0.14931642,0.00030456364,0.00032917553,0.00009097843,0.00007581094,0.27672273],"genre_scores_gemma":[0.99277323,0.0008083848,0.0023793096,0.0013197117,0.000024056519,0.00010750161,0.000022850814,0.000015775806,0.0025493724],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9750779,0.014537181,0.00089479657,0.0016750785,0.0027320168,0.005082959],"domain_scores_gemma":[0.93755686,0.04715269,0.0037063465,0.0017748409,0.0046554655,0.005153733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042931642,0.0003725519,0.00036921125,0.0032865377,0.008657239,0.017187104,0.0020360104,0.005151814,0.0037964566],"category_scores_gemma":[0.05198839,0.0011098472,0.00046558818,0.0016621683,0.032691456,0.016096454,0.016435847,0.006354947,0.00044746257],"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":[0.000028566294,0.00009647204,0.00948029,0.00035452613,0.000016809312,0.00073177455,0.6087597,0.0007279522,0.00096548203,0.3510586,0.0025774096,0.025202395],"study_design_scores_gemma":[0.000026025773,0.00009609057,0.013542849,0.0016928447,0.000024167543,0.0005181634,0.6325268,0.0021015818,0.0014157351,0.18707074,0.16090749,0.00007746088],"about_ca_topic_score_codex":0.010686764,"about_ca_topic_score_gemma":0.0061647575,"teacher_disagreement_score":0.042931642,"about_ca_system_score_codex":0.01576472,"about_ca_system_score_gemma":0.042119585,"threshold_uncertainty_score":0.22704697},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022481482,0.048023723,0.47461417,0.14064531,0.0013741045,0.0021299093,0.00075240235,0.00064991286,0.30932903],"genre_scores_gemma":[0.7432141,0.028058387,0.19628622,0.008496804,0.0006930374,0.0046942583,0.00039084573,0.00032946613,0.017836982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90642184,0.08254065,0.0015790322,0.002438617,0.005752508,0.0012674299],"domain_scores_gemma":[0.8996687,0.08347393,0.00393809,0.0048300526,0.0063166074,0.0017726348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05965632,0.0026236335,0.0021466897,0.007989075,0.0038197485,0.017460005,0.0036514248,0.004581306,0.009281097],"category_scores_gemma":[0.06352913,0.0009808718,0.002879695,0.0066457926,0.030969566,0.018924529,0.0053676376,0.00574596,0.001211397],"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":[0.00009207498,0.00014166792,0.0016201707,0.0014337738,0.00011209687,0.00006151002,0.006958306,0.0056008874,0.00006646957,0.9422372,0.00397811,0.03769775],"study_design_scores_gemma":[0.00011767982,0.00020317742,0.0017681811,0.004494212,0.000192562,0.00010179154,0.006506549,0.012409266,0.00030175803,0.91191256,0.061920956,0.000071386894],"about_ca_topic_score_codex":0.018048763,"about_ca_topic_score_gemma":0.010437789,"teacher_disagreement_score":0.05965632,"about_ca_system_score_codex":0.023453308,"about_ca_system_score_gemma":0.029003002,"threshold_uncertainty_score":0.31549656},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024114482,0.95301765,0.010708602,0.0051951474,0.0009801935,0.002916556,0.0010218541,0.000054966116,0.001990647],"genre_scores_gemma":[0.42081872,0.5218398,0.03251968,0.0070438087,0.001007688,0.014807839,0.001348166,0.00013655059,0.00047778114],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.39705834,0.32616898,0.18227258,0.018012982,0.07412668,0.0023603758],"domain_scores_gemma":[0.14220601,0.6988387,0.103621185,0.016997779,0.036623586,0.0017128242],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34189454,0.001366792,0.007258726,0.026085181,0.0026249392,0.011185951,0.0037862773,0.004195461,0.002000997],"category_scores_gemma":[0.69563234,0.0028857864,0.008090867,0.028800042,0.005545353,0.010439124,0.006589376,0.00271234,0.0003542823],"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":[0.0005619868,0.00012358536,0.08219012,0.7129799,0.02158335,0.00058644626,0.012932473,0.00039346106,0.0005363377,0.0056035267,0.0035507707,0.15895802],"study_design_scores_gemma":[0.00031342174,0.0004227358,0.04095095,0.89495194,0.020856997,0.0023332213,0.008732166,0.00075621204,0.00073817687,0.0040981756,0.025654558,0.0001914706],"about_ca_topic_score_codex":0.008379609,"about_ca_topic_score_gemma":0.013466793,"teacher_disagreement_score":0.6581055,"about_ca_system_score_codex":0.011727849,"about_ca_system_score_gemma":0.028347611,"threshold_uncertainty_score":0.8115612},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11701523,0.040367037,0.067637004,0.072151944,0.001854612,0.00092480046,0.0007885021,0.0002880543,0.6989728],"genre_scores_gemma":[0.9164156,0.017723361,0.02861458,0.0044738404,0.00020095232,0.0007531717,0.00032728192,0.00024053457,0.03125065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9756246,0.014803399,0.00078669126,0.0020079354,0.004988228,0.0017890765],"domain_scores_gemma":[0.9683358,0.019080443,0.0020976376,0.0030789596,0.006156983,0.0012502002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01940389,0.0011424691,0.0013107661,0.0076418268,0.017351443,0.021146335,0.0024659447,0.0030322196,0.010731274],"category_scores_gemma":[0.029483773,0.00065314013,0.00079162617,0.009383119,0.0343344,0.013945518,0.008351082,0.005451237,0.0010570891],"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":[0.00003839463,0.000022227701,0.004041678,0.0009907873,0.00003541913,0.00029618214,0.15784375,0.00032110754,0.00042492335,0.78418714,0.005114317,0.04668411],"study_design_scores_gemma":[0.000023141203,0.000054940723,0.011832388,0.006456251,0.000114505325,0.0005167185,0.24641879,0.00088268577,0.001020788,0.14905168,0.5835018,0.00012625205],"about_ca_topic_score_codex":0.4342218,"about_ca_topic_score_gemma":0.58812016,"teacher_disagreement_score":0.4342218,"about_ca_system_score_codex":0.054679748,"about_ca_system_score_gemma":0.07490626,"threshold_uncertainty_score":0.8633887},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019837325,0.004202729,0.00028476043,0.9840158,0.0021639676,0.00003723571,0.000121647216,0.000012940841,0.007177173],"genre_scores_gemma":[0.11571072,0.006444767,0.003750655,0.8605883,0.005383903,0.00013813966,0.00016026742,0.00005458027,0.0077686105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9424575,0.02061804,0.0036132406,0.0016968949,0.02295838,0.008655827],"domain_scores_gemma":[0.7672296,0.0989291,0.0060819276,0.002598316,0.09408299,0.031078013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0664689,0.000718322,0.0010980567,0.0032038959,0.021303933,0.015738757,0.0053056558,0.01978946,0.004748403],"category_scores_gemma":[0.20681494,0.00052537123,0.00093587616,0.0038145212,0.016527448,0.004717223,0.0065073147,0.027610116,0.00054842146],"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":[0.00010950848,0.000053121305,0.008386276,0.00042001274,0.00010403106,0.00075554795,0.007698758,0.0005454493,0.00020031104,0.059038673,0.86282146,0.059866756],"study_design_scores_gemma":[0.00012858349,0.00011574416,0.016763972,0.0039071077,0.00019509278,0.00042858548,0.027500823,0.002060727,0.00077325845,0.07614877,0.8716424,0.0003349865],"about_ca_topic_score_codex":0.9274665,"about_ca_topic_score_gemma":0.9656722,"teacher_disagreement_score":0.85484254,"about_ca_system_score_codex":0.14515746,"about_ca_system_score_gemma":0.4315197,"threshold_uncertainty_score":0.9914962},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008703036,0.01399335,0.8621856,0.08615723,0.0021534294,0.0034541201,0.00021533588,0.00036947482,0.022768363],"genre_scores_gemma":[0.1505398,0.0083149215,0.8088528,0.017686358,0.0010455693,0.011237842,0.00013186621,0.00036061014,0.0018301448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27115017,0.67447263,0.011278245,0.008944833,0.032427683,0.0017265367],"domain_scores_gemma":[0.22956009,0.6663426,0.022420855,0.0477841,0.030132012,0.0037602386],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53533834,0.0026235324,0.0035854145,0.010374558,0.00963106,0.032916583,0.00746838,0.006646346,0.0053680628],"category_scores_gemma":[0.49404514,0.0024843034,0.0027732158,0.0069929333,0.049068764,0.028572269,0.025076857,0.014317348,0.0020435047],"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":[0.0002030229,0.00017107087,0.002921023,0.009038959,0.00046509114,0.0002742493,0.077861525,0.002563874,0.0014291633,0.739802,0.006153567,0.1591164],"study_design_scores_gemma":[0.00017356471,0.0004365056,0.0008086768,0.013215073,0.00019981938,0.00028722556,0.021285878,0.0045074206,0.0024485372,0.8556956,0.10072887,0.00021290938],"about_ca_topic_score_codex":0.002539765,"about_ca_topic_score_gemma":0.0049495683,"teacher_disagreement_score":0.46466166,"about_ca_system_score_codex":0.017334834,"about_ca_system_score_gemma":0.036088727,"threshold_uncertainty_score":0.57301056},"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":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040406235,0.008231462,0.92760944,0.006062595,0.0016722057,0.032366842,0.0013790363,0.0008776931,0.01776],"genre_scores_gemma":[0.026282446,0.0015717143,0.9106138,0.0007581127,0.00009250886,0.05989946,0.00037191587,0.00011467953,0.00029534285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.24724834,0.669307,0.031656053,0.015612846,0.03291473,0.0032611154],"domain_scores_gemma":[0.29595903,0.59626126,0.015811829,0.045028612,0.044538766,0.0024006143],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.51795906,0.0057745194,0.011528835,0.029162114,0.00819052,0.02065295,0.00977789,0.008474527,0.0101111885],"category_scores_gemma":[0.5390613,0.0042221504,0.015651442,0.032482516,0.025115997,0.015699951,0.016593747,0.014473799,0.0017210298],"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":[0.00037055096,0.0005224564,0.0053468295,0.027277734,0.0029724292,0.0002563934,0.013910943,0.007170639,0.00031944283,0.66881007,0.010271715,0.26277083],"study_design_scores_gemma":[0.0015950766,0.0025932859,0.006624392,0.051134553,0.00218075,0.00065341755,0.0144525105,0.047679216,0.0013283866,0.7558299,0.115249865,0.0006787259],"about_ca_topic_score_codex":0.012061635,"about_ca_topic_score_gemma":0.010617906,"teacher_disagreement_score":0.51795906,"about_ca_system_score_codex":0.02962373,"about_ca_system_score_gemma":0.07406012,"threshold_uncertainty_score":0.59444237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88290477,0.002341069,0.015295306,0.016992325,0.00026134288,0.0015304936,0.0010213746,0.00019383496,0.079459526],"genre_scores_gemma":[0.9564836,0.0013994284,0.008541711,0.0009593057,0.000028580671,0.000766565,0.0003597966,0.0000352298,0.031425644],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9855848,0.0077381823,0.0007382846,0.0008149923,0.003495499,0.0016282749],"domain_scores_gemma":[0.94955313,0.018825956,0.0029027516,0.001712123,0.023126436,0.0038795425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018803313,0.000487255,0.00060086703,0.0014897897,0.0035268741,0.0049980264,0.0011030938,0.0010480763,0.008098065],"category_scores_gemma":[0.050064545,0.00035603024,0.0005048746,0.002044125,0.0026815555,0.0019378333,0.00248887,0.0022594936,0.0009047471],"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":[0.0017931319,0.0010545126,0.19742009,0.0023009176,0.00033311103,0.0006556702,0.19672537,0.0053360164,0.005269838,0.02066343,0.026664803,0.54178303],"study_design_scores_gemma":[0.00020953058,0.0013521822,0.57774854,0.0032053697,0.00030065392,0.0001501627,0.16291772,0.0055092247,0.0066390303,0.005728225,0.23591545,0.00032394181],"about_ca_topic_score_codex":0.66906893,"about_ca_topic_score_gemma":0.78504676,"teacher_disagreement_score":0.66906893,"about_ca_system_score_codex":0.032002095,"about_ca_system_score_gemma":0.06570217,"threshold_uncertainty_score":0.6657599},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45481396,0.0032369301,0.2113541,0.09741982,0.00220662,0.015876044,0.0022038291,0.008234308,0.20465438],"genre_scores_gemma":[0.79462326,0.0011644635,0.17144005,0.006795311,0.00037481808,0.0027003817,0.0012302885,0.0005629235,0.021108497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94138235,0.041451264,0.0033456304,0.0021241533,0.009290104,0.0024064095],"domain_scores_gemma":[0.9367212,0.016190214,0.007991565,0.009714577,0.021401707,0.007980811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033096444,0.00057075237,0.00041397067,0.0022509187,0.0026945472,0.006217237,0.0017507601,0.000604786,0.015006978],"category_scores_gemma":[0.06128196,0.0005325376,0.00078118,0.0020526736,0.001187966,0.002185312,0.005724737,0.0024463732,0.002561062],"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":[0.00011258061,0.002744301,0.07850952,0.0007110149,0.000104732615,0.00008483148,0.0035794755,0.0018233618,0.002388964,0.0039967597,0.06348973,0.8424546],"study_design_scores_gemma":[0.00082051865,0.004569536,0.43380043,0.0037752858,0.00030530905,0.00079532096,0.024490248,0.020112297,0.021113196,0.012582198,0.4772582,0.0003774315],"about_ca_topic_score_codex":0.0127241695,"about_ca_topic_score_gemma":0.023675026,"teacher_disagreement_score":0.033096444,"about_ca_system_score_codex":0.0069725527,"about_ca_system_score_gemma":0.02940368,"threshold_uncertainty_score":0.17503285},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02245774,0.0024837845,0.87646365,0.05213671,0.00025310376,0.0004793657,0.000090591595,0.00084442424,0.044790722],"genre_scores_gemma":[0.24534428,0.0035937277,0.7446542,0.0028339885,0.00017062816,0.0005193372,0.0001677859,0.00012058858,0.0025954903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97425044,0.018971125,0.0014052684,0.0012255765,0.0033059623,0.00084164465],"domain_scores_gemma":[0.8825358,0.09807766,0.004784391,0.0067663486,0.0060288943,0.0018069047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059832662,0.001238854,0.0007672244,0.0038540382,0.0020525125,0.009766729,0.0040894737,0.0029143794,0.00417803],"category_scores_gemma":[0.0883434,0.0009215974,0.0010368238,0.0019947828,0.010141731,0.01248576,0.0090747615,0.008190703,0.0010353841],"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":[0.00006241549,0.00065377756,0.0048410376,0.0010960033,0.00006121282,0.0001850769,0.012153645,0.039191674,0.0015048045,0.48037705,0.007019554,0.4528538],"study_design_scores_gemma":[0.000040008737,0.00008020982,0.00089387776,0.0023451769,0.000031904623,0.00009110373,0.0029469805,0.03296951,0.0018904081,0.8972091,0.061445117,0.000056597426],"about_ca_topic_score_codex":0.0038005637,"about_ca_topic_score_gemma":0.0045671347,"teacher_disagreement_score":0.059832662,"about_ca_system_score_codex":0.00700055,"about_ca_system_score_gemma":0.017180275,"threshold_uncertainty_score":0.31642914},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9667721,0.00040502424,0.004165722,0.0024415352,0.00005688434,0.0007782742,0.00019889647,0.000047510108,0.025134036],"genre_scores_gemma":[0.97634447,0.0006409801,0.0060915146,0.0005955057,0.000016150081,0.0007804436,0.0001706232,0.000058793867,0.015301614],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9915427,0.0043526306,0.00028018182,0.0009047408,0.0013963995,0.001523371],"domain_scores_gemma":[0.988948,0.006031841,0.00068086555,0.00067402446,0.0016800691,0.0019851862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012176065,0.00085336843,0.00071250304,0.001643929,0.031400755,0.006128477,0.0024136214,0.0015934895,0.0039537563],"category_scores_gemma":[0.012059533,0.00068823766,0.0004568417,0.0024808731,0.015279134,0.0031633105,0.010363808,0.0016067673,0.0004767712],"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":[0.00003574196,0.000024950337,0.0034360185,0.000073798125,0.000003020605,0.00051172747,0.9893777,0.0000392598,0.0008859542,0.00068010105,0.00060033135,0.004331468],"study_design_scores_gemma":[0.000011572847,0.000045802328,0.0064751003,0.00011707505,0.0000138060595,0.00008621393,0.95675904,0.00012836457,0.00046956493,0.0005531419,0.03531208,0.000028120397],"about_ca_topic_score_codex":0.8192859,"about_ca_topic_score_gemma":0.9330836,"teacher_disagreement_score":0.18071407,"about_ca_system_score_codex":0.0497065,"about_ca_system_score_gemma":0.069609836,"threshold_uncertainty_score":0.36355662},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089908145,0.0069281203,0.02905566,0.58184665,0.014356159,0.0023934257,0.0013104982,0.004534711,0.26966664],"genre_scores_gemma":[0.332772,0.005966523,0.043101415,0.08689541,0.0028823123,0.0012836098,0.000685198,0.0022977046,0.5241158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97826093,0.011017442,0.00081419793,0.0022082638,0.0061950395,0.0015039976],"domain_scores_gemma":[0.9336077,0.014373668,0.003161625,0.0027581837,0.02981945,0.016279401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017270038,0.0005268792,0.0005699057,0.0027707338,0.0076933824,0.005471664,0.0011751261,0.0023776882,0.035291813],"category_scores_gemma":[0.041177243,0.00057247153,0.00044585104,0.0015772479,0.0039366074,0.0031709007,0.0029567108,0.0067719193,0.0063248957],"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":[0.00019679408,0.000387449,0.012369008,0.00039748056,0.000031187777,0.0015280213,0.018116528,0.0005001927,0.0019998276,0.011233143,0.80909383,0.14414655],"study_design_scores_gemma":[0.00003208739,0.00031387684,0.010194877,0.00060687657,0.00003957728,0.00082843617,0.027218346,0.00065391976,0.0018153269,0.003110509,0.9550929,0.00009313092],"about_ca_topic_score_codex":0.02297212,"about_ca_topic_score_gemma":0.03960889,"teacher_disagreement_score":0.035291813,"about_ca_system_score_codex":0.01035169,"about_ca_system_score_gemma":0.03559303,"threshold_uncertainty_score":0.11806291},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011159287,0.07064354,0.022593388,0.71224844,0.002144623,0.00024141809,0.00006674345,0.0001007676,0.18080173],"genre_scores_gemma":[0.7574718,0.07534708,0.029481951,0.1069907,0.0032924148,0.0014409046,0.00009007748,0.0007264848,0.02515856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.6425169,0.31611684,0.0065137893,0.008871807,0.021083862,0.004896726],"domain_scores_gemma":[0.48925146,0.47180656,0.0064044367,0.013085226,0.015479944,0.0039724107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23690395,0.0008741115,0.0014749406,0.0083277095,0.0129596535,0.037470292,0.0030701829,0.0096213985,0.004139649],"category_scores_gemma":[0.2240807,0.0011087159,0.0012898411,0.010556011,0.08804721,0.0294061,0.017259875,0.020447416,0.0006748141],"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":[0.000021295593,0.00003496194,0.00079661544,0.00044432067,0.000020829875,0.00010954033,0.036996864,0.00047421805,0.000053335818,0.90559256,0.022238981,0.033216376],"study_design_scores_gemma":[0.000038117574,0.00011138808,0.0024089455,0.0065057753,0.00004612878,0.00024196343,0.033730716,0.00094000046,0.0008616318,0.35857671,0.5964558,0.00008276703],"about_ca_topic_score_codex":0.017875088,"about_ca_topic_score_gemma":0.010435721,"teacher_disagreement_score":0.23690395,"about_ca_system_score_codex":0.044152383,"about_ca_system_score_gemma":0.04400253,"threshold_uncertainty_score":0.9410333},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8940905,0.0020023673,0.03589105,0.005285693,0.0002554426,0.0013648417,0.00061207206,0.00025171388,0.06024627],"genre_scores_gemma":[0.9714632,0.00054066477,0.016420133,0.0002533692,0.000017198405,0.000491651,0.00021155177,0.000053181648,0.010549034],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97444475,0.0130063,0.0016747396,0.0011843166,0.008147397,0.0015424924],"domain_scores_gemma":[0.9181255,0.02446122,0.006338017,0.0025545312,0.04361754,0.00490318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03297958,0.0005382141,0.00045516447,0.0037197163,0.0046151457,0.0076153157,0.0012049221,0.00088214397,0.00522398],"category_scores_gemma":[0.07120617,0.0003866826,0.000677881,0.0036531668,0.0043595373,0.0038813043,0.0032480669,0.0022237604,0.00065147434],"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":[0.00080957,0.00034321472,0.28434935,0.00129281,0.00015864709,0.00034556302,0.2584637,0.0024229453,0.0071664047,0.027319951,0.009155675,0.4081722],"study_design_scores_gemma":[0.000060457143,0.0009190638,0.6583518,0.0025948626,0.00015218867,0.00022590517,0.21803163,0.006032606,0.005827735,0.0049111834,0.10249582,0.00039680314],"about_ca_topic_score_codex":0.58321893,"about_ca_topic_score_gemma":0.7126853,"teacher_disagreement_score":0.41678107,"about_ca_system_score_codex":0.039473314,"about_ca_system_score_gemma":0.040054362,"threshold_uncertainty_score":0.8384712},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17012018,0.012057595,0.6316352,0.05562041,0.00032645575,0.0005657487,0.00020156037,0.00025385257,0.12921897],"genre_scores_gemma":[0.86514705,0.0031863572,0.12752326,0.0014430664,0.00018811495,0.00063101394,0.00006939794,0.000089492285,0.0017222081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90386164,0.087582305,0.0015389408,0.0020685373,0.0039844257,0.0009641363],"domain_scores_gemma":[0.87480515,0.11095917,0.005238509,0.004846097,0.003267315,0.0008837189],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07376749,0.0009799377,0.0010287772,0.010472277,0.0041368725,0.012244071,0.0021964388,0.0021443702,0.0017111029],"category_scores_gemma":[0.06756501,0.00055827666,0.00040510896,0.0077359267,0.03515353,0.023870012,0.0068628676,0.003640289,0.00023118706],"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":[0.00003789618,0.00016395799,0.0066329893,0.0004124184,0.000026464555,0.00011678849,0.13279667,0.001571791,0.0005354618,0.78247267,0.0014150429,0.07381775],"study_design_scores_gemma":[0.000029725403,0.00021357801,0.0075405,0.0013512862,0.000022266526,0.00027347045,0.1217116,0.004276058,0.0010464444,0.80676687,0.056670856,0.00009736403],"about_ca_topic_score_codex":0.0031175606,"about_ca_topic_score_gemma":0.003662457,"teacher_disagreement_score":0.9262325,"about_ca_system_score_codex":0.0059011807,"about_ca_system_score_gemma":0.004514871,"threshold_uncertainty_score":0.39012444},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019046164,0.0028484461,0.010351228,0.054401256,0.00073270785,0.0002300845,0.00007860099,0.00007577056,0.92937744],"genre_scores_gemma":[0.25697652,0.0063716886,0.01610048,0.024314428,0.0005987366,0.0005985276,0.00022042509,0.00029004243,0.6945291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9832962,0.0065993723,0.00047621745,0.0015007815,0.005893602,0.0022338412],"domain_scores_gemma":[0.9889949,0.0037842994,0.0003493347,0.001643595,0.003821429,0.0014065132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017071038,0.0006449423,0.00046157723,0.000830157,0.0054284954,0.013806534,0.0027026525,0.0047711157,0.029145185],"category_scores_gemma":[0.021733968,0.00031263995,0.00044682363,0.0010117476,0.019788945,0.010381522,0.007945515,0.0067721405,0.0049235923],"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":[0.0000045287707,0.00001614459,0.0001174241,0.00007696287,0.0000018022367,0.000028695662,0.002732874,0.00013153948,0.00006927943,0.9401001,0.02413608,0.032584593],"study_design_scores_gemma":[0.000006928981,0.000022517463,0.00034443752,0.0005882895,0.0000041810163,0.00003797437,0.0037681866,0.00018395604,0.00022511806,0.11743452,0.87737566,0.000008150844],"about_ca_topic_score_codex":0.1278949,"about_ca_topic_score_gemma":0.11128572,"teacher_disagreement_score":0.1278949,"about_ca_system_score_codex":0.028004022,"about_ca_system_score_gemma":0.081993304,"threshold_uncertainty_score":0.2543009},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52345276,0.010271024,0.35868198,0.02106705,0.002836083,0.023316722,0.0017501401,0.001078174,0.057546105],"genre_scores_gemma":[0.78923076,0.002931029,0.13818589,0.0065011596,0.0004244046,0.05182609,0.0009927438,0.0007924326,0.009115535],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.546176,0.32296664,0.037383147,0.013461373,0.07501744,0.004995431],"domain_scores_gemma":[0.23087552,0.59155756,0.018351637,0.051552504,0.10553895,0.0021238204],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4397807,0.0016179226,0.0014088409,0.004123279,0.0038974613,0.008635956,0.00450731,0.0029004042,0.0033716704],"category_scores_gemma":[0.5904818,0.0018874793,0.0017323359,0.0034622008,0.0108760055,0.01031377,0.006906987,0.0051440336,0.0015533647],"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":[0.0018258393,0.0010315987,0.13734984,0.010128336,0.00077997026,0.00085451896,0.2962244,0.0017306609,0.010414903,0.040020403,0.013437107,0.48620242],"study_design_scores_gemma":[0.00083822245,0.00480567,0.35043186,0.025216414,0.0010735173,0.0022872158,0.09705003,0.015485471,0.031169571,0.044802625,0.4259607,0.000878727],"about_ca_topic_score_codex":0.025675723,"about_ca_topic_score_gemma":0.01713796,"teacher_disagreement_score":0.4397807,"about_ca_system_score_codex":0.008802718,"about_ca_system_score_gemma":0.021330018,"threshold_uncertainty_score":0.69085014},"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":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054701354,0.000120692916,0.89128107,0.0048381216,0.00020072628,0.000834785,0.0016346088,0.002580142,0.043808516],"genre_scores_gemma":[0.5360079,0.00009356962,0.45120075,0.00075484323,0.00015399844,0.00081417017,0.0012762822,0.00047553208,0.009223004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.987015,0.004381201,0.0015500913,0.0023671102,0.002615137,0.0020715175],"domain_scores_gemma":[0.95556927,0.025433844,0.0025539927,0.007879078,0.0059992913,0.0025645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011890699,0.00051409565,0.00073386024,0.0015646382,0.0025652337,0.006606133,0.003482077,0.0027054497,0.02174276],"category_scores_gemma":[0.03923678,0.0009652688,0.0033237594,0.0015970523,0.006793377,0.00993745,0.0060901544,0.004891369,0.0020744067],"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":[0.0001129914,0.00014087511,0.0031910762,0.00013068628,0.00004807037,0.0002750835,0.0010525748,0.01401068,0.0008713477,0.957807,0.0037563886,0.018603241],"study_design_scores_gemma":[0.00022897997,0.0001817203,0.0016564666,0.0001725268,0.00011243997,0.00030014777,0.0012603367,0.18584013,0.0025711872,0.7727527,0.034834955,0.0000883407],"about_ca_topic_score_codex":0.030298203,"about_ca_topic_score_gemma":0.02210246,"teacher_disagreement_score":0.9961539,"about_ca_system_score_codex":0.0038461047,"about_ca_system_score_gemma":0.009543736,"threshold_uncertainty_score":0.0727368},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36610666,0.020791879,0.18038921,0.060397748,0.0004178345,0.0024737231,0.00045596034,0.00022390604,0.36874318],"genre_scores_gemma":[0.9721281,0.0015385457,0.023052923,0.0005849155,0.000044318265,0.0007687638,0.00008349633,0.000023988876,0.0017750273],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97190946,0.021513633,0.0012764017,0.0012689917,0.0017341274,0.0022973672],"domain_scores_gemma":[0.96476704,0.022512255,0.0034061784,0.0018908585,0.0030008121,0.0044227657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026463183,0.0010449329,0.000716387,0.010031019,0.0084813,0.017789235,0.0035337277,0.0035305077,0.0039218026],"category_scores_gemma":[0.024190495,0.0007447372,0.0014355663,0.007172517,0.060512256,0.020937575,0.0141910855,0.004121607,0.00028323533],"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":[0.00002571526,0.000082207254,0.0109290285,0.000364696,0.00002775195,0.0003338144,0.14499296,0.0012109427,0.00019327027,0.8289424,0.0010660327,0.011831192],"study_design_scores_gemma":[0.00004489161,0.00010369679,0.0197356,0.0033078818,0.000055504785,0.00055226183,0.41138998,0.0050783968,0.00029905318,0.47780913,0.081484996,0.00013859077],"about_ca_topic_score_codex":0.035706017,"about_ca_topic_score_gemma":0.02716125,"teacher_disagreement_score":0.035706017,"about_ca_system_score_codex":0.024296673,"about_ca_system_score_gemma":0.02574994,"threshold_uncertainty_score":0.1762855},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033202175,0.008308248,0.124420986,0.8098192,0.0038773075,0.0015764937,0.000073442214,0.0003155537,0.018406613],"genre_scores_gemma":[0.60722244,0.0061820988,0.2432124,0.12921923,0.0018433204,0.006949179,0.00007254232,0.0010141289,0.004284698],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16969848,0.740988,0.02276801,0.008686215,0.051042568,0.0068167085],"domain_scores_gemma":[0.09649129,0.7965585,0.010610735,0.02150321,0.0696441,0.005192111],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7113553,0.0017572849,0.0018036179,0.003327159,0.014703599,0.030166155,0.010341936,0.013850324,0.0026082986],"category_scores_gemma":[0.7276533,0.0018313698,0.0021023043,0.0026471687,0.06766578,0.032091625,0.019204194,0.040957127,0.0007622943],"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":[0.00031229277,0.00072812836,0.0061168163,0.0035499295,0.0002708472,0.00086407125,0.5050537,0.0023798803,0.0019122984,0.2218634,0.058251325,0.19869731],"study_design_scores_gemma":[0.0002914596,0.00088991004,0.0037717675,0.013714998,0.00011655905,0.00096340117,0.40831417,0.0067177336,0.005239808,0.24456042,0.3148697,0.0005500294],"about_ca_topic_score_codex":0.01408598,"about_ca_topic_score_gemma":0.011825813,"teacher_disagreement_score":0.28864467,"about_ca_system_score_codex":0.026083315,"about_ca_system_score_gemma":0.061218176,"threshold_uncertainty_score":0.3559503},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842619,0.00028805365,0.0020027694,0.0040079746,0.000040487503,0.00018392726,0.00008230781,0.000022713337,0.0091098845],"genre_scores_gemma":[0.9934149,0.0003534562,0.00092152745,0.0005311899,0.0000108082,0.000118853655,0.00004667814,0.000032252436,0.0045703],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9820796,0.012267872,0.00042055486,0.0010155588,0.0018316067,0.0023847967],"domain_scores_gemma":[0.978404,0.013776181,0.0019373088,0.0013227978,0.002369767,0.0021899578],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014810622,0.00041364264,0.00057030405,0.0012678142,0.023766272,0.0050671767,0.001775602,0.0014072143,0.0019146978],"category_scores_gemma":[0.02593468,0.00079789315,0.0003167499,0.0019380649,0.017418614,0.0030725757,0.0053284056,0.0040526995,0.00022774278],"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":[0.000010015519,0.000017058723,0.0027658837,0.000017463477,0.0000013251581,0.00019460237,0.9936826,0.000023927701,0.00023947415,0.00076650514,0.000314403,0.0019666941],"study_design_scores_gemma":[0.0000027809806,0.000016829588,0.0042895335,0.000064074586,0.000002905573,0.000066975364,0.97630095,0.00013249015,0.00019869485,0.00025621915,0.018655779,0.0000127674275],"about_ca_topic_score_codex":0.6549621,"about_ca_topic_score_gemma":0.8453823,"teacher_disagreement_score":0.9985928,"about_ca_system_score_codex":0.051128153,"about_ca_system_score_gemma":0.05619063,"threshold_uncertainty_score":0.6941397},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008564159,0.0029033953,0.9612246,0.0015090352,0.0007955258,0.0008417617,0.008533798,0.0039006053,0.019434914],"genre_scores_gemma":[0.017179519,0.004561442,0.9306097,0.0014728911,0.00047578456,0.004129748,0.008920242,0.0044936,0.028157003],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9787931,0.013980385,0.0013507335,0.0026501701,0.0028099627,0.00041571786],"domain_scores_gemma":[0.9558344,0.03431551,0.0014420119,0.0033930906,0.0046775197,0.00033747585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020472456,0.0024428498,0.002754819,0.0022904866,0.0011360943,0.0079216575,0.0062876465,0.002873782,0.07516751],"category_scores_gemma":[0.085447475,0.0014451975,0.005935707,0.004097428,0.0010784396,0.0032340074,0.0038444644,0.0043588895,0.0295174],"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":[0.00028888762,0.00017343981,0.0032080614,0.0048340857,0.0021357348,0.00032684318,0.0019131626,0.042334545,0.0012525964,0.28306085,0.2043714,0.4561004],"study_design_scores_gemma":[0.00013332062,0.00019485623,0.0013387025,0.0019865662,0.00082382583,0.00045536095,0.00035877473,0.079739414,0.001460987,0.30873603,0.6045434,0.000228821],"about_ca_topic_score_codex":0.0065168254,"about_ca_topic_score_gemma":0.007913365,"teacher_disagreement_score":0.07516751,"about_ca_system_score_codex":0.0020737317,"about_ca_system_score_gemma":0.004052792,"threshold_uncertainty_score":0.25146037},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020814696,0.086763375,0.0016183333,0.8211831,0.0047857533,0.00006211324,0.00037856007,0.000039335573,0.06435467],"genre_scores_gemma":[0.25385505,0.18781243,0.004296856,0.16238433,0.0045793434,0.00041483057,0.00042123944,0.00037376166,0.3858622],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978618,0.0011267962,0.00008750293,0.00026441697,0.00049516757,0.00016421123],"domain_scores_gemma":[0.9954501,0.0022797345,0.00045253028,0.00014596277,0.0008798762,0.00079183833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00492448,0.0005697248,0.00047152615,0.0015524286,0.0065130414,0.007536512,0.0011039254,0.0031887342,0.019945014],"category_scores_gemma":[0.008584057,0.0005198714,0.00027484092,0.0023425973,0.0060211867,0.008466356,0.004120979,0.0048086597,0.0021439318],"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":[0.00015016898,0.00011282804,0.010658829,0.0007168686,0.00003177003,0.00024511575,0.043924596,0.00016298825,0.00039163703,0.117944226,0.7327034,0.0929576],"study_design_scores_gemma":[0.000016093778,0.00006523559,0.014548812,0.0017866549,0.000022419857,0.00016109418,0.08709097,0.00017650366,0.00036302942,0.038059995,0.85765624,0.0000529459],"about_ca_topic_score_codex":0.03029269,"about_ca_topic_score_gemma":0.09497445,"teacher_disagreement_score":0.03029269,"about_ca_system_score_codex":0.0044839126,"about_ca_system_score_gemma":0.004622488,"threshold_uncertainty_score":0.06672275},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004063557,0.024852699,0.026059207,0.88406146,0.029316878,0.0004108762,0.00013363,0.0010795235,0.030022217],"genre_scores_gemma":[0.14829133,0.059704315,0.2255384,0.47653404,0.032266125,0.0022404105,0.00060919754,0.0031524678,0.051663715],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8617473,0.08538679,0.009945787,0.005153664,0.031339996,0.0064264084],"domain_scores_gemma":[0.54825073,0.300893,0.007956877,0.019941593,0.09667338,0.02628442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.136359,0.0024073883,0.001453694,0.003786612,0.008226848,0.021421406,0.005074403,0.014006301,0.020153275],"category_scores_gemma":[0.33245972,0.0009612591,0.0018930861,0.0027510398,0.013641601,0.028828718,0.009831392,0.030224614,0.012981654],"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":[0.00023895114,0.001062278,0.0014111953,0.0012397928,0.00013094452,0.0004593174,0.0069482867,0.0007232282,0.0005959044,0.028492523,0.57483584,0.38386172],"study_design_scores_gemma":[0.0003504622,0.0008679741,0.0015453092,0.008976097,0.00013197621,0.001029991,0.018153835,0.0013419747,0.00215018,0.09669955,0.86842835,0.0003242895],"about_ca_topic_score_codex":0.001755074,"about_ca_topic_score_gemma":0.0031393047,"teacher_disagreement_score":0.136359,"about_ca_system_score_codex":0.0043690107,"about_ca_system_score_gemma":0.013479267,"threshold_uncertainty_score":0.72114396},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030478449,0.0050399657,0.92721844,0.03266375,0.0017327277,0.000994382,0.00050221453,0.00021803631,0.028582595],"genre_scores_gemma":[0.24856648,0.009686196,0.69756585,0.02215549,0.0030884703,0.008659557,0.0005733854,0.00038596656,0.009318695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8924502,0.07937147,0.005918519,0.010665167,0.010021778,0.0015728782],"domain_scores_gemma":[0.71991104,0.23950368,0.013557339,0.020284217,0.0057461285,0.000997588],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12393707,0.0032263892,0.006041013,0.006078239,0.0039037347,0.011598799,0.005148408,0.0103395,0.013554032],"category_scores_gemma":[0.17332715,0.0020139194,0.006809373,0.0042396523,0.035945356,0.025039276,0.013601489,0.017741792,0.0016631475],"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":[0.00004269662,0.00004439928,0.00048231083,0.0006386522,0.00016289242,0.00007125567,0.0010120266,0.0017671842,0.00008880207,0.9855591,0.0010722665,0.009058473],"study_design_scores_gemma":[0.00003771402,0.000053431766,0.00018355709,0.00036022015,0.00009811741,0.00004487625,0.00024373851,0.0018038227,0.00022778742,0.983781,0.013133432,0.00003222973],"about_ca_topic_score_codex":0.003277461,"about_ca_topic_score_gemma":0.003349701,"teacher_disagreement_score":0.8760629,"about_ca_system_score_codex":0.008172424,"about_ca_system_score_gemma":0.013030318,"threshold_uncertainty_score":0.65544975},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795864,0.020110808,0.00026746813,0.00544935,0.0000961684,0.00008174348,0.00011296845,0.000012204084,0.015910648],"genre_scores_gemma":[0.99591357,0.0033990438,0.00011305104,0.00032940498,0.0000172736,0.000024932739,0.00002933886,0.0000018190099,0.00017167696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9879155,0.0063171913,0.00090894144,0.0005075141,0.003224048,0.0011268122],"domain_scores_gemma":[0.9659913,0.018794447,0.0053646476,0.00089493534,0.0066674273,0.0022871573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020617954,0.0003170082,0.00071808044,0.009224916,0.0040455116,0.006876688,0.000816482,0.0007916503,0.001049602],"category_scores_gemma":[0.030028507,0.00022119399,0.00046822496,0.014323088,0.004620178,0.0036475619,0.00384861,0.0010599995,0.00006917188],"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":[0.00022971768,0.0006069335,0.5784427,0.002782848,0.00023417454,0.000667223,0.08505268,0.0007167695,0.00050388847,0.020046515,0.0037007881,0.30701578],"study_design_scores_gemma":[0.000025276375,0.0004063264,0.8749011,0.0033390713,0.00016652685,0.00014810031,0.10424727,0.00088132697,0.0005726807,0.0017508335,0.013488902,0.000072529],"about_ca_topic_score_codex":0.10088954,"about_ca_topic_score_gemma":0.1391602,"teacher_disagreement_score":0.10088954,"about_ca_system_score_codex":0.018629493,"about_ca_system_score_gemma":0.03103696,"threshold_uncertainty_score":0.20060456},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29911688,0.011107863,0.29849598,0.053554274,0.001638236,0.0023422244,0.00031703734,0.00046791133,0.3329595],"genre_scores_gemma":[0.9566611,0.0007558607,0.03719165,0.00077764376,0.00012443782,0.00090133486,0.0000395768,0.000055284025,0.003493157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94136477,0.045736305,0.0022805824,0.0032036994,0.003885352,0.003529212],"domain_scores_gemma":[0.9051613,0.07367077,0.005220209,0.0072412034,0.003982088,0.0047244946],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.06305739,0.001156798,0.0018687653,0.004460293,0.00848153,0.020853164,0.0036573124,0.00588507,0.0118674105],"category_scores_gemma":[0.091458164,0.0011821521,0.0011665679,0.003682179,0.04203689,0.021004723,0.01632623,0.0035884532,0.0008531644],"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":[0.00048057563,0.00031368743,0.004915049,0.0009601925,0.00009106179,0.00026746021,0.020145394,0.0020953182,0.0008739393,0.89711773,0.0013258115,0.07141372],"study_design_scores_gemma":[0.00014127993,0.00030850488,0.004070069,0.001177211,0.00015192406,0.00020104513,0.017979471,0.0045144996,0.002301768,0.9514732,0.017583117,0.00009793793],"about_ca_topic_score_codex":0.006295409,"about_ca_topic_score_gemma":0.006366653,"teacher_disagreement_score":0.9915185,"about_ca_system_score_codex":0.012965246,"about_ca_system_score_gemma":0.021454282,"threshold_uncertainty_score":0.33348334},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013522356,0.00023889495,0.000081398284,0.9863869,0.012363204,0.000023865825,0.000085183136,0.000030099967,0.00065515394],"genre_scores_gemma":[0.00066008104,0.000106540974,0.00015356333,0.9845598,0.013108214,0.000044474178,0.000020030353,0.000018157058,0.0013290496],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9792336,0.0058031306,0.004090493,0.0028175819,0.005298598,0.0027566208],"domain_scores_gemma":[0.9032306,0.06398861,0.0067501646,0.0020139692,0.015636949,0.008379635],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02294289,0.0014053114,0.003859574,0.0018284502,0.0072407564,0.00928499,0.004019915,0.13910642,0.011957768],"category_scores_gemma":[0.16491397,0.0022718043,0.003078778,0.001729091,0.0060408046,0.0051093544,0.003797415,0.08724948,0.014254926],"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":[0.00009017466,0.000022012413,0.0003457119,0.00008749702,0.000027005177,0.00048621304,0.00016982232,0.000058708112,0.0001377287,0.0014662724,0.9937698,0.003338901],"study_design_scores_gemma":[0.0005272573,0.00016900503,0.0026999987,0.0014358344,0.00016745123,0.001407171,0.0009081424,0.0013909268,0.0005317419,0.012678351,0.9778035,0.00028057405],"about_ca_topic_score_codex":0.013137527,"about_ca_topic_score_gemma":0.018120645,"teacher_disagreement_score":0.9770571,"about_ca_system_score_codex":0.009777572,"about_ca_system_score_gemma":0.01463978,"threshold_uncertainty_score":0.12133503},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99713564,0.00027072735,0.00009111349,0.0005959803,0.0000114269105,0.00001163026,0.00029385719,0.000004684561,0.0015848749],"genre_scores_gemma":[0.99784184,0.00024853845,0.00014715505,0.00025311846,0.000014936888,0.000022420316,0.00029998852,0.000008671428,0.0011632511],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99883896,0.00025848698,0.0001059208,0.00021349221,0.00035242512,0.00023068849],"domain_scores_gemma":[0.9863832,0.0032208345,0.002964458,0.0006609684,0.003527191,0.0032433465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020622273,0.000110276276,0.000194318,0.0015325397,0.00096750475,0.0010124848,0.00069385266,0.0004950532,0.0037762402],"category_scores_gemma":[0.013154594,0.0001655514,0.00013501491,0.002623354,0.0005561734,0.0010317847,0.0011402125,0.0007795696,0.0004954989],"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":[0.00013179368,0.00013582032,0.9634779,0.000027321947,0.000013093046,0.00006501893,0.008288131,0.000036567435,0.00064519624,0.00017831073,0.0013367834,0.025664056],"study_design_scores_gemma":[0.0000016761104,0.000023390292,0.9962529,0.000011407608,0.000002982228,0.000034844055,0.0027886678,0.000065714215,0.000039069404,0.000032246815,0.0007450772,0.0000020485043],"about_ca_topic_score_codex":0.09548485,"about_ca_topic_score_gemma":0.15954545,"teacher_disagreement_score":0.9979378,"about_ca_system_score_codex":0.0010179892,"about_ca_system_score_gemma":0.0029054196,"threshold_uncertainty_score":0.18985814},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009660417,0.9957877,0.0011659602,0.001795337,0.00027479028,0.00021728312,0.0000588184,0.000009327917,0.00059415615],"genre_scores_gemma":[0.001995744,0.99247813,0.0039436654,0.00090599386,0.00014208023,0.00034951218,0.000053720712,0.0000069170555,0.00012427443],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9621293,0.01773103,0.009486868,0.0015404875,0.008395001,0.00071731955],"domain_scores_gemma":[0.81884927,0.14901985,0.009639894,0.002709779,0.018634398,0.0011467735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08697104,0.0022501242,0.006998021,0.028085306,0.0017342658,0.008614391,0.0035351387,0.004544392,0.004062819],"category_scores_gemma":[0.20310766,0.0017241422,0.0049632695,0.023657896,0.0033748876,0.008006762,0.0055492194,0.0044072606,0.00059526094],"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":[0.00010534852,0.000072519135,0.00055227795,0.36447117,0.002045144,0.000075631084,0.0005746519,0.0005455669,0.00017881635,0.010843045,0.010633337,0.6099025],"study_design_scores_gemma":[0.00006911216,0.00007957727,0.001018863,0.88027346,0.0059702573,0.00014716786,0.0004621388,0.00032336244,0.000236742,0.00836727,0.103002824,0.000049271224],"about_ca_topic_score_codex":0.018640446,"about_ca_topic_score_gemma":0.042590573,"teacher_disagreement_score":0.91302896,"about_ca_system_score_codex":0.012817829,"about_ca_system_score_gemma":0.05075446,"threshold_uncertainty_score":0.4599523},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5978241,0.0036352375,0.14466849,0.032886006,0.00042421854,0.0007524647,0.00007974267,0.000696495,0.21903323],"genre_scores_gemma":[0.93728113,0.0007828113,0.05683234,0.00054314424,0.00003087566,0.00020235559,0.00002634096,0.00008711011,0.004213873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9866563,0.010806236,0.00014115065,0.00038261662,0.0011786569,0.00083502644],"domain_scores_gemma":[0.99110776,0.0056419824,0.00044777157,0.0009850424,0.00050555833,0.001311879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013606692,0.00046708775,0.00038099306,0.0016986981,0.0054205284,0.014372795,0.0016906615,0.0024260646,0.0035159795],"category_scores_gemma":[0.017042218,0.00039047896,0.00044511893,0.00092600717,0.013850513,0.01266101,0.014821188,0.0019065901,0.00058410625],"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":[0.00024745657,0.00079889334,0.007891907,0.00077304855,0.000051279498,0.0013936202,0.27007702,0.004500017,0.006168473,0.27217737,0.014649959,0.42127103],"study_design_scores_gemma":[0.00012483259,0.0008442944,0.006932592,0.0011975521,0.00006560855,0.0009591784,0.38871673,0.0068558445,0.006883931,0.26508933,0.3221622,0.00016786307],"about_ca_topic_score_codex":0.0010062702,"about_ca_topic_score_gemma":0.0027980984,"teacher_disagreement_score":0.014372795,"about_ca_system_score_codex":0.0021585184,"about_ca_system_score_gemma":0.0035757448,"threshold_uncertainty_score":0.07195997},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032705714,0.9367374,0.0015191346,0.046815082,0.0024630185,0.0022299648,0.0008163755,0.000035554025,0.0061128163],"genre_scores_gemma":[0.079643056,0.88990086,0.009676188,0.014731303,0.00070701214,0.0032350721,0.000971507,0.000064824686,0.0010701161],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.863845,0.06045799,0.031881817,0.0045790114,0.03345017,0.0057860287],"domain_scores_gemma":[0.3669221,0.38660136,0.02636366,0.0075258627,0.20606461,0.006522355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21758367,0.0018868059,0.005723852,0.040793777,0.012104878,0.020501975,0.008764249,0.009489983,0.0029039406],"category_scores_gemma":[0.48738956,0.0022460192,0.0038405857,0.045628224,0.01471418,0.00887685,0.0074937837,0.008554116,0.00047518752],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00028049696,0.000076199154,0.0059052138,0.5448649,0.0024321475,0.00093781186,0.038511626,0.0021253792,0.0005324057,0.023165932,0.06483138,0.3163365],"study_design_scores_gemma":[0.000023520844,0.00003828522,0.0023887088,0.87666357,0.0018848006,0.00010343261,0.011108946,0.00028188093,0.00022197474,0.002502616,0.10468652,0.00009573519],"about_ca_topic_score_codex":0.7931326,"about_ca_topic_score_gemma":0.8908228,"teacher_disagreement_score":0.8132042,"about_ca_system_score_codex":0.18679579,"about_ca_system_score_gemma":0.5412035,"threshold_uncertainty_score":0.96485865},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039775964,0.0006432856,0.9541922,0.00054072065,0.00013325596,0.000416644,0.00065068196,0.0007631676,0.0028841035],"genre_scores_gemma":[0.52216434,0.00047089442,0.4723026,0.0004313485,0.00019925392,0.0011299908,0.0016156599,0.00038457444,0.0013013182],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9666463,0.0209972,0.002004796,0.00406889,0.0056616208,0.00062115566],"domain_scores_gemma":[0.69480497,0.23673347,0.01190254,0.04327318,0.012480131,0.00080571533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.053754322,0.0013270406,0.0021853808,0.0031986407,0.0006910494,0.0031638625,0.0027556876,0.0023704625,0.00504943],"category_scores_gemma":[0.30425036,0.00096337154,0.0018962023,0.00339486,0.0024351152,0.0045494447,0.002817374,0.004676475,0.0013453248],"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":[0.0014817609,0.0008751136,0.12896106,0.001363776,0.0017018155,0.000651159,0.0018676925,0.15416774,0.0055112904,0.12559006,0.008146776,0.56968176],"study_design_scores_gemma":[0.00028469996,0.0013125888,0.101905905,0.0007775544,0.001083784,0.0012179671,0.00043410627,0.63771266,0.010598385,0.22525847,0.018886331,0.00052757544],"about_ca_topic_score_codex":0.0020626325,"about_ca_topic_score_gemma":0.0018509255,"teacher_disagreement_score":0.9462457,"about_ca_system_score_codex":0.0011018462,"about_ca_system_score_gemma":0.001611942,"threshold_uncertainty_score":0.2842834},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7938539,0.008238042,0.001383889,0.0063868295,0.0009516415,0.00055571896,0.04964774,0.00025365117,0.13872862],"genre_scores_gemma":[0.6906865,0.0036758492,0.004063729,0.0014438485,0.000059796843,0.00034618287,0.014859604,0.0001222744,0.2847422],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994717,0.0000441047,0.000033674067,0.0000818861,0.000118221586,0.0002503682],"domain_scores_gemma":[0.9992054,0.000117807474,0.00009411314,0.000053440366,0.00026488086,0.00026429544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005244241,0.00041090124,0.00041745623,0.0008703172,0.0017189812,0.0022990676,0.0004931481,0.0004990313,0.011770086],"category_scores_gemma":[0.0013845427,0.0002867212,0.00027062904,0.0012559604,0.0005772565,0.00036778953,0.0013557832,0.00063677627,0.0019622524],"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":[0.0032547645,0.0003524854,0.38627082,0.0023223183,0.00045417584,0.007827861,0.008086196,0.0065149576,0.013183097,0.019977458,0.21591547,0.33584034],"study_design_scores_gemma":[0.00014744465,0.00013334685,0.75832033,0.0007803229,0.00007599774,0.0005287043,0.0080789,0.00086548104,0.0020225402,0.00094057614,0.22804467,0.00006160949],"about_ca_topic_score_codex":0.8933705,"about_ca_topic_score_gemma":0.9768585,"teacher_disagreement_score":0.10662949,"about_ca_system_score_codex":0.0131304255,"about_ca_system_score_gemma":0.02792618,"threshold_uncertainty_score":0.21451485},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01603234,0.00021060456,0.1026106,0.0020845497,0.00028773057,0.86758244,0.001730379,0.0004053432,0.0090560205],"genre_scores_gemma":[0.020028906,0.00017268762,0.112695165,0.00039942394,0.00003374184,0.86430126,0.00032416685,0.000038820734,0.0020059282],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9097933,0.06831449,0.009172038,0.0043354617,0.0049841073,0.0034006329],"domain_scores_gemma":[0.82966685,0.11955651,0.0059747254,0.014501984,0.023708656,0.0065912483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17214137,0.0033534917,0.0027574454,0.0030836484,0.010480423,0.0064439094,0.004959999,0.00933377,0.04122639],"category_scores_gemma":[0.16130808,0.0042085377,0.003537792,0.0022078562,0.0060810694,0.006186267,0.011356039,0.012819222,0.0092253],"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":[0.024637014,0.0127555905,0.0039639794,0.038835544,0.00048481685,0.0029439903,0.2824255,0.024195021,0.021041647,0.13304318,0.038202714,0.41747105],"study_design_scores_gemma":[0.03920898,0.014549658,0.012320685,0.028562438,0.0015958,0.0007769455,0.11490334,0.028362347,0.05788002,0.13491966,0.5652149,0.0017052852],"about_ca_topic_score_codex":0.0032066854,"about_ca_topic_score_gemma":0.005290621,"teacher_disagreement_score":0.17214137,"about_ca_system_score_codex":0.012256015,"about_ca_system_score_gemma":0.044654623,"threshold_uncertainty_score":0.9103815},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14968896,0.03081476,0.031855103,0.08481153,0.0060357843,0.00064592983,0.005181411,0.0017166922,0.6892498],"genre_scores_gemma":[0.56182235,0.021833763,0.035418957,0.0068578,0.0013274177,0.0002640474,0.0034565628,0.0009112299,0.36810783],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9902891,0.004083746,0.00043749635,0.0009215603,0.0036265363,0.0006415548],"domain_scores_gemma":[0.99501604,0.0019453699,0.0004562149,0.0004508837,0.0017631563,0.0003682881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008401334,0.0008803352,0.0008520046,0.0015534903,0.0012549099,0.008129825,0.0011700769,0.00230551,0.048120998],"category_scores_gemma":[0.012556232,0.00034049427,0.00079277286,0.0013013106,0.0012967563,0.0034421713,0.0026993554,0.0020675764,0.019170389],"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":[0.0012464635,0.001234657,0.008958833,0.0016512361,0.00017672215,0.0005778355,0.0020117804,0.0035876725,0.0073006116,0.026690258,0.10482931,0.84173465],"study_design_scores_gemma":[0.00013098585,0.0023420851,0.014237621,0.0025024635,0.00028744497,0.00088305114,0.007647306,0.0031024243,0.028330943,0.02292045,0.91740656,0.0002086756],"about_ca_topic_score_codex":0.005602811,"about_ca_topic_score_gemma":0.007093718,"teacher_disagreement_score":0.048120998,"about_ca_system_score_codex":0.0026250815,"about_ca_system_score_gemma":0.0041587395,"threshold_uncertainty_score":0.16098082},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.669345,0.000828265,0.2326009,0.0024843698,0.00084222056,0.010827794,0.0039938064,0.0031680455,0.07590956],"genre_scores_gemma":[0.7327443,0.0002787851,0.24902363,0.0007006321,0.00008955535,0.0070326263,0.0016006519,0.00034352508,0.008186335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9760393,0.014249928,0.0011426347,0.0012533093,0.00673197,0.0005829632],"domain_scores_gemma":[0.9140918,0.06441719,0.0036258942,0.0053540883,0.011361434,0.0011495075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029885117,0.0007385904,0.0006438798,0.0014166705,0.00074938714,0.003577614,0.001120197,0.0011689984,0.0134662995],"category_scores_gemma":[0.09737561,0.00055036315,0.0014863429,0.0013186502,0.0006771284,0.0017558694,0.0021394773,0.0015914494,0.0029374156],"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":[0.006823959,0.007283986,0.11044259,0.0017660571,0.00072960864,0.00013752498,0.0023095878,0.007829947,0.010313918,0.01704294,0.015186427,0.82013345],"study_design_scores_gemma":[0.0052561536,0.054237943,0.348037,0.0024830536,0.0032923473,0.00087160966,0.0064056385,0.30709627,0.12729356,0.04183564,0.10226674,0.0009240575],"about_ca_topic_score_codex":0.0018856253,"about_ca_topic_score_gemma":0.0015865972,"teacher_disagreement_score":0.9701149,"about_ca_system_score_codex":0.001042091,"about_ca_system_score_gemma":0.0032309487,"threshold_uncertainty_score":0.15804946},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013296603,0.9733331,0.0044418764,0.0108598005,0.0007184594,0.0015435793,0.003933654,0.000030507934,0.0038094812],"genre_scores_gemma":[0.04265149,0.92147785,0.019619122,0.006722799,0.00041499312,0.006731049,0.0014869103,0.00008048976,0.0008153394],"study_design_codex":"systematic_review","study_design_gemma":"qualitative","domain_scores_codex":[0.8824322,0.07596001,0.020061659,0.0028996898,0.017069098,0.0015773062],"domain_scores_gemma":[0.57320017,0.37158835,0.01520772,0.0042533996,0.034716893,0.0010334273],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14885354,0.0014951719,0.0053012036,0.018677523,0.0024591251,0.008534258,0.0036864688,0.002564963,0.009311618],"category_scores_gemma":[0.40914658,0.0012107614,0.007591608,0.028075758,0.0034801334,0.004752303,0.005663218,0.0042677317,0.0006115888],"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":[0.00051027426,0.000046639172,0.0016672935,0.6018941,0.0046810615,0.00006971127,0.0048280037,0.0008759995,0.00022612089,0.021040605,0.022878721,0.3412815],"study_design_scores_gemma":[0.00019829127,0.00007511137,0.003104798,0.8860502,0.0062154946,0.000089507725,0.0024690046,0.000312,0.0003505509,0.008132357,0.09289879,0.00010387782],"about_ca_topic_score_codex":0.14946768,"about_ca_topic_score_gemma":0.23053221,"teacher_disagreement_score":0.9648019,"about_ca_system_score_codex":0.035198107,"about_ca_system_score_gemma":0.09501975,"threshold_uncertainty_score":0.78722215},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064566857,0.006319586,0.31907457,0.008601882,0.0040539037,0.47155336,0.14212036,0.007952163,0.03386752],"genre_scores_gemma":[0.007911754,0.00197376,0.3946294,0.0014736308,0.00020365429,0.5735546,0.015865345,0.00082248624,0.0035653994],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3439507,0.30329925,0.30084696,0.0071581476,0.040397268,0.00434767],"domain_scores_gemma":[0.19981755,0.41640192,0.064042054,0.107104145,0.2094495,0.003184894],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3476496,0.0036955506,0.006416078,0.03394677,0.005273544,0.009511846,0.007092653,0.00604946,0.037799403],"category_scores_gemma":[0.6532912,0.006567543,0.016141139,0.032504268,0.004189055,0.004928498,0.010640336,0.008328817,0.014117124],"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":[0.0018549539,0.00069559045,0.012346733,0.20264101,0.004123382,0.0005919253,0.020708008,0.0024752999,0.0033665684,0.030612757,0.30468795,0.4158958],"study_design_scores_gemma":[0.0032533347,0.00094520726,0.0328661,0.23309846,0.0033363441,0.000671306,0.011358151,0.0055885664,0.010964032,0.031425748,0.66576785,0.000724842],"about_ca_topic_score_codex":0.016230267,"about_ca_topic_score_gemma":0.022425834,"teacher_disagreement_score":0.6523504,"about_ca_system_score_codex":0.007946342,"about_ca_system_score_gemma":0.060320042,"threshold_uncertainty_score":0.8044642},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945076,0.00047905458,0.000260613,0.0018203873,0.000024151968,0.00005437013,0.00017840443,0.00002369364,0.0026517517],"genre_scores_gemma":[0.9916427,0.0012987099,0.0013793831,0.0020601014,0.0000804065,0.0002052972,0.0004288222,0.00004852202,0.0028561933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99363285,0.0023580147,0.00061077497,0.0007230386,0.0019397221,0.0007356895],"domain_scores_gemma":[0.9393923,0.021198668,0.01449541,0.002959844,0.010745414,0.011208387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0126871485,0.0001790862,0.00033002935,0.003842858,0.0025440084,0.0027370579,0.0012429795,0.00094940304,0.003770712],"category_scores_gemma":[0.043914147,0.00052069564,0.0002993762,0.0041143037,0.0014720003,0.003014339,0.0033070887,0.0015580619,0.0007170588],"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":[0.00024531188,0.00045879403,0.7837927,0.00028395167,0.00003172164,0.00040848774,0.111194246,0.000056241868,0.0025020489,0.0009675159,0.005295711,0.09476331],"study_design_scores_gemma":[0.000010415552,0.0002086166,0.9268324,0.0001543808,0.000010772353,0.00035753066,0.06347152,0.00024729554,0.00023657085,0.00020500366,0.0082401745,0.000025408453],"about_ca_topic_score_codex":0.01455653,"about_ca_topic_score_gemma":0.024936786,"teacher_disagreement_score":0.98731285,"about_ca_system_score_codex":0.0015505465,"about_ca_system_score_gemma":0.004451483,"threshold_uncertainty_score":0.06709683},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945076,0.00047905458,0.000260613,0.0018203873,0.000024151968,0.00005437013,0.00017840443,0.00002369364,0.0026517517],"genre_scores_gemma":[0.9916427,0.0012987099,0.0013793831,0.0020601014,0.0000804065,0.0002052972,0.0004288222,0.00004852202,0.0028561933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99363285,0.0023580147,0.00061077497,0.0007230386,0.0019397221,0.0007356895],"domain_scores_gemma":[0.9393923,0.021198668,0.01449541,0.002959844,0.010745414,0.011208387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0126871485,0.0001790862,0.00033002935,0.003842858,0.0025440084,0.0027370579,0.0012429795,0.00094940304,0.003770712],"category_scores_gemma":[0.043914147,0.00052069564,0.0002993762,0.0041143037,0.0014720003,0.003014339,0.0033070887,0.0015580619,0.0007170588],"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":[0.00024531188,0.00045879403,0.7837927,0.00028395167,0.00003172164,0.00040848774,0.111194246,0.000056241868,0.0025020489,0.0009675159,0.005295711,0.09476331],"study_design_scores_gemma":[0.000010415552,0.0002086166,0.9268324,0.0001543808,0.000010772353,0.00035753066,0.06347152,0.00024729554,0.00023657085,0.00020500366,0.0082401745,0.000025408453],"about_ca_topic_score_codex":0.01455653,"about_ca_topic_score_gemma":0.024936786,"teacher_disagreement_score":0.98731285,"about_ca_system_score_codex":0.0015505465,"about_ca_system_score_gemma":0.004451483,"threshold_uncertainty_score":0.06709683},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051829503,0.020591687,0.07841939,0.017776538,0.0020012483,0.0001335542,0.000050203238,0.00022748731,0.875617],"genre_scores_gemma":[0.38827157,0.035951316,0.12590043,0.016667115,0.0021286153,0.000596011,0.00016143828,0.00091678475,0.42940676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948395,0.0034639642,0.00008465651,0.00012274414,0.0013593822,0.00012978652],"domain_scores_gemma":[0.9923618,0.0061146724,0.0001521841,0.00035058684,0.00082044135,0.0002004419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049290573,0.00064234657,0.00047904465,0.0009820701,0.0011871295,0.008361098,0.0009762653,0.0014279997,0.00767502],"category_scores_gemma":[0.011777416,0.00020719327,0.00023319632,0.0010815045,0.0058929175,0.003508248,0.0026192837,0.0029771747,0.0016013623],"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":[0.000023252209,0.00005564043,0.00023456168,0.00024190088,0.000013438341,0.000089748384,0.0047354554,0.001009063,0.00069788704,0.70130086,0.049643815,0.24195431],"study_design_scores_gemma":[0.000010563112,0.000044261396,0.0006330392,0.0009768741,0.000015165457,0.0002082936,0.0034845327,0.0019449069,0.0016444423,0.6416419,0.34936178,0.00003424538],"about_ca_topic_score_codex":0.002005632,"about_ca_topic_score_gemma":0.004943457,"teacher_disagreement_score":0.008361098,"about_ca_system_score_codex":0.002725331,"about_ca_system_score_gemma":0.0037564144,"threshold_uncertainty_score":0.026067615},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019134841,0.0085053425,0.7096765,0.010643243,0.0007486375,0.00021962315,0.00015809979,0.0006678957,0.2674672],"genre_scores_gemma":[0.19527005,0.017346272,0.6511536,0.0024117096,0.00084514735,0.0014054129,0.00041389852,0.00063859654,0.13051535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9881842,0.007978751,0.00041710888,0.000545534,0.002647403,0.00022690558],"domain_scores_gemma":[0.98797554,0.009279847,0.00026091843,0.0011083619,0.0012433343,0.00013201835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013450035,0.0011945837,0.0011433646,0.0026487755,0.001228824,0.008852541,0.0020173409,0.002435078,0.010591645],"category_scores_gemma":[0.027208727,0.00109718,0.0009245392,0.0023985454,0.005253601,0.008565281,0.002605712,0.0033695274,0.0031079843],"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":[0.0000031150134,0.000015373014,0.00004316558,0.000057585097,0.00000644332,0.000008788759,0.000105031846,0.0037744201,0.00002219045,0.9532066,0.0055059767,0.03725137],"study_design_scores_gemma":[0.0000032316207,0.000008160751,0.000052810836,0.00015342624,0.0000063523394,0.000020273877,0.00010156041,0.0112897055,0.00011109163,0.9419446,0.04629965,0.000009045965],"about_ca_topic_score_codex":0.0038485792,"about_ca_topic_score_gemma":0.0033623737,"teacher_disagreement_score":0.013450035,"about_ca_system_score_codex":0.00427321,"about_ca_system_score_gemma":0.004465386,"threshold_uncertainty_score":0.07113147},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011689006,0.0010719053,0.8931655,0.010261753,0.0012497285,0.0026444227,0.0007119869,0.01361638,0.06558928],"genre_scores_gemma":[0.03817145,0.0009779574,0.93870586,0.0011943122,0.0001304216,0.0020627019,0.00089733646,0.00082578376,0.017034154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98805785,0.0065256506,0.0012550494,0.0009053236,0.0028518587,0.00040435058],"domain_scores_gemma":[0.97233284,0.011933725,0.0011681654,0.0026776022,0.0089203585,0.002967238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023693785,0.0013330138,0.0008018876,0.003026701,0.001309153,0.0059172786,0.0020591374,0.0016865195,0.018937642],"category_scores_gemma":[0.045912392,0.00075699243,0.0010653686,0.0012525402,0.0016693448,0.008502351,0.0072850036,0.0047572404,0.018245256],"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":[0.00012985575,0.0009897741,0.0055584977,0.0006794092,0.000048860955,0.00030825727,0.0039337017,0.004764037,0.0036684514,0.046941556,0.08129286,0.8516848],"study_design_scores_gemma":[0.00021375329,0.00080316723,0.0081728315,0.004468948,0.000069714195,0.0020410637,0.006027461,0.043499943,0.011479244,0.14449446,0.778386,0.000343381],"about_ca_topic_score_codex":0.0012466183,"about_ca_topic_score_gemma":0.0019970927,"teacher_disagreement_score":0.023693785,"about_ca_system_score_codex":0.001803629,"about_ca_system_score_gemma":0.009994619,"threshold_uncertainty_score":0.12530619},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012766158,0.3663956,0.2426334,0.33949238,0.003691738,0.008701877,0.0005784186,0.0005647696,0.025175663],"genre_scores_gemma":[0.1524039,0.16838904,0.6462029,0.015290639,0.00059003785,0.015194901,0.00027099028,0.0001857136,0.0014718578],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.6564214,0.28382704,0.032193203,0.0052557695,0.018862419,0.0034401284],"domain_scores_gemma":[0.49950394,0.44148684,0.01166914,0.012777016,0.031866733,0.0026963062],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39682946,0.0038189122,0.0054383185,0.033740208,0.00832286,0.036134917,0.005452206,0.007898801,0.0036815144],"category_scores_gemma":[0.36557716,0.0030117233,0.0037290193,0.021243278,0.0180846,0.035731703,0.018355401,0.010495062,0.00081153907],"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":[0.00016422936,0.00024772342,0.0032920353,0.062093407,0.00077400845,0.00049525104,0.08512911,0.0019233465,0.0008542486,0.22986434,0.01340022,0.601762],"study_design_scores_gemma":[0.00021072275,0.0003165911,0.0023287442,0.30289224,0.0015460055,0.00042123033,0.18558045,0.0030759338,0.0018582895,0.33427978,0.16713947,0.00035046897],"about_ca_topic_score_codex":0.010631215,"about_ca_topic_score_gemma":0.030315172,"teacher_disagreement_score":0.6031705,"about_ca_system_score_codex":0.03153656,"about_ca_system_score_gemma":0.09374053,"threshold_uncertainty_score":0.7438167},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18621406,0.0049383533,0.5556605,0.07603108,0.0008555316,0.00090469414,0.00007592406,0.0010391844,0.1742807],"genre_scores_gemma":[0.89204717,0.0010367885,0.101364605,0.0011833294,0.00016482423,0.0004084794,0.000036273126,0.00013685106,0.0036216336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.83963615,0.13437918,0.003659611,0.0052744704,0.013761608,0.0032890746],"domain_scores_gemma":[0.73537993,0.18810748,0.012608264,0.03550438,0.017560737,0.010839206],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.12647912,0.000948487,0.0007701482,0.005376093,0.0061055166,0.026767122,0.005164699,0.005247088,0.0065072863],"category_scores_gemma":[0.17204213,0.00082329434,0.00059320335,0.004566625,0.020768743,0.027145032,0.028839545,0.0063732653,0.0014951541],"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":[0.0002096344,0.00045909875,0.0066059018,0.00091583794,0.00017296645,0.000452933,0.07930419,0.0029938868,0.0022433153,0.5171013,0.0075373123,0.38200358],"study_design_scores_gemma":[0.000112242196,0.0004654724,0.0023174994,0.0013794991,0.000105746105,0.00059506844,0.056799054,0.009004541,0.0041219834,0.84321916,0.08174527,0.00013444295],"about_ca_topic_score_codex":0.0006762371,"about_ca_topic_score_gemma":0.0012410945,"teacher_disagreement_score":0.9948353,"about_ca_system_score_codex":0.005293111,"about_ca_system_score_gemma":0.019502578,"threshold_uncertainty_score":0.6688935},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81828135,0.006767606,0.033030745,0.039122894,0.00052308623,0.00014435004,0.000072613184,0.00010542108,0.101951964],"genre_scores_gemma":[0.99482524,0.00074878836,0.0014403468,0.0006052168,0.00003763505,0.00003846388,0.000010634554,0.000024674046,0.0022689744],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9614681,0.026343388,0.0010825725,0.0022588961,0.0058444645,0.0030025507],"domain_scores_gemma":[0.96889234,0.02332747,0.0017782802,0.0015002367,0.0017441314,0.0027575188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025247442,0.0006442632,0.0008940499,0.0025627885,0.010170675,0.01640044,0.002131006,0.0033789866,0.0051466012],"category_scores_gemma":[0.03334228,0.0006340795,0.00049940747,0.0021276758,0.043667097,0.020780256,0.017033217,0.0056656674,0.00057305023],"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":[0.000030434341,0.00001935687,0.003488817,0.00020101995,0.000009830272,0.0013043826,0.9092978,0.00014479656,0.0008207768,0.06868701,0.00081340835,0.015182309],"study_design_scores_gemma":[0.000005783379,0.000033750195,0.0013398762,0.00046752268,0.000007933898,0.0009955316,0.91065425,0.00029277257,0.00030402504,0.03461031,0.051251415,0.000036886573],"about_ca_topic_score_codex":0.0055349153,"about_ca_topic_score_gemma":0.0060909567,"teacher_disagreement_score":0.025247442,"about_ca_system_score_codex":0.006248086,"about_ca_system_score_gemma":0.0064032297,"threshold_uncertainty_score":0.13352281},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2549393,0.11587808,0.004551034,0.15724967,0.0021900733,0.005630189,0.07054863,0.0006793128,0.38833365],"genre_scores_gemma":[0.5625089,0.07793214,0.023551164,0.01703575,0.00066661224,0.003927094,0.028916134,0.0004594409,0.2850028],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979773,0.0002884712,0.00018362647,0.00012324537,0.00046110316,0.0009662773],"domain_scores_gemma":[0.9926605,0.0010551543,0.00085147645,0.00022644732,0.0025920938,0.0026142346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057648337,0.00040757115,0.0002807102,0.004007835,0.0016325605,0.0040139193,0.00072086,0.0015170216,0.01940944],"category_scores_gemma":[0.0072879805,0.00048668456,0.0002997955,0.005442926,0.0007958592,0.0018793993,0.0022398608,0.00086368853,0.0021825368],"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":[0.0004292296,0.00017813237,0.065239444,0.006211768,0.000072485636,0.0027159108,0.006859492,0.0009899013,0.0059384196,0.05968352,0.5446276,0.30705416],"study_design_scores_gemma":[0.00001939599,0.00004441967,0.10869621,0.0015860694,0.000010267941,0.0006459087,0.0014645233,0.0001210408,0.00033213687,0.00047253526,0.88658535,0.000022201355],"about_ca_topic_score_codex":0.14030348,"about_ca_topic_score_gemma":0.14884415,"teacher_disagreement_score":0.14030348,"about_ca_system_score_codex":0.009033784,"about_ca_system_score_gemma":0.031026248,"threshold_uncertainty_score":0.2789737},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36386347,0.038502466,0.14109151,0.15708329,0.0017008943,0.0023796137,0.00020770743,0.00034573054,0.29482532],"genre_scores_gemma":[0.9780473,0.002966447,0.012985404,0.0030613975,0.00018603913,0.00075118564,0.00003142274,0.00007437327,0.0018964142],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5651576,0.40292475,0.005797733,0.005340577,0.017119767,0.0036595636],"domain_scores_gemma":[0.3778877,0.54166496,0.018186942,0.021676464,0.031771764,0.008812181],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2723688,0.00082861236,0.0017441497,0.010643755,0.010695735,0.02262862,0.0036448091,0.003877523,0.005984748],"category_scores_gemma":[0.29851195,0.0006422098,0.00066882634,0.0073435395,0.041092694,0.025007818,0.01881148,0.0061833565,0.00047275392],"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":[0.00020561094,0.0010115901,0.019938918,0.003612632,0.00020855227,0.00038826687,0.3828173,0.0012133723,0.0006079891,0.37543756,0.00661499,0.20794319],"study_design_scores_gemma":[0.00017547896,0.00070602656,0.014243603,0.012487412,0.00013926241,0.00040243764,0.5558316,0.003391275,0.0021128033,0.28937748,0.12096217,0.00017045354],"about_ca_topic_score_codex":0.003629763,"about_ca_topic_score_gemma":0.0053415257,"teacher_disagreement_score":0.7276312,"about_ca_system_score_codex":0.014126192,"about_ca_system_score_gemma":0.023181317,"threshold_uncertainty_score":0.8972988},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27045658,0.0071747447,0.55892646,0.010623,0.00084729353,0.0200657,0.00030034335,0.00026467422,0.13134126],"genre_scores_gemma":[0.79846096,0.00127532,0.17922759,0.0006494825,0.00008126552,0.018458012,0.00008387083,0.00007230987,0.0016911678],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.3460022,0.5937834,0.016550066,0.006128681,0.033765506,0.0037702925],"domain_scores_gemma":[0.43300733,0.48378262,0.027493995,0.018991461,0.033091165,0.0036333988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.35197943,0.0016688887,0.0022461796,0.013120537,0.009920041,0.014403562,0.0030025868,0.0024727902,0.0036166129],"category_scores_gemma":[0.3894767,0.0012729646,0.0015064368,0.012216789,0.030599365,0.013411626,0.016596796,0.002830798,0.00032805122],"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":[0.0004925078,0.0005241446,0.052220006,0.007222512,0.00048788023,0.00081319344,0.40680623,0.003909304,0.0017683591,0.25655055,0.0027008727,0.26650438],"study_design_scores_gemma":[0.0003599124,0.0019342883,0.046065968,0.009085024,0.00046836774,0.0011523141,0.46847144,0.011319657,0.0044164374,0.350407,0.10593695,0.0003826395],"about_ca_topic_score_codex":0.0049919616,"about_ca_topic_score_gemma":0.010565543,"teacher_disagreement_score":0.35197943,"about_ca_system_score_codex":0.010697728,"about_ca_system_score_gemma":0.033780634,"threshold_uncertainty_score":0.7991247},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57321286,0.0148204,0.02274739,0.022854744,0.00063726393,0.0012349879,0.0029367055,0.00026285183,0.36129275],"genre_scores_gemma":[0.96772486,0.0025604044,0.011510463,0.0008471511,0.000038616014,0.00035491717,0.0004646793,0.000067252666,0.016431594],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9665069,0.013901242,0.0011693723,0.0014631449,0.014762247,0.0021971373],"domain_scores_gemma":[0.944142,0.017996782,0.0032589794,0.0015650556,0.031161852,0.0018753451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022029664,0.00069695327,0.00074914336,0.004421009,0.0060319635,0.010664101,0.0012250971,0.00090182124,0.0050529097],"category_scores_gemma":[0.048101075,0.0003568228,0.00070600444,0.0070273275,0.004210815,0.0023415857,0.0030023386,0.0017707169,0.00053453003],"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":[0.0006820366,0.00028291615,0.15570499,0.0028542727,0.0005097811,0.0006336966,0.13093618,0.0040470525,0.0019251815,0.072138146,0.03550653,0.59477925],"study_design_scores_gemma":[0.000091424656,0.0006187049,0.40641907,0.0071303113,0.00077794486,0.0005719062,0.19265753,0.010154847,0.004873327,0.016755154,0.35946396,0.0004859439],"about_ca_topic_score_codex":0.84112656,"about_ca_topic_score_gemma":0.8991262,"teacher_disagreement_score":0.94377863,"about_ca_system_score_codex":0.05622135,"about_ca_system_score_gemma":0.08123536,"threshold_uncertainty_score":0.40791637},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9338609,0.0024166733,0.00069520884,0.015811447,0.00005184519,0.0003493555,0.00060333667,0.000040304978,0.046171036],"genre_scores_gemma":[0.9909469,0.0015104514,0.00091586163,0.0010642064,0.0000036887122,0.00008347163,0.00017009789,0.000020777275,0.0052845376],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98995614,0.004825072,0.00027543528,0.0005525977,0.0014974814,0.0028933513],"domain_scores_gemma":[0.98774105,0.0042869938,0.00068284426,0.00046351162,0.0043025543,0.0025231785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007912976,0.00047607502,0.00061126484,0.0016947638,0.020283109,0.009048322,0.0027858193,0.00090103754,0.0028301345],"category_scores_gemma":[0.012540621,0.00046696176,0.00041080976,0.0050141914,0.008229184,0.0018515448,0.0051000435,0.0020960255,0.0002986299],"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":[0.00044393077,0.0005471034,0.2857155,0.00094664184,0.00029298844,0.004342849,0.49555767,0.005667396,0.002465993,0.03844932,0.03637726,0.12919329],"study_design_scores_gemma":[0.000030338566,0.000069228256,0.14242409,0.0007710536,0.000090813206,0.00011891437,0.80318296,0.0013529664,0.0005390358,0.002493452,0.04879295,0.00013427096],"about_ca_topic_score_codex":0.99644023,"about_ca_topic_score_gemma":0.998838,"teacher_disagreement_score":0.21656834,"about_ca_system_score_codex":0.21656834,"about_ca_system_score_gemma":0.29814252,"threshold_uncertainty_score":0.9086697},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058041763,0.004384706,0.1238074,0.1690956,0.0021094545,0.00040048428,0.00023616769,0.0005506486,0.6413738],"genre_scores_gemma":[0.9281714,0.001414411,0.032039687,0.010646906,0.00026863365,0.00029572228,0.00013649896,0.0002411512,0.02678559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97760105,0.014526854,0.0008811747,0.001444206,0.003201973,0.0023447345],"domain_scores_gemma":[0.9665441,0.014723649,0.0023030431,0.0040404215,0.0044163517,0.007972551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024925102,0.0008209367,0.0007128569,0.002699231,0.0062994105,0.016908618,0.0020855374,0.0036715022,0.011566869],"category_scores_gemma":[0.040253505,0.0007665875,0.00088327186,0.001646346,0.02586256,0.014206157,0.009781239,0.0055081616,0.0017053003],"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":[0.00010648177,0.00030950806,0.013832781,0.00018753261,0.00009104655,0.00024118138,0.016907012,0.001909826,0.00022722306,0.82054716,0.028337402,0.117302775],"study_design_scores_gemma":[0.00003448806,0.000095710035,0.002993804,0.0003790714,0.000042115487,0.00020780721,0.013996181,0.0013032866,0.0003990471,0.86402863,0.116462834,0.00005695688],"about_ca_topic_score_codex":0.013892963,"about_ca_topic_score_gemma":0.0141858235,"teacher_disagreement_score":0.024925102,"about_ca_system_score_codex":0.0069602453,"about_ca_system_score_gemma":0.021887626,"threshold_uncertainty_score":0.13181812},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015077692,0.026355432,0.24268483,0.58491904,0.005387601,0.000952452,0.00036090234,0.0003147819,0.12394723],"genre_scores_gemma":[0.6986411,0.012804275,0.19350605,0.07468904,0.009057436,0.0034905726,0.0003067446,0.000285267,0.0072194203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7626415,0.16876954,0.010332136,0.014546841,0.03964183,0.0040681614],"domain_scores_gemma":[0.5476184,0.32694602,0.0122786565,0.061168335,0.039629165,0.012359358],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21554662,0.00087435934,0.0035201353,0.004174851,0.010639528,0.019614048,0.0039335852,0.008013582,0.0044089537],"category_scores_gemma":[0.331499,0.0014291424,0.00092994963,0.0032466918,0.057139,0.031411104,0.023931507,0.01633723,0.0020139876],"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":[0.0000716005,0.00008324424,0.001847639,0.0007265294,0.00007725163,0.000093961324,0.00928052,0.00053363596,0.0003368888,0.9326436,0.010052593,0.044252455],"study_design_scores_gemma":[0.000032316242,0.000051927986,0.0005294493,0.0008889849,0.000014863423,0.00018146042,0.0020912776,0.0003688725,0.00016799849,0.95496637,0.040671702,0.000034823956],"about_ca_topic_score_codex":0.0023649312,"about_ca_topic_score_gemma":0.002009641,"teacher_disagreement_score":0.7844534,"about_ca_system_score_codex":0.005877886,"about_ca_system_score_gemma":0.023093862,"threshold_uncertainty_score":0.9673707},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22420147,0.0024235346,0.26693532,0.11465728,0.001817977,0.020049786,0.0066414764,0.005689835,0.35758328],"genre_scores_gemma":[0.54631275,0.0008167102,0.38965672,0.006174128,0.00014108836,0.005220855,0.004527612,0.00049885636,0.04665133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.96583265,0.014357722,0.0029450047,0.00258268,0.008262491,0.006019489],"domain_scores_gemma":[0.93898624,0.012889444,0.0036210564,0.004317983,0.03014986,0.010035572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037132096,0.0010716041,0.0006010635,0.0035787122,0.007157894,0.010766386,0.0040288256,0.0027733739,0.004502742],"category_scores_gemma":[0.043876763,0.000915993,0.0013203236,0.0018452809,0.004230866,0.0030427002,0.007945256,0.003341023,0.001037599],"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":[0.00040882753,0.0011697918,0.09448316,0.002051063,0.00021814326,0.0072621554,0.06367258,0.054237325,0.011181079,0.3665331,0.13554373,0.26323903],"study_design_scores_gemma":[0.0003496491,0.0008990005,0.10547361,0.0068956255,0.00015398249,0.001035824,0.03706403,0.06182631,0.005012657,0.04517604,0.73551905,0.0005943145],"about_ca_topic_score_codex":0.6389964,"about_ca_topic_score_gemma":0.70796686,"teacher_disagreement_score":0.36100358,"about_ca_system_score_codex":0.079780266,"about_ca_system_score_gemma":0.19880572,"threshold_uncertainty_score":0.72625923},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08001354,0.0042794156,0.6147262,0.22149217,0.0021303282,0.013642171,0.01496657,0.004944911,0.04380471],"genre_scores_gemma":[0.23379351,0.0020575265,0.74138916,0.004212594,0.00051159057,0.008799923,0.0071029626,0.0005043075,0.001628472],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80888236,0.1469907,0.015414933,0.0070651076,0.017565072,0.004081864],"domain_scores_gemma":[0.6999981,0.11489939,0.030380564,0.06200948,0.0747109,0.018001677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22909185,0.0015905434,0.0017584573,0.01043777,0.0065385154,0.017492814,0.006529158,0.0025445833,0.0050107357],"category_scores_gemma":[0.25421822,0.000966711,0.0018108125,0.009759629,0.009605351,0.021339092,0.023647869,0.006086068,0.0014793483],"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":[0.0003963698,0.0011037592,0.072047584,0.0045639705,0.00041347428,0.0002390262,0.015466425,0.020959565,0.0017502253,0.12062748,0.070617676,0.69181454],"study_design_scores_gemma":[0.00041972988,0.0029413903,0.0860406,0.019938944,0.0004135415,0.00029901718,0.042505994,0.04712639,0.009180682,0.3948166,0.39550892,0.0008081687],"about_ca_topic_score_codex":0.02022749,"about_ca_topic_score_gemma":0.02639833,"teacher_disagreement_score":0.22909185,"about_ca_system_score_codex":0.02485513,"about_ca_system_score_gemma":0.093949586,"threshold_uncertainty_score":0.950667},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002803836,0.9818762,0.0053096046,0.0049554147,0.00074139115,0.0028263456,0.0001644794,0.000029983448,0.0012928611],"genre_scores_gemma":[0.09164884,0.8543649,0.039138954,0.0034526272,0.00037790355,0.0103789875,0.00032489208,0.000046535333,0.00026640284],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.67903095,0.18878175,0.08098328,0.009713273,0.039541982,0.0019487278],"domain_scores_gemma":[0.31693748,0.57669544,0.039141994,0.01381052,0.05115325,0.0022613208],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26739362,0.001927317,0.0077699563,0.03953016,0.0036751586,0.010932877,0.0044685644,0.005181111,0.002344959],"category_scores_gemma":[0.56961,0.0025362414,0.0063104015,0.03251974,0.008446326,0.016302317,0.008976991,0.004955205,0.00036912868],"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":[0.00023790948,0.00011823367,0.0026574163,0.64708424,0.0037899453,0.00020148374,0.010814526,0.00055952714,0.00032097954,0.007614995,0.004296316,0.32230446],"study_design_scores_gemma":[0.00014972077,0.00015165994,0.0016618223,0.962301,0.004419383,0.00022354328,0.0040040673,0.00026876872,0.00022968098,0.003956664,0.0225723,0.00006132328],"about_ca_topic_score_codex":0.009200981,"about_ca_topic_score_gemma":0.0259329,"teacher_disagreement_score":0.7326064,"about_ca_system_score_codex":0.01938085,"about_ca_system_score_gemma":0.07264046,"threshold_uncertainty_score":0.9034341},"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":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23878667,0.001321686,0.43537307,0.046251003,0.0013182531,0.021635838,0.009638256,0.014225482,0.23144972],"genre_scores_gemma":[0.44512635,0.00044803193,0.5070556,0.0024642064,0.000096429656,0.005319847,0.006505815,0.00070472615,0.032279074],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97622764,0.008907462,0.0024092868,0.002243736,0.0064356183,0.0037761284],"domain_scores_gemma":[0.95182145,0.008731513,0.0036961876,0.0035899526,0.02618921,0.0059717647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03008727,0.0010610643,0.00057009584,0.0033472946,0.004457374,0.008420145,0.0033193629,0.0016973336,0.004304596],"category_scores_gemma":[0.039404973,0.0007744509,0.0010622719,0.0016337351,0.0021526488,0.0025738887,0.00605503,0.002191082,0.0009790866],"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":[0.000569236,0.0014739071,0.12771876,0.0021234567,0.0002535208,0.005512841,0.041503396,0.08309174,0.01697456,0.1967984,0.121936195,0.40204394],"study_design_scores_gemma":[0.00029126168,0.0011009728,0.11007285,0.0062036472,0.00015681882,0.00070234743,0.022798238,0.15509099,0.009880484,0.023676204,0.66942495,0.0006012953],"about_ca_topic_score_codex":0.5552553,"about_ca_topic_score_gemma":0.59292394,"teacher_disagreement_score":0.9533312,"about_ca_system_score_codex":0.046668854,"about_ca_system_score_gemma":0.113277666,"threshold_uncertainty_score":0.89472777},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073236965,0.005158117,0.05689008,0.70534587,0.012616358,0.00194769,0.0004564174,0.0012657132,0.1430828],"genre_scores_gemma":[0.7933622,0.0037563185,0.04105266,0.11087338,0.0022011043,0.0016063125,0.0005940316,0.00061751134,0.045936465],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.94823,0.032606814,0.0010559233,0.0027270007,0.004486697,0.010893615],"domain_scores_gemma":[0.91104597,0.012237087,0.0036857757,0.0036196138,0.009692901,0.059718702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04586187,0.0012322582,0.0008594512,0.0019717005,0.04717946,0.022170715,0.0042361226,0.009614077,0.038477797],"category_scores_gemma":[0.03565381,0.0012442546,0.0017645169,0.0017488211,0.01571805,0.018894466,0.04270243,0.020846501,0.0071663503],"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":[0.00028494548,0.0005510091,0.01614691,0.0013376726,0.00014205446,0.0033870046,0.46081764,0.00080901454,0.0045997063,0.094178565,0.277582,0.14016357],"study_design_scores_gemma":[0.000053710144,0.00017204465,0.0045148344,0.0009521268,0.00005537715,0.00037528653,0.30828762,0.0005277409,0.0006757999,0.02858029,0.65565753,0.00014756231],"about_ca_topic_score_codex":0.0600645,"about_ca_topic_score_gemma":0.08906184,"teacher_disagreement_score":0.0600645,"about_ca_system_score_codex":0.023368975,"about_ca_system_score_gemma":0.07303748,"threshold_uncertainty_score":0.24254364},"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":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6357584,0.009440354,0.0656431,0.16473953,0.0049734577,0.0005982692,0.0001808842,0.00034737203,0.118318714],"genre_scores_gemma":[0.9246013,0.0036896167,0.009133431,0.016108023,0.0007375835,0.00021706041,0.00004543091,0.00019387025,0.04527361],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9813318,0.0139031,0.00042164445,0.0010727266,0.0025595147,0.0007112527],"domain_scores_gemma":[0.9800593,0.012830783,0.0008407782,0.0012343546,0.0025029993,0.0025318325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013940803,0.0007091965,0.000749948,0.0011516738,0.008490243,0.01690299,0.0016498169,0.0036656447,0.0024181802],"category_scores_gemma":[0.050573897,0.0005665295,0.00049419794,0.00073871715,0.018623745,0.008908083,0.01306779,0.010755863,0.0011867112],"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":[0.00008098046,0.00014394357,0.0014502986,0.00023508443,0.000017794104,0.0022480998,0.91480327,0.00018287888,0.0021310826,0.036801122,0.008126718,0.033778712],"study_design_scores_gemma":[0.00001961237,0.00031929568,0.0008020688,0.00066203595,0.000011852643,0.0031672555,0.76657,0.00042101552,0.0022925446,0.025366383,0.20028925,0.00007870689],"about_ca_topic_score_codex":0.0011379898,"about_ca_topic_score_gemma":0.001192485,"teacher_disagreement_score":0.01690299,"about_ca_system_score_codex":0.0025224604,"about_ca_system_score_gemma":0.0041860207,"threshold_uncertainty_score":0.07372683},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0397038,0.05054861,0.22556584,0.6205358,0.0034362113,0.0005245794,0.00014029724,0.00018343254,0.059361495],"genre_scores_gemma":[0.90290105,0.010331208,0.06274066,0.019070167,0.0016911667,0.0011029344,0.00005969962,0.00012186413,0.0019812966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6493989,0.2947229,0.013280359,0.009989126,0.028436892,0.0041718977],"domain_scores_gemma":[0.32828087,0.6024911,0.018514913,0.024726404,0.02325699,0.0027297884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3236335,0.001260894,0.0028803125,0.01854178,0.009369109,0.034649625,0.007302909,0.010393684,0.0030647102],"category_scores_gemma":[0.3534218,0.0011376245,0.0013115179,0.011505822,0.14125954,0.05491557,0.020440714,0.016590843,0.0004961151],"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":[0.000042667765,0.000047105663,0.0007936643,0.0011201397,0.000043101198,0.00013194427,0.04501586,0.0004595383,0.00018385434,0.92724067,0.0027033603,0.022218058],"study_design_scores_gemma":[0.00002930532,0.00006502786,0.00068941305,0.004092139,0.000039430368,0.00013383082,0.024703698,0.0013310593,0.0006010341,0.92852956,0.039732203,0.000053409203],"about_ca_topic_score_codex":0.0024970104,"about_ca_topic_score_gemma":0.0027943195,"teacher_disagreement_score":0.3236335,"about_ca_system_score_codex":0.01481765,"about_ca_system_score_gemma":0.028924052,"threshold_uncertainty_score":0.83408034},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91050667,0.001158909,0.0017236253,0.014609439,0.00003829219,0.00025928815,0.0003066035,0.000025513378,0.07137157],"genre_scores_gemma":[0.97757393,0.0014083735,0.0019790905,0.000836323,0.0000039736765,0.00011227216,0.00014797751,0.000018063578,0.017920021],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9971048,0.0007517018,0.0000822964,0.00017864566,0.0009011256,0.0009814606],"domain_scores_gemma":[0.9944899,0.0014547923,0.00041347343,0.00020723644,0.002245836,0.0011887107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041183517,0.00024289174,0.00022389852,0.0006935734,0.007477724,0.004522975,0.001731781,0.00065261376,0.0023886145],"category_scores_gemma":[0.007165841,0.00031282153,0.00016095799,0.0015028364,0.0042535304,0.0013020892,0.003277469,0.0013262257,0.00012280789],"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":[0.000436642,0.00059094344,0.39490068,0.0006061804,0.00006766537,0.0055331835,0.22046813,0.009820879,0.007960737,0.12069657,0.026747553,0.21217081],"study_design_scores_gemma":[0.00008842305,0.00034675194,0.2694579,0.0005995206,0.000063446605,0.00046086186,0.4711707,0.0037035106,0.004081194,0.0056120483,0.2442561,0.00015957115],"about_ca_topic_score_codex":0.96998805,"about_ca_topic_score_gemma":0.9934366,"teacher_disagreement_score":0.08877021,"about_ca_system_score_codex":0.08877021,"about_ca_system_score_gemma":0.11531231,"threshold_uncertainty_score":0.644076},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9470485,0.00043898445,0.0011853045,0.03095185,0.00017844005,0.000143227,0.00003921599,0.000015434269,0.019999046],"genre_scores_gemma":[0.98701257,0.00026429695,0.00091459043,0.0033214665,0.000022976832,0.00010092649,0.000017315,0.000010677029,0.008335172],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96043926,0.03278748,0.0006611311,0.0008936326,0.0031845605,0.0020339806],"domain_scores_gemma":[0.92670554,0.054968834,0.0038607148,0.0015857287,0.007078568,0.005800684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028363904,0.00031781165,0.00028391124,0.0011364975,0.015157063,0.008354486,0.0010743937,0.003505157,0.0033075837],"category_scores_gemma":[0.056531627,0.00045253622,0.00039599228,0.0007600116,0.0040538334,0.0033463228,0.0059427847,0.004199553,0.00029632048],"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":[0.00024667918,0.00047568843,0.036844045,0.00023768061,0.000052302203,0.001533681,0.8999703,0.00019655317,0.0027606033,0.0053378195,0.0071457247,0.045198943],"study_design_scores_gemma":[0.000017034516,0.0003176837,0.018486096,0.00017364058,0.000034528253,0.00041181408,0.9435222,0.00018168002,0.0016102399,0.0012619882,0.03391734,0.000065725006],"about_ca_topic_score_codex":0.013056203,"about_ca_topic_score_gemma":0.027674787,"teacher_disagreement_score":0.9869438,"about_ca_system_score_codex":0.003845975,"about_ca_system_score_gemma":0.009752295,"threshold_uncertainty_score":0.15000445},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023471612,0.89866555,0.019224558,0.009959299,0.002475597,0.02715407,0.006195873,0.00022527039,0.012628182],"genre_scores_gemma":[0.16410889,0.7212811,0.06628948,0.003483735,0.00075457897,0.036479753,0.0042605367,0.00014344836,0.0031985093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88183326,0.05576568,0.03175385,0.0020307342,0.027916785,0.00069968647],"domain_scores_gemma":[0.670497,0.18800429,0.04125845,0.008992298,0.08963301,0.0016149654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.084952556,0.0008421081,0.0034400616,0.010408215,0.0010412852,0.0034487396,0.0020956625,0.0014845867,0.0027190298],"category_scores_gemma":[0.2967518,0.0009146181,0.003566748,0.009846708,0.0012301127,0.002156602,0.0016717743,0.0012078327,0.0008123612],"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":[0.00084899017,0.000094097544,0.008318553,0.44956556,0.007934119,0.0003526833,0.0022305262,0.000332777,0.0014678141,0.0015467542,0.021601284,0.5057068],"study_design_scores_gemma":[0.0010679133,0.0016033394,0.075554706,0.6222087,0.031289056,0.0016860069,0.0013770686,0.001298469,0.0026758637,0.0015226473,0.25944468,0.00027153976],"about_ca_topic_score_codex":0.0058827917,"about_ca_topic_score_gemma":0.022277672,"teacher_disagreement_score":0.084952556,"about_ca_system_score_codex":0.0049387887,"about_ca_system_score_gemma":0.018754993,"threshold_uncertainty_score":0.4492774},"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":"protocol","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13532351,0.0037193128,0.10599268,0.11251657,0.009570539,0.28323257,0.103113964,0.0044487035,0.24208228],"genre_scores_gemma":[0.23551366,0.0020309377,0.44976953,0.023593917,0.0011108872,0.21663137,0.024048267,0.0013280739,0.045973398],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.859954,0.0642499,0.02208523,0.0033599862,0.048105218,0.0022456932],"domain_scores_gemma":[0.45406276,0.1703365,0.03016179,0.041890305,0.29611236,0.007436234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1404475,0.00090120675,0.001218123,0.0028704186,0.001825604,0.0029878092,0.0032259799,0.004870016,0.027947566],"category_scores_gemma":[0.49623808,0.0008551564,0.002901179,0.003286788,0.001635718,0.003390009,0.0021880153,0.002997032,0.020817608],"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":[0.0018252067,0.0017793595,0.05793315,0.0057560275,0.00050232356,0.00009716789,0.0019305125,0.00039869203,0.0016832642,0.002214338,0.5115113,0.4143685],"study_design_scores_gemma":[0.006247199,0.0042483076,0.4230055,0.02216119,0.0012252899,0.00042959818,0.0037333055,0.006878571,0.011067758,0.004713475,0.51583093,0.00045896735],"about_ca_topic_score_codex":0.011044132,"about_ca_topic_score_gemma":0.023314731,"teacher_disagreement_score":0.1404475,"about_ca_system_score_codex":0.0040349644,"about_ca_system_score_gemma":0.015067611,"threshold_uncertainty_score":0.74276626},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027842833,0.8917547,0.020372987,0.009326783,0.0025272449,0.028974006,0.006203569,0.00022962061,0.012768222],"genre_scores_gemma":[0.18844406,0.6899009,0.07148336,0.0033341257,0.0007609048,0.038595792,0.0043124864,0.00014371992,0.0030246966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.874007,0.059383426,0.034572538,0.0020993697,0.029219039,0.0007186063],"domain_scores_gemma":[0.65455,0.2003105,0.042866852,0.0094785215,0.091205135,0.0015889833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08978117,0.0008347351,0.003551905,0.010627664,0.0010559694,0.0035407285,0.0021044682,0.0014852039,0.0025109928],"category_scores_gemma":[0.31340444,0.0009305434,0.0037124096,0.009922275,0.0012322448,0.0021763905,0.0017033125,0.0011928866,0.00075158995],"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":[0.0008956829,0.00010091646,0.009849264,0.44239417,0.008892556,0.00036485007,0.002432459,0.00035039402,0.001488447,0.001552743,0.019404428,0.5122741],"study_design_scores_gemma":[0.001162529,0.0017759295,0.088758156,0.62047577,0.03505497,0.0017792088,0.0015638549,0.0014883947,0.0027644883,0.0015731372,0.2433074,0.00029616992],"about_ca_topic_score_codex":0.00573304,"about_ca_topic_score_gemma":0.021784235,"teacher_disagreement_score":0.08978117,"about_ca_system_score_codex":0.004831393,"about_ca_system_score_gemma":0.017968448,"threshold_uncertainty_score":0.47481388},"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":"protocol","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13605219,0.0037735046,0.10650971,0.111516446,0.009844237,0.28086564,0.104437776,0.0044503687,0.24255027],"genre_scores_gemma":[0.23429057,0.0020275358,0.45641196,0.023238368,0.0011236729,0.21158978,0.024203494,0.0012816663,0.045833014],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8610453,0.06400577,0.022391982,0.003297821,0.047056414,0.0022027509],"domain_scores_gemma":[0.45323595,0.17202415,0.029566083,0.041193135,0.29639563,0.0075849975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14124171,0.00089576497,0.0012072225,0.002919201,0.0018186261,0.002982605,0.0032378493,0.0050287074,0.02754032],"category_scores_gemma":[0.49486986,0.0008510607,0.002940297,0.003330106,0.0016475165,0.0034017684,0.0022156115,0.002990879,0.020802723],"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":[0.0019171998,0.0018344758,0.058945432,0.005984674,0.0005195156,0.000098368764,0.0019082453,0.00041103555,0.0017648813,0.0022702257,0.50523806,0.41910788],"study_design_scores_gemma":[0.006276857,0.004333707,0.4252427,0.022669975,0.0012520506,0.00042755125,0.0037126765,0.006863941,0.011148377,0.0047629923,0.5128495,0.0004595708],"about_ca_topic_score_codex":0.010794848,"about_ca_topic_score_gemma":0.022366323,"teacher_disagreement_score":0.14124171,"about_ca_system_score_codex":0.0039298316,"about_ca_system_score_gemma":0.014815813,"threshold_uncertainty_score":0.7469665},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027843721,0.8895558,0.021395562,0.009290654,0.002538606,0.029710563,0.0064213965,0.00023673751,0.0130069805],"genre_scores_gemma":[0.19271126,0.67952794,0.07524545,0.0033435235,0.0007680796,0.040585138,0.004577248,0.00014826634,0.0030931432],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.869001,0.06156635,0.0361296,0.0022023453,0.030360583,0.0007401138],"domain_scores_gemma":[0.6458982,0.20439109,0.043707762,0.009721685,0.09465556,0.0016257083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09340704,0.0008404808,0.0036125688,0.010911911,0.0010654741,0.0035900136,0.0021431462,0.001493185,0.0025307406],"category_scores_gemma":[0.3193726,0.00093765446,0.0037685866,0.010203153,0.0012534866,0.002216262,0.0017480712,0.001208243,0.0007575358],"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":[0.00090508483,0.00009989187,0.010212882,0.44034505,0.008934289,0.00036708813,0.002495178,0.00036071878,0.0014710056,0.0016092804,0.0193933,0.5138062],"study_design_scores_gemma":[0.0011670884,0.0017736317,0.091447905,0.614194,0.035080846,0.0018146344,0.0015879138,0.0015431581,0.0027684784,0.0016359248,0.24668127,0.0003051353],"about_ca_topic_score_codex":0.0057762223,"about_ca_topic_score_gemma":0.021816516,"teacher_disagreement_score":0.09340704,"about_ca_system_score_codex":0.0049286126,"about_ca_system_score_gemma":0.017988568,"threshold_uncertainty_score":0.4939896},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026713545,0.89433986,0.020074362,0.009506783,0.0024878797,0.027933748,0.0061787465,0.00022658138,0.0125385225],"genre_scores_gemma":[0.18425289,0.69639677,0.06951242,0.003364312,0.00076349353,0.03809621,0.004359872,0.00014370977,0.0031103143],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87515116,0.058743987,0.034193303,0.0021120848,0.029079294,0.0007202247],"domain_scores_gemma":[0.6543658,0.1977375,0.042873863,0.009423656,0.09396904,0.0016302599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.089735806,0.000845055,0.0035471471,0.010701095,0.0010573152,0.0035339377,0.0021107811,0.0014932844,0.0025356733],"category_scores_gemma":[0.3100801,0.00093069865,0.0036545403,0.010128078,0.0012425102,0.0021867475,0.0017010178,0.001191499,0.00076926145],"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":[0.00090521586,0.00009953325,0.009713928,0.44132572,0.008506945,0.0003699065,0.0024174755,0.00034824145,0.0015084278,0.0015616909,0.020047,0.513196],"study_design_scores_gemma":[0.001142754,0.001764246,0.0877337,0.61645114,0.034118034,0.001808678,0.0015332832,0.001482066,0.0028437069,0.0015803821,0.24924845,0.00029352718],"about_ca_topic_score_codex":0.005800467,"about_ca_topic_score_gemma":0.021812124,"teacher_disagreement_score":0.089735806,"about_ca_system_score_codex":0.0048995344,"about_ca_system_score_gemma":0.01823305,"threshold_uncertainty_score":0.47457397},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023387412,0.9031541,0.018620048,0.009282346,0.0024138207,0.025396489,0.0057223425,0.00021518736,0.011808276],"genre_scores_gemma":[0.16818847,0.7207322,0.06459734,0.003377873,0.0007385295,0.035106394,0.004100833,0.0001384684,0.0030198353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87910426,0.056989882,0.03286322,0.002079544,0.02825659,0.0007065225],"domain_scores_gemma":[0.6627283,0.1938415,0.04186822,0.0092157265,0.09072623,0.0016200595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08704618,0.0008572772,0.0035747117,0.010760619,0.0010640987,0.003558153,0.0021317657,0.0015292147,0.0025931615],"category_scores_gemma":[0.3021831,0.0009324179,0.003652417,0.0101361275,0.0012646767,0.0022151489,0.0017021471,0.001216022,0.0007844308],"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":[0.00085830124,0.00009421996,0.008799764,0.4529126,0.008383416,0.00036491957,0.0022800213,0.00033941434,0.0014561885,0.0015690043,0.020253377,0.5026887],"study_design_scores_gemma":[0.0010726767,0.0016248913,0.07802547,0.6275529,0.03348374,0.0017410591,0.0014381146,0.0013695391,0.0026687304,0.0015507371,0.24919371,0.00027842802],"about_ca_topic_score_codex":0.0059322556,"about_ca_topic_score_gemma":0.02216631,"teacher_disagreement_score":0.08704618,"about_ca_system_score_codex":0.004986283,"about_ca_system_score_gemma":0.018505268,"threshold_uncertainty_score":0.46034974},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027116561,0.89485675,0.019747922,0.009049733,0.0024684349,0.028431578,0.0059797796,0.00022280488,0.012126424],"genre_scores_gemma":[0.18581937,0.6925329,0.070988536,0.003307896,0.00075035664,0.039183598,0.004319759,0.0001403035,0.0029572814],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8736516,0.059677143,0.0349006,0.0021297054,0.028920874,0.0007199855],"domain_scores_gemma":[0.6527928,0.19987358,0.043333724,0.0094875945,0.09287307,0.0016392116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.091094844,0.0008571212,0.0036753733,0.010886605,0.0010747776,0.0035959834,0.0021445304,0.0015164295,0.0024627564],"category_scores_gemma":[0.31282073,0.0009421123,0.0037444013,0.010348971,0.0012567125,0.0022165512,0.0017285222,0.001206946,0.00074558903],"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":[0.0009074914,0.000100064484,0.009863811,0.45264408,0.0088716885,0.0003736223,0.0024875335,0.00034900234,0.0014762455,0.0015419661,0.01902153,0.5023629],"study_design_scores_gemma":[0.0011690054,0.0017834693,0.08967152,0.62150794,0.035623435,0.0018387809,0.0016041652,0.0015012131,0.002732076,0.0015651924,0.24070427,0.00029888932],"about_ca_topic_score_codex":0.0057661426,"about_ca_topic_score_gemma":0.021849388,"teacher_disagreement_score":0.091094844,"about_ca_system_score_codex":0.0049362215,"about_ca_system_score_gemma":0.01789038,"threshold_uncertainty_score":0.48176134},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80386466,0.0006376554,0.1142182,0.0019086447,0.00080293167,0.035193797,0.0043114275,0.00047163444,0.03859106],"genre_scores_gemma":[0.7719494,0.00025606746,0.18296279,0.00040695496,0.00014401706,0.032352537,0.0026545073,0.000243194,0.009030529],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.8763513,0.06375508,0.017573401,0.0050939,0.03539349,0.0018328003],"domain_scores_gemma":[0.7372178,0.1190338,0.022003287,0.020133926,0.099406764,0.0022043902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11934887,0.00056327524,0.00083272427,0.0025261538,0.0010811749,0.0020230706,0.0012080594,0.00087416236,0.00457297],"category_scores_gemma":[0.25235727,0.00058724376,0.0018476687,0.0014999213,0.0011964297,0.0016808745,0.0022739018,0.0011205715,0.0020208422],"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":[0.0035462398,0.0022493256,0.47686172,0.0014260918,0.000620477,0.000205826,0.016193666,0.001508918,0.009395902,0.0060975216,0.02097176,0.4609225],"study_design_scores_gemma":[0.0009254673,0.0056198076,0.86746943,0.0014481728,0.00045150734,0.0005820973,0.005771828,0.02251771,0.026754264,0.0031487937,0.06506351,0.00024738733],"about_ca_topic_score_codex":0.0015398131,"about_ca_topic_score_gemma":0.003794899,"teacher_disagreement_score":0.11934887,"about_ca_system_score_codex":0.0014665185,"about_ca_system_score_gemma":0.002468314,"threshold_uncertainty_score":0.6311847},"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":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011659554,0.16782555,0.0667215,0.6850156,0.0094373245,0.00023605821,0.00021991141,0.00027086778,0.058613654],"genre_scores_gemma":[0.39149353,0.26939666,0.21107952,0.10107428,0.009934347,0.000994439,0.00045429327,0.0009930193,0.014579948],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8770228,0.091062374,0.0045630396,0.0043952325,0.019697282,0.003259263],"domain_scores_gemma":[0.6387846,0.24999152,0.0120822415,0.016775275,0.07189567,0.010470697],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2206747,0.0015127301,0.002026008,0.011588768,0.009222863,0.031404614,0.005110443,0.0063444325,0.0064558634],"category_scores_gemma":[0.27000168,0.0007254363,0.0015416669,0.012226771,0.025791885,0.061132416,0.010637129,0.0120174065,0.0018939099],"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":[0.00012935157,0.00011649555,0.007156039,0.0043166257,0.00018400107,0.00021464074,0.031443227,0.00082809996,0.0004275241,0.4027951,0.066085055,0.48630384],"study_design_scores_gemma":[0.000027356371,0.000092142596,0.0033856179,0.014780559,0.00013826387,0.00029141392,0.04171317,0.0016300309,0.0008908977,0.45701042,0.47988135,0.00015881417],"about_ca_topic_score_codex":0.022371314,"about_ca_topic_score_gemma":0.04176387,"teacher_disagreement_score":0.97939366,"about_ca_system_score_codex":0.020606311,"about_ca_system_score_gemma":0.038917724,"threshold_uncertainty_score":0.9610469},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96117693,0.0008051273,0.0071377996,0.0049908916,0.00003074573,0.00035869723,0.00002506901,0.000020335046,0.025454592],"genre_scores_gemma":[0.99453837,0.0005032589,0.0028186617,0.00020899433,0.000007749679,0.00013515596,0.000008359822,0.000017841956,0.0017617132],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96471435,0.0298572,0.00058304874,0.0009464126,0.0014056274,0.0024933107],"domain_scores_gemma":[0.9551356,0.037165746,0.0018888969,0.0024122675,0.0012754148,0.0021221617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022965545,0.0007678183,0.0006118413,0.0025762096,0.025286395,0.010302109,0.0031284331,0.004232146,0.003625096],"category_scores_gemma":[0.02751402,0.00070624606,0.0006107483,0.0035525227,0.03517067,0.008553085,0.019432338,0.0044969064,0.0004076613],"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":[0.00004942754,0.00013264825,0.0030285593,0.00019138765,0.000015963251,0.004648612,0.95716345,0.0005113059,0.0006344803,0.024817515,0.00032370904,0.008482997],"study_design_scores_gemma":[0.000026609949,0.00010984442,0.0025274858,0.00042745937,0.000021107453,0.0013067028,0.9593402,0.0006338725,0.00090913725,0.007915416,0.026753284,0.000028831737],"about_ca_topic_score_codex":0.0144592095,"about_ca_topic_score_gemma":0.04043379,"teacher_disagreement_score":0.025286395,"about_ca_system_score_codex":0.013024583,"about_ca_system_score_gemma":0.0104883,"threshold_uncertainty_score":0.121454895},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044210643,0.0082689235,0.77349913,0.029809166,0.00123897,0.0015177854,0.00011615261,0.0010239074,0.14031531],"genre_scores_gemma":[0.3891637,0.003768948,0.588969,0.0028885375,0.00062637706,0.0018307158,0.00018126266,0.0003509652,0.012220455],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84796923,0.08674335,0.00970688,0.0054425434,0.047715284,0.0024226608],"domain_scores_gemma":[0.8427993,0.060795613,0.009921012,0.020204656,0.05765293,0.008626507],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13517722,0.0016481244,0.002784785,0.01515527,0.0053220405,0.030134775,0.0051599387,0.0027364749,0.0027981182],"category_scores_gemma":[0.10380021,0.00094989873,0.0018849425,0.006912157,0.015825177,0.02150781,0.021449948,0.008046649,0.0012284665],"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":[0.00016296626,0.0006358104,0.020392215,0.0019775247,0.00025254674,0.00024581418,0.05621634,0.0023996548,0.0033935867,0.22727719,0.008776422,0.67827],"study_design_scores_gemma":[0.0001292951,0.0011011098,0.04191901,0.008847523,0.0004214087,0.0015510273,0.08897055,0.01331495,0.0054926085,0.6068327,0.23096463,0.00045526793],"about_ca_topic_score_codex":0.006051487,"about_ca_topic_score_gemma":0.007989733,"teacher_disagreement_score":0.86482275,"about_ca_system_score_codex":0.009003425,"about_ca_system_score_gemma":0.01927729,"threshold_uncertainty_score":0.71489406},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97578526,0.00016184061,0.003592809,0.0003707914,0.00018802866,0.01421241,0.0005468052,0.00012532769,0.00501691],"genre_scores_gemma":[0.96503043,0.00052266,0.011076209,0.0007282746,0.00029119191,0.015452535,0.0009898,0.00006740853,0.0058415495],"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.9939261,0.0036692517,0.0004950359,0.0005546923,0.0009001266,0.0004547828],"domain_scores_gemma":[0.9719876,0.016658595,0.0010926874,0.0029588358,0.004280325,0.0030219564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016323805,0.0015078124,0.0014817133,0.0005124767,0.0014443836,0.0010955277,0.0012423771,0.0018393348,0.00786554],"category_scores_gemma":[0.023981776,0.00062386115,0.0012012486,0.000386332,0.0014231849,0.0017886158,0.0012069202,0.0027984257,0.0027767138],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.18777306,0.6287174,0.020341143,0.001521319,0.0007044051,0.00053379795,0.0062190713,0.0011285689,0.022629151,0.00046014023,0.003004752,0.12696719],"study_design_scores_gemma":[0.036795843,0.89307564,0.043922607,0.00017774024,0.0008080227,0.00020037842,0.0019645374,0.0010901308,0.016611913,0.00045639617,0.0048138266,0.00008297304],"about_ca_topic_score_codex":0.0013405763,"about_ca_topic_score_gemma":0.001947654,"teacher_disagreement_score":0.016323805,"about_ca_system_score_codex":0.0005834244,"about_ca_system_score_gemma":0.0029075812,"threshold_uncertainty_score":0.08632958},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14183237,0.73688465,0.04289114,0.03271986,0.002001516,0.015872607,0.0034310205,0.00028913023,0.024077728],"genre_scores_gemma":[0.68809515,0.19516985,0.08886385,0.006842995,0.00032641462,0.018182272,0.0017067041,0.00015398838,0.0006587559],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.76873785,0.1359415,0.053022813,0.0077522304,0.03089972,0.0036458513],"domain_scores_gemma":[0.35333225,0.53636706,0.057923753,0.013292174,0.036094114,0.002990632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19662236,0.0018073863,0.0056375903,0.013209403,0.00199711,0.00963737,0.005414208,0.0048824716,0.007850464],"category_scores_gemma":[0.488215,0.0021363208,0.009923156,0.010657788,0.003406418,0.012762233,0.00654993,0.0052039963,0.00079674704],"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":[0.0014091039,0.0010333922,0.0900754,0.25014797,0.015354972,0.00020831572,0.007260238,0.0014671322,0.0002966294,0.007628194,0.005966169,0.6191526],"study_design_scores_gemma":[0.0014803967,0.0014809871,0.07187271,0.8363689,0.023655467,0.00038560823,0.009788974,0.0027034425,0.0019262881,0.0107493065,0.039330177,0.00025778043],"about_ca_topic_score_codex":0.009335181,"about_ca_topic_score_gemma":0.015824093,"teacher_disagreement_score":0.19662236,"about_ca_system_score_codex":0.0071119945,"about_ca_system_score_gemma":0.026793294,"threshold_uncertainty_score":0.99070764},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071100436,0.027636034,0.014090898,0.83658534,0.0023019898,0.001970486,0.00044827998,0.00021858445,0.04564795],"genre_scores_gemma":[0.85811615,0.021139095,0.028953886,0.08118818,0.0011130159,0.005316441,0.00030040514,0.00033429093,0.00353849],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5073846,0.4029395,0.031343535,0.011409524,0.028226806,0.018695973],"domain_scores_gemma":[0.26402563,0.6357125,0.02984057,0.02627459,0.022664156,0.02148253],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3857266,0.0010055217,0.001920057,0.0046923403,0.0114036435,0.028408566,0.006785608,0.009357627,0.011369392],"category_scores_gemma":[0.5319597,0.0023584845,0.001565218,0.0045791403,0.022705194,0.023527127,0.036753763,0.0155116925,0.0017654427],"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":[0.00060707674,0.0008546331,0.035302185,0.023023259,0.0006044623,0.003902814,0.25467703,0.0034427582,0.0015925794,0.17706229,0.07430633,0.42462453],"study_design_scores_gemma":[0.00058763346,0.0010778598,0.020548228,0.08584429,0.00033246345,0.0021832855,0.30960917,0.0021970593,0.0014312092,0.19176066,0.38403612,0.00039201835],"about_ca_topic_score_codex":0.0181679,"about_ca_topic_score_gemma":0.018058497,"teacher_disagreement_score":0.6142734,"about_ca_system_score_codex":0.017317096,"about_ca_system_score_gemma":0.10991541,"threshold_uncertainty_score":0.75750846},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13858509,0.35643244,0.002578812,0.35121194,0.0014277357,0.000374898,0.0013326472,0.000033644505,0.14802279],"genre_scores_gemma":[0.90741885,0.066400565,0.0016285871,0.018795496,0.00026892105,0.00019071305,0.0003220323,0.000027382928,0.004947527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.938461,0.028401375,0.0031585202,0.0028790268,0.022504788,0.0045952997],"domain_scores_gemma":[0.9086372,0.049812764,0.01040573,0.0040199617,0.023124462,0.0039999066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05701656,0.00025530296,0.0010118464,0.0034286182,0.0076702503,0.010422223,0.0026796218,0.0024274706,0.0031708241],"category_scores_gemma":[0.09591644,0.00064024195,0.00066862296,0.008888519,0.020790895,0.0046614707,0.0038556985,0.0022479144,0.00019363458],"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":[0.00050038914,0.000059473405,0.05906243,0.015555878,0.00075396325,0.0006285838,0.1292397,0.0012600236,0.00046136035,0.48298126,0.0852117,0.22428535],"study_design_scores_gemma":[0.0002731912,0.00009499651,0.1231436,0.023605254,0.00060614536,0.00013355937,0.0680364,0.0004082404,0.0004931796,0.037839804,0.7452027,0.0001629626],"about_ca_topic_score_codex":0.95726687,"about_ca_topic_score_gemma":0.9785454,"teacher_disagreement_score":0.19892414,"about_ca_system_score_codex":0.19892414,"about_ca_system_score_gemma":0.24321142,"threshold_uncertainty_score":0.9291344},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39573017,0.05907602,0.2586201,0.0811431,0.0026128613,0.0009094165,0.0019171392,0.00046399352,0.19952726],"genre_scores_gemma":[0.9656652,0.0037808593,0.026245726,0.0013274369,0.00043802828,0.0005029628,0.00020425979,0.000096095675,0.00173942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.6787048,0.23871873,0.014188994,0.016468463,0.04836473,0.0035543174],"domain_scores_gemma":[0.10393116,0.8314767,0.019639626,0.020925669,0.022928026,0.0010988849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22849442,0.0026503645,0.005331093,0.017775536,0.004665922,0.026429784,0.0065950365,0.008013707,0.0115183955],"category_scores_gemma":[0.60874915,0.0014925466,0.003363034,0.01969005,0.02584602,0.029041423,0.011190323,0.0077712657,0.0011888999],"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":[0.0016115245,0.0005928648,0.030926935,0.0052926727,0.0036234898,0.00051497837,0.029435623,0.009734413,0.0005376384,0.7898995,0.0064324127,0.12139795],"study_design_scores_gemma":[0.0006433145,0.0006430955,0.020042786,0.00500695,0.0021171193,0.0006562042,0.022524185,0.03955428,0.0022665055,0.8780264,0.02822292,0.00029631212],"about_ca_topic_score_codex":0.01435506,"about_ca_topic_score_gemma":0.006564924,"teacher_disagreement_score":0.98665076,"about_ca_system_score_codex":0.013349231,"about_ca_system_score_gemma":0.0106265005,"threshold_uncertainty_score":0.95140374},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077877333,0.00420519,0.002717204,0.26431292,0.619745,0.0017020943,0.0018071125,0.0022452492,0.10248639],"genre_scores_gemma":[0.003505209,0.0026508362,0.002305376,0.07313155,0.14544497,0.0014581706,0.0014107528,0.001808046,0.76828516],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9841493,0.0024716766,0.0013291425,0.0012746182,0.008775027,0.0020002937],"domain_scores_gemma":[0.884979,0.016820917,0.0059041763,0.0071461047,0.03774892,0.04740087],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019357149,0.0035626376,0.0038939423,0.0045519955,0.006296516,0.024311405,0.0046554985,0.03847205,0.5593603],"category_scores_gemma":[0.09319521,0.0019086557,0.0034464772,0.00375335,0.0020894075,0.012945174,0.010023274,0.01066483,0.51938903],"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":[0.000033158944,0.00003116471,0.000058123926,0.00006662434,0.00000402221,0.000027895292,0.000012836088,0.00001714745,0.000065591,0.00025110506,0.9906356,0.008796797],"study_design_scores_gemma":[0.000108439235,0.00007354811,0.0006063783,0.00015212469,0.000010969159,0.000049864946,0.00024770436,0.00009886621,0.00009672917,0.0015726674,0.9969459,0.00003685489],"about_ca_topic_score_codex":0.0012569783,"about_ca_topic_score_gemma":0.0043572346,"teacher_disagreement_score":0.5593603,"about_ca_system_score_codex":0.003741716,"about_ca_system_score_gemma":0.009173818,"threshold_uncertainty_score":0.628519},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6681759,0.0027124046,0.0625741,0.08289848,0.0019302517,0.0104895085,0.00070455234,0.00034340954,0.17017147],"genre_scores_gemma":[0.86831695,0.001916896,0.06953152,0.010776912,0.00028695108,0.0053277514,0.00034428807,0.0001457628,0.04335293],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9717246,0.020662775,0.0005592565,0.001312062,0.0022183647,0.003522973],"domain_scores_gemma":[0.9777671,0.008892207,0.0010561827,0.0011876193,0.0018926879,0.009204304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018901724,0.0007591434,0.00070923904,0.0021374605,0.028652502,0.0066306363,0.004662347,0.007895484,0.009869971],"category_scores_gemma":[0.018503038,0.00060087966,0.0013125682,0.002187066,0.0064912485,0.0053377445,0.011840762,0.009212477,0.001968094],"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":[0.00056416367,0.012681365,0.024702584,0.0016561826,0.00010428675,0.09488127,0.53150606,0.0023413498,0.0051667555,0.14686126,0.059697095,0.1198377],"study_design_scores_gemma":[0.0001431364,0.0015884644,0.006306835,0.0013794173,0.000047852463,0.014494415,0.67161405,0.002906616,0.002370061,0.01828874,0.28071946,0.00014090478],"about_ca_topic_score_codex":0.009247248,"about_ca_topic_score_gemma":0.029483398,"teacher_disagreement_score":0.028652502,"about_ca_system_score_codex":0.0087984,"about_ca_system_score_gemma":0.017727371,"threshold_uncertainty_score":0.09996307},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100328945,0.058174442,0.48554188,0.16498144,0.00094765174,0.0010355938,0.00025716337,0.00023673337,0.18849611],"genre_scores_gemma":[0.93435454,0.011036587,0.04579053,0.0049678185,0.00031401726,0.0006752606,0.00005566423,0.000033110053,0.0027724535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98144686,0.014136944,0.00060785335,0.0011719428,0.0019997265,0.0006367603],"domain_scores_gemma":[0.9732354,0.017840853,0.003999551,0.0011861272,0.0027400984,0.0009979471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026953932,0.0008233081,0.00071234925,0.0040486543,0.0018240997,0.0069691036,0.0024368474,0.0037228756,0.002302624],"category_scores_gemma":[0.018704994,0.00047043772,0.0010499621,0.002310792,0.022848263,0.008153445,0.0020720786,0.0036408582,0.00037847317],"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":[0.000046639092,0.00018863397,0.0031304753,0.0005938454,0.000044601482,0.00008556769,0.006093054,0.0038879593,0.000329336,0.95548034,0.0013408471,0.02877875],"study_design_scores_gemma":[0.00008791486,0.00031266353,0.00849102,0.0019480152,0.000083201594,0.0001913333,0.0060142656,0.014637333,0.00061000924,0.9204873,0.047022257,0.00011464696],"about_ca_topic_score_codex":0.006123164,"about_ca_topic_score_gemma":0.004388526,"teacher_disagreement_score":0.026953932,"about_ca_system_score_codex":0.0073490674,"about_ca_system_score_gemma":0.009226489,"threshold_uncertainty_score":0.14254773},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9081806,0.00037047238,0.032199405,0.008779076,0.00065392605,0.024471726,0.0010858602,0.0012488464,0.0230101],"genre_scores_gemma":[0.8094098,0.0003121399,0.15741469,0.002647497,0.00016186964,0.02608225,0.00081502507,0.00011164805,0.003045057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98131716,0.012895153,0.0009913909,0.0009515868,0.0026737947,0.0011709614],"domain_scores_gemma":[0.98065335,0.008544173,0.003196511,0.0016873626,0.0035808391,0.0023377542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02472681,0.00061200454,0.0006325844,0.0010928457,0.0012395509,0.002070679,0.0018587454,0.001276947,0.006257754],"category_scores_gemma":[0.044164915,0.0003596691,0.0015150728,0.0006835613,0.0017020273,0.00259165,0.004161904,0.0022412573,0.0014354883],"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":[0.0019594615,0.011584514,0.08535493,0.0040671076,0.00046093416,0.00014652831,0.022195166,0.0017439823,0.0064502684,0.0058211526,0.026982754,0.83323324],"study_design_scores_gemma":[0.0026285397,0.04872171,0.76809394,0.0067455126,0.001336244,0.0004088852,0.032835085,0.013856378,0.020283498,0.012349532,0.091991484,0.000749218],"about_ca_topic_score_codex":0.001554091,"about_ca_topic_score_gemma":0.0033544844,"teacher_disagreement_score":0.02472681,"about_ca_system_score_codex":0.00218614,"about_ca_system_score_gemma":0.00765625,"threshold_uncertainty_score":0.13076943},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19340622,0.009887287,0.28031394,0.32021126,0.0012823292,0.0009942141,0.00007643366,0.00023576019,0.19359261],"genre_scores_gemma":[0.970586,0.0021149737,0.021944854,0.0027538666,0.00007311332,0.00040682417,0.000012520912,0.000033543893,0.0020742195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.88666946,0.0911481,0.004015393,0.004694732,0.009210727,0.0042615505],"domain_scores_gemma":[0.78159267,0.17466505,0.013365129,0.007572501,0.016225804,0.0065788766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.088722974,0.0010188052,0.00091986393,0.002888555,0.007339584,0.020472199,0.004325777,0.0065192617,0.0036550036],"category_scores_gemma":[0.11001652,0.0007996625,0.0005143571,0.0023098092,0.038835283,0.016528076,0.01402841,0.009479613,0.00050076813],"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":[0.00009657274,0.00033552354,0.006673135,0.0015573279,0.000050547947,0.0006985087,0.2453993,0.004066923,0.0011418429,0.6671752,0.0032401371,0.06956504],"study_design_scores_gemma":[0.00006275887,0.0004825536,0.0028876585,0.0066572744,0.000056793215,0.00054128753,0.45236087,0.006897915,0.0017765434,0.39561576,0.1325191,0.0001415247],"about_ca_topic_score_codex":0.00671042,"about_ca_topic_score_gemma":0.0053008012,"teacher_disagreement_score":0.088722974,"about_ca_system_score_codex":0.013239382,"about_ca_system_score_gemma":0.03296165,"threshold_uncertainty_score":0.46921754},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005327095,0.014657001,0.07016293,0.7873466,0.0116721755,0.0014421677,0.00023120618,0.0010488246,0.10811205],"genre_scores_gemma":[0.37527978,0.022434134,0.2542831,0.29679322,0.011474742,0.0057993927,0.0006634284,0.0013128432,0.031959385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84596103,0.079402305,0.0068086693,0.011820268,0.042645734,0.013362038],"domain_scores_gemma":[0.8481083,0.07795968,0.0073121157,0.017921085,0.022708427,0.025990414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11768428,0.0031136333,0.003049577,0.0044690035,0.010984824,0.028327757,0.0051540458,0.017794877,0.019218272],"category_scores_gemma":[0.18451145,0.00096951314,0.0027438032,0.0026715992,0.030666623,0.02444472,0.022536935,0.022110393,0.010225835],"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":[0.0001324874,0.00069784775,0.0022475764,0.00280131,0.00039009945,0.00041084824,0.011617848,0.0023848861,0.00059918273,0.4914215,0.25117218,0.23612428],"study_design_scores_gemma":[0.00016518765,0.0003035726,0.0013899049,0.0030148549,0.00008184942,0.00018635283,0.008682521,0.00091000716,0.00055348064,0.632241,0.35237718,0.00009398968],"about_ca_topic_score_codex":0.0048409966,"about_ca_topic_score_gemma":0.0035003005,"teacher_disagreement_score":0.11768428,"about_ca_system_score_codex":0.01132297,"about_ca_system_score_gemma":0.05666361,"threshold_uncertainty_score":0.62238145},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015345893,0.00021542884,0.012115828,0.0013704366,0.00063673145,0.9806815,0.0017070087,0.00020714784,0.0015314335],"genre_scores_gemma":[0.0008667444,0.00007906763,0.010411745,0.00028222974,0.000023781782,0.98789036,0.00014228374,0.000018232004,0.00028557132],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.8392378,0.12234974,0.017252453,0.0062154694,0.011159522,0.0037849925],"domain_scores_gemma":[0.708836,0.14002283,0.015751174,0.037915897,0.091831766,0.00564232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21049014,0.004122801,0.004429757,0.008732336,0.0064182035,0.006392066,0.0051177824,0.005489977,0.056315232],"category_scores_gemma":[0.27603382,0.003989395,0.0045152786,0.009268298,0.0066344882,0.0080679655,0.007786591,0.010106111,0.016397733],"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":[0.014717005,0.0032304758,0.0021703918,0.10427403,0.0007018087,0.002191812,0.11358176,0.005033772,0.011133084,0.040642273,0.44261768,0.25970584],"study_design_scores_gemma":[0.01684329,0.0033834765,0.008577991,0.079265535,0.0004247076,0.0006559544,0.062365282,0.006260818,0.011808604,0.047347844,0.76217157,0.00089496287],"about_ca_topic_score_codex":0.003920765,"about_ca_topic_score_gemma":0.006575843,"teacher_disagreement_score":0.21049014,"about_ca_system_score_codex":0.011519704,"about_ca_system_score_gemma":0.07485295,"threshold_uncertainty_score":0.9736062},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085924484,0.010687255,0.2966585,0.22243515,0.0059362906,0.0013706423,0.0010739141,0.00059338537,0.37532046],"genre_scores_gemma":[0.86241907,0.003157124,0.08614288,0.02074986,0.00057498954,0.0010941728,0.00018761196,0.00022191045,0.025452288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9528508,0.027552664,0.002227094,0.0034569288,0.011208004,0.0027044746],"domain_scores_gemma":[0.95916516,0.02407013,0.002862055,0.0017184118,0.010588368,0.0015958254],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.037962265,0.00094077224,0.0006900119,0.0066497596,0.01980512,0.008117115,0.0041494383,0.0039529977,0.0028538515],"category_scores_gemma":[0.08839759,0.00059976446,0.00059493224,0.0057485485,0.056423225,0.0046947566,0.005313798,0.006239807,0.0005254521],"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":[0.00004743141,0.000026212809,0.006311543,0.00038659474,0.000016181417,0.00040563184,0.19757651,0.00043897462,0.00071904797,0.6916835,0.025092075,0.077296354],"study_design_scores_gemma":[0.000027574511,0.00011231613,0.02859301,0.0026916827,0.000041500454,0.0008017978,0.16172841,0.0037160416,0.0021813214,0.24910565,0.55065656,0.00034424468],"about_ca_topic_score_codex":0.84929407,"about_ca_topic_score_gemma":0.8817449,"teacher_disagreement_score":0.98019487,"about_ca_system_score_codex":0.089666836,"about_ca_system_score_gemma":0.07635704,"threshold_uncertainty_score":0.6505815},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001242017,0.005828183,0.00017139966,0.98659724,0.0070019783,0.000005339015,0.0000038448143,0.0000062239415,0.00026155476],"genre_scores_gemma":[0.01059177,0.01403421,0.0015954415,0.9500901,0.021880502,0.00007125473,0.000012506068,0.000044970326,0.0016792667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9453735,0.027943252,0.0044946168,0.004362385,0.014548746,0.0032775148],"domain_scores_gemma":[0.7054018,0.1927179,0.008980436,0.0049118265,0.05682437,0.031163685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066444434,0.00123319,0.0028432885,0.0025785337,0.015678741,0.02442592,0.006007427,0.066695146,0.0063252584],"category_scores_gemma":[0.1502864,0.0013812858,0.0019192913,0.0032149435,0.036953125,0.028690264,0.018408837,0.10845659,0.0021300025],"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":[0.000073642856,0.0002199335,0.0008450635,0.0010986067,0.00004458396,0.0003372407,0.009548858,0.00024689003,0.00027804665,0.028984461,0.92075366,0.037569035],"study_design_scores_gemma":[0.00006413454,0.00009554123,0.0019853122,0.00380085,0.00002819371,0.0007400615,0.024056302,0.00052016176,0.00022880864,0.050230835,0.91806495,0.00018489966],"about_ca_topic_score_codex":0.019737722,"about_ca_topic_score_gemma":0.034534197,"teacher_disagreement_score":0.066695146,"about_ca_system_score_codex":0.01700572,"about_ca_system_score_gemma":0.05079778,"threshold_uncertainty_score":0.35139596},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019110968,0.0013510189,0.35159996,0.12489165,0.0010772063,0.0018961427,0.00029104616,0.00082338793,0.49895862],"genre_scores_gemma":[0.67716956,0.001279537,0.19477488,0.011877783,0.0003073848,0.003287949,0.0003016456,0.0003720261,0.11062925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.890065,0.07128279,0.0019222274,0.0052266265,0.025907554,0.005595938],"domain_scores_gemma":[0.97073776,0.014600311,0.0012434141,0.0028634972,0.006846965,0.0037080552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036456563,0.0011667879,0.001126905,0.0026908221,0.0095786955,0.01281556,0.0051562465,0.0087960875,0.015077343],"category_scores_gemma":[0.028636826,0.0007412798,0.0018758819,0.0024689222,0.01603214,0.008724546,0.01634167,0.00789297,0.00202296],"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":[0.00009343906,0.0003115017,0.001406482,0.0006342774,0.00010729609,0.00024772834,0.013642177,0.00783414,0.0009797164,0.83669955,0.04485083,0.09319292],"study_design_scores_gemma":[0.0001739292,0.00038455846,0.0038596606,0.0009057163,0.00011635723,0.00024513953,0.017725812,0.024086438,0.0014716784,0.53912735,0.41160545,0.00029786088],"about_ca_topic_score_codex":0.09774603,"about_ca_topic_score_gemma":0.16361251,"teacher_disagreement_score":0.09774603,"about_ca_system_score_codex":0.028127648,"about_ca_system_score_gemma":0.061229542,"threshold_uncertainty_score":0.2040813},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032820674,0.03827723,0.12501101,0.3015523,0.006684921,0.00075054116,0.00019769158,0.0005005063,0.5237437],"genre_scores_gemma":[0.20247565,0.06287641,0.3127058,0.1084698,0.003508925,0.003130361,0.0005155137,0.0013725143,0.30494505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9803044,0.015541641,0.00044725748,0.00053587224,0.0025738874,0.0005969194],"domain_scores_gemma":[0.9850198,0.01153938,0.00029862372,0.000807644,0.0016503772,0.0006841305],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020542886,0.0009811962,0.00093489984,0.0020176212,0.0047489437,0.01776687,0.0021960374,0.00535723,0.011742502],"category_scores_gemma":[0.01969041,0.0005035587,0.00074903516,0.0016837824,0.021096852,0.018841282,0.008097797,0.008893982,0.0025638677],"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":[0.000013734076,0.00004828792,0.00013535297,0.00037827613,0.000011801512,0.00008601523,0.006688937,0.0005296837,0.0001320343,0.82575345,0.09599227,0.07023019],"study_design_scores_gemma":[0.00001526961,0.000033238477,0.00014988809,0.0016684389,0.000006690148,0.00011294148,0.0063165273,0.00054359384,0.0002011772,0.5016856,0.4892408,0.000025887879],"about_ca_topic_score_codex":0.0050948975,"about_ca_topic_score_gemma":0.011461868,"teacher_disagreement_score":0.97945714,"about_ca_system_score_codex":0.008953838,"about_ca_system_score_gemma":0.015230651,"threshold_uncertainty_score":0.10864246},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009172107,0.022723412,0.10494632,0.38728404,0.0031796035,0.0018598315,0.0001585052,0.000920101,0.4697562],"genre_scores_gemma":[0.39686573,0.034218777,0.34716552,0.067027256,0.0029103355,0.005413583,0.0005773282,0.0012130239,0.14460844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9365154,0.04663965,0.0018748095,0.0024138088,0.00919411,0.003362233],"domain_scores_gemma":[0.85319203,0.115592696,0.0026380287,0.00711236,0.013513799,0.007951128],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10930072,0.0008607317,0.0009998416,0.003954562,0.0071058148,0.02462921,0.005511963,0.006953699,0.015896274],"category_scores_gemma":[0.11476941,0.001081723,0.000891638,0.0032133057,0.019716257,0.033194564,0.024746861,0.010500396,0.0034660692],"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":[0.00003850566,0.00016015986,0.0007460144,0.0006308409,0.000027082504,0.00014670266,0.009252139,0.0014325354,0.00028520686,0.64840925,0.106347054,0.23252453],"study_design_scores_gemma":[0.00007626428,0.00008190926,0.0008328469,0.003025109,0.000017021213,0.00012848353,0.008139991,0.0027713578,0.0005880573,0.5211607,0.46309868,0.00007971282],"about_ca_topic_score_codex":0.01124402,"about_ca_topic_score_gemma":0.0228785,"teacher_disagreement_score":0.89069927,"about_ca_system_score_codex":0.016211456,"about_ca_system_score_gemma":0.078454636,"threshold_uncertainty_score":0.57804435},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004869974,0.07522344,0.027380968,0.8663159,0.0039449427,0.000548983,0.00020454335,0.00044242202,0.021068787],"genre_scores_gemma":[0.33471376,0.1882311,0.30350927,0.1333269,0.009172227,0.007172681,0.0014853283,0.00065215887,0.021736588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.90141743,0.07017099,0.006234834,0.003963748,0.009327685,0.008885312],"domain_scores_gemma":[0.5216223,0.2577044,0.012525426,0.020052778,0.06493943,0.12315559],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.23231673,0.0021579547,0.0048352988,0.012518503,0.016462421,0.07002818,0.009338771,0.036039546,0.03944216],"category_scores_gemma":[0.15796807,0.0023767755,0.0033767824,0.009613746,0.05066877,0.09659878,0.04756877,0.03401448,0.005600306],"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":[0.00066641346,0.0018347399,0.00588146,0.005219067,0.00014440791,0.0006329798,0.013252589,0.0011823117,0.00056085805,0.63265496,0.07925535,0.25871488],"study_design_scores_gemma":[0.00024141876,0.000470887,0.0015349002,0.008792127,0.00005841014,0.00031034366,0.024038518,0.0011974551,0.0003502004,0.77653074,0.18627657,0.00019840032],"about_ca_topic_score_codex":0.011122019,"about_ca_topic_score_gemma":0.01809192,"teacher_disagreement_score":0.23231673,"about_ca_system_score_codex":0.02634361,"about_ca_system_score_gemma":0.17067185,"threshold_uncertainty_score":0.94669014},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090690754,0.009224064,0.45327806,0.12389782,0.0025506655,0.008984641,0.00047656178,0.00264231,0.30825505],"genre_scores_gemma":[0.72740746,0.0035572108,0.2456345,0.008440185,0.00076215464,0.005973264,0.00022314943,0.00034259853,0.0076595526],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8162185,0.15385504,0.005596188,0.004663545,0.014549347,0.0051173745],"domain_scores_gemma":[0.54213166,0.339957,0.022282675,0.027541475,0.043162607,0.024924636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16111833,0.0008874789,0.0007974158,0.0045414185,0.0034790442,0.011481086,0.0029658335,0.002229674,0.017066399],"category_scores_gemma":[0.3020498,0.0008102024,0.0010284416,0.0026648194,0.0066130995,0.011814346,0.020466221,0.0050552953,0.0018811857],"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":[0.00037127538,0.0020864613,0.02306352,0.0032201135,0.00017424385,0.00022177507,0.012805221,0.0065918704,0.0018516005,0.12969981,0.0360775,0.78383654],"study_design_scores_gemma":[0.0008064186,0.004110488,0.06411243,0.026006106,0.00033250148,0.0013528909,0.019830514,0.030742308,0.015244799,0.31547964,0.5211865,0.00079553516],"about_ca_topic_score_codex":0.0040840125,"about_ca_topic_score_gemma":0.008554981,"teacher_disagreement_score":0.16111833,"about_ca_system_score_codex":0.010575153,"about_ca_system_score_gemma":0.04454731,"threshold_uncertainty_score":0.85208535},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017685561,0.006173986,0.010132508,0.024272779,0.0027328345,0.00008484641,0.000068919806,0.00022189485,0.95454377],"genre_scores_gemma":[0.15106489,0.007970596,0.009913934,0.013775403,0.0028262325,0.0002762489,0.00018996271,0.00053563947,0.8134472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912039,0.0037227985,0.00024374507,0.0010769428,0.0031235896,0.00062901806],"domain_scores_gemma":[0.99225086,0.0027713084,0.0003872353,0.0015351836,0.0021298442,0.00092555565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053823283,0.0010253941,0.0006734174,0.0016517288,0.00690877,0.013594792,0.0016279425,0.002805722,0.03585515],"category_scores_gemma":[0.019336006,0.00038536108,0.000616499,0.0010158495,0.016755328,0.009827861,0.009204503,0.0058941245,0.016729511],"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":[0.000014383611,0.000020787378,0.00018902133,0.00011227535,0.000009216544,0.00015119283,0.008067671,0.00017345573,0.00014635005,0.82160753,0.12646389,0.043044254],"study_design_scores_gemma":[0.0000041095554,0.000009597762,0.00008481574,0.00018949305,0.0000028233437,0.0001481637,0.0014491628,0.00010483469,0.00011494747,0.12182448,0.876058,0.00000969378],"about_ca_topic_score_codex":0.0022049649,"about_ca_topic_score_gemma":0.003026026,"teacher_disagreement_score":0.03585515,"about_ca_system_score_codex":0.00465585,"about_ca_system_score_gemma":0.0061646285,"threshold_uncertainty_score":0.11994743},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038982325,0.0021558348,0.007063259,0.018574184,0.0055641485,0.00018713978,0.0013893587,0.00066159695,0.9605062],"genre_scores_gemma":[0.054248802,0.002560179,0.007415453,0.013822113,0.0010221782,0.0002373635,0.0029628722,0.0007354817,0.9169955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972095,0.00041158017,0.00012446157,0.0006349112,0.001156457,0.00046317326],"domain_scores_gemma":[0.99774605,0.00027496202,0.00009721981,0.0002843566,0.001199164,0.000398282],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019888368,0.00070727355,0.00047875592,0.0012586052,0.003364738,0.0073810453,0.0019431887,0.003021672,0.25735173],"category_scores_gemma":[0.007318849,0.00027137782,0.00087330985,0.0011821886,0.0011901145,0.0043195724,0.0039708363,0.002710192,0.12572686],"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":[0.00014607151,0.00008900877,0.0019447553,0.0004899724,0.000022852937,0.0005052515,0.0022076701,0.0003106147,0.000642219,0.1767973,0.60701966,0.20982464],"study_design_scores_gemma":[0.000007636211,0.000013714084,0.0005931787,0.00020310895,0.000006060111,0.00016177358,0.0009860512,0.000085455365,0.00027286293,0.010807811,0.98685515,0.0000071782383],"about_ca_topic_score_codex":0.005671005,"about_ca_topic_score_gemma":0.006375975,"teacher_disagreement_score":0.74264824,"about_ca_system_score_codex":0.0038497914,"about_ca_system_score_gemma":0.0045697545,"threshold_uncertainty_score":0},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010077038,0.016352719,0.012899237,0.07483638,0.012226573,0.000072985844,0.00014349887,0.00036303606,0.8820979],"genre_scores_gemma":[0.04157472,0.01859068,0.00911453,0.045337718,0.0055579427,0.00021495309,0.00026276644,0.0008270001,0.8785197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972595,0.0010330324,0.000064115644,0.00042655648,0.00093738316,0.00027944567],"domain_scores_gemma":[0.99711156,0.0014275969,0.000114203656,0.00036999356,0.00067685696,0.00029983302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031212098,0.0008438179,0.00066438847,0.0009213617,0.004191644,0.0107716285,0.0012695139,0.0035737082,0.06987235],"category_scores_gemma":[0.011638328,0.000395444,0.0006737611,0.0008784249,0.0099950805,0.017423136,0.0046016476,0.0075228466,0.032858726],"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":[0.000018971854,0.00002301535,0.00009291698,0.0001138309,0.0000058755363,0.000062801315,0.0024604567,0.00014186846,0.00012202692,0.61070204,0.33355904,0.05269717],"study_design_scores_gemma":[0.0000025623297,0.0000055369233,0.000035579837,0.00025879935,0.000001856256,0.00004552953,0.00084151723,0.000070299626,0.0000497653,0.0702763,0.9284067,0.0000054589527],"about_ca_topic_score_codex":0.003209206,"about_ca_topic_score_gemma":0.0036961176,"teacher_disagreement_score":0.06987235,"about_ca_system_score_codex":0.0031354108,"about_ca_system_score_gemma":0.0056139613,"threshold_uncertainty_score":0.23374629},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012312667,0.047605682,0.09428118,0.11927966,0.0038872652,0.0003604139,0.000059294125,0.00041736953,0.72179645],"genre_scores_gemma":[0.4813579,0.040110454,0.10648345,0.04305341,0.0035849118,0.0013570738,0.00016550669,0.0005393049,0.32334793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98748696,0.008356629,0.00030105948,0.00048387918,0.0029284437,0.00044310206],"domain_scores_gemma":[0.9866708,0.010554756,0.0003836371,0.00074131426,0.00127686,0.00037256166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009388066,0.0005909326,0.0005212218,0.0014119941,0.0029170685,0.009735824,0.0010184142,0.0025880751,0.004317208],"category_scores_gemma":[0.016610632,0.000302732,0.0004063743,0.00088315946,0.019500976,0.009907527,0.0039893175,0.0065557845,0.0014387963],"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":[0.000011621851,0.00003288249,0.00016457986,0.0002323754,0.000008044642,0.00006265086,0.017653162,0.000276894,0.000266097,0.8706986,0.03499369,0.07559926],"study_design_scores_gemma":[0.000011922206,0.00004187693,0.00036706962,0.0009780717,0.0000065660897,0.00019898085,0.00583744,0.0005108446,0.000369413,0.608631,0.383023,0.000023760205],"about_ca_topic_score_codex":0.001036215,"about_ca_topic_score_gemma":0.0017636485,"teacher_disagreement_score":0.009735824,"about_ca_system_score_codex":0.0036576963,"about_ca_system_score_gemma":0.004974607,"threshold_uncertainty_score":0.049649417},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026544048,0.01716199,0.046960603,0.07541738,0.0025904342,0.00021112779,0.000072419614,0.0002540579,0.85467756],"genre_scores_gemma":[0.4518744,0.029744616,0.095671274,0.04161106,0.0028626812,0.0013300952,0.00031767885,0.0006904202,0.3758978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9814285,0.011408402,0.00056192774,0.0013270155,0.00441683,0.0008573213],"domain_scores_gemma":[0.98767763,0.008254861,0.0004898928,0.0013228881,0.001587118,0.00066759496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014434443,0.0010593907,0.0008249473,0.0020109613,0.0063592303,0.01719429,0.002125037,0.005542669,0.010983451],"category_scores_gemma":[0.017253527,0.00044793263,0.0006796508,0.0013468735,0.03797377,0.014829843,0.007623497,0.008329218,0.00409671],"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":[0.000006440234,0.000014293437,0.00006690685,0.00015905725,0.0000057989114,0.000046032797,0.0070548058,0.00027836996,0.00007043814,0.9323302,0.034585368,0.025382245],"study_design_scores_gemma":[0.0000086596665,0.000014064073,0.00010945807,0.00071852404,0.000003860254,0.00008560236,0.004631088,0.0003187689,0.00012173861,0.5079925,0.4859821,0.000013722067],"about_ca_topic_score_codex":0.0028296516,"about_ca_topic_score_gemma":0.003668835,"teacher_disagreement_score":0.01719429,"about_ca_system_score_codex":0.0075598345,"about_ca_system_score_gemma":0.012846907,"threshold_uncertainty_score":0.07633752},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00579071,0.022882944,0.042551666,0.056926537,0.0017474586,0.00017937286,0.000026356687,0.000116217314,0.86977875],"genre_scores_gemma":[0.49110433,0.048344858,0.079680406,0.0265795,0.0024847847,0.0009583834,0.0001574834,0.0003509004,0.35033938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98590773,0.009138373,0.00032612536,0.0004347094,0.0036892358,0.00050372357],"domain_scores_gemma":[0.9883774,0.0086921025,0.00043264305,0.00059007015,0.0013588716,0.0005489545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008491556,0.00057509466,0.00044298422,0.0015018114,0.0035751213,0.011527949,0.0010553297,0.002798733,0.003766122],"category_scores_gemma":[0.016119571,0.00033704052,0.00030046335,0.0011841903,0.03507603,0.009933191,0.0044231843,0.007032336,0.0014802297],"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":[0.0000037428933,0.000017660806,0.0000910899,0.00014438291,0.0000021320996,0.000054859454,0.0109142065,0.00025715603,0.0000802447,0.93735635,0.017942356,0.03313581],"study_design_scores_gemma":[0.000006338507,0.000021890832,0.00035407118,0.0009875185,0.0000022938978,0.00023143068,0.008411384,0.0006365367,0.00020513654,0.62368566,0.36543906,0.000018760686],"about_ca_topic_score_codex":0.0029080994,"about_ca_topic_score_gemma":0.0042667515,"teacher_disagreement_score":0.011527949,"about_ca_system_score_codex":0.00606162,"about_ca_system_score_gemma":0.011217042,"threshold_uncertainty_score":0.044908226},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004742254,0.051123623,0.032592177,0.2076867,0.011429682,0.0001618662,0.00009141631,0.00030027772,0.69187194],"genre_scores_gemma":[0.35305053,0.040891238,0.034653753,0.08912484,0.011533068,0.0007027723,0.00023600424,0.00088446494,0.46892327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9750461,0.012256028,0.0006831419,0.0019263473,0.009007042,0.0010814427],"domain_scores_gemma":[0.98018485,0.012609615,0.0006271632,0.0016781285,0.004187599,0.0007126929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014424527,0.0010305096,0.0009964951,0.0020702712,0.006431456,0.01968802,0.0018486952,0.004731377,0.009178634],"category_scores_gemma":[0.038006805,0.000471883,0.0007093482,0.0015663182,0.033869997,0.022127979,0.007490976,0.012960641,0.0033967076],"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":[0.000013250529,0.000017246846,0.000101709586,0.00014963277,0.0000067637143,0.000057225443,0.006892074,0.00016851333,0.00009771656,0.8899954,0.06557349,0.036927003],"study_design_scores_gemma":[0.00000828184,0.00001776626,0.00011657295,0.00066536234,0.0000061853266,0.000101195656,0.0035107222,0.00036212435,0.00020112652,0.4187248,0.57627016,0.000015775606],"about_ca_topic_score_codex":0.0032752266,"about_ca_topic_score_gemma":0.003786504,"teacher_disagreement_score":0.01968802,"about_ca_system_score_codex":0.009531715,"about_ca_system_score_gemma":0.010559847,"threshold_uncertainty_score":0.076285124},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0111664245,0.1030818,0.62581754,0.03436439,0.00481445,0.0005548251,0.0011312886,0.0006991675,0.21837007],"genre_scores_gemma":[0.15024039,0.07708461,0.6232335,0.012137781,0.0045547793,0.0027060744,0.0010891957,0.0010062474,0.12794751],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91762584,0.04940118,0.0033727475,0.0027802028,0.026397886,0.0004221972],"domain_scores_gemma":[0.7367773,0.24607088,0.0037208765,0.00628843,0.0068672635,0.0002752769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.068502285,0.0008886814,0.0011182517,0.0042564925,0.0005561037,0.006478695,0.002291171,0.002016504,0.0039599673],"category_scores_gemma":[0.15402809,0.0007041338,0.0005621655,0.004412924,0.006350733,0.006656358,0.0024649797,0.0035526643,0.0022710855],"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":[0.00004392299,0.00007619932,0.006159736,0.0014382612,0.00010903772,0.00008685074,0.0025941508,0.0016204491,0.00039906942,0.3817108,0.038200673,0.56756085],"study_design_scores_gemma":[0.000026096504,0.00012683035,0.00989435,0.003704526,0.00014311922,0.001118448,0.0019177432,0.009312538,0.004761314,0.728568,0.24028595,0.00014108849],"about_ca_topic_score_codex":0.0020484047,"about_ca_topic_score_gemma":0.0029039888,"teacher_disagreement_score":0.068502285,"about_ca_system_score_codex":0.0016504822,"about_ca_system_score_gemma":0.0015919632,"threshold_uncertainty_score":0.36227906},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3535649,0.002207767,0.3601355,0.050542925,0.00084630266,0.0025510846,0.00027756605,0.0025254665,0.22734857],"genre_scores_gemma":[0.8609928,0.00040066135,0.13419765,0.0010520032,0.000079717924,0.0003610801,0.00006135482,0.00012981334,0.0027249935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.82607555,0.1474064,0.00342275,0.0030244302,0.015788825,0.004282028],"domain_scores_gemma":[0.7188417,0.20152356,0.014797918,0.019248484,0.041445944,0.004142411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14069113,0.001178172,0.0013562138,0.006719004,0.005367383,0.020290073,0.0030696806,0.0028404493,0.0044684373],"category_scores_gemma":[0.24297689,0.00071151444,0.00064798,0.004772361,0.008218418,0.0149775855,0.006992811,0.004351512,0.0008317045],"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":[0.00095542794,0.0015791256,0.019157736,0.0008548428,0.00017788101,0.0007800453,0.044215363,0.022418099,0.0025775458,0.14529431,0.014340222,0.74764943],"study_design_scores_gemma":[0.0010120216,0.004224928,0.038586304,0.0072260424,0.0005283351,0.0008134583,0.081302226,0.16348952,0.018738408,0.56166595,0.12109965,0.0013132527],"about_ca_topic_score_codex":0.024487484,"about_ca_topic_score_gemma":0.04035099,"teacher_disagreement_score":0.14069113,"about_ca_system_score_codex":0.012080463,"about_ca_system_score_gemma":0.02457763,"threshold_uncertainty_score":0.7440547},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04969215,0.03920178,0.48286128,0.2706071,0.0021432387,0.0009412765,0.00007585939,0.00033481172,0.15414254],"genre_scores_gemma":[0.8469325,0.006884668,0.13222355,0.0062241224,0.0011899944,0.0011343852,0.000034691104,0.00020145635,0.0051744934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.68761146,0.27039167,0.007576373,0.006416239,0.023755984,0.004248297],"domain_scores_gemma":[0.4651393,0.48827457,0.008076977,0.016486904,0.018475529,0.003546755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26339328,0.0012817913,0.0026998252,0.0069809663,0.0130240815,0.04050844,0.0054114894,0.010978236,0.0029413018],"category_scores_gemma":[0.28967163,0.0013641092,0.0011316254,0.0049009966,0.105614625,0.054486815,0.024180992,0.015196319,0.0004612012],"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":[0.000034750163,0.000059657796,0.0012241699,0.0007365881,0.000035452013,0.00027695645,0.038719967,0.0017013242,0.00017807879,0.90094954,0.0019600273,0.05412351],"study_design_scores_gemma":[0.000035412737,0.00007754543,0.0005925562,0.002240956,0.000028007475,0.00028994816,0.023931904,0.0046139723,0.0005933383,0.912279,0.055239268,0.00007812099],"about_ca_topic_score_codex":0.005979077,"about_ca_topic_score_gemma":0.006340201,"teacher_disagreement_score":0.26339328,"about_ca_system_score_codex":0.017451476,"about_ca_system_score_gemma":0.021317255,"threshold_uncertainty_score":0.9083672},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48847792,0.038943104,0.0019902734,0.15124717,0.0009401883,0.00012730566,0.00013253861,0.00005963055,0.3180818],"genre_scores_gemma":[0.9845653,0.0029724631,0.00022996131,0.0021773921,0.000032365246,0.000031783227,0.000017019247,0.000011600619,0.009962089],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9916358,0.004969566,0.00014626632,0.00029828912,0.0015617624,0.001388336],"domain_scores_gemma":[0.9950541,0.0030148262,0.00026326368,0.00013858791,0.00073441066,0.0007948699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00573038,0.00026037404,0.0003350312,0.0014771959,0.020977682,0.008154871,0.0010217694,0.0018884597,0.0024657007],"category_scores_gemma":[0.007435608,0.00017683112,0.00017146245,0.0021759174,0.040223822,0.0041261935,0.0051520728,0.0029318626,0.00018882158],"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":[0.000034127803,0.000049227812,0.0025669923,0.00014169735,0.0000037101154,0.00012583788,0.81490564,0.000045747376,0.00011361394,0.14885266,0.0057765343,0.027384192],"study_design_scores_gemma":[0.000012970924,0.000036257363,0.007142495,0.00046334814,0.000008554792,0.00013641444,0.839801,0.0001119039,0.00020652785,0.008882326,0.14317708,0.000021085476],"about_ca_topic_score_codex":0.70949024,"about_ca_topic_score_gemma":0.75626636,"teacher_disagreement_score":0.70949024,"about_ca_system_score_codex":0.0600863,"about_ca_system_score_gemma":0.052051272,"threshold_uncertainty_score":0.58444124},"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":"other","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063156486,0.20834586,0.066284135,0.22042839,0.01675832,0.048383567,0.0027582713,0.00070430053,0.37318063],"genre_scores_gemma":[0.6219457,0.06317889,0.19190376,0.03388997,0.00567918,0.073157355,0.0008243134,0.00032687327,0.009093991],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3474927,0.58411676,0.020619964,0.0058009857,0.039449316,0.002520303],"domain_scores_gemma":[0.23178104,0.7319739,0.012148518,0.007093921,0.014720241,0.002282405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.42440683,0.0024536792,0.0073173074,0.0074794265,0.006941425,0.025654893,0.0098242555,0.0130054625,0.016647318],"category_scores_gemma":[0.6369193,0.0018004392,0.005255612,0.0131698,0.023481112,0.021185325,0.009571782,0.0089816125,0.00128324],"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":[0.0031868045,0.002216849,0.008169948,0.028783267,0.004098962,0.0004928652,0.013476078,0.008964011,0.0003329799,0.2554698,0.032208472,0.6426],"study_design_scores_gemma":[0.0046751243,0.016345153,0.025401395,0.12292255,0.004967189,0.0011173144,0.047983665,0.0134448,0.001999564,0.6263047,0.13427304,0.00056550966],"about_ca_topic_score_codex":0.011431023,"about_ca_topic_score_gemma":0.018039979,"teacher_disagreement_score":0.42440683,"about_ca_system_score_codex":0.018739805,"about_ca_system_score_gemma":0.029016493,"threshold_uncertainty_score":0.7098089},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046849687,0.36260676,0.017632298,0.38426894,0.0010680235,0.00033510503,0.00011838053,0.00024077647,0.18688007],"genre_scores_gemma":[0.824522,0.14418377,0.012949543,0.006331715,0.0007028301,0.0001911725,0.0000812023,0.000046971596,0.010990669],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9826413,0.012053691,0.0004928758,0.00049906556,0.0029126345,0.0014004231],"domain_scores_gemma":[0.9553182,0.023894481,0.0023672606,0.001811914,0.012093755,0.0045142947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03140705,0.00033184918,0.00050764624,0.0025840166,0.0032188473,0.0069238287,0.0012840562,0.0020021047,0.006133611],"category_scores_gemma":[0.031922482,0.00027407813,0.00024711623,0.0051583485,0.012178617,0.0035464126,0.004192289,0.0016582411,0.0003296514],"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":[0.00014488035,0.00016686221,0.016113976,0.0024623836,0.000039219616,0.0004149827,0.010193189,0.0027876038,0.00016872662,0.12921314,0.053339392,0.7849556],"study_design_scores_gemma":[0.00012355797,0.00021121383,0.058289163,0.012302851,0.000062808176,0.0007576347,0.03437266,0.0038526242,0.0007026174,0.13770382,0.75149554,0.00012551821],"about_ca_topic_score_codex":0.24120292,"about_ca_topic_score_gemma":0.21258889,"teacher_disagreement_score":0.24120292,"about_ca_system_score_codex":0.02987247,"about_ca_system_score_gemma":0.045430355,"threshold_uncertainty_score":0.47959793},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2417518,0.00591866,0.042754017,0.11377996,0.006632268,0.080164276,0.015076464,0.002159927,0.4917627],"genre_scores_gemma":[0.21572882,0.0038194174,0.06990246,0.010005113,0.0004667783,0.05772987,0.0067540733,0.0007586458,0.6348349],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9879716,0.0072976775,0.0002848256,0.0010412257,0.00154417,0.001860551],"domain_scores_gemma":[0.9872479,0.002933042,0.00035547305,0.00090714684,0.003020648,0.005535814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032231785,0.0009410519,0.00080461055,0.00095756305,0.009300957,0.0035226704,0.0033082,0.0023517534,0.046755806],"category_scores_gemma":[0.015154252,0.0008328632,0.00064009917,0.00094335625,0.0015796751,0.0017326319,0.00826363,0.004859617,0.0055903336],"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":[0.0009248239,0.004676067,0.005079415,0.002138741,0.00006115887,0.0016642687,0.17390132,0.0009363864,0.0075193103,0.009452794,0.4710684,0.32257733],"study_design_scores_gemma":[0.00022292299,0.0011702556,0.021942372,0.0009156191,0.00003540803,0.00018805682,0.06001011,0.0004093855,0.0030419277,0.0023493243,0.9095883,0.00012632283],"about_ca_topic_score_codex":0.060058314,"about_ca_topic_score_gemma":0.10361726,"teacher_disagreement_score":0.060058314,"about_ca_system_score_codex":0.006357739,"about_ca_system_score_gemma":0.041628372,"threshold_uncertainty_score":0.17046005},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1354509,0.0007198485,0.8391396,0.001868907,0.00017237739,0.0012356244,0.0004395833,0.0013128897,0.019660285],"genre_scores_gemma":[0.6239963,0.00037269027,0.36940816,0.00019107871,0.000033125874,0.0014079195,0.00046845217,0.0001349339,0.003987384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9801406,0.012980957,0.0009411013,0.0019793934,0.0035315051,0.00042639053],"domain_scores_gemma":[0.91046196,0.07429604,0.0023146537,0.0040103532,0.008247425,0.00066962134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026072005,0.0014913447,0.0011392148,0.001702896,0.0010298633,0.008518819,0.0017459698,0.0029720117,0.0063422774],"category_scores_gemma":[0.09343963,0.00082849356,0.001703642,0.001419852,0.0021744748,0.0069658435,0.002282056,0.0017294843,0.0009612088],"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":[0.0049938243,0.0024840662,0.023888197,0.0017512183,0.00079486484,0.00024792654,0.005438853,0.39555565,0.0155181745,0.1482562,0.006285099,0.39478588],"study_design_scores_gemma":[0.00041411413,0.0012274887,0.0049997666,0.0004109575,0.00025985352,0.00007864034,0.0007669336,0.9375548,0.009486017,0.038533036,0.006146013,0.00012234246],"about_ca_topic_score_codex":0.021183562,"about_ca_topic_score_gemma":0.012036978,"teacher_disagreement_score":0.026072005,"about_ca_system_score_codex":0.005528683,"about_ca_system_score_gemma":0.006775281,"threshold_uncertainty_score":0.1378836},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009154267,0.003022826,0.0030422262,0.5554095,0.054311384,0.007027621,0.07824736,0.0009061471,0.28887865],"genre_scores_gemma":[0.021277035,0.0014977627,0.0034451548,0.14491163,0.0023379547,0.0041257846,0.021148497,0.0002786346,0.8009776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942807,0.00065042975,0.00028571842,0.0004513504,0.0025041685,0.0018276485],"domain_scores_gemma":[0.9602086,0.002558453,0.00050785724,0.001909108,0.025224585,0.009591373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007480195,0.00077679055,0.0010938253,0.0015739661,0.009271552,0.0038391594,0.0028876897,0.007926744,0.10891357],"category_scores_gemma":[0.014879598,0.00052054354,0.00090915425,0.0025816176,0.001339831,0.0019850566,0.005118916,0.0052531646,0.03468291],"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":[0.000072701696,0.00001964563,0.0010262541,0.000059434413,0.000006163623,0.00005473214,0.00009766052,0.00002768943,0.00012626355,0.00090147863,0.9932115,0.004396283],"study_design_scores_gemma":[0.00003614685,0.000024949637,0.0048249355,0.000078759454,0.000013108636,0.000014814306,0.0014115328,0.00008289971,0.000119769116,0.00039385044,0.9929807,0.000018526096],"about_ca_topic_score_codex":0.7175755,"about_ca_topic_score_gemma":0.88960445,"teacher_disagreement_score":0.2824245,"about_ca_system_score_codex":0.011110078,"about_ca_system_score_gemma":0.1565665,"threshold_uncertainty_score":0.5681755},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8783245,0.003014838,0.016596517,0.0037376552,0.00030225373,0.03900608,0.0006452616,0.00061755977,0.05775532],"genre_scores_gemma":[0.9329434,0.0027918639,0.043052282,0.00062900595,0.00005791765,0.007948651,0.0005723522,0.00004947854,0.011954971],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97914666,0.011428043,0.00086246646,0.00057473837,0.0064720227,0.0015159497],"domain_scores_gemma":[0.9709098,0.011277699,0.0021618723,0.0011772832,0.011957595,0.0025158047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025405416,0.0006323469,0.00046818523,0.0019215334,0.002365048,0.0019562244,0.002114224,0.0006523942,0.0034697328],"category_scores_gemma":[0.032540455,0.0002926691,0.00079659256,0.0010583003,0.0010125798,0.0011264478,0.002769082,0.0010696423,0.00030827636],"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":[0.0056878254,0.0331321,0.016690144,0.007319594,0.00021242442,0.00061954866,0.0267576,0.008132355,0.008841965,0.007146746,0.007743473,0.87771624],"study_design_scores_gemma":[0.012131496,0.1815931,0.27630258,0.013675079,0.0033991968,0.0010071247,0.1279241,0.0316065,0.099260256,0.008078664,0.2444599,0.0005620556],"about_ca_topic_score_codex":0.059318595,"about_ca_topic_score_gemma":0.086693875,"teacher_disagreement_score":0.059318595,"about_ca_system_score_codex":0.011862904,"about_ca_system_score_gemma":0.04765555,"threshold_uncertainty_score":0.13435835},"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":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3840859,0.14257956,0.069996744,0.27133536,0.018521912,0.019463586,0.0012734511,0.0009219036,0.091821596],"genre_scores_gemma":[0.7990389,0.02717509,0.12601846,0.030592224,0.0044351583,0.006842745,0.00047525705,0.000397554,0.0050246646],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.21822225,0.62985957,0.05507907,0.0067391065,0.086272635,0.0038273837],"domain_scores_gemma":[0.04164113,0.7676253,0.059905913,0.015388317,0.1112943,0.0041450216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.55802417,0.0013485876,0.003053295,0.014862985,0.00433934,0.01910085,0.0046182396,0.0059677013,0.0015618659],"category_scores_gemma":[0.8889415,0.0011740325,0.002205154,0.010384756,0.0045017954,0.012256142,0.0060442756,0.004495771,0.00059956213],"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":[0.0023349077,0.0004331264,0.10994995,0.023570469,0.002954248,0.0027177853,0.042234257,0.0008454161,0.0018875147,0.011655316,0.052785046,0.748632],"study_design_scores_gemma":[0.0019695936,0.0060734786,0.20460743,0.13226509,0.009377517,0.00883111,0.09223693,0.01331311,0.011430618,0.03824931,0.480269,0.0013768494],"about_ca_topic_score_codex":0.004172427,"about_ca_topic_score_gemma":0.010630276,"teacher_disagreement_score":0.98905724,"about_ca_system_score_codex":0.01094274,"about_ca_system_score_gemma":0.030619888,"threshold_uncertainty_score":0.5450349},"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":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020292604,0.0058208634,0.014817588,0.020635527,0.0016150149,0.0014416258,0.03616563,0.003976856,0.91349745],"genre_scores_gemma":[0.057409376,0.017595345,0.10724073,0.010415355,0.0007497306,0.002545774,0.05123008,0.0020593395,0.7507543],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97907126,0.0023712567,0.0011827113,0.0016326631,0.014033216,0.0017089451],"domain_scores_gemma":[0.9415026,0.0021278432,0.00076814246,0.0021470613,0.050309926,0.003144444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012020169,0.0013929444,0.001173753,0.012561671,0.010896786,0.013564798,0.0047742864,0.0023596482,0.050434098],"category_scores_gemma":[0.029377736,0.00086281623,0.00093292526,0.019724673,0.0025553922,0.0041602147,0.0040404927,0.0029079337,0.019540396],"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":[0.00003126324,0.000020899028,0.0011458145,0.00026778883,0.000015168189,0.000052998148,0.00033191196,0.0005877849,0.00020596977,0.082579784,0.7947435,0.1200172],"study_design_scores_gemma":[0.0000075011226,0.000004883858,0.0023018904,0.00021035624,0.000009887291,0.000028270388,0.0001549198,0.00059626147,0.00012068412,0.003338153,0.99318093,0.000046327343],"about_ca_topic_score_codex":0.9795929,"about_ca_topic_score_gemma":0.9803673,"teacher_disagreement_score":0.9879798,"about_ca_system_score_codex":0.1392172,"about_ca_system_score_gemma":0.34389812,"threshold_uncertainty_score":0.998386},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98386025,0.0006360167,0.0020139723,0.00279814,0.00003704827,0.0003192072,0.0001591471,0.000020897467,0.010155414],"genre_scores_gemma":[0.9884328,0.00040253793,0.0012086877,0.00052886683,0.000011837997,0.0003940591,0.00009918859,0.000009057241,0.0089128865],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9862178,0.007447681,0.00044865516,0.0011541224,0.002516017,0.0022157575],"domain_scores_gemma":[0.9704014,0.012554417,0.002863619,0.0013117794,0.009915098,0.0029536495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02055322,0.0005007777,0.00048354128,0.002458821,0.016114203,0.006598821,0.0012698228,0.0010375279,0.005476129],"category_scores_gemma":[0.01948506,0.00043493908,0.00034189507,0.0026925835,0.0070873797,0.0019417708,0.0035920406,0.0013483019,0.00029800503],"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":[0.00024622405,0.0002137944,0.19140303,0.000363659,0.000048928014,0.0005340458,0.7247704,0.000279899,0.0032231128,0.005242581,0.0051673306,0.06850707],"study_design_scores_gemma":[0.000022544895,0.00014490433,0.29353788,0.00040734923,0.000025253034,0.00012364656,0.6684759,0.00030753727,0.0009846956,0.0005823145,0.03531107,0.00007690375],"about_ca_topic_score_codex":0.8450715,"about_ca_topic_score_gemma":0.91739696,"teacher_disagreement_score":0.1549285,"about_ca_system_score_codex":0.05167784,"about_ca_system_score_gemma":0.054803323,"threshold_uncertainty_score":0.3749507},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006032085,0.12364407,0.11576277,0.013282787,0.006134593,0.00049691834,0.003798039,0.005097663,0.7311801],"genre_scores_gemma":[0.011129268,0.1340949,0.16580991,0.0064713517,0.003218862,0.0012498297,0.0048284153,0.0042527514,0.6689446],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960951,0.0010481466,0.00036156023,0.00017051847,0.002220941,0.00010370736],"domain_scores_gemma":[0.98604184,0.008931818,0.00042603415,0.00072434614,0.0034381675,0.0004377894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004311518,0.0015567316,0.0020195069,0.0052529057,0.00087892724,0.006399635,0.0016981628,0.0016428954,0.043776795],"category_scores_gemma":[0.0121962,0.0010531227,0.00059019856,0.007200313,0.0018810226,0.004877614,0.0014722393,0.004047714,0.040574044],"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":[0.000010873131,0.00004205514,0.00012269615,0.00056408555,0.000013213311,0.000033134103,0.0003205585,0.00065906154,0.00014875244,0.04151431,0.6273326,0.32923868],"study_design_scores_gemma":[0.0000064309656,0.000016314058,0.00041190343,0.0011339947,0.000010864791,0.00015110825,0.00021752826,0.00043585117,0.00016302636,0.060890265,0.9365363,0.000026562177],"about_ca_topic_score_codex":0.0049527492,"about_ca_topic_score_gemma":0.010585735,"teacher_disagreement_score":0.043776795,"about_ca_system_score_codex":0.0025162438,"about_ca_system_score_gemma":0.0069931885,"threshold_uncertainty_score":0.1464479},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97044575,0.0002476133,0.0015455323,0.0020978884,0.000040606097,0.00025608635,0.000070394206,0.00002731848,0.025268877],"genre_scores_gemma":[0.9860341,0.00020602968,0.0040239315,0.0002458592,0.0000098786695,0.00007753343,0.00004633787,0.000018809616,0.009337531],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9922792,0.0030506845,0.000159728,0.00058181316,0.0010995669,0.0028290793],"domain_scores_gemma":[0.9866877,0.004912672,0.0007867433,0.00053040165,0.0019838363,0.005098566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005590254,0.00077811454,0.0005569564,0.0022737246,0.055155147,0.006411994,0.0041142744,0.005993994,0.0042829686],"category_scores_gemma":[0.010693464,0.000581867,0.00059578085,0.0031187066,0.008780308,0.0030303635,0.0054710307,0.0037412043,0.0004182349],"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":[0.00039005876,0.0019946112,0.038579106,0.00030219118,0.00006137369,0.029091168,0.8509932,0.0019622797,0.0015430265,0.016154421,0.0067704143,0.052158054],"study_design_scores_gemma":[0.000030987292,0.00023726055,0.017429583,0.00020726425,0.00002726102,0.0019478503,0.9322181,0.001143651,0.00067077775,0.0018361607,0.04417994,0.000071199],"about_ca_topic_score_codex":0.70788723,"about_ca_topic_score_gemma":0.92637485,"teacher_disagreement_score":0.29211277,"about_ca_system_score_codex":0.033458523,"about_ca_system_score_gemma":0.047215067,"threshold_uncertainty_score":0.58766615},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9612666,0.0010752283,0.0002924923,0.004601028,0.000047700727,0.00013315376,0.00007786168,0.000009441372,0.032496523],"genre_scores_gemma":[0.98228365,0.00129117,0.00039666216,0.00074687286,0.000008313598,0.00007516231,0.000040524137,0.000010949926,0.01514663],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9974947,0.0009918382,0.00006424426,0.00013528444,0.000508272,0.0008057802],"domain_scores_gemma":[0.99691486,0.0009893174,0.00020319686,0.000086098815,0.00086644554,0.00093996583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023843911,0.00020746885,0.00030671377,0.00087470183,0.01757051,0.0047881748,0.0009695094,0.0006423377,0.0041595707],"category_scores_gemma":[0.0036099022,0.00020881477,0.000108715336,0.0020254934,0.004861658,0.00070296484,0.001849754,0.0015817914,0.00035940687],"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":[0.000034905555,0.000059283837,0.013692639,0.00017705704,0.000004472566,0.00095099065,0.96002156,0.000067457484,0.0006562717,0.0026784681,0.003677484,0.017979313],"study_design_scores_gemma":[0.0000022340892,0.000020709243,0.012996886,0.00012403289,0.000003174088,0.000092788585,0.9668356,0.00004516052,0.00009437508,0.00012887862,0.019647798,0.0000082568695],"about_ca_topic_score_codex":0.91882885,"about_ca_topic_score_gemma":0.9671153,"teacher_disagreement_score":0.9659916,"about_ca_system_score_codex":0.03400837,"about_ca_system_score_gemma":0.06630799,"threshold_uncertainty_score":0.24674916},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067616533,0.068512,0.7685721,0.030468592,0.0015430761,0.006068215,0.0006211091,0.0006506393,0.116802566],"genre_scores_gemma":[0.2472753,0.03946062,0.68500674,0.002358432,0.0009974656,0.020595869,0.0002922767,0.00022603375,0.00378726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.5273342,0.43467203,0.013040292,0.0057369214,0.017194908,0.002021676],"domain_scores_gemma":[0.41538578,0.5247752,0.014996273,0.016264623,0.025841752,0.002736395],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.29106683,0.0031505048,0.00500558,0.020436523,0.0040889843,0.018633727,0.0052445577,0.007209372,0.0116642695],"category_scores_gemma":[0.3976702,0.0016038496,0.002085489,0.02819227,0.017479395,0.0149545865,0.012599071,0.0045824824,0.0016115224],"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":[0.00016414844,0.0002930739,0.0042148344,0.009704257,0.0005441407,0.00014781089,0.0052566165,0.01356348,0.00009435651,0.6561197,0.011162051,0.29873547],"study_design_scores_gemma":[0.0002132157,0.00029503647,0.0019455935,0.014172561,0.00023307189,0.00012803458,0.005903215,0.022142341,0.00033869094,0.8941503,0.0603671,0.00011090976],"about_ca_topic_score_codex":0.009681512,"about_ca_topic_score_gemma":0.0072068567,"teacher_disagreement_score":0.29106683,"about_ca_system_score_codex":0.023034694,"about_ca_system_score_gemma":0.028370434,"threshold_uncertainty_score":0.8742408},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05751114,0.02338626,0.83886594,0.053523283,0.0073147644,0.007097965,0.00017238938,0.0007306408,0.0113977045],"genre_scores_gemma":[0.19094016,0.0029385895,0.7949368,0.0049785823,0.0008565099,0.004264272,0.000058971327,0.0002617552,0.00076443714],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3971647,0.44687647,0.055055384,0.008878498,0.0903029,0.0017219947],"domain_scores_gemma":[0.084217116,0.7866567,0.015076236,0.018486092,0.09408608,0.0014776906],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.6180485,0.0019288181,0.0030024326,0.015684526,0.010202132,0.010973154,0.008854651,0.004516674,0.0010744653],"category_scores_gemma":[0.80215484,0.0020448568,0.0019992106,0.006029646,0.016778717,0.013719087,0.007916922,0.013140742,0.00050515553],"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":[0.001376658,0.0005841764,0.022000019,0.00847117,0.0006173187,0.0009782643,0.12694669,0.0021705884,0.0066504963,0.17527889,0.031401236,0.6235246],"study_design_scores_gemma":[0.0011608015,0.0026543038,0.024243012,0.04498732,0.0013775193,0.004981509,0.096263714,0.0614957,0.038696025,0.4370129,0.28425774,0.0028695294],"about_ca_topic_score_codex":0.0037896135,"about_ca_topic_score_gemma":0.0057904604,"teacher_disagreement_score":0.6180485,"about_ca_system_score_codex":0.012798516,"about_ca_system_score_gemma":0.020552821,"threshold_uncertainty_score":0.47101426},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08567787,0.014626714,0.82484615,0.01721727,0.0014743584,0.014214705,0.001104096,0.0013530395,0.039485708],"genre_scores_gemma":[0.43579164,0.0029427465,0.5362124,0.0026250812,0.00033120398,0.020033456,0.00030914354,0.0004788645,0.0012754616],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.2761631,0.655105,0.028513074,0.01290986,0.025258508,0.0020503984],"domain_scores_gemma":[0.17960183,0.7029696,0.04109273,0.051694747,0.02316491,0.0014761173],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4983808,0.002817674,0.0031631766,0.0143242795,0.0048052403,0.026934104,0.0044383095,0.003519876,0.0036351006],"category_scores_gemma":[0.6584572,0.0025297645,0.0038130244,0.018692387,0.024407405,0.026030941,0.011390363,0.00614409,0.0007788022],"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":[0.0008013576,0.00049916474,0.02780106,0.020888278,0.00174648,0.0001822951,0.19730657,0.0052277553,0.001622097,0.13879216,0.005417585,0.5997152],"study_design_scores_gemma":[0.0014063397,0.0045532417,0.05641017,0.056885824,0.0030574554,0.00076256256,0.10111932,0.041975327,0.011159645,0.5447189,0.17654791,0.0014032776],"about_ca_topic_score_codex":0.007542139,"about_ca_topic_score_gemma":0.007478882,"teacher_disagreement_score":0.5016192,"about_ca_system_score_codex":0.018356297,"about_ca_system_score_gemma":0.021966089,"threshold_uncertainty_score":0.61858577},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97542405,0.00014724808,0.00060854095,0.001140627,0.00006666953,0.00020121764,0.00004192582,0.00003250875,0.022337195],"genre_scores_gemma":[0.988808,0.00021831844,0.0014886541,0.00018305439,0.00001993529,0.0002222239,0.0001089867,0.000018301173,0.008932482],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9938922,0.003281574,0.00021068282,0.00021092448,0.0018329028,0.00057171576],"domain_scores_gemma":[0.98595506,0.003064175,0.0012035479,0.00040747647,0.0045087514,0.0048610396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011019483,0.00018260516,0.00021810496,0.000991604,0.0018744691,0.0026792358,0.0004684348,0.00029786388,0.0032163786],"category_scores_gemma":[0.01639178,0.00013203468,0.00024164462,0.0006483662,0.00090765045,0.0010142023,0.0022329967,0.0012421701,0.00046336398],"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":[0.00039061636,0.005493957,0.37100726,0.00032539337,0.00006526519,0.00033718112,0.110072486,0.0003334652,0.0011729292,0.003697472,0.031014092,0.47608995],"study_design_scores_gemma":[0.000052351537,0.002789849,0.7345796,0.00045215554,0.000061007304,0.00019930347,0.18394923,0.0014627511,0.0032129188,0.0011799306,0.071945,0.000115917566],"about_ca_topic_score_codex":0.004334662,"about_ca_topic_score_gemma":0.010841871,"teacher_disagreement_score":0.011019483,"about_ca_system_score_codex":0.0017844865,"about_ca_system_score_gemma":0.004268477,"threshold_uncertainty_score":0.05827731},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025931667,0.02602523,0.8262347,0.07271523,0.013213117,0.00070287293,0.0019831616,0.002498609,0.054033868],"genre_scores_gemma":[0.03547048,0.020992383,0.82627577,0.011794921,0.009066334,0.001653923,0.002224176,0.0014815648,0.09104039],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97012275,0.015123909,0.0027691743,0.0017286926,0.009810443,0.00044503197],"domain_scores_gemma":[0.91181463,0.049399417,0.0019112615,0.011951367,0.023992673,0.000930769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028858796,0.0022464658,0.0013398667,0.0037068797,0.0026185839,0.009737322,0.0023306268,0.0047944505,0.03337479],"category_scores_gemma":[0.09722851,0.0009057796,0.0017737547,0.0040088366,0.005960885,0.011163104,0.003820948,0.010911448,0.018666292],"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":[0.00019605093,0.0001904062,0.00066140725,0.0023861695,0.000096182805,0.00031204865,0.0022958084,0.0032128568,0.0052616973,0.3301454,0.25197652,0.4032655],"study_design_scores_gemma":[0.000065496904,0.0001765146,0.0012588028,0.0017810995,0.000055415643,0.00068750134,0.0007443227,0.0045960643,0.0041986955,0.17251009,0.81380963,0.00011634226],"about_ca_topic_score_codex":0.00902007,"about_ca_topic_score_gemma":0.01160872,"teacher_disagreement_score":0.03337479,"about_ca_system_score_codex":0.0030436171,"about_ca_system_score_gemma":0.004883503,"threshold_uncertainty_score":0.15262175},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002366718,0.000018901712,0.000476234,0.00017674465,0.000027730483,0.00035702277,0.9950132,0.00019005836,0.0035034297],"genre_scores_gemma":[0.0142183425,0.00024223852,0.00939194,0.00090517575,0.00009929415,0.0139371,0.93625104,0.0010683744,0.02388648],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964665,0.0013001447,0.00066571124,0.00042090536,0.0007472913,0.0003994431],"domain_scores_gemma":[0.8884909,0.089057624,0.0036611205,0.0047500283,0.01262729,0.0014130643],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006879241,0.0009991371,0.0013319808,0.004774876,0.0013936211,0.0021754166,0.002131791,0.0016522125,0.9085105],"category_scores_gemma":[0.099911585,0.0007248655,0.0011734398,0.008135329,0.00040420974,0.0035246373,0.0019749242,0.0014925246,0.16767593],"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":[0.00017990645,0.00006666767,0.0012266969,0.0024511896,0.00002740478,0.000025448893,0.00015447912,0.00023634458,0.0000198489,0.001698466,0.986299,0.0076146284],"study_design_scores_gemma":[0.0031217933,0.00020367747,0.018002652,0.0065647177,0.00021558777,0.00015821987,0.0019396145,0.0011822996,0.00036338708,0.017822953,0.95029634,0.00012866901],"about_ca_topic_score_codex":0.012773695,"about_ca_topic_score_gemma":0.024637464,"teacher_disagreement_score":0.9085105,"about_ca_system_score_codex":0.0021421523,"about_ca_system_score_gemma":0.004867059,"threshold_uncertainty_score":0.13049865},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066347937,0.0026345332,0.6553737,0.032418247,0.0008168536,0.028669281,0.0042663137,0.002033413,0.2671528],"genre_scores_gemma":[0.098703936,0.0011701987,0.8495539,0.0051945355,0.0001648075,0.024992889,0.0024362253,0.0001875404,0.017595971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.85155976,0.1005214,0.012913208,0.0054308414,0.02442581,0.0051490082],"domain_scores_gemma":[0.8982836,0.044681687,0.0042859595,0.0039902204,0.04618961,0.0025689392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1482272,0.0018621394,0.0015431402,0.01045782,0.005848344,0.018442687,0.0055748,0.005515451,0.009456555],"category_scores_gemma":[0.07787035,0.0010805334,0.003923256,0.006559509,0.0073207025,0.008017908,0.0043040793,0.005815853,0.0020087336],"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":[0.0000773583,0.00018762688,0.00076798216,0.00069564104,0.000051352283,0.00009641694,0.0015853159,0.008337016,0.0002310323,0.9158466,0.028828422,0.043295234],"study_design_scores_gemma":[0.00051287335,0.00088772713,0.0030043195,0.0048158653,0.00024179011,0.00021229817,0.0043056235,0.048287023,0.001997327,0.35241625,0.58301723,0.0003017636],"about_ca_topic_score_codex":0.141726,"about_ca_topic_score_gemma":0.095929235,"teacher_disagreement_score":0.1482272,"about_ca_system_score_codex":0.06837016,"about_ca_system_score_gemma":0.1163001,"threshold_uncertainty_score":0.78390974},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002486432,0.00020621483,0.00035585393,0.00032205982,0.000047063404,0.0020402246,0.9945781,0.00019649252,0.0020053126],"genre_scores_gemma":[0.013363786,0.0024397532,0.016597772,0.0017821932,0.0002740842,0.11380343,0.8274934,0.00088982657,0.023355652],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9935435,0.0014194772,0.0029495943,0.00053164293,0.0011556182,0.00040013515],"domain_scores_gemma":[0.8482521,0.114957,0.014690219,0.0031091066,0.017568724,0.0014228406],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011981532,0.0016946751,0.0028117585,0.014259275,0.0011702529,0.00365113,0.0024210243,0.0021117376,0.80244917],"category_scores_gemma":[0.12334469,0.0010600651,0.003082294,0.017325267,0.0005110896,0.0045030033,0.002593106,0.0012128546,0.06337032],"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":[0.0012117256,0.00011703777,0.0025514166,0.20879266,0.0004638552,0.00014362842,0.00038529426,0.0006568587,0.0001643962,0.0033103323,0.751876,0.030326825],"study_design_scores_gemma":[0.009961759,0.00046661202,0.024037713,0.15030587,0.002191377,0.0004883509,0.001323089,0.0014688054,0.0009322051,0.012810886,0.7957337,0.00027966395],"about_ca_topic_score_codex":0.0072794403,"about_ca_topic_score_gemma":0.013964598,"teacher_disagreement_score":0.80244917,"about_ca_system_score_codex":0.0044003446,"about_ca_system_score_gemma":0.009184434,"threshold_uncertainty_score":0.28178233},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002366718,0.000018901712,0.000476234,0.00017674465,0.000027730483,0.00035702277,0.9950132,0.00019005836,0.0035034297],"genre_scores_gemma":[0.0142183425,0.00024223852,0.00939194,0.00090517575,0.00009929415,0.0139371,0.93625104,0.0010683744,0.02388648],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964665,0.0013001447,0.00066571124,0.00042090536,0.0007472913,0.0003994431],"domain_scores_gemma":[0.8884909,0.089057624,0.0036611205,0.0047500283,0.01262729,0.0014130643],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006879241,0.0009991371,0.0013319808,0.004774876,0.0013936211,0.0021754166,0.002131791,0.0016522125,0.9085105],"category_scores_gemma":[0.099911585,0.0007248655,0.0011734398,0.008135329,0.00040420974,0.0035246373,0.0019749242,0.0014925246,0.16767593],"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":[0.00017990645,0.00006666767,0.0012266969,0.0024511896,0.00002740478,0.000025448893,0.00015447912,0.00023634458,0.0000198489,0.001698466,0.986299,0.0076146284],"study_design_scores_gemma":[0.0031217933,0.00020367747,0.018002652,0.0065647177,0.00021558777,0.00015821987,0.0019396145,0.0011822996,0.00036338708,0.017822953,0.95029634,0.00012866901],"about_ca_topic_score_codex":0.012773695,"about_ca_topic_score_gemma":0.024637464,"teacher_disagreement_score":0.9085105,"about_ca_system_score_codex":0.0021421523,"about_ca_system_score_gemma":0.004867059,"threshold_uncertainty_score":0.13049865},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020997647,0.000020810361,0.0011762627,0.000310384,0.000055009063,0.00091967336,0.9926641,0.00040093364,0.0042428467],"genre_scores_gemma":[0.017923562,0.00030122863,0.024048176,0.0015781784,0.00020939524,0.046102807,0.8681879,0.0027165667,0.03893222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937563,0.0025819312,0.0011267869,0.0006611764,0.001376894,0.00049686385],"domain_scores_gemma":[0.80052924,0.16491987,0.006125251,0.00831654,0.017907538,0.0022016093],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014766262,0.0013931115,0.0014802748,0.004842688,0.0017098075,0.003058369,0.0027884885,0.0018841928,0.92962545],"category_scores_gemma":[0.1574928,0.0010444223,0.0015390547,0.007583393,0.00065718,0.004141922,0.0022740825,0.0019063588,0.19242126],"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":[0.0002982237,0.00006985377,0.00074802176,0.0029699819,0.000034529836,0.000026088659,0.00012905411,0.00034621567,0.000021829803,0.0020375014,0.9845121,0.008806548],"study_design_scores_gemma":[0.0067147245,0.00028439378,0.011250432,0.009194388,0.00029570243,0.00017468003,0.001341157,0.0019470545,0.0005182691,0.027036339,0.941071,0.00017193251],"about_ca_topic_score_codex":0.010095479,"about_ca_topic_score_gemma":0.01805233,"teacher_disagreement_score":0.92962545,"about_ca_system_score_codex":0.0025232262,"about_ca_system_score_gemma":0.0071422313,"threshold_uncertainty_score":0.10038078},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98437405,0.00044423252,0.00039026418,0.005448145,0.000034534347,0.00014546174,0.00025525413,0.0000178274,0.008890342],"genre_scores_gemma":[0.99645907,0.00040414048,0.0005383139,0.000736017,0.000013133346,0.000050069466,0.0001229109,0.0000055307237,0.0016709196],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961067,0.0006825438,0.00008688361,0.0003188307,0.0011887588,0.0016162476],"domain_scores_gemma":[0.9930126,0.00091530295,0.0015318764,0.00035592035,0.001956266,0.0022279234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035093718,0.00024072503,0.00033365266,0.0012401768,0.008249851,0.0026249303,0.0020722295,0.00070242403,0.0031173592],"category_scores_gemma":[0.016278416,0.00026169533,0.00038899857,0.0013223687,0.00388589,0.001428817,0.0035513802,0.00164929,0.00020784386],"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":[0.0003475373,0.00061395165,0.7051647,0.00049576187,0.00015249678,0.0009842623,0.08726875,0.0009251308,0.0028127609,0.008988011,0.014347074,0.17789966],"study_design_scores_gemma":[0.000030644318,0.00017873009,0.92824656,0.00029409328,0.000062936124,0.00016678138,0.05526055,0.00067350664,0.0005533699,0.0011315809,0.013335864,0.00006525488],"about_ca_topic_score_codex":0.95774,"about_ca_topic_score_gemma":0.9913953,"teacher_disagreement_score":0.047558434,"about_ca_system_score_codex":0.047558434,"about_ca_system_score_gemma":0.07679924,"threshold_uncertainty_score":0.3450622},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001937513,0.000022429924,0.0005972931,0.0002041523,0.000049231163,0.0005082235,0.99302906,0.00030934246,0.005086514],"genre_scores_gemma":[0.01228509,0.00026391595,0.012942348,0.0009378387,0.00017163485,0.020336637,0.9119033,0.002261747,0.03889735],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965978,0.0012726289,0.0005554103,0.00039007212,0.0008496104,0.00033450115],"domain_scores_gemma":[0.8813781,0.095517695,0.0031675217,0.0046443935,0.013766502,0.0015258072],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008104272,0.001241345,0.0014457757,0.004757773,0.001553943,0.0027985838,0.0024196496,0.0016862096,0.930284],"category_scores_gemma":[0.11299434,0.00074385985,0.0015458359,0.0081041455,0.0004453617,0.0038067866,0.001948722,0.0016096261,0.2402042],"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":[0.00025662882,0.000057112196,0.0005219462,0.0029873399,0.00003256058,0.000025197003,0.00011328821,0.00025413005,0.000026255666,0.0016167782,0.986451,0.0076578287],"study_design_scores_gemma":[0.00367506,0.00016624028,0.009224934,0.0066653797,0.00022997498,0.00012293695,0.0009190178,0.0010118253,0.00035680586,0.01343678,0.9640907,0.00010035697],"about_ca_topic_score_codex":0.010374118,"about_ca_topic_score_gemma":0.019209137,"teacher_disagreement_score":0.99189574,"about_ca_system_score_codex":0.0022134252,"about_ca_system_score_gemma":0.005117241,"threshold_uncertainty_score":0.09944129},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001937513,0.000022429924,0.0005972931,0.0002041523,0.000049231163,0.0005082235,0.99302906,0.00030934246,0.005086514],"genre_scores_gemma":[0.01228509,0.00026391595,0.012942348,0.0009378387,0.00017163485,0.020336637,0.9119033,0.002261747,0.03889735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965978,0.0012726289,0.0005554103,0.00039007212,0.0008496104,0.00033450115],"domain_scores_gemma":[0.8813781,0.095517695,0.0031675217,0.0046443935,0.013766502,0.0015258072],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008104272,0.001241345,0.0014457757,0.004757773,0.001553943,0.0027985838,0.0024196496,0.0016862096,0.930284],"category_scores_gemma":[0.11299434,0.00074385985,0.0015458359,0.0081041455,0.0004453617,0.0038067866,0.001948722,0.0016096261,0.2402042],"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":[0.00025662882,0.000057112196,0.0005219462,0.0029873399,0.00003256058,0.000025197003,0.00011328821,0.00025413005,0.000026255666,0.0016167782,0.986451,0.0076578287],"study_design_scores_gemma":[0.00367506,0.00016624028,0.009224934,0.0066653797,0.00022997498,0.00012293695,0.0009190178,0.0010118253,0.00035680586,0.01343678,0.9640907,0.00010035697],"about_ca_topic_score_codex":0.010374118,"about_ca_topic_score_gemma":0.019209137,"teacher_disagreement_score":0.930284,"about_ca_system_score_codex":0.0022134252,"about_ca_system_score_gemma":0.005117241,"threshold_uncertainty_score":0.09944129},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020997647,0.000020810361,0.0011762627,0.000310384,0.000055009063,0.00091967336,0.9926641,0.00040093364,0.0042428467],"genre_scores_gemma":[0.017923562,0.00030122863,0.024048176,0.0015781784,0.00020939524,0.046102807,0.8681879,0.0027165667,0.03893222],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937563,0.0025819312,0.0011267869,0.0006611764,0.001376894,0.00049686385],"domain_scores_gemma":[0.80052924,0.16491987,0.006125251,0.00831654,0.017907538,0.0022016093],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014766262,0.0013931115,0.0014802748,0.004842688,0.0017098075,0.003058369,0.0027884885,0.0018841928,0.92962545],"category_scores_gemma":[0.1574928,0.0010444223,0.0015390547,0.007583393,0.00065718,0.004141922,0.0022740825,0.0019063588,0.19242126],"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":[0.0002982237,0.00006985377,0.00074802176,0.0029699819,0.000034529836,0.000026088659,0.00012905411,0.00034621567,0.000021829803,0.0020375014,0.9845121,0.008806548],"study_design_scores_gemma":[0.0067147245,0.00028439378,0.011250432,0.009194388,0.00029570243,0.00017468003,0.001341157,0.0019470545,0.0005182691,0.027036339,0.941071,0.00017193251],"about_ca_topic_score_codex":0.010095479,"about_ca_topic_score_gemma":0.01805233,"teacher_disagreement_score":0.92962545,"about_ca_system_score_codex":0.0025232262,"about_ca_system_score_gemma":0.0071422313,"threshold_uncertainty_score":0.10038078},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031411112,0.00026666428,0.0003657564,0.0002753454,0.000050883915,0.002578856,0.99422777,0.00014852638,0.0017720913],"genre_scores_gemma":[0.016733415,0.0030369938,0.016400568,0.002097279,0.00033255658,0.16137975,0.76981694,0.00077244325,0.029430045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954236,0.0009923513,0.0020879859,0.00044644234,0.00073552603,0.00031411575],"domain_scores_gemma":[0.8770767,0.09396498,0.012479242,0.0023239404,0.013063642,0.0010915202],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008583367,0.001537169,0.0030527986,0.012881579,0.0011047386,0.0026884559,0.0021402766,0.0018994161,0.8086782],"category_scores_gemma":[0.09323626,0.0010129078,0.0028109697,0.015770137,0.00048637405,0.0038440372,0.0018682452,0.0012076107,0.05520727],"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":[0.0016227257,0.00015635937,0.0025780373,0.2697981,0.000536397,0.00016159375,0.00042387584,0.00070911547,0.00020862903,0.0036212048,0.6902879,0.029896071],"study_design_scores_gemma":[0.01568745,0.0006143477,0.030650448,0.18055777,0.0025756774,0.0005903517,0.0016098951,0.00176988,0.0010182582,0.01472899,0.7498917,0.00030522875],"about_ca_topic_score_codex":0.0074211652,"about_ca_topic_score_gemma":0.015565472,"teacher_disagreement_score":0.19132179,"about_ca_system_score_codex":0.003907642,"about_ca_system_score_gemma":0.007937404,"threshold_uncertainty_score":0.2728973},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003466528,0.000021994894,0.0014512935,0.0002626685,0.000039916886,0.0019898228,0.99125016,0.00036596155,0.004271587],"genre_scores_gemma":[0.027253402,0.000422465,0.03814825,0.0017539853,0.00024015704,0.105511695,0.772989,0.0021892264,0.05149184],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9963225,0.0018957583,0.0005724926,0.00035656372,0.00055917754,0.00029348067],"domain_scores_gemma":[0.8740898,0.10829912,0.0039578127,0.0034053854,0.008854852,0.0013930525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008726431,0.00087323657,0.0010653883,0.0030890664,0.001331223,0.001622536,0.0020894601,0.0012486249,0.8970172],"category_scores_gemma":[0.105877005,0.0008068755,0.0010245582,0.004868265,0.00032443088,0.002393511,0.001558651,0.0013287517,0.11810807],"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":[0.00037446182,0.00016975084,0.0011502078,0.002315338,0.00003870038,0.000021426706,0.00011575493,0.00036791366,0.000019678984,0.0013946409,0.9779081,0.016124021],"study_design_scores_gemma":[0.01686817,0.00090148865,0.032664604,0.009974693,0.0005061914,0.0002534992,0.0016202788,0.0041056224,0.00068716897,0.021856094,0.9103607,0.00020154245],"about_ca_topic_score_codex":0.010215175,"about_ca_topic_score_gemma":0.022046791,"teacher_disagreement_score":0.8970172,"about_ca_system_score_codex":0.0017786184,"about_ca_system_score_gemma":0.003992623,"threshold_uncertainty_score":0.14689249},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003466528,0.000021994894,0.0014512935,0.0002626685,0.000039916886,0.0019898228,0.99125016,0.00036596155,0.004271587],"genre_scores_gemma":[0.027253402,0.000422465,0.03814825,0.0017539853,0.00024015704,0.105511695,0.772989,0.0021892264,0.05149184],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9963225,0.0018957583,0.0005724926,0.00035656372,0.00055917754,0.00029348067],"domain_scores_gemma":[0.8740898,0.10829912,0.0039578127,0.0034053854,0.008854852,0.0013930525],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008726431,0.00087323657,0.0010653883,0.0030890664,0.001331223,0.001622536,0.0020894601,0.0012486249,0.8970172],"category_scores_gemma":[0.105877005,0.0008068755,0.0010245582,0.004868265,0.00032443088,0.002393511,0.001558651,0.0013287517,0.11810807],"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":[0.00037446182,0.00016975084,0.0011502078,0.002315338,0.00003870038,0.000021426706,0.00011575493,0.00036791366,0.000019678984,0.0013946409,0.9779081,0.016124021],"study_design_scores_gemma":[0.01686817,0.00090148865,0.032664604,0.009974693,0.0005061914,0.0002534992,0.0016202788,0.0041056224,0.00068716897,0.021856094,0.9103607,0.00020154245],"about_ca_topic_score_codex":0.010215175,"about_ca_topic_score_gemma":0.022046791,"teacher_disagreement_score":0.8970172,"about_ca_system_score_codex":0.0017786184,"about_ca_system_score_gemma":0.003992623,"threshold_uncertainty_score":0.14689249},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032509273,0.000019172761,0.0012423482,0.00027078766,0.00004175183,0.0017799959,0.99140704,0.00037412485,0.0045396844],"genre_scores_gemma":[0.025337242,0.0003419343,0.03179251,0.0018027454,0.00024489165,0.08907443,0.7896133,0.0022527894,0.059540097],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666,0.0015880903,0.0005465085,0.00032982262,0.00057059695,0.00030487144],"domain_scores_gemma":[0.8892931,0.09328146,0.0037689595,0.003203397,0.009078035,0.0013751581],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008088801,0.0008565207,0.0010897119,0.0030182952,0.0013261397,0.0016521715,0.0021090314,0.0012671389,0.905349],"category_scores_gemma":[0.096855104,0.00078909675,0.001046797,0.004709105,0.00031960465,0.002344486,0.0015465851,0.0012297607,0.12092492],"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":[0.00033862158,0.00014991866,0.0011353852,0.0020848445,0.000034630644,0.000023817938,0.000108119006,0.00034311487,0.00002030202,0.0012913984,0.98000336,0.014466501],"study_design_scores_gemma":[0.015181315,0.0006841779,0.031024171,0.008569953,0.00042820149,0.0002290151,0.0015456332,0.0036471623,0.00066765177,0.020506227,0.9173322,0.00018428118],"about_ca_topic_score_codex":0.011650863,"about_ca_topic_score_gemma":0.025408065,"teacher_disagreement_score":0.905349,"about_ca_system_score_codex":0.0017535558,"about_ca_system_score_gemma":0.0037777205,"threshold_uncertainty_score":0.13500804},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84589535,0.003124385,0.095793314,0.0071891733,0.0003391861,0.010474245,0.00036073203,0.0006310308,0.036192596],"genre_scores_gemma":[0.91551536,0.0012802447,0.07314009,0.0008397699,0.0001456613,0.0035869926,0.00024104032,0.0001262646,0.005124533],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8353212,0.13649248,0.0051580067,0.0019524856,0.018138316,0.0029374165],"domain_scores_gemma":[0.62237775,0.28768542,0.013632237,0.0067533883,0.066171475,0.0033796644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13419366,0.00095487817,0.0008879187,0.0032764922,0.0019920678,0.0059625297,0.002346624,0.001210469,0.0018255137],"category_scores_gemma":[0.23126477,0.00060463045,0.00054361735,0.0021802513,0.0021475162,0.0028996335,0.0028230734,0.0022080916,0.0004322965],"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":[0.0018007003,0.0066789635,0.059673455,0.0028850494,0.000093571834,0.00046105395,0.112151265,0.0023382565,0.006565732,0.0039225747,0.003512557,0.79991686],"study_design_scores_gemma":[0.0009062901,0.03961525,0.40114093,0.007245513,0.00049750163,0.002208084,0.3516127,0.02948453,0.07216184,0.011805214,0.08246277,0.00085936644],"about_ca_topic_score_codex":0.004927324,"about_ca_topic_score_gemma":0.008178239,"teacher_disagreement_score":0.13419366,"about_ca_system_score_codex":0.0069841505,"about_ca_system_score_gemma":0.007969007,"threshold_uncertainty_score":0.70969236},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9333832,0.0017798492,0.0015245709,0.015630487,0.00015838121,0.00021298806,0.0003500215,0.00004988526,0.046910584],"genre_scores_gemma":[0.9950506,0.0005485585,0.00068468205,0.00057117105,0.000009286799,0.00003345574,0.000060691083,0.000010581358,0.003030958],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.96577317,0.010312081,0.0008639285,0.0018271498,0.011707568,0.009516129],"domain_scores_gemma":[0.9090415,0.024684288,0.006060802,0.0024482878,0.040379375,0.017385649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025939414,0.00030907177,0.00055545237,0.0023975724,0.015894856,0.008843881,0.0016330968,0.00081519585,0.0031767662],"category_scores_gemma":[0.062490612,0.00036287188,0.0003783725,0.0052094543,0.0071394145,0.0021011822,0.00745453,0.0023814123,0.00018185143],"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":[0.00086071534,0.00042642807,0.41795003,0.0008034165,0.00012168716,0.00072178344,0.2236738,0.0020425569,0.0020090959,0.04081215,0.020294951,0.2902834],"study_design_scores_gemma":[0.00006432788,0.0002826141,0.63505316,0.0007704637,0.00008430852,0.000113209906,0.28363138,0.0018287469,0.0014449344,0.0025333015,0.0740263,0.00016726665],"about_ca_topic_score_codex":0.9827763,"about_ca_topic_score_gemma":0.9924642,"teacher_disagreement_score":0.9740606,"about_ca_system_score_codex":0.20861976,"about_ca_system_score_gemma":0.36542785,"threshold_uncertainty_score":0.9178889},"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":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002486432,0.00020621483,0.00035585393,0.00032205982,0.000047063404,0.0020402246,0.9945781,0.00019649252,0.0020053126],"genre_scores_gemma":[0.013363786,0.0024397532,0.016597772,0.0017821932,0.0002740842,0.11380343,0.8274934,0.00088982657,0.023355652],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9935435,0.0014194772,0.0029495943,0.00053164293,0.0011556182,0.00040013515],"domain_scores_gemma":[0.8482521,0.114957,0.014690219,0.0031091066,0.017568724,0.0014228406],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011981532,0.0016946751,0.0028117585,0.014259275,0.0011702529,0.00365113,0.0024210243,0.0021117376,0.80244917],"category_scores_gemma":[0.12334469,0.0010600651,0.003082294,0.017325267,0.0005110896,0.0045030033,0.002593106,0.0012128546,0.06337032],"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":[0.0012117256,0.00011703777,0.0025514166,0.20879266,0.0004638552,0.00014362842,0.00038529426,0.0006568587,0.0001643962,0.0033103323,0.751876,0.030326825],"study_design_scores_gemma":[0.009961759,0.00046661202,0.024037713,0.15030587,0.002191377,0.0004883509,0.001323089,0.0014688054,0.0009322051,0.012810886,0.7957337,0.00027966395],"about_ca_topic_score_codex":0.0072794403,"about_ca_topic_score_gemma":0.013964598,"teacher_disagreement_score":0.98801845,"about_ca_system_score_codex":0.0044003446,"about_ca_system_score_gemma":0.009184434,"threshold_uncertainty_score":0.28178233},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032509273,0.000019172761,0.0012423482,0.00027078766,0.00004175183,0.0017799959,0.99140704,0.00037412485,0.0045396844],"genre_scores_gemma":[0.025337242,0.0003419343,0.03179251,0.0018027454,0.00024489165,0.08907443,0.7896133,0.0022527894,0.059540097],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666,0.0015880903,0.0005465085,0.00032982262,0.00057059695,0.00030487144],"domain_scores_gemma":[0.8892931,0.09328146,0.0037689595,0.003203397,0.009078035,0.0013751581],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008088801,0.0008565207,0.0010897119,0.0030182952,0.0013261397,0.0016521715,0.0021090314,0.0012671389,0.905349],"category_scores_gemma":[0.096855104,0.00078909675,0.001046797,0.004709105,0.00031960465,0.002344486,0.0015465851,0.0012297607,0.12092492],"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":[0.00033862158,0.00014991866,0.0011353852,0.0020848445,0.000034630644,0.000023817938,0.000108119006,0.00034311487,0.00002030202,0.0012913984,0.98000336,0.014466501],"study_design_scores_gemma":[0.015181315,0.0006841779,0.031024171,0.008569953,0.00042820149,0.0002290151,0.0015456332,0.0036471623,0.00066765177,0.020506227,0.9173322,0.00018428118],"about_ca_topic_score_codex":0.011650863,"about_ca_topic_score_gemma":0.025408065,"teacher_disagreement_score":0.905349,"about_ca_system_score_codex":0.0017535558,"about_ca_system_score_gemma":0.0037777205,"threshold_uncertainty_score":0.13500804},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008270527,0.05649127,0.0033744022,0.90369475,0.0024576038,0.00017439197,0.00007755982,0.000033028595,0.025426377],"genre_scores_gemma":[0.6096518,0.14466858,0.040942945,0.18920827,0.0040023974,0.0014044968,0.00027010014,0.00014663776,0.009704767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.80475587,0.14772601,0.008508633,0.004591206,0.021869669,0.012548612],"domain_scores_gemma":[0.5361772,0.34076566,0.007973085,0.008421441,0.06945528,0.03720737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18263642,0.0005800207,0.002238215,0.005379195,0.013965287,0.030885862,0.0037360005,0.013805833,0.0056834975],"category_scores_gemma":[0.20977262,0.0007313755,0.0014211045,0.0051873378,0.031241147,0.03245928,0.018710535,0.021462549,0.00094970065],"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":[0.00014031114,0.00066704577,0.008955329,0.007242888,0.000058650585,0.0011299872,0.13919282,0.0004774145,0.00037064758,0.4312351,0.111674264,0.29885554],"study_design_scores_gemma":[0.0000672215,0.00020729507,0.00710976,0.03726853,0.00006259545,0.00086007256,0.3422323,0.0008203145,0.00045221354,0.16911303,0.4416671,0.00013952337],"about_ca_topic_score_codex":0.020650988,"about_ca_topic_score_gemma":0.028231882,"teacher_disagreement_score":0.18263642,"about_ca_system_score_codex":0.038266886,"about_ca_system_score_gemma":0.13549428,"threshold_uncertainty_score":0.9658853},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009321088,0.00278448,0.8161884,0.021106172,0.0005325948,0.0061514806,0.00018222957,0.00025188242,0.14348175],"genre_scores_gemma":[0.21958977,0.002307479,0.7605219,0.0019806991,0.00013529634,0.0078567015,0.00012795633,0.00012278817,0.0073575377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8217075,0.16352847,0.002796553,0.0019040649,0.008581595,0.0014819069],"domain_scores_gemma":[0.8444689,0.13435107,0.0035452058,0.0051910365,0.010779722,0.0016640045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12490096,0.0013093482,0.0009896085,0.008819584,0.0050573824,0.014153092,0.0027237844,0.001843398,0.0075065084],"category_scores_gemma":[0.09915911,0.0007752229,0.0010332793,0.006376802,0.020365603,0.0065875747,0.0052236184,0.004589008,0.0008473522],"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":[0.00007401123,0.00025881926,0.0023748234,0.0013308568,0.00006918338,0.00017888792,0.010407324,0.009535,0.00018702185,0.74422896,0.00870985,0.22264531],"study_design_scores_gemma":[0.00024194481,0.00037549235,0.00337466,0.0036369525,0.00006917524,0.00031637936,0.02059917,0.02918772,0.0015182706,0.8446763,0.09586952,0.00013443724],"about_ca_topic_score_codex":0.01748254,"about_ca_topic_score_gemma":0.033238713,"teacher_disagreement_score":0.87509906,"about_ca_system_score_codex":0.031000154,"about_ca_system_score_gemma":0.040631738,"threshold_uncertainty_score":0.6605473},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010582029,0.0004096014,0.00086289836,0.004150186,0.00084606156,0.00012261386,0.002120666,0.00093187025,0.9894978],"genre_scores_gemma":[0.0023649356,0.00017342142,0.0004486047,0.00020964952,0.000025353744,0.000012102441,0.00044539195,0.00015037399,0.9961701],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919087,0.000040653296,0.000010904924,0.00007764188,0.0004786661,0.00020118826],"domain_scores_gemma":[0.99681467,0.00006621687,0.00003560555,0.00011488768,0.0018243146,0.0011443449],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00081088283,0.0007565622,0.000370421,0.0012316065,0.008302278,0.0040999604,0.0009071819,0.0009765807,0.6065218],"category_scores_gemma":[0.0015594584,0.0003986681,0.00033157817,0.0015548645,0.00072678534,0.0010028717,0.0015395985,0.0013188958,0.2724223],"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":[0.000009921183,0.000012496946,0.0002390082,0.000013528577,7.8960534e-7,0.000028918543,0.00009136498,0.000028982653,0.0002224765,0.00057892466,0.97782063,0.020953055],"study_design_scores_gemma":[0.0000022101265,0.0000044158014,0.0011331631,0.000014302476,0.0000010653698,0.000020260642,0.00032486973,0.00003813954,0.00014320719,0.00009975473,0.99821365,0.0000050099566],"about_ca_topic_score_codex":0.73905814,"about_ca_topic_score_gemma":0.950612,"teacher_disagreement_score":0.6065218,"about_ca_system_score_codex":0.010881968,"about_ca_system_score_gemma":0.019522598,"threshold_uncertainty_score":0.5612489},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043261286,0.010807867,0.20289221,0.12175456,0.0015836956,0.023295347,0.0031855837,0.0023409545,0.59087855],"genre_scores_gemma":[0.21302319,0.005665376,0.69966835,0.0062306444,0.00009692952,0.015563455,0.0021608758,0.000425236,0.057165932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9424266,0.03294457,0.0043503013,0.0027752838,0.013436371,0.004066936],"domain_scores_gemma":[0.8815498,0.034791496,0.003457379,0.0039889044,0.06784907,0.008363292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09717591,0.0011246143,0.0010609315,0.011479273,0.010050385,0.020191496,0.0033471866,0.003218717,0.0060713957],"category_scores_gemma":[0.08035599,0.0010772034,0.0008351058,0.010286548,0.008015982,0.006526873,0.006264207,0.0050071143,0.0014570645],"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":[0.00010288337,0.00040409362,0.008869708,0.00272635,0.00006871822,0.00073168764,0.046550676,0.006270958,0.0017766567,0.4650174,0.13449046,0.3329904],"study_design_scores_gemma":[0.000093963,0.00013361765,0.009996345,0.011724448,0.00007129524,0.00021968775,0.04723851,0.0055578747,0.0013523363,0.054153666,0.869233,0.0002251915],"about_ca_topic_score_codex":0.71275383,"about_ca_topic_score_gemma":0.7964014,"teacher_disagreement_score":0.71275383,"about_ca_system_score_codex":0.15236036,"about_ca_system_score_gemma":0.30467194,"threshold_uncertainty_score":0.98314184},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062349034,0.00065971,0.9344934,0.0043169814,0.00024750354,0.00022635139,0.00021272262,0.00020978428,0.053398583],"genre_scores_gemma":[0.24562114,0.0013579678,0.7376582,0.0009000478,0.0002198316,0.00060921017,0.000406059,0.00012891034,0.013098578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916638,0.004656146,0.00065878447,0.0008929613,0.0017607884,0.0003674522],"domain_scores_gemma":[0.9809621,0.012547328,0.0009823192,0.0013153619,0.0036071092,0.00058583036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012457981,0.0007283835,0.0005709349,0.003219799,0.0017033297,0.0073833624,0.0025071893,0.0016921728,0.008725974],"category_scores_gemma":[0.022837538,0.0007430947,0.002066408,0.0027070993,0.0057774796,0.016322762,0.0032291475,0.0037849145,0.0014865545],"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":[0.000021499158,0.000024085013,0.00019196616,0.000059654936,0.0000072215216,0.00006187298,0.0005738314,0.004424997,0.00015138937,0.9779358,0.00069317385,0.015854476],"study_design_scores_gemma":[0.000032979475,0.00005987996,0.000117273834,0.00020548287,0.000024797633,0.000117781456,0.00055964803,0.056317158,0.00067817175,0.8855934,0.056264468,0.000029005972],"about_ca_topic_score_codex":0.007736691,"about_ca_topic_score_gemma":0.0048440397,"teacher_disagreement_score":0.012457981,"about_ca_system_score_codex":0.006286488,"about_ca_system_score_gemma":0.0062411968,"threshold_uncertainty_score":0.06588489},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10924781,0.0034943356,0.029093733,0.3340738,0.0018275637,0.0016734105,0.00013119669,0.00027347286,0.5201846],"genre_scores_gemma":[0.8695857,0.0017466617,0.037570287,0.039743166,0.00045236223,0.0013720037,0.00011789571,0.00031791924,0.049093917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.8396534,0.12543492,0.0026228908,0.0029372391,0.013754023,0.015597641],"domain_scores_gemma":[0.7689888,0.14591105,0.0040998803,0.010580555,0.032326393,0.038093414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1140527,0.00054279354,0.0006520101,0.0031334278,0.028313419,0.018913222,0.0032159507,0.008220315,0.012847204],"category_scores_gemma":[0.1300827,0.0008045078,0.001358766,0.0027361899,0.014490235,0.008685514,0.015708692,0.012476162,0.0011395013],"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":[0.0002992183,0.0016394388,0.022758152,0.0013123369,0.00017462982,0.011310581,0.09177466,0.004550706,0.0011210787,0.46393242,0.17957963,0.22154705],"study_design_scores_gemma":[0.00028858063,0.0004932783,0.017586162,0.002902007,0.00014064822,0.002947132,0.09036019,0.007365059,0.0012984241,0.1149575,0.7613403,0.0003206976],"about_ca_topic_score_codex":0.10010313,"about_ca_topic_score_gemma":0.23647813,"teacher_disagreement_score":0.9626476,"about_ca_system_score_codex":0.03735241,"about_ca_system_score_gemma":0.10306062,"threshold_uncertainty_score":0.6031755},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040620383,0.023871941,0.8302735,0.02058685,0.009066701,0.059160873,0.00204709,0.0011559449,0.013216609],"genre_scores_gemma":[0.29178447,0.0038330967,0.59160125,0.0062101143,0.002419238,0.10180474,0.0005993461,0.00028124885,0.0014664292],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.13446142,0.7945714,0.023911614,0.015127254,0.030477116,0.0014511794],"domain_scores_gemma":[0.049363278,0.9158618,0.009564868,0.020176454,0.004229785,0.00080386683],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.65206444,0.0051263277,0.018722026,0.002978398,0.004566339,0.010761046,0.011093148,0.00965138,0.0068493253],"category_scores_gemma":[0.78485143,0.004246952,0.008030908,0.003458498,0.02505384,0.016909957,0.009754648,0.015517249,0.0013519563],"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":[0.057604004,0.015308452,0.015397309,0.026499344,0.02508139,0.00036292415,0.0036159253,0.046638034,0.00216618,0.26794094,0.017126689,0.5222589],"study_design_scores_gemma":[0.038039986,0.02790271,0.008823681,0.00623922,0.0069182804,0.0003966784,0.0011702282,0.09298502,0.0040379553,0.7917818,0.020962168,0.0007423187],"about_ca_topic_score_codex":0.0041219518,"about_ca_topic_score_gemma":0.0034089636,"teacher_disagreement_score":0.34793556,"about_ca_system_score_codex":0.009521847,"about_ca_system_score_gemma":0.013845993,"threshold_uncertainty_score":0.42906654},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096874515,0.0077382484,0.0034984858,0.9454082,0.0065137106,0.00006734872,0.00006314494,0.00013733414,0.0356047],"genre_scores_gemma":[0.14310241,0.050965913,0.026081285,0.43006063,0.010660037,0.001256249,0.00031591507,0.0019443788,0.33561322],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94347376,0.033048604,0.0012645008,0.0028193374,0.016606884,0.0027869218],"domain_scores_gemma":[0.8798431,0.066809006,0.002521081,0.0036535785,0.030053424,0.017119734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059479244,0.0010614668,0.0013665557,0.0022031688,0.016647225,0.020006275,0.0021419933,0.01050856,0.027949216],"category_scores_gemma":[0.079491794,0.0011294526,0.0010621808,0.0022237583,0.03212707,0.019082652,0.009907943,0.026482325,0.008432196],"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":[0.000042960746,0.00008923815,0.0004927623,0.0003498276,0.000010506429,0.00012699905,0.018676842,0.0001789898,0.0003602992,0.08606079,0.8445356,0.04907517],"study_design_scores_gemma":[0.000020159161,0.000035372464,0.00038075575,0.0010965442,0.0000058820783,0.000053080308,0.009550252,0.00024507035,0.0003500148,0.037366766,0.95083266,0.00006339397],"about_ca_topic_score_codex":0.13829602,"about_ca_topic_score_gemma":0.20133267,"teacher_disagreement_score":0.13829602,"about_ca_system_score_codex":0.05199574,"about_ca_system_score_gemma":0.07119107,"threshold_uncertainty_score":0.3772573},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8022753,0.009493994,0.020617409,0.052243225,0.00033925302,0.007639347,0.0018545053,0.000489644,0.10504735],"genre_scores_gemma":[0.9702555,0.004087045,0.016326323,0.0010710815,0.000036582096,0.0017905453,0.00036249068,0.00008751844,0.0059828707],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.87635666,0.05708127,0.011766008,0.0035475034,0.04561737,0.0056311595],"domain_scores_gemma":[0.6172361,0.19940662,0.036775492,0.013420606,0.1230444,0.010116816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11313233,0.00041406046,0.00076190894,0.005832317,0.012501155,0.0096658375,0.0032426992,0.0010247969,0.0019065848],"category_scores_gemma":[0.24803531,0.0012226478,0.0006120128,0.009372022,0.009310892,0.004886764,0.006502446,0.0019498996,0.00015482093],"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":[0.00026133403,0.00020012817,0.07806451,0.003993961,0.00013741745,0.0010483046,0.6715369,0.0017825903,0.0018532091,0.0136943925,0.012741639,0.21468557],"study_design_scores_gemma":[0.00008566038,0.0004564954,0.20502721,0.006656332,0.0002581751,0.0003057741,0.5356811,0.0049724467,0.003992285,0.0043909005,0.23782025,0.00035337103],"about_ca_topic_score_codex":0.8775076,"about_ca_topic_score_gemma":0.94318837,"teacher_disagreement_score":0.20373508,"about_ca_system_score_codex":0.20373508,"about_ca_system_score_gemma":0.34757864,"threshold_uncertainty_score":0.9235544},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027444403,0.0016932206,0.0030716436,0.0045845117,0.0016779118,0.00017059693,0.0039358456,0.0014269216,0.9831648],"genre_scores_gemma":[0.0024246706,0.002692951,0.0025054542,0.001184071,0.00046919848,0.00024104543,0.0031827816,0.001362657,0.9859372],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967077,0.0008846755,0.00031316423,0.00032901307,0.0015223875,0.00024300518],"domain_scores_gemma":[0.99153066,0.003448708,0.00040188458,0.0009096214,0.0025766252,0.0011325346],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053956723,0.00083028205,0.00084256724,0.0028784222,0.0013008837,0.01409929,0.0017241784,0.0029094117,0.8457451],"category_scores_gemma":[0.019271124,0.00046807431,0.0006225906,0.004576655,0.0012629505,0.0055686757,0.004938702,0.002233117,0.7520427],"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":[0.000031718475,0.000034583296,0.00013180198,0.00036358697,0.000004148379,0.000028966115,0.00008551803,0.00012621557,0.000112589325,0.015335516,0.6987619,0.2849835],"study_design_scores_gemma":[0.0000069002062,0.0000073084984,0.00017616538,0.0003596592,0.000001149554,0.000029453218,0.00005571119,0.00005528871,0.00009507072,0.0023599807,0.996847,0.000006334177],"about_ca_topic_score_codex":0.0024309393,"about_ca_topic_score_gemma":0.0030931733,"teacher_disagreement_score":0.15425491,"about_ca_system_score_codex":0.0026436145,"about_ca_system_score_gemma":0.0035325647,"threshold_uncertainty_score":0.22002584},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010026156,0.006520689,0.010218546,0.3858951,0.31649697,0.008567173,0.0033998492,0.0028011452,0.25607437],"genre_scores_gemma":[0.0053956043,0.00089362956,0.0018570318,0.021523075,0.013909189,0.0014244312,0.0009322536,0.00050234125,0.9535623],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98863727,0.0013838614,0.00075686834,0.0010208037,0.005703088,0.0024980763],"domain_scores_gemma":[0.9163652,0.0049870536,0.0023092064,0.0038538894,0.044372357,0.028112315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017011045,0.0018817945,0.002512026,0.0034967114,0.008305038,0.0132146925,0.0030333297,0.022599554,0.27116504],"category_scores_gemma":[0.032098394,0.0012099359,0.0028181484,0.0016194708,0.0016596713,0.004739308,0.0065844767,0.008368131,0.26542866],"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":[0.000099446064,0.00015803144,0.00038353424,0.00009366661,0.000009721881,0.0001512785,0.00004417423,0.00007842808,0.0006860466,0.0010553269,0.97756344,0.019676933],"study_design_scores_gemma":[0.00008237983,0.00017850472,0.003461938,0.00017240034,0.000016693502,0.000110294764,0.0004760596,0.00039939318,0.00032811353,0.0012654507,0.9934557,0.000053035197],"about_ca_topic_score_codex":0.010849661,"about_ca_topic_score_gemma":0.025608387,"teacher_disagreement_score":0.27116504,"about_ca_system_score_codex":0.0035031573,"about_ca_system_score_gemma":0.019820724,"threshold_uncertainty_score":0.90713745},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26633936,0.011739799,0.067906104,0.0042882296,0.0014628547,0.122868605,0.025732208,0.0008447388,0.49881804],"genre_scores_gemma":[0.6056299,0.010649489,0.11782937,0.0018703165,0.0009278175,0.08875502,0.01349574,0.00036288542,0.16047944],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9323179,0.03795509,0.0071825436,0.0019881148,0.018449707,0.0021065006],"domain_scores_gemma":[0.84853375,0.04908614,0.010008482,0.0112995915,0.078361794,0.0027102665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05347654,0.0010276395,0.00084552134,0.015685057,0.0019108397,0.0025169896,0.0017371195,0.0005541518,0.03311477],"category_scores_gemma":[0.104240954,0.0003744258,0.0007672778,0.008717192,0.00096428156,0.0014806632,0.0024266439,0.00072044897,0.0062246597],"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":[0.00092542754,0.0011943005,0.0489304,0.0052023907,0.00012505203,0.00013133542,0.006643884,0.00041897592,0.0030664613,0.006146244,0.04201255,0.8852031],"study_design_scores_gemma":[0.00045775768,0.0077285157,0.38521546,0.0106716445,0.0005771518,0.0002687695,0.023149919,0.0019730798,0.029301357,0.004775812,0.5356916,0.00018883191],"about_ca_topic_score_codex":0.004333203,"about_ca_topic_score_gemma":0.010280404,"teacher_disagreement_score":0.05347654,"about_ca_system_score_codex":0.0041151787,"about_ca_system_score_gemma":0.01218202,"threshold_uncertainty_score":0.28281438},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54303974,0.006782657,0.1256357,0.009392942,0.00035840788,0.0076855966,0.019813253,0.0007870103,0.28650466],"genre_scores_gemma":[0.8273378,0.0025359676,0.13279799,0.0004494379,0.0000532757,0.0027679827,0.010980458,0.0003353032,0.022741765],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98873925,0.0036726408,0.00095581607,0.00050096127,0.0041590785,0.0019723673],"domain_scores_gemma":[0.97429276,0.005929554,0.0028029336,0.0007758864,0.013335881,0.0028630344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012159093,0.0009401396,0.0011026384,0.014434598,0.0030126525,0.010050775,0.0019782665,0.0011725588,0.004835679],"category_scores_gemma":[0.03753618,0.00054647203,0.00072699034,0.018996654,0.002255878,0.0018395056,0.005886058,0.0014968201,0.00059073576],"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":[0.00059979025,0.0004127306,0.2280259,0.0021633042,0.00027515503,0.00059980515,0.007870493,0.118871555,0.0008974561,0.17360564,0.08451211,0.38216603],"study_design_scores_gemma":[0.00036430912,0.0007803246,0.5663694,0.0042429906,0.00034401854,0.0003458409,0.036617056,0.14414118,0.003622203,0.077371396,0.16541696,0.00038436273],"about_ca_topic_score_codex":0.66361326,"about_ca_topic_score_gemma":0.7505887,"teacher_disagreement_score":0.33638674,"about_ca_system_score_codex":0.03472903,"about_ca_system_score_gemma":0.06836031,"threshold_uncertainty_score":0.6767355},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47743896,0.004112838,0.008403322,0.09840409,0.00031370323,0.00053596025,0.0005957148,0.00012846704,0.41006693],"genre_scores_gemma":[0.9863513,0.0005134743,0.0010684214,0.0013654823,0.000017369832,0.000074554155,0.00006618904,0.000023020682,0.010520075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9870429,0.008046678,0.00026941136,0.00039863837,0.0015598186,0.0026825678],"domain_scores_gemma":[0.96339756,0.015979305,0.0020930064,0.0013304593,0.014168981,0.003030771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014470344,0.0003878795,0.00046586938,0.0040198923,0.015106467,0.014056773,0.002677525,0.0021324635,0.008194014],"category_scores_gemma":[0.037624877,0.00024317001,0.0004333439,0.008197298,0.014601467,0.0025724971,0.0035467092,0.0024279475,0.00024196],"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":[0.00032935475,0.0002519005,0.073854715,0.00035195323,0.00010780629,0.00095608464,0.121165626,0.00884718,0.0005561207,0.6226191,0.06023568,0.11072453],"study_design_scores_gemma":[0.00012204555,0.0001506544,0.2721029,0.0015322147,0.00017128499,0.00012215361,0.42834267,0.012545165,0.0011618707,0.06331751,0.22022226,0.00020936353],"about_ca_topic_score_codex":0.9886014,"about_ca_topic_score_gemma":0.99389887,"teacher_disagreement_score":0.7564806,"about_ca_system_score_codex":0.24351946,"about_ca_system_score_gemma":0.16765782,"threshold_uncertainty_score":0.87741023},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31118026,0.0021862402,0.112928145,0.0073059364,0.0007619265,0.014119744,0.0013305125,0.0008608418,0.54932636],"genre_scores_gemma":[0.8261716,0.0017811824,0.13082696,0.0008542992,0.00018720578,0.0075384555,0.00107808,0.00017046824,0.03139179],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8425619,0.11420077,0.007473662,0.0023976967,0.030463975,0.002901984],"domain_scores_gemma":[0.83026344,0.06268941,0.015570356,0.005537269,0.08042042,0.0055190385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.078572854,0.0010927526,0.0007919857,0.007750364,0.002303849,0.007390222,0.0017709411,0.0010655584,0.006764947],"category_scores_gemma":[0.132618,0.00024395491,0.000768791,0.0055620256,0.0025746601,0.0038212552,0.003897567,0.0012673705,0.0012878304],"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":[0.0009340698,0.0018224547,0.026641168,0.0026379738,0.00018881986,0.00026951695,0.028502516,0.011335585,0.0022994569,0.06814957,0.02444987,0.8327689],"study_design_scores_gemma":[0.0010137239,0.010276796,0.14420535,0.008782136,0.00047116587,0.00046630742,0.11777627,0.04156594,0.02443937,0.14181557,0.5082057,0.0009817411],"about_ca_topic_score_codex":0.0054115998,"about_ca_topic_score_gemma":0.007538067,"teacher_disagreement_score":0.078572854,"about_ca_system_score_codex":0.013371325,"about_ca_system_score_gemma":0.012667799,"threshold_uncertainty_score":0.41553795},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6878135,0.013608257,0.007285947,0.015997125,0.0012761268,0.00890483,0.038663108,0.0005987135,0.22585237],"genre_scores_gemma":[0.92524034,0.0026581434,0.0053117685,0.0016109268,0.00022282758,0.0027033086,0.015521583,0.00018509172,0.04654598],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96582264,0.017687235,0.0024027263,0.00093493663,0.010124585,0.0030277781],"domain_scores_gemma":[0.91888875,0.01174621,0.007575082,0.0035778333,0.054304052,0.003908011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052748248,0.0006767829,0.0006471429,0.00498868,0.0016071055,0.0043565603,0.0007812686,0.00057040947,0.005809237],"category_scores_gemma":[0.06919215,0.00036687503,0.00041049896,0.0059864414,0.0013142695,0.0015299086,0.0047741323,0.00086697756,0.0012306108],"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":[0.006646606,0.0012410397,0.21357563,0.0076894383,0.0004512762,0.0003865875,0.0119858235,0.0058273887,0.0022341027,0.014168505,0.1950999,0.5406937],"study_design_scores_gemma":[0.00058176066,0.00313006,0.63242227,0.0037509531,0.00039645153,0.00024231545,0.015697416,0.0028626882,0.004965397,0.0015995627,0.33424288,0.000108164495],"about_ca_topic_score_codex":0.026201868,"about_ca_topic_score_gemma":0.034349933,"teacher_disagreement_score":0.052748248,"about_ca_system_score_codex":0.012031983,"about_ca_system_score_gemma":0.02319861,"threshold_uncertainty_score":0.27896273},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027444403,0.0016932206,0.0030716436,0.0045845117,0.0016779118,0.00017059693,0.0039358456,0.0014269216,0.9831648],"genre_scores_gemma":[0.0024246706,0.002692951,0.0025054542,0.001184071,0.00046919848,0.00024104543,0.0031827816,0.001362657,0.9859372],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967077,0.0008846755,0.00031316423,0.00032901307,0.0015223875,0.00024300518],"domain_scores_gemma":[0.99153066,0.003448708,0.00040188458,0.0009096214,0.0025766252,0.0011325346],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0053956723,0.00083028205,0.00084256724,0.0028784222,0.0013008837,0.01409929,0.0017241784,0.0029094117,0.8457451],"category_scores_gemma":[0.019271124,0.00046807431,0.0006225906,0.004576655,0.0012629505,0.0055686757,0.004938702,0.002233117,0.7520427],"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":[0.000031718475,0.000034583296,0.00013180198,0.00036358697,0.000004148379,0.000028966115,0.00008551803,0.00012621557,0.000112589325,0.015335516,0.6987619,0.2849835],"study_design_scores_gemma":[0.0000069002062,0.0000073084984,0.00017616538,0.0003596592,0.000001149554,0.000029453218,0.00005571119,0.00005528871,0.00009507072,0.0023599807,0.996847,0.000006334177],"about_ca_topic_score_codex":0.0024309393,"about_ca_topic_score_gemma":0.0030931733,"teacher_disagreement_score":0.15425491,"about_ca_system_score_codex":0.0026436145,"about_ca_system_score_gemma":0.0035325647,"threshold_uncertainty_score":0.22002584},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008886161,0.008707736,0.0020517271,0.00695995,0.0030733878,0.0003921889,0.0035390065,0.00067808805,0.9657118],"genre_scores_gemma":[0.075168274,0.010936065,0.007054083,0.0017843102,0.00070778705,0.00055098487,0.004031841,0.0006167558,0.89914995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995436,0.0014581122,0.0002664397,0.00047265977,0.0019574563,0.00040928274],"domain_scores_gemma":[0.9963665,0.00090407144,0.00020392351,0.0005398161,0.0014634668,0.00052222644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039055396,0.001067586,0.00065902364,0.0032426976,0.0023147936,0.008171519,0.0010319051,0.0017408833,0.2679869],"category_scores_gemma":[0.008709819,0.00044764215,0.0007999601,0.0023843776,0.0010497206,0.0026206195,0.0032270318,0.002577884,0.054739594],"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":[0.0004667751,0.00026857533,0.004723683,0.00085397664,0.00003825984,0.001080297,0.001310884,0.0006171743,0.0013585556,0.12134256,0.3803958,0.48754355],"study_design_scores_gemma":[0.00001185689,0.000033802724,0.0014712985,0.00028515703,0.0000042241254,0.00018131718,0.00039360605,0.00008166894,0.00034886983,0.0010401476,0.99613696,0.000011105403],"about_ca_topic_score_codex":0.02893259,"about_ca_topic_score_gemma":0.02398437,"teacher_disagreement_score":0.7320131,"about_ca_system_score_codex":0.004509979,"about_ca_system_score_gemma":0.0076033645,"threshold_uncertainty_score":0.8965055},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08520047,0.0040321276,0.029816782,0.07010186,0.01207741,0.24828482,0.02038966,0.0017925617,0.5283043],"genre_scores_gemma":[0.373611,0.0041621956,0.09000876,0.02038497,0.0023369633,0.26361158,0.011299383,0.000860157,0.23372498],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9062398,0.06359701,0.0045777145,0.0017608892,0.019940155,0.003884359],"domain_scores_gemma":[0.8846822,0.027058493,0.003662622,0.0066094147,0.06656604,0.011421264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08084298,0.0007622583,0.0012068534,0.006097091,0.003064601,0.005933923,0.0019354268,0.0024476221,0.058937572],"category_scores_gemma":[0.13972038,0.00055970665,0.0015801686,0.004208718,0.0016846892,0.0033373954,0.0043466724,0.0029799049,0.007531022],"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":[0.0035613892,0.004123219,0.004793664,0.004359733,0.00022043729,0.00035839362,0.0049487236,0.0024018777,0.0010518114,0.038414985,0.34109792,0.59466785],"study_design_scores_gemma":[0.0024093208,0.011614925,0.031709265,0.009075498,0.00034603133,0.00025868398,0.0075598215,0.0030499804,0.00291574,0.0132724745,0.9176136,0.00017455292],"about_ca_topic_score_codex":0.0084512355,"about_ca_topic_score_gemma":0.0071710097,"teacher_disagreement_score":0.08084298,"about_ca_system_score_codex":0.01566362,"about_ca_system_score_gemma":0.028881738,"threshold_uncertainty_score":0.42754364},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005477255,0.009886063,0.007102663,0.22277635,0.028575247,0.006509819,0.0117249675,0.0013463552,0.70660126],"genre_scores_gemma":[0.010216511,0.0038879607,0.006274528,0.016811816,0.002167667,0.000863062,0.005341574,0.0003966295,0.9540403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9377455,0.004875088,0.0036570851,0.0020369182,0.045410216,0.006275302],"domain_scores_gemma":[0.6818823,0.0061045783,0.0026197664,0.0049722395,0.2890084,0.015412614],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.045938563,0.0012936865,0.0016543438,0.010671535,0.011495631,0.012496147,0.004942249,0.008904416,0.075515784],"category_scores_gemma":[0.062988676,0.0014942288,0.0018102153,0.0071189576,0.0026774257,0.0027742444,0.0029703279,0.005495294,0.030025339],"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":[0.000028950364,0.000033638975,0.0006092981,0.00007991043,0.000008273105,0.00003654096,0.000069001115,0.000083172825,0.00014490362,0.003953911,0.9780456,0.01690683],"study_design_scores_gemma":[0.000020092502,0.000008992111,0.00297517,0.00016771711,0.000016208864,0.000033409655,0.00019516236,0.0001943014,0.00023376085,0.00075353927,0.99537474,0.000026840342],"about_ca_topic_score_codex":0.79568696,"about_ca_topic_score_gemma":0.8838053,"teacher_disagreement_score":0.9244842,"about_ca_system_score_codex":0.046678733,"about_ca_system_score_gemma":0.31538105,"threshold_uncertainty_score":0.4110325},"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":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02351572,0.05484318,0.013015744,0.13302076,0.002417554,0.0015508415,0.0016855766,0.00071678136,0.7692338],"genre_scores_gemma":[0.5414945,0.052601255,0.045090966,0.021595486,0.00043293674,0.0010904819,0.0017614488,0.00080066046,0.3351323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9114015,0.018791793,0.0037788297,0.0039017606,0.054423355,0.0077026845],"domain_scores_gemma":[0.8969168,0.011050459,0.0018482023,0.0030018345,0.07837429,0.008808447],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046324983,0.0006959832,0.0011709521,0.011100678,0.023315622,0.027674556,0.0046823313,0.0037117235,0.009089876],"category_scores_gemma":[0.07168881,0.00081652525,0.0010208932,0.020077951,0.014560291,0.00444242,0.006545972,0.004605417,0.001698251],"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":[0.00009858182,0.00014818911,0.009915475,0.0018960356,0.00012473586,0.0007835321,0.031868037,0.0031774691,0.0011046554,0.35354137,0.25815398,0.33918792],"study_design_scores_gemma":[0.000020231872,0.00004029333,0.014210914,0.0020700109,0.00003669099,0.00014399737,0.01792592,0.0009924341,0.0006646127,0.01418328,0.94957435,0.00013732375],"about_ca_topic_score_codex":0.98861164,"about_ca_topic_score_gemma":0.9887428,"teacher_disagreement_score":0.95367503,"about_ca_system_score_codex":0.31887215,"about_ca_system_score_gemma":0.59755903,"threshold_uncertainty_score":0.79001176},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05397641,0.011959744,0.19554809,0.54202855,0.025586832,0.012928176,0.00044157365,0.003322639,0.15420805],"genre_scores_gemma":[0.22840165,0.010389672,0.39172336,0.24613859,0.0078043244,0.027516635,0.0006609322,0.0031601454,0.084204674],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.75919306,0.1794745,0.021141307,0.006138439,0.024673186,0.009379539],"domain_scores_gemma":[0.64242804,0.13267992,0.018037243,0.017213518,0.14678429,0.042856984],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2283818,0.0011213212,0.0020604627,0.004932508,0.008083787,0.018794984,0.0041432814,0.009736201,0.02367646],"category_scores_gemma":[0.3801286,0.0016767349,0.0016963878,0.0025767623,0.0066148066,0.022088407,0.01251479,0.008752443,0.016755486],"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":[0.00085609814,0.0007640623,0.018081747,0.0035405199,0.00017369325,0.005106597,0.10265316,0.0006658863,0.007175775,0.023705602,0.42704713,0.4102297],"study_design_scores_gemma":[0.0005115335,0.0006417965,0.0110645415,0.011458922,0.00016608124,0.003332972,0.12992558,0.0017699474,0.0033583487,0.029770209,0.8074895,0.0005105568],"about_ca_topic_score_codex":0.0026814805,"about_ca_topic_score_gemma":0.0067404103,"teacher_disagreement_score":0.2283818,"about_ca_system_score_codex":0.0061833244,"about_ca_system_score_gemma":0.021135366,"threshold_uncertainty_score":0.9515426},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009099752,0.0068028574,0.001584309,0.9538875,0.004607644,0.000056612836,0.00006942353,0.00004622597,0.023845615],"genre_scores_gemma":[0.7241202,0.016130462,0.01044912,0.14341299,0.0045697824,0.00038755656,0.00021443533,0.0005116535,0.100203745],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.842273,0.06433669,0.004565409,0.007293864,0.063085906,0.018445149],"domain_scores_gemma":[0.78257394,0.059312604,0.00585265,0.0054635736,0.126073,0.02072431],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.16636594,0.00083050155,0.0012148081,0.006993039,0.060660385,0.035800148,0.006298014,0.012509935,0.007962711],"category_scores_gemma":[0.18263635,0.0011537315,0.001200512,0.01258076,0.053888958,0.011591886,0.010782843,0.018592801,0.00066332205],"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":true,"study_design_scores_codex":[0.00009024861,0.000051163584,0.0037197517,0.00032959777,0.000051816667,0.0005783358,0.24557318,0.00040488094,0.0006190783,0.29354018,0.40410215,0.050939657],"study_design_scores_gemma":[0.00002435922,0.000030638595,0.008731313,0.0010678915,0.00003697356,0.000106600244,0.1299653,0.00040533283,0.0005738763,0.020643542,0.8381007,0.00031357352],"about_ca_topic_score_codex":0.9505018,"about_ca_topic_score_gemma":0.9542735,"teacher_disagreement_score":0.9505018,"about_ca_system_score_codex":0.2776111,"about_ca_system_score_gemma":0.25911343,"threshold_uncertainty_score":0.8798377},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62814265,0.0048432304,0.0011789366,0.21937795,0.00092184346,0.00033417283,0.0004261821,0.00006385042,0.14471108],"genre_scores_gemma":[0.93881106,0.0030995123,0.0006374429,0.01675579,0.00025477892,0.0000888716,0.00017815396,0.000025553047,0.040148675],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9929889,0.0022847694,0.00022860977,0.00020587117,0.0032815256,0.0010104221],"domain_scores_gemma":[0.9665236,0.01877841,0.0024855786,0.0005005044,0.008379042,0.0033329017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008100931,0.000114657516,0.0002892025,0.0012317266,0.0041249283,0.0068954118,0.00045250758,0.0019945854,0.008103513],"category_scores_gemma":[0.03715892,0.0001438368,0.000107667365,0.001776861,0.00286752,0.0014562877,0.0016452029,0.0021414123,0.001018435],"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":[0.00013161926,0.00053967466,0.1498205,0.00088545517,0.000027724278,0.0025214024,0.26399058,0.00043509997,0.0029621734,0.025978902,0.35872898,0.19397789],"study_design_scores_gemma":[0.000027074693,0.00022636978,0.20213263,0.0008152142,0.000019022957,0.00046926297,0.28690457,0.0004986704,0.0009800359,0.0036166667,0.5042254,0.00008513846],"about_ca_topic_score_codex":0.09338052,"about_ca_topic_score_gemma":0.15101008,"teacher_disagreement_score":0.9066195,"about_ca_system_score_codex":0.010734672,"about_ca_system_score_gemma":0.013784658,"threshold_uncertainty_score":0.18567395},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03538469,0.004338394,0.06443892,0.0069024255,0.0019906592,0.0040823473,0.0119790435,0.0015013148,0.86938226],"genre_scores_gemma":[0.66986257,0.0055324147,0.07778378,0.0018842354,0.0009417264,0.005141919,0.020466976,0.0011818691,0.21720454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9445478,0.020940965,0.0033202306,0.0037643684,0.024652524,0.0027741906],"domain_scores_gemma":[0.9217541,0.022213953,0.005824006,0.0073828986,0.039515074,0.0033098976],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.035355803,0.0014667979,0.0012878648,0.006108012,0.0017059726,0.008673021,0.0020335207,0.0010597722,0.06304648],"category_scores_gemma":[0.1095065,0.00027960306,0.0016235241,0.009027489,0.0014127897,0.0043712407,0.0034998646,0.0016629576,0.01748083],"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":[0.00077214,0.00078755384,0.020083772,0.0019005233,0.00032188473,0.000059803668,0.0018172525,0.008804704,0.000605944,0.10553317,0.17506376,0.6842495],"study_design_scores_gemma":[0.000259912,0.0032645056,0.09361837,0.0045053028,0.0005566512,0.0003048808,0.008421559,0.02370578,0.004160504,0.06551175,0.7953615,0.0003292898],"about_ca_topic_score_codex":0.008747729,"about_ca_topic_score_gemma":0.0064049684,"teacher_disagreement_score":0.93695354,"about_ca_system_score_codex":0.008972716,"about_ca_system_score_gemma":0.012774729,"threshold_uncertainty_score":0.21091151},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98392993,0.00016656652,0.0001508014,0.00029065955,0.0000067314263,0.00045763463,0.00009393371,0.000006165516,0.014897617],"genre_scores_gemma":[0.99374545,0.00037199564,0.0009545146,0.0000921809,0.0000041021417,0.00018449854,0.00017003986,0.0000051510274,0.0044720434],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99506277,0.0021869927,0.00017098791,0.00018246929,0.0016889909,0.00070783694],"domain_scores_gemma":[0.99297684,0.0015376458,0.00040334318,0.00014094656,0.0035511823,0.0013900929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044996208,0.00024241768,0.00032137617,0.00089517277,0.002595869,0.003969867,0.0007122654,0.00047795888,0.0025811559],"category_scores_gemma":[0.008070496,0.00017762127,0.00021425699,0.001548085,0.0010672905,0.0008860134,0.0014362104,0.000647261,0.00021534739],"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":[0.005764912,0.0077706454,0.33675206,0.002702069,0.00027116193,0.002538129,0.06176206,0.016662562,0.01328006,0.009793792,0.012288854,0.5304136],"study_design_scores_gemma":[0.0006446674,0.011622831,0.64540297,0.0010281587,0.00018754954,0.00037082713,0.23493475,0.007979952,0.0084901275,0.0016106846,0.08753218,0.00019538516],"about_ca_topic_score_codex":0.437073,"about_ca_topic_score_gemma":0.7540313,"teacher_disagreement_score":0.562927,"about_ca_system_score_codex":0.015898198,"about_ca_system_score_gemma":0.012129851,"threshold_uncertainty_score":0.8690579},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006375015,0.032238796,0.14710228,0.016653676,0.0057896227,0.009534069,0.009038879,0.0028501991,0.77041745],"genre_scores_gemma":[0.22155268,0.03627419,0.35164276,0.008720667,0.0020495339,0.02083146,0.014512166,0.0016131236,0.34280345],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.85780287,0.05371811,0.01163716,0.007753438,0.0663521,0.0027362597],"domain_scores_gemma":[0.81738377,0.039855804,0.0066216947,0.020166596,0.110893875,0.005078257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08584253,0.0014744771,0.0021304737,0.010228665,0.0045454837,0.013355104,0.0027165352,0.002731411,0.035646677],"category_scores_gemma":[0.14300355,0.0012028929,0.001423622,0.01263184,0.0062044077,0.005033768,0.005935499,0.0044250935,0.017121326],"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":[0.00023273048,0.00018179997,0.008771735,0.0025713902,0.00020734212,0.00011601725,0.0024223994,0.0009812936,0.0009970933,0.1655223,0.16877563,0.6492203],"study_design_scores_gemma":[0.0000918886,0.00029952748,0.023507291,0.0069391597,0.00013834941,0.00026784485,0.0027479113,0.0015640366,0.0012014705,0.055785798,0.9073204,0.0001363078],"about_ca_topic_score_codex":0.10651873,"about_ca_topic_score_gemma":0.09855057,"teacher_disagreement_score":0.10651873,"about_ca_system_score_codex":0.024713982,"about_ca_system_score_gemma":0.07705704,"threshold_uncertainty_score":0.45398408},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005733651,0.0067066103,0.01714903,0.35554728,0.097746044,0.06902573,0.08764511,0.0046637305,0.35578278],"genre_scores_gemma":[0.014545157,0.0036120845,0.011903538,0.035866953,0.0115591055,0.024983818,0.027751235,0.0021156366,0.8676626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9744075,0.0068968376,0.003631206,0.0011376737,0.011821393,0.0021052477],"domain_scores_gemma":[0.75922036,0.010179773,0.0074751275,0.005136225,0.20408767,0.01390087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03074322,0.0011300547,0.0009985489,0.0031652777,0.0018326287,0.0074232905,0.0022000137,0.0040470758,0.23674598],"category_scores_gemma":[0.09838949,0.0007291617,0.00059377495,0.002838323,0.00075728353,0.0027234864,0.0024058542,0.0035923428,0.15356274],"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":[0.00006757984,0.000033199674,0.00017355135,0.0002587479,0.0000026196499,0.000017558414,0.000044583834,0.000045536068,0.000094812676,0.00035797548,0.98139614,0.017507877],"study_design_scores_gemma":[0.00008086223,0.00008296547,0.002178155,0.00084536255,0.000013056677,0.000024001738,0.00031777055,0.0002023094,0.00037191802,0.00042131133,0.99544156,0.0000207438],"about_ca_topic_score_codex":0.0100834835,"about_ca_topic_score_gemma":0.011458433,"teacher_disagreement_score":0.23674598,"about_ca_system_score_codex":0.007782149,"about_ca_system_score_gemma":0.043621045,"threshold_uncertainty_score":0.7919942},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1574146,0.0046806606,0.30381113,0.03004479,0.00065901777,0.00213209,0.00022494255,0.0009201928,0.50011253],"genre_scores_gemma":[0.96886325,0.0005561651,0.022107331,0.0006346562,0.000061536775,0.00027868326,0.00005091439,0.00006206544,0.007385406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96671325,0.023273148,0.00048435482,0.0011339332,0.0064478894,0.0019474254],"domain_scores_gemma":[0.95829916,0.025630496,0.0024893521,0.0030706786,0.008138265,0.0023721056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04055504,0.0011022232,0.0009769561,0.0038199062,0.002314855,0.010775536,0.0017884474,0.0028246106,0.009524725],"category_scores_gemma":[0.04389559,0.00032306483,0.00052328565,0.0023059687,0.0069526522,0.0074585113,0.006720191,0.0028088412,0.0010601004],"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":[0.00052186724,0.0005840273,0.0055885897,0.00060686277,0.00011403961,0.00012548223,0.0016229536,0.016247163,0.0017331996,0.7330136,0.01195186,0.22789039],"study_design_scores_gemma":[0.00015078808,0.0011657574,0.00743169,0.00087435864,0.00011798089,0.00012315619,0.005707687,0.063575625,0.014239427,0.8464435,0.06005632,0.00011374183],"about_ca_topic_score_codex":0.0037675821,"about_ca_topic_score_gemma":0.0035632153,"teacher_disagreement_score":0.04055504,"about_ca_system_score_codex":0.009894186,"about_ca_system_score_gemma":0.01627869,"threshold_uncertainty_score":0.21447814},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010355781,0.0071706753,0.088857196,0.6637144,0.005231649,0.005760294,0.0004795004,0.0024659967,0.21596456],"genre_scores_gemma":[0.23892531,0.014406668,0.57042557,0.06756708,0.0015011542,0.0055305674,0.0014380197,0.0031286203,0.09707706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7606203,0.075784974,0.011432116,0.010103413,0.119139984,0.022919245],"domain_scores_gemma":[0.66188097,0.07312076,0.00755383,0.032824468,0.14109555,0.08352442],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21277857,0.0039148848,0.0021394845,0.014235674,0.03444187,0.045705136,0.008704189,0.014174025,0.014994839],"category_scores_gemma":[0.18679789,0.0024958597,0.0026448371,0.010834881,0.040235143,0.024999017,0.039640747,0.019274535,0.008311788],"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":[0.000098529345,0.00067568664,0.0036355318,0.001739347,0.00008620107,0.0012366064,0.037704878,0.0015861754,0.0025850656,0.13745941,0.21708561,0.59610695],"study_design_scores_gemma":[0.00012289423,0.00030160518,0.008176343,0.0046059065,0.000093534196,0.0006543863,0.0370369,0.0015009624,0.0018777245,0.09059761,0.8546818,0.00035034958],"about_ca_topic_score_codex":0.608901,"about_ca_topic_score_gemma":0.6844354,"teacher_disagreement_score":0.857193,"about_ca_system_score_codex":0.14280699,"about_ca_system_score_gemma":0.59966964,"threshold_uncertainty_score":0.9942224},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010355781,0.0071706753,0.088857196,0.6637144,0.005231649,0.005760294,0.0004795004,0.0024659967,0.21596456],"genre_scores_gemma":[0.23892531,0.014406668,0.57042557,0.06756708,0.0015011542,0.0055305674,0.0014380197,0.0031286203,0.09707706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7606203,0.075784974,0.011432116,0.010103413,0.119139984,0.022919245],"domain_scores_gemma":[0.66188097,0.07312076,0.00755383,0.032824468,0.14109555,0.08352442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21277857,0.0039148848,0.0021394845,0.014235674,0.03444187,0.045705136,0.008704189,0.014174025,0.014994839],"category_scores_gemma":[0.18679789,0.0024958597,0.0026448371,0.010834881,0.040235143,0.024999017,0.039640747,0.019274535,0.008311788],"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":[0.000098529345,0.00067568664,0.0036355318,0.001739347,0.00008620107,0.0012366064,0.037704878,0.0015861754,0.0025850656,0.13745941,0.21708561,0.59610695],"study_design_scores_gemma":[0.00012289423,0.00030160518,0.008176343,0.0046059065,0.000093534196,0.0006543863,0.0370369,0.0015009624,0.0018777245,0.09059761,0.8546818,0.00035034958],"about_ca_topic_score_codex":0.608901,"about_ca_topic_score_gemma":0.6844354,"teacher_disagreement_score":0.857193,"about_ca_system_score_codex":0.14280699,"about_ca_system_score_gemma":0.59966964,"threshold_uncertainty_score":0.9942224},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22989115,0.17056952,0.034712043,0.27047068,0.0015772315,0.00089611876,0.003572132,0.0008099955,0.28750107],"genre_scores_gemma":[0.9335228,0.026752423,0.01713645,0.0026897339,0.000111000525,0.00015326226,0.0004995357,0.00011353555,0.019021362],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96280986,0.015529842,0.0015958176,0.0009796043,0.015721805,0.0033630447],"domain_scores_gemma":[0.8750705,0.04674159,0.0049929908,0.0021957355,0.061797637,0.009201474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042817973,0.000570388,0.00044840365,0.0048232125,0.008947409,0.008634858,0.0022454625,0.001359173,0.002432633],"category_scores_gemma":[0.058110137,0.00034806528,0.0002844645,0.013247053,0.0085470695,0.0021651213,0.0032023264,0.0019156967,0.0003364559],"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":[0.00020582184,0.00018448608,0.06335982,0.002202055,0.00008330576,0.00027903626,0.048813272,0.0036036202,0.00150677,0.056196757,0.1716967,0.6518684],"study_design_scores_gemma":[0.00003422349,0.0002280262,0.38846734,0.004617196,0.00009004185,0.00028863695,0.11332041,0.003681813,0.0047048125,0.01582775,0.46840248,0.00033724165],"about_ca_topic_score_codex":0.962885,"about_ca_topic_score_gemma":0.9796143,"teacher_disagreement_score":0.11443196,"about_ca_system_score_codex":0.11443196,"about_ca_system_score_gemma":0.22174542,"threshold_uncertainty_score":0.8302659},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65513456,0.0023680513,0.030903252,0.012764395,0.0011931112,0.036006197,0.0011412608,0.0009190044,0.25957018],"genre_scores_gemma":[0.87719756,0.0020710055,0.08859836,0.002659334,0.00020001958,0.010881673,0.00057818444,0.00011630457,0.017697582],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98453957,0.009443235,0.00049734977,0.0006123507,0.0037178195,0.0011896448],"domain_scores_gemma":[0.9875759,0.0027282967,0.00085502083,0.00069616025,0.0055053825,0.0026392904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012904178,0.0005794374,0.00043854778,0.0021105513,0.005953343,0.0043477537,0.0014812605,0.0008943046,0.0076483414],"category_scores_gemma":[0.02286017,0.00037122634,0.0005687987,0.0011972254,0.0012991324,0.0023421694,0.0049767294,0.0023071594,0.0009837445],"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":[0.0015300047,0.009794817,0.04966198,0.0024031496,0.00008426927,0.0026872708,0.06748351,0.0025745067,0.010792697,0.043725144,0.052021068,0.7572416],"study_design_scores_gemma":[0.0013293254,0.024472367,0.1664382,0.0069761355,0.00032102386,0.0021405318,0.2965439,0.010483931,0.02260599,0.015370238,0.4529532,0.00036520747],"about_ca_topic_score_codex":0.009942341,"about_ca_topic_score_gemma":0.025582816,"teacher_disagreement_score":0.012904178,"about_ca_system_score_codex":0.011962428,"about_ca_system_score_gemma":0.020948114,"threshold_uncertainty_score":0.0867939},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05141077,0.076125085,0.021879321,0.5608286,0.0016310343,0.0006085397,0.00018401982,0.00011586365,0.28721672],"genre_scores_gemma":[0.9188515,0.022203963,0.008339002,0.005060437,0.0007186317,0.00034697496,0.000040581057,0.00009930359,0.04433955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.96781856,0.020878626,0.0013438936,0.0009920653,0.005792914,0.0031740125],"domain_scores_gemma":[0.9133573,0.059348576,0.003872679,0.0013944802,0.017051516,0.004975493],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045062024,0.0006851938,0.0008435517,0.004595087,0.020754522,0.03157059,0.0025836146,0.0047392426,0.003762932],"category_scores_gemma":[0.065719225,0.0009405831,0.00033827164,0.0064924606,0.0500705,0.010410299,0.003384129,0.0048354366,0.00025325533],"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":[0.000089177345,0.00008119371,0.006197131,0.0011936941,0.000027589334,0.000564273,0.19078037,0.002934807,0.00048337207,0.56992084,0.089678325,0.13804927],"study_design_scores_gemma":[0.00006443457,0.00010784288,0.020376831,0.0036865599,0.000060787006,0.00021094084,0.19888282,0.0032558108,0.0011002576,0.170038,0.60206044,0.00015524193],"about_ca_topic_score_codex":0.8462028,"about_ca_topic_score_gemma":0.906303,"teacher_disagreement_score":0.954938,"about_ca_system_score_codex":0.16027425,"about_ca_system_score_gemma":0.19128306,"threshold_uncertainty_score":0.97396284},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024941703,0.029850073,0.048254803,0.7462078,0.008598574,0.00037804278,0.0002461498,0.0005217051,0.16344874],"genre_scores_gemma":[0.4646234,0.050174464,0.13744012,0.21272363,0.018277146,0.0033433265,0.0007651695,0.0010919315,0.11156086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.69715524,0.21933828,0.009336715,0.022197029,0.043391358,0.008581376],"domain_scores_gemma":[0.4071186,0.41248965,0.019164339,0.08138276,0.053331297,0.02651336],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3139384,0.0020112838,0.0028603547,0.008409557,0.009690494,0.040679824,0.0065789274,0.017095074,0.017730452],"category_scores_gemma":[0.34440133,0.0013231094,0.0026340217,0.005153691,0.057850607,0.046302427,0.027705414,0.019645385,0.0058319652],"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":[0.00006940346,0.000073892,0.0016281151,0.0007870306,0.0001165247,0.00013461836,0.002669267,0.00063782866,0.00012181371,0.8764465,0.057172306,0.06014276],"study_design_scores_gemma":[0.000049104354,0.000050789306,0.00049988995,0.0012005862,0.000033363092,0.00008314243,0.0018533247,0.00062352134,0.00018413176,0.7678955,0.22746924,0.00005738636],"about_ca_topic_score_codex":0.0068169455,"about_ca_topic_score_gemma":0.0048910165,"teacher_disagreement_score":0.6860616,"about_ca_system_score_codex":0.019283574,"about_ca_system_score_gemma":0.11576482,"threshold_uncertainty_score":0.8460361},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07899037,0.0031176563,0.8305878,0.005183607,0.00020941175,0.012090559,0.00070398516,0.0006388785,0.06847767],"genre_scores_gemma":[0.2984804,0.0005321297,0.6926617,0.00033798267,0.00002327692,0.0069589335,0.00027812965,0.000030937146,0.0006964906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8259225,0.13290402,0.009662547,0.005768755,0.022933096,0.00280906],"domain_scores_gemma":[0.86721176,0.09512371,0.008131059,0.004924018,0.023296807,0.0013126306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12065748,0.0017338382,0.0025888078,0.0129687395,0.0037159368,0.009998757,0.0038078283,0.0021905995,0.0027638674],"category_scores_gemma":[0.12378123,0.0008478812,0.003224162,0.008725145,0.008018731,0.010238957,0.006865394,0.003290356,0.00041337794],"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":[0.00019586361,0.0011790221,0.03422951,0.0032233363,0.00046932037,0.00015807006,0.013043489,0.030510355,0.00084799976,0.6126965,0.005093903,0.29835272],"study_design_scores_gemma":[0.00085088407,0.0051940037,0.056219343,0.010850427,0.0012968344,0.00059289334,0.043235097,0.34942693,0.006655055,0.46033075,0.0647475,0.0006003354],"about_ca_topic_score_codex":0.01795077,"about_ca_topic_score_gemma":0.026234433,"teacher_disagreement_score":0.12065748,"about_ca_system_score_codex":0.017746452,"about_ca_system_score_gemma":0.03089478,"threshold_uncertainty_score":0.6381054},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92231977,0.000529482,0.009174429,0.023711061,0.00018279334,0.0011149723,0.0001267533,0.00006687186,0.042773835],"genre_scores_gemma":[0.97258085,0.0007592232,0.007450527,0.0028256907,0.00006323635,0.0007126136,0.0000628795,0.00005865957,0.015486292],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9627621,0.028740091,0.00058116874,0.0012640124,0.0025100613,0.0041425377],"domain_scores_gemma":[0.9777529,0.01494768,0.0016699516,0.00084568956,0.0014598563,0.003323825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020256318,0.0007286095,0.00089339074,0.0017560741,0.03805436,0.0073590577,0.004980407,0.0069739395,0.004409048],"category_scores_gemma":[0.032005507,0.000981609,0.000762708,0.0037764322,0.025776714,0.006882594,0.0075312676,0.007676328,0.00043113847],"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":[0.000018720597,0.00013345129,0.0012326789,0.00008275747,0.000004170132,0.0034885253,0.9800571,0.0002011491,0.0002506853,0.00942491,0.00095913914,0.004146624],"study_design_scores_gemma":[0.000011629627,0.00008103824,0.000804827,0.0001414779,0.0000048807988,0.0005316488,0.96830297,0.0003164607,0.00029055055,0.0013300343,0.028166922,0.000017617074],"about_ca_topic_score_codex":0.15353961,"about_ca_topic_score_gemma":0.26181248,"teacher_disagreement_score":0.15353961,"about_ca_system_score_codex":0.03382094,"about_ca_system_score_gemma":0.03671181,"threshold_uncertainty_score":0.30529177},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6746614,0.0030306212,0.08733447,0.08404333,0.0007530963,0.0033687588,0.0001732562,0.00024644792,0.1463887],"genre_scores_gemma":[0.9119816,0.0015786332,0.06808687,0.0031909193,0.00010212431,0.0016875352,0.00006718503,0.00013406115,0.013171157],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9242323,0.061775412,0.001238658,0.0015975797,0.0066125193,0.004543522],"domain_scores_gemma":[0.9430445,0.040845115,0.0020553104,0.0029262668,0.005210996,0.0059178662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06931463,0.00059844885,0.00068974565,0.0029606407,0.018146422,0.012866684,0.0028321163,0.0054644886,0.003050753],"category_scores_gemma":[0.06262509,0.0006116008,0.0008654518,0.0030786286,0.013817108,0.008878696,0.013165463,0.0062924954,0.00038551158],"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":[0.0002876633,0.0023410341,0.015599705,0.0012305033,0.000086537635,0.014147738,0.48722062,0.007920129,0.0024388214,0.25524518,0.03142793,0.18205409],"study_design_scores_gemma":[0.00014152781,0.0015279553,0.0056619765,0.0017980103,0.00006443886,0.002697124,0.51289576,0.00596455,0.0040562362,0.052527215,0.412441,0.00022420165],"about_ca_topic_score_codex":0.014340473,"about_ca_topic_score_gemma":0.027846068,"teacher_disagreement_score":0.98565954,"about_ca_system_score_codex":0.0182315,"about_ca_system_score_gemma":0.02493156,"threshold_uncertainty_score":0.36657518},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16967562,0.03396649,0.21101741,0.08779056,0.0044997893,0.00062853436,0.0038034252,0.0016176007,0.48700055],"genre_scores_gemma":[0.7626291,0.021413552,0.13989303,0.008856519,0.002116128,0.0005195723,0.0023941728,0.0006235509,0.061554354],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9903216,0.0030898708,0.0010439842,0.0011568345,0.00392545,0.00046234802],"domain_scores_gemma":[0.9799749,0.0078001004,0.00187643,0.0023403673,0.007131362,0.0008767936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016783193,0.00035363916,0.00051070045,0.0032854492,0.0020217367,0.0073217805,0.000706307,0.0013580323,0.010312933],"category_scores_gemma":[0.023806654,0.00049980794,0.00046182418,0.0041486523,0.007532101,0.008525705,0.0018436173,0.0023562931,0.0046437825],"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":[0.00043536746,0.00022841945,0.022961339,0.001286318,0.00014025615,0.00086228736,0.010462977,0.0009072737,0.008409168,0.24696739,0.09118617,0.616153],"study_design_scores_gemma":[0.00013090891,0.00033231845,0.037761122,0.0013587679,0.00028130462,0.0021959976,0.01287185,0.0036343879,0.022131484,0.21018857,0.7088471,0.00026615587],"about_ca_topic_score_codex":0.008925507,"about_ca_topic_score_gemma":0.011171914,"teacher_disagreement_score":0.016783193,"about_ca_system_score_codex":0.003250175,"about_ca_system_score_gemma":0.0049641076,"threshold_uncertainty_score":0.088759065},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000083923245,0.98245066,0.00048939086,0.008595589,0.0029961334,0.00003119071,0.00005157537,0.000014987547,0.005286546],"genre_scores_gemma":[0.00077191996,0.9820693,0.0012766931,0.006617667,0.0016155744,0.00009812939,0.000075040494,0.000024879708,0.007450856],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977265,0.0006568407,0.00020982751,0.00020330102,0.0011393224,0.00006425154],"domain_scores_gemma":[0.99163896,0.0057474743,0.00037517934,0.000113679904,0.0018955807,0.00022918968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034652262,0.0008638165,0.0013729746,0.0051103095,0.00096044847,0.0033310715,0.0010705176,0.0017341238,0.0066244677],"category_scores_gemma":[0.010889515,0.0006999209,0.0006258517,0.0077313306,0.0019017328,0.003954449,0.0014245124,0.0046978216,0.003630332],"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":[0.00002792539,0.000048498296,0.00012977766,0.013185984,0.000046371326,0.00011199393,0.0011605918,0.00016875267,0.0002671363,0.01719606,0.58666396,0.38099298],"study_design_scores_gemma":[0.000003637692,0.000014748651,0.0002112952,0.008275778,0.00001296403,0.00016802938,0.0002155144,0.000014442711,0.000048647787,0.0016061375,0.9894175,0.000011361323],"about_ca_topic_score_codex":0.007716434,"about_ca_topic_score_gemma":0.020016655,"teacher_disagreement_score":0.007716434,"about_ca_system_score_codex":0.002827673,"about_ca_system_score_gemma":0.0073968004,"threshold_uncertainty_score":0.022161007},"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":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009388959,0.021901127,0.0049083442,0.4826498,0.016226146,0.000078792466,0.00019772328,0.00025281752,0.4643964],"genre_scores_gemma":[0.16016917,0.017174281,0.007323359,0.19214557,0.0029013616,0.00017001916,0.00021089282,0.00031711522,0.61958826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975908,0.0012021316,0.000072468574,0.00033953227,0.0004587374,0.00033645137],"domain_scores_gemma":[0.9978642,0.0004850662,0.0001770784,0.00030435092,0.0006142244,0.0005549632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004731036,0.0007802333,0.00083671,0.0004636616,0.0073801335,0.010778683,0.0010399142,0.0043949103,0.031612087],"category_scores_gemma":[0.008332811,0.00040208086,0.00059537496,0.0005574296,0.011007589,0.015418247,0.0047943,0.011187048,0.014876746],"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":[0.00013241699,0.00015898117,0.002895497,0.00037538164,0.00003729447,0.00045611005,0.03013064,0.00010445378,0.00057057134,0.40581805,0.43116462,0.12815593],"study_design_scores_gemma":[0.000008638697,0.00004057238,0.00046191725,0.0002968768,0.000007935649,0.000210906,0.013643966,0.00004008146,0.00007689614,0.024781145,0.96041393,0.000017167635],"about_ca_topic_score_codex":0.010938715,"about_ca_topic_score_gemma":0.015865324,"teacher_disagreement_score":0.031612087,"about_ca_system_score_codex":0.0018367391,"about_ca_system_score_gemma":0.0029480597,"threshold_uncertainty_score":0.105753005},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01087886,0.00026002314,0.97144204,0.0018638524,0.000075517855,0.00031683873,0.00047574876,0.00064124155,0.01404589],"genre_scores_gemma":[0.37212768,0.0003982835,0.61946553,0.00040078492,0.00007849611,0.00085824204,0.0012145031,0.0000725681,0.005384078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99548244,0.0023163154,0.00031366193,0.00070664694,0.0009063697,0.00027449685],"domain_scores_gemma":[0.98860395,0.006581801,0.0005368411,0.0005905137,0.0033472704,0.00033962182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076641734,0.0010198132,0.0006922111,0.0030765631,0.0010353014,0.0037025516,0.0029267222,0.0021852737,0.009266445],"category_scores_gemma":[0.031357843,0.000548382,0.0010022045,0.0015298387,0.0014844806,0.004536485,0.002445767,0.002051954,0.002737399],"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":[0.00021560641,0.00027644783,0.016239513,0.0002861812,0.00016946632,0.0004967834,0.0009997678,0.16637416,0.0008491145,0.43769827,0.011062249,0.3653325],"study_design_scores_gemma":[0.000048006084,0.00008033904,0.0008504776,0.000097553595,0.00005093358,0.0001876926,0.00025645364,0.74126315,0.00044738213,0.24694751,0.009741814,0.000028704153],"about_ca_topic_score_codex":0.010282336,"about_ca_topic_score_gemma":0.005980832,"teacher_disagreement_score":0.010282336,"about_ca_system_score_codex":0.0029529035,"about_ca_system_score_gemma":0.0037731577,"threshold_uncertainty_score":0.04053253},"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":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28839305,0.008270262,0.15548937,0.11354276,0.00049763813,0.004024823,0.0008344074,0.00044211347,0.42850563],"genre_scores_gemma":[0.95676965,0.0012701111,0.037674204,0.0010460209,0.00008376011,0.0009204914,0.00013274234,0.000047760954,0.0020552373],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75299156,0.17561646,0.010111173,0.002346446,0.052275356,0.0066590984],"domain_scores_gemma":[0.63307923,0.26172096,0.01662575,0.012868807,0.06738993,0.008315417],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17492023,0.00087684946,0.00078128197,0.006862215,0.005430491,0.01640041,0.0015392693,0.0026094636,0.0029456473],"category_scores_gemma":[0.2593578,0.00060288457,0.00087143877,0.0044193976,0.009627891,0.011764242,0.011160446,0.0035827563,0.00036541006],"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":[0.0007538963,0.00067205867,0.06643864,0.0063911118,0.00033528713,0.0005037031,0.030474532,0.0064533534,0.002201977,0.30954486,0.009875242,0.5663554],"study_design_scores_gemma":[0.00031657607,0.0014619022,0.1568156,0.021288756,0.0010713396,0.0008159307,0.07849305,0.019029194,0.021826215,0.50759,0.19094868,0.00034278532],"about_ca_topic_score_codex":0.014013875,"about_ca_topic_score_gemma":0.025445256,"teacher_disagreement_score":0.9782882,"about_ca_system_score_codex":0.021711836,"about_ca_system_score_gemma":0.048438266,"threshold_uncertainty_score":0.9250777},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008212173,0.013409201,0.4076815,0.21544051,0.0047836285,0.00022370736,0.00012418549,0.00088597153,0.34923917],"genre_scores_gemma":[0.44022754,0.014694083,0.39749554,0.032644704,0.0023597523,0.0008316089,0.00026489265,0.0017467382,0.10973517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9457191,0.038356,0.0013433374,0.0016136745,0.011070471,0.0018973835],"domain_scores_gemma":[0.93991566,0.042645406,0.0037292072,0.00624327,0.0060570673,0.0014094048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0464773,0.0014996971,0.0011765033,0.002514093,0.0039528306,0.019273913,0.0030349898,0.0072065666,0.0106754815],"category_scores_gemma":[0.09539699,0.00079923926,0.00062374456,0.0027268077,0.021534128,0.029753266,0.0071737664,0.010890779,0.0042006],"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":[0.000030958847,0.000058892045,0.00028299986,0.00025252975,0.000038070444,0.00003694576,0.004801775,0.0017737144,0.00023648272,0.81393516,0.049022496,0.12952994],"study_design_scores_gemma":[0.000010050967,0.000011750423,0.00013966241,0.00045950664,0.00001158596,0.000026985526,0.0018792073,0.0011396753,0.00046932162,0.9163577,0.07946845,0.000026096119],"about_ca_topic_score_codex":0.0028802266,"about_ca_topic_score_gemma":0.004634203,"teacher_disagreement_score":0.0464773,"about_ca_system_score_codex":0.0051285853,"about_ca_system_score_gemma":0.013609662,"threshold_uncertainty_score":0.24579841},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75245374,0.035809997,0.165598,0.015234398,0.0012312031,0.010222001,0.0032491102,0.0007565958,0.015444931],"genre_scores_gemma":[0.7651227,0.006662627,0.21105053,0.00081787637,0.00041384564,0.011073226,0.0010483904,0.00013306663,0.0036777493],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8572415,0.10474312,0.009391791,0.0031301728,0.02450608,0.0009873753],"domain_scores_gemma":[0.6037581,0.339266,0.01194141,0.010825326,0.03230624,0.0019029195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09867653,0.001653891,0.0027994316,0.0033839825,0.0010729909,0.0039485353,0.0022307723,0.0022401751,0.0048023565],"category_scores_gemma":[0.33406338,0.0014139418,0.0026738949,0.0023737678,0.0014358993,0.0033488823,0.0020955328,0.0027271283,0.00070819695],"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":[0.020936491,0.0030788668,0.16468082,0.0078036864,0.0045419787,0.00027950923,0.006909471,0.0094552925,0.0061440715,0.006094959,0.0034206824,0.7666542],"study_design_scores_gemma":[0.00918011,0.038099743,0.70415694,0.013386406,0.008241767,0.0026240349,0.0056972066,0.10674758,0.04602577,0.014191034,0.05062922,0.0010202315],"about_ca_topic_score_codex":0.01630439,"about_ca_topic_score_gemma":0.015015728,"teacher_disagreement_score":0.09867653,"about_ca_system_score_codex":0.0036608377,"about_ca_system_score_gemma":0.012415269,"threshold_uncertainty_score":0.5218576},"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":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05902731,0.5012447,0.03302472,0.24221449,0.023170954,0.00045190429,0.0010818447,0.00019567744,0.13958843],"genre_scores_gemma":[0.55384624,0.25948438,0.022876505,0.0035664486,0.013441229,0.0005885322,0.0023024054,0.00057992525,0.1433144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939809,0.0030645682,0.0004355974,0.0006182444,0.0014852143,0.0004155497],"domain_scores_gemma":[0.9768548,0.01317892,0.0010846822,0.0009970532,0.0051167854,0.0027675976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016681183,0.0013141674,0.0023530673,0.0037910612,0.0065343785,0.026914567,0.0019222705,0.0049204673,0.011699061],"category_scores_gemma":[0.019284377,0.0012874256,0.0011265948,0.0072651743,0.019212477,0.011446621,0.0049749184,0.005506704,0.001234939],"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":[0.0008590365,0.00046361744,0.0135586765,0.0030426008,0.00036524548,0.0006491652,0.072896995,0.0026898799,0.001430039,0.290134,0.35677493,0.25713578],"study_design_scores_gemma":[0.00016183197,0.00006530869,0.03174705,0.0026159864,0.00021220319,0.0003815634,0.017157236,0.0027137175,0.00071775157,0.14694968,0.79709965,0.00017806237],"about_ca_topic_score_codex":0.36082295,"about_ca_topic_score_gemma":0.51222384,"teacher_disagreement_score":0.36082295,"about_ca_system_score_codex":0.03154847,"about_ca_system_score_gemma":0.04550735,"threshold_uncertainty_score":0.71744543},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018528396,0.06602026,0.06066835,0.8306989,0.006146688,0.00014729635,0.00011121607,0.00019372432,0.0341607],"genre_scores_gemma":[0.16552983,0.14166464,0.29181197,0.33308864,0.014582721,0.0020866785,0.00041900185,0.0023056008,0.048510965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7352993,0.21891251,0.009132625,0.004521518,0.029509706,0.002624409],"domain_scores_gemma":[0.2134254,0.7381734,0.0035547954,0.012855782,0.029536445,0.0024541528],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3992471,0.001583403,0.0022466518,0.005155577,0.005373422,0.022946624,0.007234948,0.012916977,0.0042764805],"category_scores_gemma":[0.35065955,0.001574266,0.0016986761,0.0055628484,0.05691655,0.03904965,0.010262469,0.04237945,0.0015481706],"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":[0.00005421262,0.00014726585,0.0010167577,0.00077632075,0.00003498798,0.00012461313,0.014334262,0.0010652273,0.00017889388,0.72880006,0.12820019,0.12526725],"study_design_scores_gemma":[0.000037887206,0.00007513244,0.0014364676,0.009840446,0.00002442345,0.00023203062,0.008267456,0.001506891,0.00089487433,0.5461725,0.43140724,0.000104586295],"about_ca_topic_score_codex":0.017198384,"about_ca_topic_score_gemma":0.021197863,"teacher_disagreement_score":0.6007529,"about_ca_system_score_codex":0.015303581,"about_ca_system_score_gemma":0.025048828,"threshold_uncertainty_score":0.7408353},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36287394,0.008157098,0.2660312,0.2830384,0.002344062,0.0017564311,0.0006183454,0.00027935955,0.07490112],"genre_scores_gemma":[0.9384791,0.0027169555,0.04132816,0.01197458,0.00017810322,0.0015515302,0.00009823869,0.0001250063,0.0035483532],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.851867,0.12812881,0.0047284793,0.0024987652,0.0104652345,0.0023116856],"domain_scores_gemma":[0.8462832,0.12316894,0.0072869114,0.007580485,0.013411735,0.0022686978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1456451,0.0006881111,0.0013118434,0.004341467,0.007837283,0.013471121,0.0027856869,0.0034855122,0.002374929],"category_scores_gemma":[0.14223358,0.0007888279,0.0006717466,0.0033705283,0.034061152,0.02575824,0.014170514,0.008333082,0.0003337694],"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":[0.000029820298,0.000019194416,0.0009755563,0.00040012365,0.000010277578,0.00015984388,0.94720024,0.00010664414,0.00072783645,0.038308337,0.0015055779,0.010556587],"study_design_scores_gemma":[0.000022830242,0.00004393876,0.001239365,0.001560742,0.000020574718,0.0003511132,0.86070603,0.0007145186,0.0008366887,0.09797196,0.03644905,0.00008310659],"about_ca_topic_score_codex":0.011090346,"about_ca_topic_score_gemma":0.012711249,"teacher_disagreement_score":0.1456451,"about_ca_system_score_codex":0.010827755,"about_ca_system_score_gemma":0.0113276895,"threshold_uncertainty_score":0.77025414},"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":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08909789,0.0053627365,0.0021831137,0.13905118,0.010035665,0.00023703306,0.002372994,0.00031658783,0.75134283],"genre_scores_gemma":[0.27316982,0.0037855757,0.001302062,0.034508593,0.0030127952,0.00031188643,0.0011596555,0.0003183143,0.6824312],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949332,0.0015869315,0.00012883914,0.0004116898,0.0013857142,0.0015537567],"domain_scores_gemma":[0.9959657,0.00093643,0.00034050536,0.0003585098,0.0011762345,0.0012225487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063894074,0.0004129833,0.00045584288,0.001092967,0.008212521,0.0052954415,0.0010644302,0.0034483303,0.026055904],"category_scores_gemma":[0.009108931,0.00027964968,0.0005422829,0.0018288445,0.0027928227,0.0019856328,0.007316375,0.005978278,0.0046027442],"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":[0.00067148654,0.00021268941,0.00943141,0.0006342044,0.000020479563,0.0018737931,0.049215652,0.0004862621,0.0026354804,0.109848,0.75414634,0.07082417],"study_design_scores_gemma":[0.0000043842115,0.000024308894,0.0034003442,0.00010103344,0.0000021039089,0.000037201527,0.0046400204,0.000026622507,0.00022620909,0.0005348768,0.9909951,0.000007782782],"about_ca_topic_score_codex":0.043373525,"about_ca_topic_score_gemma":0.077587396,"teacher_disagreement_score":0.043373525,"about_ca_system_score_codex":0.007681608,"about_ca_system_score_gemma":0.008661512,"threshold_uncertainty_score":0.08716565},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06374881,0.001401849,0.87841976,0.0050249635,0.000641577,0.014410211,0.00025917063,0.0011633845,0.0349303],"genre_scores_gemma":[0.29317155,0.00039901765,0.69169676,0.0005334766,0.000120536504,0.012082706,0.0001568253,0.00026325762,0.0015758422],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.24365577,0.6748077,0.024958044,0.008535584,0.045188993,0.0028538024],"domain_scores_gemma":[0.35176316,0.46889803,0.043469716,0.045904502,0.08479341,0.0051712645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.50033945,0.0017196654,0.0019624056,0.011426706,0.0048728827,0.018699503,0.0028024071,0.0031620911,0.003495882],"category_scores_gemma":[0.5947321,0.0012640962,0.0015985128,0.010102588,0.0096423505,0.014109454,0.013428142,0.00639942,0.001155088],"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":[0.0011394199,0.0013970726,0.033403132,0.0024956595,0.0004481829,0.00012699066,0.034817815,0.010547297,0.0036961571,0.1446143,0.004335441,0.7629785],"study_design_scores_gemma":[0.001603442,0.008336448,0.072396494,0.009322081,0.00090530684,0.0004933507,0.04079051,0.12379403,0.03900413,0.5665599,0.13533227,0.0014620363],"about_ca_topic_score_codex":0.0041981293,"about_ca_topic_score_gemma":0.0059714727,"teacher_disagreement_score":0.50033945,"about_ca_system_score_codex":0.01082942,"about_ca_system_score_gemma":0.02933925,"threshold_uncertainty_score":0.61617047},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81746626,0.0016624137,0.0032202676,0.04009588,0.00021679222,0.00027440963,0.00019627166,0.00006861463,0.13679907],"genre_scores_gemma":[0.9877043,0.00032573275,0.0010898047,0.0008476883,0.000008360337,0.000041822223,0.000039380695,0.00002140142,0.009921502],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.964597,0.0108150635,0.0010411493,0.0020165006,0.011639787,0.009890549],"domain_scores_gemma":[0.93436056,0.01960232,0.0030821047,0.0030425708,0.023366643,0.01654573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023435976,0.0002753009,0.0008147652,0.0019712285,0.025637763,0.013350072,0.003332454,0.0027672367,0.0060866307],"category_scores_gemma":[0.073503464,0.0006441094,0.00050595787,0.0046390137,0.010258426,0.0046134354,0.008700524,0.0061400267,0.0002973075],"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":[0.0006054585,0.00055027957,0.14386068,0.00042156046,0.00019657628,0.0012241475,0.3013753,0.0031351729,0.0012395675,0.26444784,0.028789265,0.2541542],"study_design_scores_gemma":[0.00012334266,0.00027455812,0.45217866,0.0006940701,0.00017499624,0.00027631805,0.30977643,0.007328581,0.0012112946,0.036531508,0.19099459,0.0004355787],"about_ca_topic_score_codex":0.99040693,"about_ca_topic_score_gemma":0.9959074,"teacher_disagreement_score":0.14203595,"about_ca_system_score_codex":0.14203595,"about_ca_system_score_gemma":0.38127935,"threshold_uncertainty_score":0.9951167},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07762791,0.02653197,0.014702281,0.5452591,0.0025482147,0.000118363714,0.00009944522,0.00009837931,0.3330143],"genre_scores_gemma":[0.948324,0.012316548,0.0037323155,0.020587336,0.001082581,0.00021382366,0.000048747654,0.00019078855,0.01350383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9640796,0.027905816,0.00058903324,0.0016350343,0.0034990683,0.0022914251],"domain_scores_gemma":[0.97575605,0.017829528,0.0015169508,0.0011390485,0.0019907951,0.0017676569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032555815,0.0010566039,0.001100816,0.0063417214,0.028101226,0.027746657,0.0024924919,0.008720238,0.00676224],"category_scores_gemma":[0.026120132,0.00087989547,0.00075230905,0.0050937175,0.08564214,0.0349476,0.029174672,0.012851128,0.001042027],"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":[0.000025222673,0.000035104516,0.00056821347,0.00017249775,0.000009011855,0.00022193318,0.22459629,0.00018688328,0.00020112577,0.749353,0.007267311,0.017363498],"study_design_scores_gemma":[0.000016263895,0.000025003352,0.0006722499,0.0012402885,0.000011700297,0.00013498109,0.20758115,0.00028628905,0.0003213669,0.46636483,0.32331902,0.000026849148],"about_ca_topic_score_codex":0.009096003,"about_ca_topic_score_gemma":0.0042709326,"teacher_disagreement_score":0.032555815,"about_ca_system_score_codex":0.026687674,"about_ca_system_score_gemma":0.015576129,"threshold_uncertainty_score":0.19363356},"labels":[],"label_agreement":null}]}