{"meta":{"query_hash":"6156bc5eeb8c","filters":{"venue":"Journal of MultiDisciplinary Evaluation"},"cohort_total":56,"direct_labels_cover":0,"predictions_cover":56,"exported":56,"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/6156bc5eeb8c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+MultiDisciplinary+Evaluation"},"results":[{"id":"W1488273786","doi":"10.56645/jmde.v1i1.148","title":"The State of Evaluation in Canada","year":2004,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Canada; Government of Canada; Industry Canada; Australian Government; Transport Canada","keywords":"State (computer science); Political science; Evaluation methods; Public administration; Library science; Regional science; Sociology; Computer science; Engineering; Reliability engineering","score_opus":0.15798301331153608,"score_gpt":0.4877877855008924,"score_spread":0.32980477218935633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488273786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99346966,0.0005740071,0.00059981004,0.0034773343,0.0009200249,0.0004627712,0.0000035350574,0.0000011134022,0.00049176643],"genre_scores_gemma":[0.9992451,0.00009568643,0.00051277026,0.000024864023,0.000056404988,0.000013518684,0.0000026432103,0.0000053357526,0.000043660562],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9887437,0.001031384,0.0019584526,0.00016402524,0.0079189325,0.00018349795],"domain_scores_gemma":[0.9928364,0.0010755212,0.0017413489,0.0003298453,0.0039459,0.00007096136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.044391565,0.00010269275,0.00025046995,0.00029674705,0.00015824266,0.00005591445,0.00041850033,0.000025784575,0.00019528622],"category_scores_gemma":[0.0035611242,0.0000598346,0.000089715184,0.0007500778,0.000051188596,0.00060753524,0.00006206142,0.00019792166,0.000010736458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013684393,0.00005556459,0.023529323,0.0000025194056,0.00001433397,0.0000025244233,0.0018086142,0.73361224,0.00064578844,0.000051794075,0.0001707677,0.23996969],"study_design_scores_gemma":[0.0024622611,0.00017276163,0.6508724,0.00005782896,0.000035870682,0.000015903834,0.0032391162,0.28862464,0.0012293236,0.053102173,0.000114827315,0.00007289255],"about_ca_topic_score_codex":0.028572258,"about_ca_topic_score_gemma":0.6946353,"teacher_disagreement_score":0.666063,"about_ca_system_score_codex":0.0019138462,"about_ca_system_score_gemma":0.013888982,"threshold_uncertainty_score":0.99170136},"labels":[],"label_agreement":null},{"id":"W1501592175","doi":"10.56645/jmde.v11i24.422","title":"Utilization Focused Developmental Evaluation: Learning Through Practice","year":2015,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Mastercard Foundation","keywords":"Data collection; Context (archaeology); Curriculum; Intervention (counseling); Sample (material); Citizen journalism; Participatory evaluation; Process (computing); Knowledge management; Computer science; Psychology; Process management; Medical education; Management science; Pedagogy; Sociology; Engineering; Medicine","score_opus":0.6300483308941991,"score_gpt":0.5906089619140568,"score_spread":0.03943936898014233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501592175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8673399,0.0015700263,0.061353836,0.009704444,0.0032551503,0.0014204931,0.0000028501347,0.0000400949,0.055313177],"genre_scores_gemma":[0.9605368,0.0000604638,0.038320918,0.00013723026,0.00042331225,0.000030746243,0.00002969428,0.000017886676,0.00044299796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9819041,0.0036068102,0.0019463428,0.0003551281,0.011948775,0.00023883351],"domain_scores_gemma":[0.9803132,0.0014017653,0.0025037923,0.00027994602,0.015298688,0.00020264788],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.075059645,0.0002055334,0.00035850206,0.00044660753,0.00036933014,0.00029247507,0.0005054672,0.00012143738,0.001525129],"category_scores_gemma":[0.034551606,0.00015416335,0.000148876,0.0011618643,0.00006678399,0.0048248954,0.00014797553,0.00038484286,0.00039196835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093501055,0.00061230385,0.024847297,0.0000069446087,0.00012887242,0.000011437022,0.048307434,0.35581607,0.0005688733,0.00040976255,0.009918499,0.5584375],"study_design_scores_gemma":[0.007250878,0.0010750075,0.037174463,0.0000788917,0.00038540465,0.00029711713,0.072895885,0.8296646,0.00081063487,0.020958483,0.029083325,0.00032535242],"about_ca_topic_score_codex":0.000008477923,"about_ca_topic_score_gemma":0.000019922036,"teacher_disagreement_score":0.55811214,"about_ca_system_score_codex":0.0012594844,"about_ca_system_score_gemma":0.004821962,"threshold_uncertainty_score":0.9993876},"labels":[],"label_agreement":null},{"id":"W1526225390","doi":"10.56645/jmde.v7i16.314","title":"Empathy Training: Methods, Evaluation Practices, and Validity","year":2011,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Empathy and Medical Education","field":"Medicine","cited_by":141,"is_retracted":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":"Empathy; Psychology; Feeling; Narrative; Social work; Social psychology; Applied psychology; Medical education; Medicine","score_opus":0.4604867244391697,"score_gpt":0.518990695771376,"score_spread":0.058503971332206306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526225390","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911806,0.0014211942,0.0022400266,0.0013507516,0.0011202582,0.0006918221,0.0000011002221,0.000012471008,0.001981804],"genre_scores_gemma":[0.92027795,0.00021702732,0.078800336,0.00007185285,0.0005279102,0.000025095635,0.000019441133,0.000014845282,0.000045554072],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9963195,0.0012953778,0.00072748534,0.00021136632,0.0012748358,0.00017147408],"domain_scores_gemma":[0.9958648,0.00037363474,0.0016443878,0.00020573977,0.001611753,0.00029969256],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021933662,0.00014247144,0.00033938076,0.00024485335,0.00012376248,0.000015354542,0.000079708996,0.00014688786,0.0005019744],"category_scores_gemma":[0.011269053,0.000111022986,0.000114563,0.00020535194,0.00008700872,0.0005805858,0.000033830896,0.00040272422,0.0000066185967],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012463582,0.0012826651,0.008528979,0.000121799385,0.00016515118,0.00002277171,0.34618452,0.000020941161,0.0074351127,0.00004694015,0.00048982573,0.6344549],"study_design_scores_gemma":[0.0063871387,0.0029069022,0.8042684,0.00041896847,0.0035633289,0.0014863432,0.11567825,0.049858794,0.005632759,0.009265169,0.00030277413,0.00023112725],"about_ca_topic_score_codex":0.000011420085,"about_ca_topic_score_gemma":0.000004311882,"teacher_disagreement_score":0.7957395,"about_ca_system_score_codex":0.00021177047,"about_ca_system_score_gemma":0.0014026923,"threshold_uncertainty_score":0.99705946},"labels":[],"label_agreement":null},{"id":"W1544634347","doi":"10.56645/jmde.v3i4.95","title":"Review of Research Evaluation, Volumes 13(3), 14(1), and 14(2)","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.365610475907359,"score_gpt":0.5976328797105598,"score_spread":0.23202240380320077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544634347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9085251,0.0732238,0.00078922405,0.008825188,0.00091537106,0.0014887194,0.000010252284,0.00000898341,0.0062133335],"genre_scores_gemma":[0.9885162,0.0073126466,0.0028826906,0.000086221255,0.00042837506,0.000041122174,0.000021087184,0.000014373369,0.0006972747],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98090583,0.0035951212,0.0026480674,0.00036688612,0.012211114,0.00027295985],"domain_scores_gemma":[0.9750879,0.0017557396,0.0018820593,0.0005359554,0.020619156,0.00011923007],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14013585,0.00016385799,0.00053152815,0.00095284125,0.00031835792,0.00011450043,0.00053456123,0.00010118729,0.0021218376],"category_scores_gemma":[0.010996145,0.00011567008,0.00018756969,0.0014378459,0.00023403227,0.0011309827,0.00018231098,0.00036975666,0.000066011984],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044229554,0.0010932928,0.14044257,0.0013839846,0.000117679876,0.0000069961225,0.0029725202,0.017091079,0.0046982034,0.0006506827,0.18197703,0.64912367],"study_design_scores_gemma":[0.0037528367,0.0009793263,0.6121509,0.0049778433,0.00036641528,0.00010478521,0.0019356698,0.27889848,0.0009194429,0.08759868,0.008037434,0.0002781913],"about_ca_topic_score_codex":0.000023625302,"about_ca_topic_score_gemma":0.000089436304,"teacher_disagreement_score":0.6488455,"about_ca_system_score_codex":0.0002758199,"about_ca_system_score_gemma":0.0015603594,"threshold_uncertainty_score":0.9987904},"labels":[],"label_agreement":null},{"id":"W1581987850","doi":"10.56645/jmde.v8i17.337","title":"‘Policing Schools’ Strategies: A Review of the Evaluation Evidence","year":2012,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Education Discipline and Inequality","field":"Social 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":"Johns Hopkins University; George Mason University","keywords":"Curriculum; Intervention (counseling); Medical education; Psychology; Scale (ratio); Mathematics education; Medicine; Pedagogy; Psychiatry","score_opus":0.4899013199200807,"score_gpt":0.5862737800061536,"score_spread":0.09637246008607292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581987850","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005065457,0.99127823,0.000036617163,0.0018064919,0.002008558,0.002750052,0.000008334169,0.0000075177873,0.0015976431],"genre_scores_gemma":[0.0035656285,0.99403536,0.00024135997,0.00003507976,0.0018772675,0.000114094306,0.00001742715,0.000024546283,0.00008924884],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9835804,0.009011175,0.0026562302,0.0002478511,0.0041766264,0.00032773468],"domain_scores_gemma":[0.98705345,0.0009984524,0.0067151343,0.00063800404,0.0044152965,0.00017968816],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054529887,0.00031121555,0.001348572,0.00027208013,0.0005256303,0.00007834279,0.0010281818,0.00028607884,0.00075165456],"category_scores_gemma":[0.009130977,0.0001965119,0.0010422848,0.0012832164,0.00019077396,0.0017421005,0.00017308773,0.00078072026,0.00002784471],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007782461,0.00022291312,0.00016050538,0.03679248,0.00013263796,1.9340717e-7,0.008948977,0.000046157526,0.0000028442985,0.0004585656,0.0017010127,0.9515259],"study_design_scores_gemma":[0.0004726774,0.00017361075,0.002744576,0.67312974,0.016344879,0.00003241017,0.015282393,0.00020126683,0.0000031241673,0.0024936784,0.2885307,0.0005909664],"about_ca_topic_score_codex":0.00014733775,"about_ca_topic_score_gemma":0.00015325623,"teacher_disagreement_score":0.95093495,"about_ca_system_score_codex":0.0014621222,"about_ca_system_score_gemma":0.017750371,"threshold_uncertainty_score":0.99921554},"labels":[],"label_agreement":null},{"id":"W1713678554","doi":"10.56645/jmde.v1i1.144","title":"Unpacking the Participatory Process","year":2004,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Unpacking; Citizen journalism; Process (computing); Participatory action research; Sociology; Computer science; Linguistics; Anthropology; World Wide Web","score_opus":0.4185578280274691,"score_gpt":0.5807891987238559,"score_spread":0.16223137069638682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1713678554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9832875,0.00025033441,0.0044285594,0.009536241,0.00086458755,0.00030063116,0.0000010211846,0.0000071525897,0.0013239892],"genre_scores_gemma":[0.9988037,0.000017224576,0.0006321574,0.00012968568,0.0003247077,0.00001664283,0.0000012067696,0.000007606176,0.00006708209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99306774,0.0005869774,0.0011801729,0.000174227,0.004807885,0.0001829753],"domain_scores_gemma":[0.99508786,0.00055989745,0.0012376412,0.00034902574,0.0026695495,0.000096052296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029263932,0.00011214218,0.00020867134,0.00024467896,0.00038554883,0.00016044626,0.00061566854,0.00005013071,0.0005789404],"category_scores_gemma":[0.002714318,0.000057794005,0.00015183864,0.0006487271,0.00009244587,0.0010406333,0.00006436052,0.0002526594,0.00013876543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020613658,0.00038435747,0.042560697,0.00000975351,0.000057395016,0.000009186549,0.03173842,0.8148253,0.0022789612,0.001044969,0.0006851172,0.1061997],"study_design_scores_gemma":[0.0045359344,0.0007419103,0.5798056,0.00016863881,0.00022664902,0.00014674317,0.026245572,0.15641181,0.0052519664,0.22499977,0.0011938454,0.0002715633],"about_ca_topic_score_codex":0.0000017855043,"about_ca_topic_score_gemma":0.000024414361,"teacher_disagreement_score":0.6584135,"about_ca_system_score_codex":0.00022936927,"about_ca_system_score_gemma":0.0012991783,"threshold_uncertainty_score":0.99957705},"labels":[],"label_agreement":null},{"id":"W1750660279","doi":"10.56645/jmde.v8i18.349","title":"An In-Depth International Comparison of Major Donor Agencies: How Do They Systematically Conduct Country Program Evaluation?","year":2012,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"International Development and Aid","field":"Social 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":"Japan International Cooperation Agency; World Bank Group; Asian Development Bank; United States Agency for International Development","keywords":"Viewpoints; Christian ministry; Ministry of Foreign Affairs; Program evaluation; Political science; Evaluation methods; International development; Public administration; Economic growth; Public relations; Economics; Engineering","score_opus":0.13999391933636257,"score_gpt":0.47660545791766407,"score_spread":0.3366115385813015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1750660279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98460644,0.0004127884,0.0001754854,0.0016551211,0.0021700356,0.0015563255,0.000009139876,0.0000150047545,0.009399649],"genre_scores_gemma":[0.9932857,0.00003055364,0.0057730926,0.000010260435,0.000690638,0.00009350322,0.000053572418,0.000012015478,0.000050648032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9940456,0.0011624377,0.0010069534,0.00015107138,0.0033626244,0.0002713223],"domain_scores_gemma":[0.99561393,0.00027905224,0.0012518747,0.0001404022,0.002570519,0.00014418956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015738254,0.00014774664,0.00035099714,0.0003785865,0.00019606715,0.0001346689,0.0004979334,0.00012536235,0.0003250004],"category_scores_gemma":[0.0011063556,0.000121870835,0.00010929545,0.00025497147,0.00012223468,0.0018145905,0.000049604943,0.00021633784,0.000010404197],"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":[0.00044771525,0.003975624,0.7321331,0.00018842373,0.00041242072,0.000004712704,0.1887736,0.0043165837,0.0074627846,0.019467877,0.00092901447,0.041888125],"study_design_scores_gemma":[0.00525483,0.0008561339,0.68310344,0.0012506569,0.0005466921,0.000028605382,0.16912961,0.12716281,0.0011115178,0.009720099,0.0012301444,0.0006054542],"about_ca_topic_score_codex":0.000050805076,"about_ca_topic_score_gemma":0.0005736573,"teacher_disagreement_score":0.12284622,"about_ca_system_score_codex":0.0009961278,"about_ca_system_score_gemma":0.001026538,"threshold_uncertainty_score":0.5454596},"labels":[],"label_agreement":null},{"id":"W1756996990","doi":"10.56645/jmde.v6i11.221","title":"Nonmarket Economic Valuation and \"The Economist’s Fallacy\"","year":2009,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Financial Reporting and Valuation Research","field":"Business, Management and Accounting","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":"Memorial University of Newfoundland","funders":"","keywords":"Nonmarket forces; Fallacy; Economics; Valuation (finance); Positive economics; Neoclassical economics; Public economics; Classical economics; Microeconomics; Factor market; Epistemology; Philosophy","score_opus":0.04982295590130277,"score_gpt":0.3348057041719891,"score_spread":0.28498274827068637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1756996990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97872216,0.00022210742,0.00039918424,0.015024494,0.00048470317,0.00056416274,3.64181e-7,0.00001149846,0.004571317],"genre_scores_gemma":[0.9980024,0.000037036465,0.00024123814,0.00025992145,0.0012786594,0.000013780104,0.000007269086,0.000008634268,0.00015103814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820334,0.00011552791,0.00079281634,0.00015698816,0.00057225215,0.0001590691],"domain_scores_gemma":[0.99769634,0.00019370695,0.0011853696,0.00015797516,0.000747387,0.000019220663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012781429,0.000117366755,0.0002361471,0.00026528406,0.00028329415,0.0002927418,0.00016823545,0.000057818797,0.00019825024],"category_scores_gemma":[0.001470335,0.000082431914,0.00012027603,0.0001228033,0.00007517316,0.0012406739,0.00005782425,0.00017894861,0.00008416976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026251809,0.00047208054,0.06400419,0.000111032896,0.00016159598,0.000013704947,0.00114604,0.041011684,0.0012544623,0.021122985,0.016826462,0.8512506],"study_design_scores_gemma":[0.0031199788,0.000050382532,0.4361172,0.000033762317,0.00011367996,0.000018783488,0.00020282927,0.4970731,0.00001538943,0.062408704,0.00074829085,0.000097892174],"about_ca_topic_score_codex":0.00008880088,"about_ca_topic_score_gemma":0.000034138702,"teacher_disagreement_score":0.85115266,"about_ca_system_score_codex":0.00014781186,"about_ca_system_score_gemma":0.00020510633,"threshold_uncertainty_score":0.44298136},"labels":[],"label_agreement":null},{"id":"W1771824113","doi":"10.56645/jmde.v4i7.8","title":"Evaluation, Sustainable Development, and the Environment in the South Pacific","year":2007,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Island Studies and Pacific Affairs","field":"Social 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":"Nipissing University","funders":"","keywords":"Argument (complex analysis); Sustainable development; Vulnerability (computing); Orthodoxy; Function (biology); Perspective (graphical); Value (mathematics); Empirical research; Regional science; Sociology; Environmental resource management; Environmental planning; Political science; Epistemology; Geography; Computer science; Economics; Law","score_opus":0.040570017837781816,"score_gpt":0.3327616416763509,"score_spread":0.2921916238385691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1771824113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94821024,0.0023395726,0.0009025006,0.0063695135,0.00024875544,0.0012138688,4.2494904e-7,0.0000032706635,0.040711883],"genre_scores_gemma":[0.99896693,0.00017493553,0.00029364947,0.000012980333,0.00017656147,0.000019123941,0.0000013471417,0.0000036779072,0.00035081524],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99602056,0.0013304829,0.00046123457,0.00010116022,0.0018368111,0.0002497439],"domain_scores_gemma":[0.9985948,0.0005171713,0.00034816968,0.00009905782,0.0004039132,0.00003685516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.078675754,0.00008018753,0.00013411482,0.000098859135,0.0011244508,0.000057673748,0.00017100993,0.000049575672,0.00005385493],"category_scores_gemma":[0.00071154226,0.000041367897,0.000049004455,0.00020274892,0.00026261844,0.00017876335,0.000042566175,0.00016947399,0.000004364873],"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":[0.00020468538,0.00008760146,0.01029119,0.000006746988,0.00004288694,0.000011418638,0.93229353,0.00069540215,0.000003970699,0.0037099847,0.000302105,0.052350473],"study_design_scores_gemma":[0.0022799573,0.00004950138,0.10761802,0.000016204021,0.00010937718,0.0000049355604,0.87456197,0.0015900466,0.000005385938,0.0071854293,0.006505874,0.00007328492],"about_ca_topic_score_codex":0.000033358672,"about_ca_topic_score_gemma":0.0002984438,"teacher_disagreement_score":0.09732683,"about_ca_system_score_codex":0.000334401,"about_ca_system_score_gemma":0.00038738805,"threshold_uncertainty_score":0.9486972},"labels":[],"label_agreement":null},{"id":"W1873333392","doi":"10.56645/jmde.v4i8.30","title":"Culturally Competent Evaluation for Aboriginal Communities: A Review of the Empirical Literature","year":2007,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Health Canada","keywords":"Multiculturalism; Context (archaeology); Cultural diversity; Cultural competence; Sociology; Psychology; Social psychology; Public relations; Pedagogy; Political science; Anthropology","score_opus":0.6594573931484259,"score_gpt":0.6618411843139824,"score_spread":0.002383791165556537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873333392","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036127027,0.9900548,0.00063884037,0.0014445833,0.0021555054,0.004742222,0.000106393345,0.0000054161146,0.0004909953],"genre_scores_gemma":[0.00022092302,0.9957064,0.0025816027,0.00019578991,0.0005950106,0.00019174643,0.0002752665,0.000028616607,0.00020468417],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97747386,0.0058592986,0.005416411,0.0003497076,0.010596241,0.00030448107],"domain_scores_gemma":[0.9682752,0.0042628543,0.008837668,0.0011082953,0.0173806,0.00013539927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08787859,0.0004867588,0.002260601,0.0007389896,0.00041175782,0.00018363832,0.001978773,0.00034709554,0.0007540873],"category_scores_gemma":[0.004595303,0.00023604969,0.002144278,0.0020182198,0.00016422119,0.00075664045,0.00018611042,0.0009844512,0.000021125968],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006665403,0.00023924415,0.00009602359,0.014389375,0.00017291428,7.9186754e-7,0.003222875,0.00040333584,0.000001256136,0.00006472092,0.009323987,0.97201884],"study_design_scores_gemma":[0.0013051105,0.00047671938,0.0008452882,0.15312105,0.003649068,0.00019024081,0.0012434163,0.01675828,0.0000018469145,0.0012702647,0.8208398,0.00029886633],"about_ca_topic_score_codex":0.0000017828313,"about_ca_topic_score_gemma":0.000025194273,"teacher_disagreement_score":0.97172,"about_ca_system_score_codex":0.0009445695,"about_ca_system_score_gemma":0.0063041425,"threshold_uncertainty_score":0.9993292},"labels":[],"label_agreement":null},{"id":"W1906589293","doi":"10.56645/jmde.v8i17.329","title":"Thinking Beyond Measurement, Description and Judgement: Fourth Generation Evaluation in Family-Centered Pediatric Healthcare Organizations","year":2012,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Child and Adolescent Health","field":"Health Professions","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","funders":"","keywords":"Health care; General partnership; Context (archaeology); Judgement; Ideal (ethics); Engineering ethics; Dialectic; Family centered care; Psychology; Sociology; Management science; Knowledge management; Computer science; Epistemology; Political science; Engineering","score_opus":0.21505837903585967,"score_gpt":0.42947964768010954,"score_spread":0.21442126864424987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906589293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9830345,0.0055233226,0.0033502702,0.0030507038,0.002755766,0.0021254949,0.0000082777315,0.000020347827,0.00013133677],"genre_scores_gemma":[0.9939239,0.0010946209,0.0016204457,0.00030142747,0.0028813684,0.00002081074,0.000113683935,0.000032147094,0.00001157109],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9927538,0.002690372,0.0015139794,0.0002382951,0.0023154805,0.00048806387],"domain_scores_gemma":[0.9949704,0.00010783582,0.0013537746,0.00019497603,0.00313034,0.00024270632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020882197,0.00020561327,0.00032348582,0.0006306352,0.00095862907,0.000033464185,0.00013144965,0.00019214828,0.00009523784],"category_scores_gemma":[0.0011288853,0.00018602044,0.000056095083,0.0006623684,0.000019448367,0.0013068116,0.000100101846,0.00066178676,0.000018868805],"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":[0.00012732518,0.0006635919,0.94692993,0.00030952407,0.000026389911,8.630527e-7,0.032196727,0.0012984016,0.005370037,0.00028127394,0.0016213336,0.011174611],"study_design_scores_gemma":[0.004917541,0.00020079856,0.939411,0.00044905258,0.00029732374,0.000010493034,0.0064323083,0.046886772,0.000029166698,0.0011085403,0.000066212284,0.00019080505],"about_ca_topic_score_codex":0.000038424605,"about_ca_topic_score_gemma":0.0003715798,"teacher_disagreement_score":0.04558837,"about_ca_system_score_codex":0.0019308677,"about_ca_system_score_gemma":0.0013197926,"threshold_uncertainty_score":0.7585693},"labels":[],"label_agreement":null},{"id":"W1912672976","doi":"10.56645/jmde.v7i16.322","title":"Return on Investment: A Placebo for the Chief Financial Officer… And Other Paradoxes","year":2011,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Intellectual Capital and Performance Analysis","field":"Business, Management and Accounting","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":"Toronto Metropolitan University; Ministry of Health and Long Term Care","funders":"","keywords":"Return on investment; Officer; Region of interest; Finance; Investment (military); Computer science; Business; Economics; Artificial intelligence; Law; Political science","score_opus":0.07392816003349144,"score_gpt":0.2925710610319062,"score_spread":0.21864290099841477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1912672976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930923,0.00041794236,0.0003910697,0.0007167852,0.00038146073,0.00042595796,0.000002229218,0.0000073272718,0.0045649232],"genre_scores_gemma":[0.99741715,0.000029780485,0.00021152201,0.00093957887,0.0012412774,0.000024674655,0.0000034356244,0.00001184259,0.00012071581],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907845,0.000021363603,0.000321439,0.00010642795,0.0003472874,0.00012503336],"domain_scores_gemma":[0.9990101,0.0001280642,0.00044417568,0.00010248318,0.00030442962,0.000010764912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016918587,0.000114883565,0.00015090684,0.00019666257,0.00029868644,0.00006375655,0.00014003244,0.00004791281,0.0002559519],"category_scores_gemma":[0.00032767537,0.00006665586,0.00012185912,0.00016625931,0.000052039606,0.00052965863,0.000045781417,0.00012460015,0.000028231136],"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":[0.07210869,0.005169718,0.1495114,0.0016716835,0.002740816,0.00004692707,0.1021566,0.015078066,0.0054479567,0.0993208,0.117518626,0.4292287],"study_design_scores_gemma":[0.006325562,0.0012392107,0.17115264,0.0003182849,0.001831339,0.000031122243,0.003392514,0.73413676,0.00089535787,0.060909744,0.019215487,0.0005519562],"about_ca_topic_score_codex":0.00002767097,"about_ca_topic_score_gemma":0.000053571195,"teacher_disagreement_score":0.7190587,"about_ca_system_score_codex":0.000026567155,"about_ca_system_score_gemma":0.000039858885,"threshold_uncertainty_score":0.28024936},"labels":[],"label_agreement":null},{"id":"W1958376939","doi":"10.56645/jmde.v6i11.207","title":"Debating Professional Designations for Evaluators","year":2009,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Process (computing); Psychology; Political science; Sociology; Engineering ethics; Pedagogy; Computer science; Engineering","score_opus":0.3373365539722523,"score_gpt":0.5875076878738227,"score_spread":0.25017113390157036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1958376939","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9128692,0.00024368153,0.07229954,0.010476411,0.0018326549,0.0011468045,0.000007337244,0.000014545256,0.001109783],"genre_scores_gemma":[0.96894455,0.000009200168,0.029874012,0.00014855765,0.00045147652,0.00003439159,0.000013308761,0.000008480579,0.00051599846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922615,0.00079351483,0.0016943987,0.0002543337,0.0047758357,0.00022041217],"domain_scores_gemma":[0.9899909,0.0018789162,0.0017074401,0.00028147054,0.0060031833,0.00013812947],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03696182,0.00015148766,0.00031434486,0.00062124967,0.0005063645,0.00013901808,0.00049906236,0.00009280973,0.0007632069],"category_scores_gemma":[0.008092914,0.00010298167,0.00026559946,0.0006307475,0.000028721324,0.0012682946,0.00003737884,0.00019790817,0.00003998446],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064160576,0.000892545,0.010934904,0.000010242321,0.000060763417,0.0000022535507,0.007500732,0.12086389,0.018735198,0.0027448093,0.013029884,0.8245832],"study_design_scores_gemma":[0.0026137223,0.0010525789,0.18711813,0.00007884251,0.00011669784,0.000026815796,0.002565079,0.6972905,0.0011804441,0.1069339,0.0008625199,0.00016080253],"about_ca_topic_score_codex":3.2957482e-7,"about_ca_topic_score_gemma":0.0000051117568,"teacher_disagreement_score":0.82442236,"about_ca_system_score_codex":0.00027002295,"about_ca_system_score_gemma":0.0014708759,"threshold_uncertainty_score":0.99165046},"labels":[],"label_agreement":null},{"id":"W2165257846","doi":"10.56645/jmde.v11i25.433","title":"The \"Usability\" of Evaluation Reports: A Precursor to Evaluation Use in Government Organizations","year":2015,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada; Australian Government","keywords":"Summative assessment; Formative assessment; Government (linguistics); Public relations; Usability; Business; Treasury; Data collection; Thematic analysis; Program evaluation; Qualitative research; Psychology; Political science; Public administration; Computer science; Sociology","score_opus":0.29165285448490014,"score_gpt":0.5123901997387377,"score_spread":0.22073734525383754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165257846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9889758,0.00031322363,0.0028550143,0.0024235507,0.0015328017,0.0025047513,0.000008020618,0.0000059140903,0.0013808775],"genre_scores_gemma":[0.99617356,0.000023389275,0.0033185775,0.000035630506,0.00012457809,0.00013769077,0.000014060414,0.000015643322,0.0001568416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9743057,0.004122294,0.0036810185,0.0004513661,0.017171705,0.00026789747],"domain_scores_gemma":[0.9732037,0.0018211743,0.0038407054,0.00090200687,0.02000094,0.00023142587],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14191337,0.0001956673,0.00040056926,0.00043618502,0.00020908004,0.00019815937,0.0004622726,0.00010299572,0.0006723349],"category_scores_gemma":[0.095248975,0.00012772724,0.00013359773,0.0023116567,0.00008715726,0.0017213187,0.00018571029,0.00022591953,0.000040522074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082402903,0.0009453921,0.3233956,0.000008523831,0.000070342525,0.0000040442646,0.020664144,0.48450318,0.0018663296,0.000240195,0.0037779915,0.16370022],"study_design_scores_gemma":[0.001995044,0.0006626174,0.53359896,0.00008255702,0.00021970835,0.000039104292,0.008102494,0.43444344,0.0010282716,0.019201647,0.00048413035,0.00014204699],"about_ca_topic_score_codex":0.000033172382,"about_ca_topic_score_gemma":0.0008898177,"teacher_disagreement_score":0.21020333,"about_ca_system_score_codex":0.0020740733,"about_ca_system_score_gemma":0.0039006397,"threshold_uncertainty_score":0.9123721},"labels":[],"label_agreement":null},{"id":"W2311665238","doi":"10.56645/jmde.v12i26.437","title":"Book Review: Evaluating Communication for Development: A Framework for Social Change","year":2016,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Social change; Sociology; Political science","score_opus":0.5475983103789693,"score_gpt":0.6087747331216172,"score_spread":0.061176422742647896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2311665238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06497585,0.12928167,0.64005065,0.15402745,0.0020485595,0.009282116,0.000059833845,0.00004027705,0.00023361969],"genre_scores_gemma":[0.3089563,0.01563419,0.6481081,0.013614448,0.004150811,0.005398609,0.00014085228,0.00012927827,0.0038673973],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99364775,0.00083733245,0.0019318796,0.00027388215,0.0030616473,0.0002474873],"domain_scores_gemma":[0.9868597,0.0043407106,0.0026484374,0.00038544883,0.00567688,0.00008886378],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425866,0.0001710157,0.0004457327,0.00030151903,0.0006991327,0.00008067839,0.0006788276,0.00011923394,0.0012208633],"category_scores_gemma":[0.011538807,0.000102516904,0.00029846723,0.00033073852,0.000057831996,0.001472148,0.00011044194,0.00012987225,0.00004531691],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040224142,0.00015307481,0.000582914,0.0001234686,0.000055928514,1.257594e-7,0.0054708086,0.00004656855,0.00068622536,0.0007032807,0.07345148,0.9183239],"study_design_scores_gemma":[0.012908835,0.002293864,0.096926615,0.008351177,0.00081964955,0.000031373325,0.0016917037,0.09599756,0.0018413047,0.14750783,0.6307495,0.00088053755],"about_ca_topic_score_codex":2.8455054e-7,"about_ca_topic_score_gemma":0.0000049644486,"teacher_disagreement_score":0.91744334,"about_ca_system_score_codex":0.00038850043,"about_ca_system_score_gemma":0.0008374989,"threshold_uncertainty_score":0.99969214},"labels":[],"label_agreement":null},{"id":"W2527468053","doi":"10.56645/jmde.v2i2.131","title":"An Update on Evaluation in Canada","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Psychology","score_opus":0.19928177835078514,"score_gpt":0.5200236305055952,"score_spread":0.32074185215481005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527468053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900646,0.0001438624,0.00033647218,0.006594589,0.0008240904,0.00045332522,0.000004663811,0.0000035369533,0.0015748331],"genre_scores_gemma":[0.9976199,0.00002804698,0.001601378,0.0002949967,0.0003710942,0.000018547342,0.000016158085,0.000009661601,0.00004019902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98746514,0.001742262,0.0016770656,0.0002983282,0.008595182,0.00022200536],"domain_scores_gemma":[0.9950003,0.00052284193,0.0011671494,0.00046875997,0.0026793752,0.00016156488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.038977165,0.00015470931,0.00030001253,0.0006601571,0.00013613398,0.000102857,0.0005614682,0.00005729958,0.0032481744],"category_scores_gemma":[0.0016544543,0.00011270343,0.000082023034,0.0006610126,0.000021285769,0.0016513354,0.000036487072,0.00028795394,0.00012947542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015249154,0.00014623484,0.038615786,0.0000010099876,0.000006978877,0.0000024870785,0.000752893,0.5586497,0.00040791946,0.00005270478,0.001234282,0.39997748],"study_design_scores_gemma":[0.0015289213,0.00021704397,0.39366388,0.000025517968,0.000026385986,0.000010073101,0.0014377781,0.5999073,0.00037465367,0.002061993,0.000656168,0.0000902962],"about_ca_topic_score_codex":0.0069668232,"about_ca_topic_score_gemma":0.56667966,"teacher_disagreement_score":0.5597128,"about_ca_system_score_codex":0.002849146,"about_ca_system_score_gemma":0.0073863408,"threshold_uncertainty_score":0.9996459},"labels":[],"label_agreement":null},{"id":"W2553254625","doi":"10.56645/jmde.v12i27.454","title":"Debate on the Appropriate Methods for Conducting Impact Evaluation of Programs within the Development Context","year":2016,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Impact evaluation; Context (archaeology); Program evaluation; Computer science; Management science; Intervention (counseling); Impact assessment; Process management; Evaluation methods; Risk analysis (engineering); Psychology; Political science; Business; Engineering; Medicine","score_opus":0.6229679264758866,"score_gpt":0.6137793347535752,"score_spread":0.009188591722311457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553254625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9423179,0.00017759087,0.048267674,0.005905836,0.00090082665,0.0021947178,0.0000030839917,0.0000056180625,0.000226741],"genre_scores_gemma":[0.98133403,0.0000060917682,0.018143686,0.00004163829,0.00016110657,0.00019586844,0.0000036878334,0.000013808723,0.000100053716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9867742,0.00504862,0.0022749947,0.0002908922,0.005380057,0.00023124058],"domain_scores_gemma":[0.98128766,0.0063530956,0.0037430755,0.00051294564,0.008023367,0.000079851045],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19909209,0.00019636091,0.00036904853,0.0002604434,0.00049437507,0.00012657487,0.00071121927,0.00007742583,0.0004060477],"category_scores_gemma":[0.015513158,0.0000673592,0.00029359906,0.0004838099,0.00014337769,0.00063356216,0.000089848894,0.00018346816,0.000022909006],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038998207,0.00015418616,0.0026795752,0.0000048380143,0.00012454027,7.330209e-8,0.008254159,0.010419583,0.011445856,0.0003549402,0.00013155668,0.96604073],"study_design_scores_gemma":[0.0067610266,0.0019558806,0.07345316,0.00048636447,0.0005341875,0.00003306768,0.022764971,0.76465076,0.05936598,0.069183625,0.0005078907,0.00030307268],"about_ca_topic_score_codex":0.000002580683,"about_ca_topic_score_gemma":0.000032631557,"teacher_disagreement_score":0.96573764,"about_ca_system_score_codex":0.00049820496,"about_ca_system_score_gemma":0.002289622,"threshold_uncertainty_score":0.9927796},"labels":[],"label_agreement":null},{"id":"W2564563180","doi":"10.56645/jmde.v2i3.107","title":"Evaluation in Canada","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"World Bank Group","keywords":"Political science; Business","score_opus":0.23999870031305678,"score_gpt":0.5137436117701629,"score_spread":0.2737449114571061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564563180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98746866,0.0005236888,0.00045065334,0.006564054,0.00091076636,0.0004331495,0.0000025139352,0.0000024369049,0.0036440506],"genre_scores_gemma":[0.99760216,0.000030374305,0.0017966053,0.00010697563,0.0003287549,0.00001765416,0.0000049156124,0.000007198002,0.0001053523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9842972,0.0016375739,0.0018950865,0.00023754904,0.011718586,0.00021401215],"domain_scores_gemma":[0.9929475,0.0007047929,0.0012111575,0.00032268377,0.0046981694,0.00011565015],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.061072104,0.00012824949,0.00029265002,0.00056630623,0.000103659695,0.00007235225,0.0004630363,0.00004956297,0.0037616158],"category_scores_gemma":[0.0042766556,0.00009407204,0.00009366534,0.0007518908,0.000020858059,0.0012916261,0.00006143937,0.00024445434,0.00008532499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00005620988,0.000072948955,0.07212818,0.0000012956395,0.00001193035,0.0000022677325,0.0010194544,0.36309075,0.00035145818,0.000024021045,0.0020933542,0.5611481],"study_design_scores_gemma":[0.0014922902,0.00006583078,0.41661492,0.000023302882,0.000045368473,0.000017273474,0.0018171805,0.5760356,0.00023207012,0.00259726,0.0009834322,0.00007546236],"about_ca_topic_score_codex":0.015731765,"about_ca_topic_score_gemma":0.7698318,"teacher_disagreement_score":0.7541,"about_ca_system_score_codex":0.0038662492,"about_ca_system_score_gemma":0.0134458,"threshold_uncertainty_score":0.99995774},"labels":[],"label_agreement":null},{"id":"W2574130935","doi":"10.56645/jmde.v2i2.141","title":"Canadian Journal of Program Evaluation, Volume 19(2), Fall 2004","year":2005,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Volume (thermodynamics); Psychology; Physics; Thermodynamics","score_opus":0.22543288998314084,"score_gpt":0.5251932649418456,"score_spread":0.2997603749587048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574130935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713532,0.002738246,0.0030427335,0.016386501,0.0023983107,0.001437274,0.000011633008,0.000009595961,0.0026225592],"genre_scores_gemma":[0.98282766,0.0000556545,0.014790956,0.00012599041,0.0012697987,0.000031931242,0.000012955354,0.000018757255,0.00086627895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98604506,0.001627094,0.0031656963,0.0002775746,0.008487716,0.00039688428],"domain_scores_gemma":[0.97937226,0.00047278052,0.0036278274,0.00047401615,0.015364289,0.0006888162],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06369709,0.00023750316,0.00053613546,0.0015912163,0.00044837344,0.00039796124,0.0010218997,0.0001652243,0.005568292],"category_scores_gemma":[0.007507977,0.00017189891,0.0003927723,0.0010783639,0.000120716,0.0024137727,0.00005541645,0.00049956713,0.00026982112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013232867,0.00035656054,0.10523536,0.000006839627,0.00008291553,0.000009071239,0.0051799873,0.21776882,0.00020674609,0.00003910989,0.033926528,0.63705575],"study_design_scores_gemma":[0.0038764465,0.0012833365,0.33017465,0.000105314786,0.00036162863,0.0003483484,0.0031145017,0.59765434,0.00013645452,0.0065436596,0.056149818,0.0002515274],"about_ca_topic_score_codex":0.00025174275,"about_ca_topic_score_gemma":0.013134108,"teacher_disagreement_score":0.6368042,"about_ca_system_score_codex":0.0018102385,"about_ca_system_score_gemma":0.014269216,"threshold_uncertainty_score":0.99534076},"labels":[],"label_agreement":null},{"id":"W2576058593","doi":"10.56645/jmde.v3i4.77","title":"Taking Evaluation Contexts Seriously: A Cross-Cultural Evaluation in Extreme Unpredictability","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology; Sociology","score_opus":0.3547556918813846,"score_gpt":0.5431977453023824,"score_spread":0.1884420534209978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2576058593","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9875534,0.001057614,0.0010256598,0.0015182595,0.0017350232,0.0019761657,0.0000110293,0.00002000757,0.005102837],"genre_scores_gemma":[0.99762475,0.000020316556,0.0013124204,0.00003936384,0.00063397974,0.0001375618,0.00008782414,0.000020848554,0.00012292998],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97485805,0.0046717986,0.0040098256,0.0007250709,0.015263999,0.0004712826],"domain_scores_gemma":[0.9777062,0.0011591057,0.0039147753,0.0006744469,0.016401023,0.00014446834],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.117622264,0.00034730323,0.0006445102,0.0010335137,0.00041626795,0.0006114856,0.0007184701,0.00023087341,0.0049127396],"category_scores_gemma":[0.013225877,0.00026023228,0.00034373588,0.0015186587,0.00020798355,0.004420624,0.00014602368,0.0004993116,0.000098172226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040764068,0.0004851742,0.42600638,0.000011325831,0.000024514093,0.0000042630604,0.0025619625,0.3383353,0.0046365336,0.00011643283,0.00047251355,0.22693795],"study_design_scores_gemma":[0.004011939,0.00017700897,0.5174589,0.00007240122,0.00011492587,0.000029182285,0.0010775749,0.4588423,0.00026692223,0.017705169,0.00008835511,0.00015529017],"about_ca_topic_score_codex":0.000113622395,"about_ca_topic_score_gemma":0.0013410401,"teacher_disagreement_score":0.22678266,"about_ca_system_score_codex":0.0023145971,"about_ca_system_score_gemma":0.0024086596,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W2611404306","doi":"10.56645/jmde.v13i28.456","title":"The World of Evaluation: Challenges Faced by Student Evaluators","year":2017,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Sociology","score_opus":0.3297996531442704,"score_gpt":0.5830362193061646,"score_spread":0.25323656616189416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611404306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595702,0.006640609,0.00021209354,0.020232763,0.0027079037,0.0011541661,0.000009270266,0.0000065474323,0.009466401],"genre_scores_gemma":[0.9972107,0.0008620375,0.00041926515,0.000019243602,0.00030162346,0.00005439047,0.0000046726004,0.000014788938,0.0011132691],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98054487,0.0024092172,0.0024525865,0.00038067717,0.0139220115,0.00029062148],"domain_scores_gemma":[0.98254776,0.0020867898,0.0056429873,0.0014828179,0.008081329,0.00015830969],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.09773402,0.0002310224,0.00050943816,0.00039844264,0.0015133062,0.000496556,0.0018485875,0.00008882129,0.0011270139],"category_scores_gemma":[0.008137129,0.0001334005,0.000321104,0.00029461103,0.00025034754,0.0014797699,0.00034718693,0.00031903078,0.00006917878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005314693,0.0007191881,0.040327236,0.000017628035,0.0003071069,0.000002886709,0.008373955,0.019282859,0.0034758188,0.00094909006,0.01626585,0.9097469],"study_design_scores_gemma":[0.0045531644,0.0007230154,0.7414655,0.00013904682,0.00040823864,0.000018168495,0.010195237,0.21575132,0.0022514774,0.017216139,0.0070328224,0.0002458856],"about_ca_topic_score_codex":0.0000042579077,"about_ca_topic_score_gemma":0.00033917456,"teacher_disagreement_score":0.909501,"about_ca_system_score_codex":0.0003663333,"about_ca_system_score_gemma":0.0012422695,"threshold_uncertainty_score":0.9997866},"labels":[],"label_agreement":null},{"id":"W2797709357","doi":"10.56645/jmde.v14i30.501","title":"Customizing the Standard to the Purpose of the Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Psychology","score_opus":0.2134546959921358,"score_gpt":0.5487707242592667,"score_spread":0.33531602826713086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797709357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9189567,0.000109771456,0.014647754,0.05967933,0.002606291,0.0010075292,0.00000879224,0.000003888149,0.0029799698],"genre_scores_gemma":[0.9966023,0.000015550657,0.0021195777,0.0003085457,0.00059685874,0.000018712284,5.7027614e-7,0.000007635706,0.0003302536],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9903857,0.0017687633,0.0013150823,0.0001806289,0.006173948,0.00017588625],"domain_scores_gemma":[0.9920549,0.0012046146,0.0015685844,0.0008012665,0.004298581,0.00007205031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04721186,0.00012319227,0.00024838938,0.00017927476,0.0008100446,0.00017099433,0.0014531803,0.00004486865,0.00079548114],"category_scores_gemma":[0.0027026485,0.000044179975,0.00023113309,0.0009896084,0.00020511294,0.0004481355,0.00035631965,0.0002939054,0.00006713737],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011251178,0.0004226338,0.113124005,0.000014136906,0.00020359295,0.0000018583394,0.046912905,0.14468713,0.01312502,0.0027388025,0.07555421,0.6020906],"study_design_scores_gemma":[0.0015504512,0.0011071519,0.73840845,0.0001236672,0.00018517379,0.00003637719,0.012461375,0.201395,0.0033782145,0.010010527,0.031210853,0.00013274865],"about_ca_topic_score_codex":0.00000399215,"about_ca_topic_score_gemma":0.00012763738,"teacher_disagreement_score":0.62528443,"about_ca_system_score_codex":0.00025682923,"about_ca_system_score_gemma":0.0012600537,"threshold_uncertainty_score":0.9810959},"labels":[],"label_agreement":null},{"id":"W2798177048","doi":"10.56645/jmde.v14i30.477","title":"Evaluating Community Development Projects Using the OECD Evaluation Criteria","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Community Development and Social Impact","field":"Economics, Econometrics and Finance","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":"International Fund for Agricultural Development; Université Laval; UNICEF","keywords":"Program evaluation; Community development; Relevance (law); Psychological intervention; Sustainability; Strengths and weaknesses; Environmental planning; Intervention (counseling); Business; Environmental resource management; Evaluation methods; Economic growth; Political science; Engineering; Geography; Psychology; Public administration; Environmental science","score_opus":0.4724031975862495,"score_gpt":0.4691999126206124,"score_spread":0.0032032849656370987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798177048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99325645,0.0005268171,0.0018144737,0.0005039283,0.0010922682,0.0007271442,0.000004155103,0.000010906646,0.0020638537],"genre_scores_gemma":[0.9865964,0.000012514458,0.01279003,0.000049329803,0.00045145187,0.000018984521,0.000018207043,0.000020774967,0.000042289965],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99643993,0.0013329892,0.0013117376,0.00014224196,0.0005157976,0.0002573166],"domain_scores_gemma":[0.9963185,0.00028474722,0.0016105699,0.00038262628,0.0013305552,0.00007299817],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.037450932,0.00017761228,0.00034959087,0.00033348307,0.0018013164,0.00015692985,0.0004984448,0.00010191333,0.00072962977],"category_scores_gemma":[0.0016938042,0.0001510731,0.0001261707,0.00030579924,0.00014361416,0.0007011501,0.00023094025,0.00051043456,0.00008371556],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077214686,0.0019201278,0.08738582,0.00014794635,0.0009826343,0.0000037561342,0.55139107,0.0053958353,0.0135137765,0.0012804266,0.0016772916,0.33552918],"study_design_scores_gemma":[0.0026817482,0.00067044975,0.46358743,0.00016177614,0.00015706537,0.00003994255,0.01060495,0.49674487,0.0012826917,0.0233244,0.000351487,0.00039317395],"about_ca_topic_score_codex":0.00009576427,"about_ca_topic_score_gemma":0.00012817957,"teacher_disagreement_score":0.5407861,"about_ca_system_score_codex":0.0010727361,"about_ca_system_score_gemma":0.00079616724,"threshold_uncertainty_score":0.9994982},"labels":[],"label_agreement":null},{"id":"W2908468726","doi":"10.56645/jmde.v14i31.497","title":"Seeking Culturally Safe Developmental Evaluation: Supporting the Shift in Services for Indigenous Children","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University","funders":"Health Canada","keywords":"Indigenous; Participatory action research; Mainstream; Psychosocial; Traditional knowledge; Context (archaeology); Intervention (counseling); Citizen journalism; Community-based participatory research; Nursing; Sociology; Psychology; Medical education; Medicine; Political science; Geography; Psychotherapist","score_opus":0.1359810264428348,"score_gpt":0.4949917022111761,"score_spread":0.35901067576834134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908468726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920376,0.00019564632,0.0018693588,0.0027488025,0.000785093,0.0017072167,0.00000703115,0.0000067628216,0.0006425186],"genre_scores_gemma":[0.99392897,0.000010764853,0.004988817,0.00015675719,0.00073136785,0.000072624076,0.00003665345,0.0000125767565,0.000061452825],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9915394,0.0009352744,0.0020260985,0.00033048153,0.0048382278,0.0003304713],"domain_scores_gemma":[0.9930476,0.0008120599,0.002076857,0.00026956454,0.003707135,0.00008680556],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.056312807,0.00019219793,0.00031955543,0.000446208,0.00079067715,0.00030635466,0.0008510069,0.00009414906,0.0010168969],"category_scores_gemma":[0.0015895113,0.00011270109,0.00016697649,0.0007572734,0.000090610025,0.0014210998,0.00014955406,0.00023150274,0.00008264642],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003829511,0.00022252167,0.6181486,0.00001402192,0.00008863457,0.0000014965965,0.091939114,0.010685379,0.0015638154,0.00003289183,0.00031647162,0.27660406],"study_design_scores_gemma":[0.0020772498,0.00034977082,0.78273183,0.00008175994,0.00008753181,0.000058739628,0.011145844,0.19492055,0.00033676747,0.007876771,0.00019169766,0.00014148925],"about_ca_topic_score_codex":0.000019850566,"about_ca_topic_score_gemma":0.0009070319,"teacher_disagreement_score":0.27646255,"about_ca_system_score_codex":0.00061766116,"about_ca_system_score_gemma":0.0019038232,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W2945434485","doi":"10.56645/jmde.v15i32.513","title":"Communication for Social Change","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Deci-; Capacity building; Public relations; Political science; Knowledge management; Business; Computer science","score_opus":0.4924261702304836,"score_gpt":0.5826940578875175,"score_spread":0.09026788765703392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945434485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856999,0.00026842084,0.0022295127,0.008198777,0.0009391094,0.0010166653,0.0000067755027,0.000006264741,0.0016345578],"genre_scores_gemma":[0.9948933,0.000028903376,0.004010875,0.000108350694,0.00039527752,0.000050550025,0.000017517055,0.000008720059,0.00048648886],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99561864,0.00055359845,0.0009776225,0.00015311474,0.002565712,0.00013129842],"domain_scores_gemma":[0.99440616,0.0008718073,0.0013431086,0.00031065728,0.0030177638,0.00005050527],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022881348,0.000092626346,0.00025606496,0.00032254364,0.00023915368,0.00010314258,0.0005155214,0.00007341976,0.0012028703],"category_scores_gemma":[0.0008582454,0.00006663739,0.00020380424,0.00032805584,0.000029985542,0.0012494719,0.000081420134,0.00013769868,0.0001852765],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010975952,0.0006816748,0.11209722,0.000043255037,0.000102707025,6.485616e-7,0.038618006,0.0058883126,0.0059068743,0.0043867133,0.011270645,0.81990635],"study_design_scores_gemma":[0.003499868,0.00058157416,0.6264889,0.0000466118,0.00008027095,0.000011443477,0.0041201185,0.32666063,0.00023909533,0.029523138,0.008601354,0.00014696016],"about_ca_topic_score_codex":0.0000018349867,"about_ca_topic_score_gemma":0.000015182361,"teacher_disagreement_score":0.81975937,"about_ca_system_score_codex":0.00016887265,"about_ca_system_score_gemma":0.00029191453,"threshold_uncertainty_score":0.99971014},"labels":[],"label_agreement":null},{"id":"W2992263007","doi":"10.56645/jmde.v10i22.388","title":"Bioeconomic Models and the Formative Evaluation of Fisheries-Related Programs","year":2014,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Complex Systems and Decision Making","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":"Fisheries and Oceans Canada; Natural Resources Canada; Government of Canada; Canadian Forest Service","funders":"Fisheries and Oceans Canada; Government of Canada","keywords":"Formative assessment; Bioeconomics; Context (archaeology); Management science; Resource (disambiguation); Environmental resource management; Computer science; Fishery; Engineering; Sociology; Economics; Geography","score_opus":0.25010842456074567,"score_gpt":0.43412697988211113,"score_spread":0.18401855532136546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992263007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97645694,0.0009929567,0.01788135,0.000798756,0.00061862764,0.0008132627,0.0000018819788,0.0000048691063,0.0024313286],"genre_scores_gemma":[0.99871457,0.000008711282,0.0011070867,0.000009440591,0.000085144624,0.000017595963,0.0000014720066,0.000007760876,0.000048232414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9910994,0.0027618092,0.0022074077,0.00021870514,0.0035763304,0.00013634509],"domain_scores_gemma":[0.9905386,0.0022715162,0.0029735412,0.0004032632,0.003742301,0.000070803544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07442505,0.00013571723,0.0005184694,0.00035053835,0.00022853208,0.0001820907,0.00043801076,0.00007591626,0.000141534],"category_scores_gemma":[0.0042109056,0.00007193149,0.00022564344,0.00038789053,0.00023257128,0.00117446,0.00016727457,0.00016266256,0.000011653269],"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":[0.00080777396,0.0001371074,0.00413773,0.00001139401,0.000111140784,3.8860452e-7,0.022115989,0.16866693,0.00025110197,0.008629093,0.0007906223,0.7943407],"study_design_scores_gemma":[0.0033016591,0.00017766064,0.01841728,0.000053481977,0.000101739446,0.000032931268,0.002629644,0.63799024,0.000017326374,0.33717808,0.000045716846,0.000054219763],"about_ca_topic_score_codex":0.000012073999,"about_ca_topic_score_gemma":0.000028544768,"teacher_disagreement_score":0.7942865,"about_ca_system_score_codex":0.00010775459,"about_ca_system_score_gemma":0.00020796344,"threshold_uncertainty_score":0.9530742},"labels":[],"label_agreement":null},{"id":"W2992830025","doi":"10.56645/jmde.v11i25.406","title":"The Promise of Participatory Evaluation in Family-Centered Rehabilitation Settings: A Qualitative Study","year":2015,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Family and Disability Support Research","field":"Psychology","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":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Empowerment; Thematic analysis; Citizen journalism; Focus group; Participatory action research; Medical education; Qualitative research; Rehabilitation; Logic model; Psychological intervention; Service delivery framework; Psychology; Program evaluation; Nursing; Service (business); Medicine; Sociology; Political science; Social science; Business","score_opus":0.32055347795488726,"score_gpt":0.5440565552918495,"score_spread":0.22350307733696223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992830025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940596,0.00076666457,0.0000387231,0.0011978797,0.00064815616,0.0026904098,0.000005501872,0.000006097417,0.00058692426],"genre_scores_gemma":[0.9992683,0.0000028678205,0.00024727505,0.000008668593,0.00007806356,0.0003355932,0.000011046534,0.000013895412,0.00003429705],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98415333,0.010981152,0.0017198548,0.00025193664,0.0025939872,0.00029972903],"domain_scores_gemma":[0.993081,0.0023028785,0.000988288,0.0004330659,0.0030565828,0.00013821761],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07007644,0.00014995763,0.00034317016,0.00030484446,0.0001178321,0.000026732603,0.00028064067,0.0000936021,0.000076940094],"category_scores_gemma":[0.008443997,0.000106683234,0.00013177624,0.00048497441,0.00023832414,0.00040495538,0.00007992543,0.00033673344,0.000021100777],"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":[0.0042801225,0.004524321,0.16291574,0.00003588423,0.0001305207,0.0000053956696,0.80392903,0.0016752369,0.0010999871,0.000072068804,0.0016659137,0.019665768],"study_design_scores_gemma":[0.0053292424,0.0026129503,0.38502175,0.000058795747,0.000100856996,0.0000032662206,0.5949266,0.00792911,0.000031502434,0.0039027669,0.000013419648,0.00006972049],"about_ca_topic_score_codex":0.00009933499,"about_ca_topic_score_gemma":0.00021813934,"teacher_disagreement_score":0.22210602,"about_ca_system_score_codex":0.0006217187,"about_ca_system_score_gemma":0.0009414421,"threshold_uncertainty_score":0.9999083},"labels":[],"label_agreement":null},{"id":"W2994567589","doi":"10.56645/jmde.v13i28.462","title":"Translating Project Achievements into Strategic Plans: A Case Study in Utilization-Focused Evaluation","year":2017,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Process management; Program evaluation; Strategic planning; Management science; Engineering management; Business; Political science; Engineering; Public administration; Marketing","score_opus":0.6383590666042548,"score_gpt":0.6091607377580164,"score_spread":0.02919832884623841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994567589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935336,0.00011591861,0.0009634929,0.0008810454,0.00078786066,0.0025183454,0.0000061307505,0.000008322869,0.001185297],"genre_scores_gemma":[0.9977452,0.000013999273,0.0018762558,0.000012480999,0.0001813725,0.000104042025,0.00001411817,0.000016582688,0.00003590645],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98722184,0.0026646357,0.002483182,0.0004787017,0.0068858755,0.00026574792],"domain_scores_gemma":[0.99233377,0.0005140776,0.0030239057,0.0008478293,0.003177431,0.00010299824],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06284669,0.00024718296,0.00047326324,0.0010655824,0.0010645181,0.0007153057,0.0008495991,0.00011074107,0.0004268962],"category_scores_gemma":[0.0032782767,0.00018439103,0.00015408834,0.00057551975,0.0000728055,0.002836868,0.00012573319,0.0003680126,0.000022700176],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040621747,0.0015145864,0.5862045,0.000017302686,0.00008119552,0.0002621842,0.051615775,0.0469554,0.0005534938,0.000032445925,0.000041367635,0.31231552],"study_design_scores_gemma":[0.00665824,0.0008977189,0.31392455,0.000087943205,0.00016208642,0.00016546168,0.061092723,0.6107671,0.00003843828,0.0060330727,0.000008946207,0.00016371894],"about_ca_topic_score_codex":0.00028524216,"about_ca_topic_score_gemma":0.009234397,"teacher_disagreement_score":0.5638117,"about_ca_system_score_codex":0.0005173789,"about_ca_system_score_gemma":0.0022399146,"threshold_uncertainty_score":0.9649966},"labels":[],"label_agreement":null},{"id":"W2996945182","doi":"10.56645/jmde.v15i33.609","title":"Big Shoes to Fill: An Evaluation Journey in the Footsteps of Daniel L. Stufflebeam","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; Laurentian University","funders":"","keywords":"Context (archaeology); Relevance (law); Foundation (evidence); Intervention (counseling); Program evaluation; Evaluation methods; Sociology; Engineering ethics; Psychology; Engineering; History; Political science; Archaeology; Law","score_opus":0.3461999936431824,"score_gpt":0.5442462073245252,"score_spread":0.19804621368134284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996945182","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987825,0.00014714766,0.00087588996,0.005641827,0.0014034376,0.001475259,0.0000073366864,0.0000040719638,0.0026200463],"genre_scores_gemma":[0.997468,0.00002209572,0.0017057712,0.0002255411,0.0002815925,0.000034878783,0.000014403819,0.000012595932,0.000235154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.98433954,0.0033840016,0.0022643034,0.00035931705,0.00940001,0.00025286016],"domain_scores_gemma":[0.9910341,0.0010418227,0.0017282248,0.0007794129,0.005255705,0.00016076221],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.083693266,0.0001906544,0.00045942108,0.0010631362,0.00013960527,0.00017198309,0.0011411224,0.00010242072,0.0012769642],"category_scores_gemma":[0.005191211,0.00011221919,0.00017553942,0.0016512079,0.000043203363,0.0013220574,0.0001218168,0.000333397,0.000113705915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088125415,0.0013894276,0.19545482,0.000029802668,0.00006514984,0.0000040106574,0.05311293,0.38796318,0.017388893,0.00029376007,0.0070519913,0.33636478],"study_design_scores_gemma":[0.002722431,0.0018133548,0.60826784,0.00014222843,0.000106861466,0.00003266642,0.025462355,0.35343394,0.00079390244,0.0060657975,0.0009931654,0.00016547822],"about_ca_topic_score_codex":0.000012910015,"about_ca_topic_score_gemma":0.00021621844,"teacher_disagreement_score":0.412813,"about_ca_system_score_codex":0.000289168,"about_ca_system_score_gemma":0.0016128757,"threshold_uncertainty_score":0.999636},"labels":[],"label_agreement":null},{"id":"W2997715932","doi":"10.56645/jmde.v15i33.575","title":"Retrospective Pretest and Counterfactual Self-Report: Different or Same?","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Resilience and Mental Health","field":"Psychology","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":"Counterfactual thinking; Retrospective cohort study; Self-efficacy; Psychology; Research design; Randomized controlled trial; Clinical psychology; Medicine; Social psychology; Statistics; Mathematics; Internal medicine","score_opus":0.039221277550391995,"score_gpt":0.42136537496664705,"score_spread":0.38214409741625505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997715932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957346,0.00045579034,0.000038084476,0.00033112406,0.0015938224,0.00064163335,0.000004276913,0.000011868462,0.0011888511],"genre_scores_gemma":[0.99816775,0.00007934677,0.0002242984,0.000028530072,0.00020868723,0.000011611063,0.0000048823285,0.000013238252,0.0012616282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998072,0.00022540799,0.0005774722,0.00022906883,0.00069552695,0.00020048917],"domain_scores_gemma":[0.99861526,0.000104257306,0.00066876924,0.0002079422,0.00028098145,0.00012277042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014561409,0.0001367923,0.00029448504,0.00012627833,0.00009347365,0.000023911483,0.00010632293,0.00008913585,0.000874839],"category_scores_gemma":[0.00007831782,0.00008963793,0.00006289074,0.00009023193,0.000037447713,0.00029016004,0.000048828868,0.00024191845,0.000069416674],"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":[0.0031297663,0.0010372783,0.93354094,0.00008998202,0.00020887585,0.00016488499,0.031174153,0.00006359115,0.004116251,0.000114032824,0.00071660546,0.025643634],"study_design_scores_gemma":[0.0024208,0.0034451496,0.98401684,0.000125714,0.00011283266,0.0015319327,0.005686008,0.0018262678,0.00025970305,0.00039641338,0.00006259079,0.00011577407],"about_ca_topic_score_codex":0.000015272633,"about_ca_topic_score_gemma":0.000026420077,"teacher_disagreement_score":0.05047587,"about_ca_system_score_codex":0.00039185045,"about_ca_system_score_gemma":0.00017677895,"threshold_uncertainty_score":0.9578874},"labels":[],"label_agreement":null},{"id":"W2998328657","doi":"10.56645/jmde.v15i33.539","title":"Using Action Research to Build Evaluation Capacity in Public Health Organizations","year":2019,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"École Nationale d'Administration Publique","funders":"","keywords":"Capacity building; Public health; Action research; Qualitative research; Data collection; Action (physics); Program evaluation; Public relations; Medical education; Psychology; Political science; Sociology; Medicine; Nursing; Public administration; Pedagogy","score_opus":0.8641173841470653,"score_gpt":0.654224582662043,"score_spread":0.20989280148502232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998328657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523886,0.00008772983,0.008164819,0.012737199,0.0013491001,0.0017093526,0.000004199184,0.000007879612,0.00070085994],"genre_scores_gemma":[0.9921501,0.000024277755,0.007297126,0.00011201326,0.00024213344,0.000023050326,0.000013468288,0.000017341898,0.00012046417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9784869,0.006539054,0.0021638141,0.0004874468,0.01183186,0.0004909032],"domain_scores_gemma":[0.9824738,0.000997468,0.0012308883,0.0005626535,0.014445614,0.0002895573],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15076882,0.00015559653,0.0004026162,0.0028882367,0.00042480568,0.00031147854,0.0005842885,0.00011428499,0.00263456],"category_scores_gemma":[0.011875446,0.00012626244,0.000091369286,0.0054733,0.00004708282,0.0022514933,0.00017164843,0.00055754115,0.0004028584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013963581,0.00067706883,0.27806774,0.00002236143,0.000030211422,9.623441e-7,0.017886039,0.5484121,0.018448172,0.00050660875,0.0013433989,0.1344657],"study_design_scores_gemma":[0.0014056762,0.00044359028,0.3869733,0.00008482278,0.000013765985,0.000020697997,0.0074021146,0.5974493,0.0002675965,0.0051924717,0.00063404645,0.000112610964],"about_ca_topic_score_codex":0.00006654676,"about_ca_topic_score_gemma":0.0004910512,"teacher_disagreement_score":0.13889337,"about_ca_system_score_codex":0.0032132945,"about_ca_system_score_gemma":0.0058328053,"threshold_uncertainty_score":0.9998032},"labels":[],"label_agreement":null},{"id":"W3094330052","doi":"10.56645/jmde.v16i36.623","title":"Evaluation Policy and Organizational Evaluation Capacity Building: Application of an Ecological Framework across Cultural Contexts","year":2020,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Ottawa; Saudi Arabian Cultural Bureau; National Science Foundation","keywords":"Context (archaeology); Focus group; Conceptual framework; Capacity building; Situated; Government (linguistics); Public relations; Political science; Sociology; Psychology; Environmental resource management; Geography; Business; Social science; Marketing; Economics","score_opus":0.3125964842906351,"score_gpt":0.5461170546069485,"score_spread":0.2335205703163134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094330052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97057176,0.00024513644,0.021497244,0.0057881763,0.00032418332,0.0013550973,0.000024912666,0.0000155491,0.00017792713],"genre_scores_gemma":[0.98770034,0.00003241248,0.011099973,0.00023361319,0.00079757016,0.000053778775,0.00006103752,0.000016239104,0.000005018666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9842613,0.0030630566,0.002098303,0.00055337703,0.009757684,0.00026631713],"domain_scores_gemma":[0.9788213,0.0011756654,0.002711902,0.00037844942,0.016588299,0.0003244281],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047018927,0.0002522032,0.0005321215,0.00031270148,0.00041432978,0.00022015806,0.0005761835,0.0002551547,0.0007623515],"category_scores_gemma":[0.03256073,0.00018759759,0.00015006556,0.001444777,0.0002169879,0.0021026304,0.0001751958,0.00038169755,0.000024807308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071621506,0.0013536186,0.06529303,0.000045809094,0.00019532074,0.0000014924934,0.035586108,0.25231382,0.042152144,0.008398825,0.00022634421,0.5937173],"study_design_scores_gemma":[0.0019142635,0.0006469739,0.31865388,0.000026903703,0.00020471061,0.000023431603,0.0025482415,0.6175789,0.0013458222,0.056852903,0.00006047452,0.00014349892],"about_ca_topic_score_codex":0.000011885293,"about_ca_topic_score_gemma":0.00003619131,"teacher_disagreement_score":0.59357375,"about_ca_system_score_codex":0.00064685463,"about_ca_system_score_gemma":0.0017520146,"threshold_uncertainty_score":0.9812946},"labels":[],"label_agreement":null},{"id":"W3128096052","doi":"10.56645/jmde.v17i38.673","title":"Evaluation in Our New Normal Environment: Navigating the Challenges with Data Collection","year":2021,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Data collection; Credibility; Best practice; Data quality; Computer science; Quality (philosophy); Public relations; Data science; Risk analysis (engineering); Process management; Business; Political science; Marketing; Sociology","score_opus":0.36889537975502795,"score_gpt":0.5129477895526718,"score_spread":0.1440524097976439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128096052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9375741,0.005121533,0.0048239315,0.048995648,0.0008673664,0.0008753542,0.0000052607397,0.0000074477734,0.0017293703],"genre_scores_gemma":[0.9935388,0.0006560086,0.005102351,0.00005124969,0.0003981951,0.000019123794,0.00003513123,0.000012378691,0.00018676711],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9872029,0.0027331607,0.001297559,0.0004312875,0.008126257,0.00020883516],"domain_scores_gemma":[0.99495703,0.00065728516,0.0013196028,0.00089585636,0.0020692672,0.00010098754],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056888513,0.00016192821,0.00028346005,0.00021002864,0.00031744965,0.0001856446,0.00073520443,0.00007972737,0.0006514844],"category_scores_gemma":[0.0033782145,0.00009697505,0.0000729303,0.00079061254,0.000031737225,0.00187518,0.00027491344,0.00051157025,0.00005369027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002504083,0.0003263514,0.019247243,0.000007095569,0.00007899556,0.000014474197,0.010331347,0.23575391,0.0009699123,0.0000644438,0.0013649157,0.7315909],"study_design_scores_gemma":[0.002972607,0.00030622905,0.2702905,0.00015269528,0.00020530191,0.00015950589,0.022236917,0.6982861,0.00039358574,0.0044022496,0.0004629114,0.00013135554],"about_ca_topic_score_codex":0.000016087688,"about_ca_topic_score_gemma":0.0007146276,"teacher_disagreement_score":0.73145956,"about_ca_system_score_codex":0.0004788222,"about_ca_system_score_gemma":0.0033633339,"threshold_uncertainty_score":0.97113174},"labels":[],"label_agreement":null},{"id":"W4362503582","doi":"10.56645/jmde.v18i42.703","title":"How did conservation agriculture go to scale?","year":2022,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Agriculture and Rural Development Research","field":"Agricultural and Biological 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":"Business Development Bank of Canada; University of Guelph","funders":"Global Affairs Canada","keywords":"Food security; Conservation agriculture; Livelihood; Agriculture; Sustainable agriculture; Business; Environmental resource management; Promotion (chess); Economic growth; Agricultural economics; Geography; Economics; Political science","score_opus":0.04144172568117667,"score_gpt":0.2953618935618358,"score_spread":0.25392016788065913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362503582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.910901,0.00019356086,0.000023931078,0.08780132,0.0003335602,0.0004787962,0.000016351632,0.000013120724,0.00023836814],"genre_scores_gemma":[0.99623674,0.00002541592,0.00048063538,0.00019340366,0.000489116,0.000054021944,0.00012791454,0.0000010540462,0.0023916722],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9972951,0.0003774556,0.00034494363,0.00018916721,0.0015740322,0.00021930793],"domain_scores_gemma":[0.9986288,0.0001230108,0.0003270668,0.000041722553,0.00072716165,0.00015222371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019038396,0.00012970419,0.00018999948,0.000044963308,0.00067204103,0.00009890234,0.00034336047,0.000053370688,0.0005534075],"category_scores_gemma":[0.00012161921,0.000043371976,0.00013467632,0.00076776213,0.0000179011,0.000361378,0.00024442002,0.00030819234,0.000022068185],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027627498,0.0003572962,0.018762378,0.000007859289,0.000042668296,0.00001726892,0.001485488,0.00096257334,0.7739935,0.000051165254,0.10896205,0.09508147],"study_design_scores_gemma":[0.00045136636,0.0012265552,0.93931717,0.000026403659,0.000045247936,0.00014411774,0.0054870076,0.0005279924,0.0036281024,0.0007926307,0.048133496,0.00021988514],"about_ca_topic_score_codex":0.000016241222,"about_ca_topic_score_gemma":0.00012489682,"teacher_disagreement_score":0.9205548,"about_ca_system_score_codex":0.00025077208,"about_ca_system_score_gemma":0.000052872063,"threshold_uncertainty_score":0.60594237},"labels":[],"label_agreement":null},{"id":"W4362503601","doi":"10.56645/jmde.v18i42.721","title":"Competitive champions versus cooperative advocates","year":2022,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"","keywords":"Interview; Nonprobability sampling; Enthusiasm; Public relations; Extant taxon; Data collection; Sociology; Psychology; Knowledge management; Social psychology; Political science; Social science; Computer science","score_opus":0.2869313256836769,"score_gpt":0.5289861200793462,"score_spread":0.2420547943956693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362503601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710362,0.0004134076,0.0012521454,0.008196087,0.0039056032,0.00055841747,0.000034675464,0.00001261296,0.014590878],"genre_scores_gemma":[0.9979879,0.000028331962,0.0010046555,0.00007594457,0.00022706685,0.000051021965,0.000025977644,0.000009452207,0.0005896095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99126565,0.0018549076,0.0011412522,0.00024710203,0.005313955,0.00017713121],"domain_scores_gemma":[0.9936605,0.0017761617,0.0012352099,0.00029534654,0.0029200113,0.00011274487],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019955589,0.00013504164,0.00029997382,0.0005233706,0.0008899349,0.00010354823,0.0005844239,0.0000312115,0.009895207],"category_scores_gemma":[0.0021730533,0.000101375495,0.00018268873,0.0008998308,0.00007742024,0.00078257103,0.0003049395,0.00039781115,0.0001272857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042171753,0.0016309915,0.013382383,0.000006884534,0.00028431547,0.0000360195,0.040511973,0.7991644,0.0060691275,0.016854702,0.016333938,0.10150809],"study_design_scores_gemma":[0.014273812,0.006804482,0.1786221,0.000044581087,0.0002770003,0.00017980079,0.16448338,0.57801706,0.001802838,0.013945556,0.041016795,0.0005326016],"about_ca_topic_score_codex":0.0000027976998,"about_ca_topic_score_gemma":0.000030071264,"teacher_disagreement_score":0.22114736,"about_ca_system_score_codex":0.00051113527,"about_ca_system_score_gemma":0.0012950251,"threshold_uncertainty_score":0.9910099},"labels":[],"label_agreement":null},{"id":"W4362503613","doi":"10.56645/jmde.v18i42.711","title":"Empowerment Evaluation of Programs Involving Youth","year":2022,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Winnipeg","funders":"","keywords":"Empowerment; Participatory evaluation; Program evaluation; Youth empowerment; Citizen journalism; Psychology; Participatory action research; Intervention (counseling); Positive Youth Development; Set (abstract data type); Medical education; Applied psychology; Sociology; Computer science; Political science; Medicine; Social science; Developmental psychology","score_opus":0.39650484374405937,"score_gpt":0.526744258074393,"score_spread":0.1302394143303336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362503613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99378353,0.000773647,0.0005276538,0.00084155577,0.0015732676,0.0009886493,0.000011918129,0.0000075762205,0.0014922076],"genre_scores_gemma":[0.99828947,0.000020852543,0.001275581,0.000027207743,0.0001494126,0.0000740598,0.000041547533,0.0000127032645,0.000109175104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97514635,0.0037042464,0.0023683913,0.0003218361,0.018233227,0.00022593202],"domain_scores_gemma":[0.9894966,0.00038802737,0.0031301172,0.00047837663,0.006398164,0.00010873606],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.10131924,0.0001582994,0.0003915739,0.0007876208,0.0004493439,0.000088386114,0.00071529904,0.000047241287,0.0038870394],"category_scores_gemma":[0.0021979162,0.00012233981,0.0002765446,0.0011261263,0.00006567212,0.0008668402,0.0003327267,0.0003268559,0.000017943998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005280332,0.0015719543,0.096870266,0.000015420088,0.00012219006,0.000002854831,0.04659998,0.44026068,0.0048614973,0.00020987079,0.00086917495,0.40808806],"study_design_scores_gemma":[0.0042999336,0.0018352941,0.16526648,0.00006335345,0.0005017038,0.000040033745,0.07099652,0.74232435,0.0006566264,0.013475291,0.00033912784,0.00020125664],"about_ca_topic_score_codex":0.0000072806356,"about_ca_topic_score_gemma":0.000016669794,"teacher_disagreement_score":0.4078868,"about_ca_system_score_codex":0.00087455765,"about_ca_system_score_gemma":0.0020811493,"threshold_uncertainty_score":0.9970235},"labels":[],"label_agreement":null},{"id":"W4362504882","doi":"10.56645/jmde.v3i5.54","title":"Collaborative Evaluation","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Psychology","score_opus":0.14730919225055178,"score_gpt":0.5253125317131393,"score_spread":0.3780033394625875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362504882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748165,0.00078670494,0.004213102,0.003441431,0.0015172232,0.0007939289,0.000009881122,0.000010581687,0.0144106485],"genre_scores_gemma":[0.9947186,0.000020512321,0.0040534763,0.000037516947,0.0006436118,0.000031475887,0.000030766772,0.000010845931,0.00045319134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9861593,0.0019169484,0.0019087093,0.0002860645,0.009528342,0.0002006361],"domain_scores_gemma":[0.9838074,0.00086416793,0.0021487952,0.00038257072,0.012706706,0.00009034848],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.050346162,0.00016773789,0.0003466404,0.0006963146,0.00028478322,0.00022288364,0.00045942658,0.000095017,0.003099008],"category_scores_gemma":[0.0032558606,0.00011708064,0.0001845056,0.0013098383,0.000073304305,0.0015584317,0.00006950708,0.00020440893,0.00020232965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059586135,0.0009724667,0.09187198,0.000009473781,0.00009194232,0.0000099545405,0.0044530164,0.48171347,0.011499148,0.0021916085,0.042911854,0.36367923],"study_design_scores_gemma":[0.0028174652,0.000371452,0.43439582,0.00003401565,0.00017842236,0.000032848708,0.003101407,0.4888171,0.0014434598,0.06587128,0.0027742062,0.00016251742],"about_ca_topic_score_codex":0.000008795309,"about_ca_topic_score_gemma":0.00009838622,"teacher_disagreement_score":0.3635167,"about_ca_system_score_codex":0.0005028403,"about_ca_system_score_gemma":0.0019577865,"threshold_uncertainty_score":0.9978123},"labels":[],"label_agreement":null},{"id":"W4362504947","doi":"10.56645/jmde.v3i4.83","title":"American Evaluation Association","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association (psychology); Psychology; Psychotherapist","score_opus":0.16413093304957194,"score_gpt":0.5246990005505626,"score_spread":0.3605680675009907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362504947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98136115,0.00022863332,0.003196411,0.0051011024,0.0013491809,0.00052379136,0.0000049289947,0.0000131064635,0.008221703],"genre_scores_gemma":[0.9952995,0.000019324525,0.002866098,0.00005681981,0.0008128215,0.000024620927,0.000024965873,0.000012241907,0.0008836084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9835074,0.0020900518,0.0019788647,0.00029298855,0.011877532,0.00025315574],"domain_scores_gemma":[0.98515934,0.0012795589,0.004204542,0.00036813618,0.008896633,0.00009180347],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.066769734,0.0001657123,0.000396558,0.00071319315,0.00025795688,0.00023585696,0.00044741778,0.000083482286,0.001732419],"category_scores_gemma":[0.005915922,0.00012271844,0.000252252,0.0011895497,0.000054649827,0.0013578676,0.00006503518,0.00024917352,0.00025531513],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002062987,0.00051003974,0.40755993,0.0000040589957,0.00006624311,0.0000026836988,0.0011819277,0.16504379,0.0050277035,0.00035176397,0.023917213,0.39612836],"study_design_scores_gemma":[0.0015656418,0.0002873642,0.63077784,0.000017159771,0.00016942392,0.000013170086,0.0010981803,0.34245884,0.00050572044,0.020980109,0.0020020287,0.00012455412],"about_ca_topic_score_codex":0.00003373453,"about_ca_topic_score_gemma":0.00016762369,"teacher_disagreement_score":0.3960038,"about_ca_system_score_codex":0.0015328007,"about_ca_system_score_gemma":0.0011451944,"threshold_uncertainty_score":0.99918014},"labels":[],"label_agreement":null},{"id":"W4362505079","doi":"10.56645/jmde.v3i4.79","title":"Using Multivariate Techniques to Measure the Performance of R&D Programs: A Case Example","year":2006,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Efficiency Analysis Using DEA","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 Ottawa; Natural Sciences and Engineering Research Council of Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Multivariate statistics; Multivariate analysis; Statistics; Computer science; Econometrics; Mathematics; Data mining","score_opus":0.30978301106322964,"score_gpt":0.4677882252431006,"score_spread":0.15800521417987096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362505079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96097404,0.0002100648,0.0374086,0.00049046846,0.00019753064,0.0005922029,0.000003659021,0.000012682575,0.000110775545],"genre_scores_gemma":[0.9405008,0.0000022003128,0.059196524,0.000012995691,0.00020081528,0.000009972461,0.0000021119918,0.000012923813,0.000061650404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929303,0.0010985954,0.0017875266,0.0002998571,0.0036453814,0.00023832278],"domain_scores_gemma":[0.9926614,0.00076241256,0.0019008651,0.0006254437,0.003971886,0.00007797283],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02897136,0.00017536529,0.00041640867,0.0006976641,0.00044225855,0.00014227061,0.000667077,0.000086665656,0.000044331275],"category_scores_gemma":[0.0021768643,0.00010059719,0.00026726734,0.0018814036,0.00013515349,0.00058752927,0.00016644406,0.00023577109,0.000012969656],"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":[0.000545444,0.0011826295,0.044414002,0.000026279005,0.00009976257,0.00009158095,0.008701114,0.51933426,0.20586386,0.00008010549,0.0005110123,0.21914996],"study_design_scores_gemma":[0.0010148901,0.00083189306,0.047580026,0.00042914474,0.00051533664,0.0021742499,0.0022920151,0.9241222,0.017439688,0.0027440765,0.0005268101,0.000329681],"about_ca_topic_score_codex":0.0003553206,"about_ca_topic_score_gemma":0.0003108326,"teacher_disagreement_score":0.40478793,"about_ca_system_score_codex":0.0002077466,"about_ca_system_score_gemma":0.0003406902,"threshold_uncertainty_score":0.99987835},"labels":[],"label_agreement":null},{"id":"W4377141999","doi":"10.56645/jmde.v19i43.825","title":"The Program Evaluation Standards in Evaluation Scholarship and Practice","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scholarship; Medical education; Systematic review; Resource (disambiguation); Professional association; Political science; Psychology; Medicine; Sociology; Public relations; MEDLINE; Computer science","score_opus":0.42328942187289514,"score_gpt":0.6372998949468092,"score_spread":0.21401047307391402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377141999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9734507,0.001763823,0.00021842735,0.017093917,0.0013527339,0.0034755256,0.000006582515,0.000026115973,0.0026121337],"genre_scores_gemma":[0.9969889,0.000597044,0.0016140958,0.000048145408,0.00023283453,0.0003938515,0.00002138741,0.00001541432,0.00008831292],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.955358,0.012586404,0.0029896987,0.00060849084,0.027946489,0.00051088707],"domain_scores_gemma":[0.975273,0.0064484654,0.001822502,0.00049986265,0.015821937,0.00013420885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3790371,0.00018921962,0.00030380738,0.0009145065,0.0006558075,0.0006930978,0.00051360053,0.00012469664,0.00030262882],"category_scores_gemma":[0.09272421,0.000118499265,0.00012005241,0.002301801,0.0001309019,0.0030387952,0.00016730532,0.00047014348,0.00007268391],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004974358,0.00015674325,0.013649196,0.0000053589683,0.00003124994,0.0000031381408,0.0030796453,0.036530416,0.00035113463,0.00012647927,0.0012637111,0.9443055],"study_design_scores_gemma":[0.00246046,0.0004113656,0.40059668,0.000063229796,0.00016049205,0.000041488158,0.0071131275,0.5621546,0.00004350179,0.02296677,0.003887026,0.000101243],"about_ca_topic_score_codex":0.0000043579166,"about_ca_topic_score_gemma":0.00018286808,"teacher_disagreement_score":0.9442043,"about_ca_system_score_codex":0.0010710917,"about_ca_system_score_gemma":0.0034313856,"threshold_uncertainty_score":0.9149182},"labels":[],"label_agreement":null},{"id":"W4377142049","doi":"10.56645/jmde.v19i43.837","title":"The Integration of the Program Evaluation Standards into an Evaluation Toolkit for a Transformative Model of Care for Mental Health Service Delivery","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":0,"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":"Transformative learning; Mental health; Process management; Process (computing); Health care; Logic model; Service delivery framework; Computer science; Service (business); Knowledge management; Psychology; Business; Sociology; Pedagogy; Political science","score_opus":0.5826331380281115,"score_gpt":0.6905983737903973,"score_spread":0.1079652357622859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377142049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93281394,0.00018575578,0.015740426,0.023791568,0.0010004326,0.02556633,0.00083956675,0.000021818034,0.000040172992],"genre_scores_gemma":[0.98615664,0.000108117114,0.009111408,0.00027166787,0.00017212173,0.003802707,0.00033877787,0.00002575025,0.000012823673],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9888519,0.003991684,0.0025685024,0.00023401788,0.003912329,0.00044156009],"domain_scores_gemma":[0.97626466,0.0016490953,0.0032873896,0.00033931396,0.018329244,0.00013030252],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.05977577,0.0001774696,0.0003914659,0.00029861426,0.0023003255,0.000022601998,0.00043853314,0.00012314388,0.000020118081],"category_scores_gemma":[0.0036603946,0.00011165671,0.0001987368,0.00089511345,0.00010092231,0.001017149,0.00006867678,0.0002827493,0.0000011712432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016095402,0.00012645757,0.00035796672,0.0011493113,0.000056248602,9.808001e-9,0.4733142,0.06926936,0.0060282364,0.00023592376,0.0019192349,0.44593352],"study_design_scores_gemma":[0.004729926,0.0015626356,0.0068767304,0.0004885338,0.00018690263,6.4643683e-7,0.12524444,0.85518765,0.0009209247,0.004304712,0.00041019276,0.000086704575],"about_ca_topic_score_codex":0.00008886348,"about_ca_topic_score_gemma":0.0043393676,"teacher_disagreement_score":0.7859183,"about_ca_system_score_codex":0.0026610768,"about_ca_system_score_gemma":0.013383484,"threshold_uncertainty_score":0.9989985},"labels":[],"label_agreement":null},{"id":"W4384928951","doi":"10.56645/jmde.v19i44.779","title":"Decolonizing Evaluation of Indigenous Guidance and Counseling Approaches: A Review of Selected Evaluated Programs","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Educational and Psychological Assessments","field":"Psychology","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; Colonialism; Curriculum; Social connectedness; Medical education; Culturally sensitive; Sociology; Medicine; Psychology; Psychotherapist; Political science; Pedagogy; Social psychology; Ecology","score_opus":0.48693098882521013,"score_gpt":0.5408138259197823,"score_spread":0.0538828370945722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384928951","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021958912,0.97215843,0.000056054392,0.00007130672,0.0009150898,0.0045513553,0.00003190659,0.000017388273,0.0002395398],"genre_scores_gemma":[0.0024744524,0.99472475,0.0013669332,0.000009594484,0.00025166429,0.00062896276,0.0004212605,0.000062357474,0.000060052815],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9881525,0.0046974095,0.0035157055,0.0005202701,0.0027826624,0.00033143855],"domain_scores_gemma":[0.98622274,0.00092587894,0.006828967,0.00043136603,0.0054648328,0.00012622344],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.029899726,0.00044394296,0.0021694205,0.00056849385,0.00012180878,0.000020398995,0.00046533105,0.00043517162,0.00027374274],"category_scores_gemma":[0.0017195462,0.0003348546,0.00047249152,0.0018275728,0.00012885105,0.00017277194,0.00007975294,0.00062933005,0.00002118957],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006601748,0.0010875638,0.00035987401,0.039595302,0.0010692928,0.0000037320906,0.0039476845,0.00005988104,0.000004489815,0.00001722945,0.00022468469,0.9535642],"study_design_scores_gemma":[0.009043726,0.006330176,0.045939337,0.83790666,0.059103865,0.0013866888,0.005348267,0.009280958,0.0000057320913,0.0052397307,0.018279891,0.0021349795],"about_ca_topic_score_codex":0.000010111365,"about_ca_topic_score_gemma":0.0000065659215,"teacher_disagreement_score":0.95142925,"about_ca_system_score_codex":0.00045744114,"about_ca_system_score_gemma":0.0025356025,"threshold_uncertainty_score":0.99991035},"labels":[],"label_agreement":null},{"id":"W4384928989","doi":"10.56645/jmde.v19i44.785","title":"Decolonizing Science: Undoing the Colonial and Racist Hegemony of Western Science","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"African cultural and philosophical studies","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Stanford Bio-X; Max-Planck-Gesellschaft; Queen's University; McGill University","keywords":"Undoing; Hegemony; Decolonization; Colonialism; Indigenous; Sociology; Science studies; Epistemology; Postcolonialism (international relations); Social science; Political science; Law; Philosophy; Ecology","score_opus":0.10545789838779038,"score_gpt":0.43662876327912237,"score_spread":0.33117086489133196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384928989","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98388845,0.0003171635,0.000013604008,0.014258009,0.0004058359,0.00022215788,0.0000015926934,0.00000957409,0.0008836226],"genre_scores_gemma":[0.999324,0.00014432108,0.00015750258,0.000015260879,0.00030402577,0.0000037487816,2.2039963e-7,0.0000028383074,0.000048074253],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99724805,0.0001932144,0.0003470963,0.00014156636,0.0018248712,0.00024521898],"domain_scores_gemma":[0.997827,0.00041049457,0.00042704202,0.00007745243,0.0011536245,0.00010438175],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.012532996,0.000069193535,0.0001583494,0.00018568205,0.002810765,0.00010072283,0.0004159151,0.000030492183,0.000009319764],"category_scores_gemma":[0.0020524487,0.000040893825,0.00004843995,0.0017687699,0.0031998907,0.0006626009,0.00025760607,0.000141361,0.0000045517345],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045258147,0.00028896343,0.27120396,0.0000747501,0.00009986405,0.000029814453,0.54846126,0.005432957,0.08343551,0.020338781,0.00045065364,0.06973087],"study_design_scores_gemma":[0.0007779866,0.00037580647,0.9346602,0.00012872819,0.000104180064,0.000017386496,0.02815542,0.008112207,0.00076219236,0.026283076,0.00047074622,0.00015206677],"about_ca_topic_score_codex":0.00005427994,"about_ca_topic_score_gemma":0.00018547682,"teacher_disagreement_score":0.66345626,"about_ca_system_score_codex":0.00022136622,"about_ca_system_score_gemma":0.00079914654,"threshold_uncertainty_score":0.99951285},"labels":[],"label_agreement":null},{"id":"W4384929312","doi":"10.56645/jmde.v19i44.773","title":"Decolonizing Evaluation of Indigenous Land-Based Programs: A Settler Perspective on What We Can Learn from the LANDBACK Movement","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aurora College","funders":"","keywords":"Indigenous; Sovereignty; Perspective (graphical); Land rights; Sociology; Environmental ethics; Political science; Ecology; Law; Ethnology; Computer science; Politics; Artificial intelligence","score_opus":0.30421046055774864,"score_gpt":0.5120849863126739,"score_spread":0.2078745257549252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384929312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9741374,0.00068457273,0.00017318633,0.022527225,0.00092132133,0.0013516451,0.000019331643,0.000015315267,0.00016995592],"genre_scores_gemma":[0.99866277,0.00021457902,0.00043694896,0.00018295721,0.00027187561,0.000081913924,0.000064573695,0.000016266004,0.000068090776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98762524,0.0022369607,0.0012191335,0.00033915872,0.008324793,0.00025471262],"domain_scores_gemma":[0.99046504,0.0019662431,0.0016719111,0.00048529575,0.005317609,0.0000939223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03766251,0.00019087367,0.00035573725,0.00050433935,0.00037849,0.00029712325,0.0005608976,0.00009801366,0.0005376642],"category_scores_gemma":[0.002367873,0.000113001,0.00023121579,0.0011821409,0.000080852355,0.00071258866,0.00009091457,0.00031280066,0.0001210315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005670809,0.00058389525,0.11475793,0.00000895101,0.0001737145,0.000004548927,0.05583861,0.4551748,0.0008007975,0.00004571433,0.0011857799,0.37085816],"study_design_scores_gemma":[0.003324469,0.00096681796,0.42402604,0.00031982228,0.0002533458,0.000001985306,0.053919833,0.4963037,0.0007609843,0.019830396,0.00015518077,0.00013741448],"about_ca_topic_score_codex":0.00009190908,"about_ca_topic_score_gemma":0.00113473,"teacher_disagreement_score":0.37072074,"about_ca_system_score_codex":0.0009722608,"about_ca_system_score_gemma":0.0020851202,"threshold_uncertainty_score":0.99092895},"labels":[],"label_agreement":null},{"id":"W4384932226","doi":"10.56645/jmde.v19i44.809","title":"Steps Toward Evaluation as Decluttering: Learnings from Hawaiian Epistemology","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Indigenous; CLARITY; Negotiation; Epistemology; Identity (music); Field (mathematics); Meaning (existential); Sociology; Social science; Aesthetics; Philosophy; Ecology","score_opus":0.35745616972763433,"score_gpt":0.5449069672074174,"score_spread":0.18745079747978305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384932226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813511,0.00023716617,0.002211588,0.010452098,0.0025117001,0.0006487091,0.000008714718,0.00004124151,0.002537724],"genre_scores_gemma":[0.9966856,0.00007483596,0.0016021471,0.00013232665,0.000580223,0.000044510958,0.00008238774,0.000024250168,0.00077367615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.985773,0.0026960995,0.002140015,0.0005199294,0.008506575,0.0003643326],"domain_scores_gemma":[0.990879,0.0019265942,0.0021539184,0.0005576487,0.0042621014,0.00022073604],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.050227974,0.00024308018,0.0005283382,0.0011605405,0.0003717786,0.00025668743,0.0008014199,0.0001839803,0.0058781244],"category_scores_gemma":[0.00818814,0.0001863408,0.0002938974,0.0013968397,0.0000959228,0.0013345188,0.0002509413,0.000417603,0.0025515703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068102207,0.0002687024,0.10150862,0.000016630289,0.00018617905,0.00004756739,0.022499379,0.18224514,0.013622812,0.00020718496,0.011314478,0.66740227],"study_design_scores_gemma":[0.0022708313,0.0005174312,0.4593824,0.00006568663,0.00016855124,0.000051416395,0.009611815,0.48951688,0.0005067382,0.03566944,0.0020520135,0.00018678377],"about_ca_topic_score_codex":0.000039914972,"about_ca_topic_score_gemma":0.00006203009,"teacher_disagreement_score":0.6672155,"about_ca_system_score_codex":0.0005057035,"about_ca_system_score_gemma":0.001506878,"threshold_uncertainty_score":0.99822503},"labels":[],"label_agreement":null},{"id":"W4386812791","doi":"10.56645/jmde.v19i45.701","title":"Excessive Evaluation Anxiety (XEA): The Last Two Decades","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Problem Solving Skills Development","field":"Health Professions","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 Ottawa","funders":"","keywords":"Stakeholder; Scopus; Anxiety; Psychology; Thematic analysis; Intervention (counseling); Inclusion (mineral); Resistance (ecology); Applied psychology; Public relations; Political science; Social psychology; Sociology; MEDLINE; Social science; Qualitative research","score_opus":0.11949339892396017,"score_gpt":0.4969720774571387,"score_spread":0.3774786785331785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386812791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98479044,0.0006394651,0.00057779107,0.0076174196,0.002968833,0.0020800133,0.0000073274973,0.00006922233,0.0012495132],"genre_scores_gemma":[0.99616766,0.00030896108,0.001678338,0.00015124991,0.0009399792,0.00031736644,0.0000581273,0.000038481267,0.0003398429],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9919956,0.0031533204,0.0014252065,0.00027413116,0.0026501208,0.00050165126],"domain_scores_gemma":[0.99328166,0.0014708075,0.001721762,0.00038406614,0.0030053677,0.00013634152],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.024635179,0.00021678097,0.00031914157,0.00039631987,0.0014777541,0.00003104787,0.0004717688,0.00016662471,0.0005267449],"category_scores_gemma":[0.0030956154,0.00014122808,0.00015827562,0.0009960826,0.00007867821,0.00056216004,0.00030546315,0.00088997895,0.0005880278],"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":[0.0005148977,0.00038892345,0.5318592,0.00028208052,0.00046953125,0.000025465011,0.099741876,0.078727424,0.013180015,0.00036927854,0.07833081,0.1961105],"study_design_scores_gemma":[0.0043718196,0.00015023092,0.85050154,0.0007621192,0.00035225225,0.000030744148,0.009574588,0.121274926,0.00025661316,0.011580738,0.00091532787,0.00022910447],"about_ca_topic_score_codex":0.000016360964,"about_ca_topic_score_gemma":0.00019878647,"teacher_disagreement_score":0.31864235,"about_ca_system_score_codex":0.0011545232,"about_ca_system_score_gemma":0.002336603,"threshold_uncertainty_score":0.9998222},"labels":[],"label_agreement":null},{"id":"W4386812841","doi":"10.56645/jmde.v19i45.743","title":"The Evaluation of Equity-Focused Community Coalitions: A Review of the Empirical Literature","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Community Health and Development","field":"Health Professions","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":"CLARITY; Framing (construction); Equity (law); Sociology; Scope (computer science); Empirical research; Public relations; Engineering ethics; Management science; Political science; Epistemology; Computer science; Economics; Engineering","score_opus":0.7978476605117001,"score_gpt":0.6764633025978322,"score_spread":0.12138435791386792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386812841","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005825476,0.98572236,0.000011362231,0.0037171706,0.0017798156,0.0074571827,0.00012119678,0.000012805181,0.00059552863],"genre_scores_gemma":[0.00015640238,0.9982248,0.00019309267,0.00017205009,0.0002755198,0.00057732407,0.0002233757,0.000043878732,0.00013358869],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.93489945,0.054868657,0.005471089,0.00017083871,0.0041675526,0.00042239885],"domain_scores_gemma":[0.968234,0.01239948,0.00915282,0.001522044,0.008529922,0.00016170938],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.116450205,0.00036842778,0.0019665156,0.00035407936,0.002676689,0.000017381866,0.0015274243,0.0005077192,0.00012694803],"category_scores_gemma":[0.02250002,0.0001866222,0.00096844597,0.0018267871,0.00019017086,0.00018337482,0.0014081015,0.0047404813,0.000027309337],"study_design_candidate":"systematic_review","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":[0.00007065956,0.00030876257,0.000069559275,0.202573,0.0002707292,6.543034e-7,0.010092418,0.000015290465,4.992094e-7,0.00008044061,0.014425184,0.7720928],"study_design_scores_gemma":[0.0017106469,0.00028720766,0.005029739,0.7580544,0.005019798,0.00003039616,0.00345072,0.0005770497,3.9937962e-7,0.0068832557,0.21871339,0.00024303645],"about_ca_topic_score_codex":0.000033266144,"about_ca_topic_score_gemma":0.00025237308,"teacher_disagreement_score":0.77184975,"about_ca_system_score_codex":0.0017332104,"about_ca_system_score_gemma":0.01705914,"threshold_uncertainty_score":0.9986217},"labels":[],"label_agreement":null},{"id":"W4386813275","doi":"10.56645/jmde.v19i45.739","title":"We Can’t Hear You – You’re on Mute: Findings From a Review of Evaluation Capacity Building (ECB) Practice Online","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Capacity building; Intervention (counseling); Descriptive statistics; Data collection; Medical education; Modalities; Computer science; The Internet; Coronavirus disease 2019 (COVID-19); Work (physics); Psychology; Sociology; Political science; Medicine; World Wide Web; Engineering; Social science; Statistics","score_opus":0.6006527710065875,"score_gpt":0.6003414472637132,"score_spread":0.0003113237428743476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386813275","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041351994,0.9792918,0.00021963807,0.009008336,0.0029019935,0.003608176,0.000547696,0.000026679847,0.00026049936],"genre_scores_gemma":[0.00041065563,0.9918234,0.0056611355,0.00020913917,0.0009359212,0.00013268762,0.00053628744,0.00008088018,0.00020992832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9672694,0.00806033,0.006882126,0.0010016978,0.01634272,0.00044368557],"domain_scores_gemma":[0.9692913,0.0085964175,0.011712356,0.0013367567,0.008774157,0.00028900878],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.091738194,0.0007417793,0.0033150262,0.001782122,0.0003618844,0.00019654538,0.0013035808,0.0004938079,0.0021089665],"category_scores_gemma":[0.04437036,0.000518566,0.0014240745,0.002823403,0.000121873505,0.001488222,0.00034754447,0.0014962554,0.0002843016],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012895667,0.000632965,0.00003608277,0.007912749,0.00046223376,0.000014539543,0.001991909,0.0023267874,0.000014746469,0.000035090412,0.008121221,0.97832274],"study_design_scores_gemma":[0.0034903404,0.0019171318,0.0015985084,0.3428222,0.014469063,0.00021537668,0.0041723144,0.058067266,0.000024026518,0.00473634,0.5672829,0.001204525],"about_ca_topic_score_codex":0.000048841244,"about_ca_topic_score_gemma":0.00007999692,"teacher_disagreement_score":0.9771182,"about_ca_system_score_codex":0.0019539306,"about_ca_system_score_gemma":0.0058782757,"threshold_uncertainty_score":0.99975747},"labels":[],"label_agreement":null},{"id":"W4389672983","doi":"10.56645/jmde.v19i46.971","title":"Building Spaces for Dialogues to Rethink Evaluator Competencies: Lessons from the Webinars Organized by the Evaluation Centre for Complex Health Interventions","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychological intervention; General partnership; Sustainability; Political science; Public relations; Capacity building; Diversity (politics); Sociology; Engineering ethics; Psychology; Engineering","score_opus":0.48782107023075144,"score_gpt":0.5796790978903889,"score_spread":0.09185802765963741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389672983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59371746,0.0009798642,0.06203971,0.3342324,0.0023998101,0.0059649525,0.00059574813,0.000041285894,0.000028749773],"genre_scores_gemma":[0.97089833,0.00012593331,0.025886834,0.000873149,0.0007850747,0.00047245508,0.00056636403,0.00004302751,0.00034882207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9880425,0.003295754,0.0022311574,0.00051438453,0.005463848,0.00045236733],"domain_scores_gemma":[0.9805071,0.0102375755,0.0023574638,0.0006663407,0.006035125,0.00019643568],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08628207,0.0002617324,0.0005913465,0.00037806336,0.0018351389,0.0005200599,0.0012747329,0.00009390596,0.00059633557],"category_scores_gemma":[0.017330427,0.00014511762,0.00057027803,0.0014047336,0.00011542993,0.00065312255,0.0002419302,0.0002642117,0.00008261446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008063603,0.00037993246,0.003163186,0.000055621353,0.00032040878,3.781619e-7,0.04256512,0.061347988,0.01423991,0.0011346529,0.6319903,0.24399616],"study_design_scores_gemma":[0.004473466,0.0009183857,0.07942727,0.00036119996,0.00045135632,0.000005364103,0.033144064,0.8088829,0.00029972746,0.054630227,0.01717115,0.00023491791],"about_ca_topic_score_codex":0.000043155793,"about_ca_topic_score_gemma":0.00062917924,"teacher_disagreement_score":0.7475349,"about_ca_system_score_codex":0.0006926871,"about_ca_system_score_gemma":0.0016965808,"threshold_uncertainty_score":0.99946433},"labels":[],"label_agreement":null},{"id":"W4389686269","doi":"10.56645/jmde.v19i46.969","title":"Rethinking Evaluator Competencies in an Age of Discontinuity – Implications of Inequities, Sustainability and the Pandemic for Training Evaluators: An Introduction to a Special Volume","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pandemic; Sustainability; Coronavirus disease 2019 (COVID-19); Sociology; Psychology; Political science; Engineering ethics; Medicine; Engineering; Biology; Ecology","score_opus":0.2642530573592116,"score_gpt":0.5106165978136467,"score_spread":0.24636354045443504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98515326,0.000050276896,0.0032827477,0.00918938,0.00049886573,0.0017650797,0.000028029035,0.000009902108,0.000022456994],"genre_scores_gemma":[0.99568963,0.000018994646,0.0030595388,0.000020097668,0.0009980089,0.0001132053,0.000041779753,0.000011404649,0.000047331192],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9921766,0.0023410767,0.0022804714,0.0003908828,0.0025593562,0.0002515939],"domain_scores_gemma":[0.991218,0.001786584,0.0016158052,0.0005604773,0.0047032055,0.00011596331],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08981225,0.0001582579,0.0006476411,0.00082723226,0.0002692367,0.00009795136,0.0005534426,0.00008795942,0.00011934169],"category_scores_gemma":[0.013254697,0.000105619205,0.00015877138,0.0012694956,0.00039252202,0.0013405839,0.00016291854,0.00022689199,0.0000011121123],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031471094,0.0004273737,0.27991113,0.00010377578,0.00006027241,8.894615e-7,0.33932143,0.10991984,0.011998098,0.0058049955,0.0004692042,0.24883586],"study_design_scores_gemma":[0.0024201728,0.0007929274,0.5547088,0.000039083978,0.000088778055,0.0000065538457,0.05065106,0.21928023,0.000055150173,0.17177342,0.00009238653,0.0000914781],"about_ca_topic_score_codex":0.000024258694,"about_ca_topic_score_gemma":0.0013046855,"teacher_disagreement_score":0.2886704,"about_ca_system_score_codex":0.000389264,"about_ca_system_score_gemma":0.0015053024,"threshold_uncertainty_score":0.9950571},"labels":[],"label_agreement":null},{"id":"W4389686508","doi":"10.56645/jmde.v19i46.893","title":"In Plain Sight or Just Plain Obscured?: A Review of Professional Evaluation Associations’ Frameworks for Evaluation Practice Supporting Equity, Diversity and Inclusion (EDI)","year":2023,"lang":"en","type":"review","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Inclusion (mineral); Equity (law); Professional development; Diversity (politics); Presentation (obstetrics); Psychology; Medical education; Pedagogy; Political science; Medicine","score_opus":0.5524989813377544,"score_gpt":0.6559057552488365,"score_spread":0.1034067739110821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686508","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023558047,0.97348636,0.00092701206,0.0053871647,0.0044613234,0.012947388,0.00021320401,0.000018290282,0.00020346078],"genre_scores_gemma":[0.0039156186,0.9905691,0.00282873,0.00018070874,0.0008953361,0.0006753307,0.0006814814,0.000058316662,0.00019537257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95092255,0.014424432,0.008913349,0.0011288899,0.023932712,0.0006780382],"domain_scores_gemma":[0.94518626,0.020781595,0.017649569,0.00067679957,0.015484086,0.00022166282],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31691056,0.00056866766,0.002625308,0.0019089653,0.002522973,0.00012407046,0.001235999,0.0009848885,0.00088429655],"category_scores_gemma":[0.14731929,0.00039129274,0.00073849206,0.0026778728,0.00010456747,0.002784206,0.008485941,0.0015191116,0.000019102199],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043922724,0.00074793986,0.00027589835,0.015305371,0.0002969877,0.000008203097,0.011348998,0.0014194138,0.000004191086,0.00007849206,0.0058936453,0.96418166],"study_design_scores_gemma":[0.014767063,0.0023107608,0.006568525,0.2561881,0.022296961,0.00021069832,0.00989009,0.57657784,0.00000981687,0.03924856,0.070271775,0.0016598135],"about_ca_topic_score_codex":0.000014813881,"about_ca_topic_score_gemma":0.00015135073,"teacher_disagreement_score":0.9625218,"about_ca_system_score_codex":0.0029367865,"about_ca_system_score_gemma":0.009255413,"threshold_uncertainty_score":0.9998539},"labels":[],"label_agreement":null},{"id":"W4389686746","doi":"10.56645/jmde.v19i46.881","title":"Glocal Evaluation Competencies for Learning As We Go: Zooming in and zooming out to connect system-level solutions to local beneficiaries","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University; Canadian Evaluation Society","funders":"","keywords":"Glocalization; Perspective (graphical); Beneficiary; Zoom; Knowledge management; Adaptation (eye); Computer science; Psychology; Business; Artificial intelligence; Political science; Engineering; Globalization","score_opus":0.4029661667108118,"score_gpt":0.5222759465913903,"score_spread":0.1193097798805785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389686746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88381404,0.0002803104,0.10382751,0.009085377,0.0011136907,0.0016276402,0.0000149621565,0.00002976219,0.00020668881],"genre_scores_gemma":[0.98980224,0.00003085094,0.009435663,0.00006489865,0.00022657774,0.00018347865,0.000020341951,0.000019961013,0.00021601004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920462,0.0011359656,0.0017799952,0.00046944065,0.0041228095,0.00044561614],"domain_scores_gemma":[0.9926208,0.0028839738,0.00078909984,0.00025402042,0.0032104491,0.00024165468],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04928083,0.00022563753,0.00053068716,0.0016113017,0.00078364555,0.0002892465,0.00036490214,0.000119790486,0.00010243789],"category_scores_gemma":[0.009994521,0.00018658458,0.00014985986,0.0013077897,0.000055601588,0.0008626751,0.00027057025,0.00027310182,0.00023491576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004436224,0.00006876039,0.007457181,0.00004209575,0.000033938075,0.0000038629205,0.023582777,0.7740499,0.0053216303,0.0006949222,0.000732809,0.18756852],"study_design_scores_gemma":[0.0018057653,0.00075560616,0.0825835,0.00041493052,0.00008434526,0.000021100883,0.07144132,0.83811575,0.00015985416,0.0039765527,0.00043730414,0.00020397933],"about_ca_topic_score_codex":0.00002731569,"about_ca_topic_score_gemma":0.0013111486,"teacher_disagreement_score":0.18736453,"about_ca_system_score_codex":0.0009541228,"about_ca_system_score_gemma":0.0011220343,"threshold_uncertainty_score":0.9983447},"labels":[],"label_agreement":null},{"id":"W4394973106","doi":"10.56645/jmde.v19i45.947","title":"In Memoriam - Chris Coryn","year":2023,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Legal case studies and regulations","field":"Social 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":"McKnight Foundation; Eli Lilly and Company; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Sociology; Theology; Psychology; Philosophy","score_opus":0.07754206848215654,"score_gpt":0.4367946990376323,"score_spread":0.35925263055547574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394973106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96966654,0.0003467751,0.00003400172,0.017735014,0.004347224,0.00029381417,0.0000022833724,0.000018189676,0.0075561833],"genre_scores_gemma":[0.99659055,0.0003294167,0.00021126309,0.000016255679,0.0017836848,0.0000073761717,0.0000028748448,0.0000059078334,0.0010526709],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99820423,0.0003294649,0.0003572155,0.0000810548,0.00085874234,0.00016931887],"domain_scores_gemma":[0.99904144,0.00018390303,0.00023609545,0.00006970592,0.0004070723,0.00006180604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050994325,0.00005608864,0.00013649145,0.00027319242,0.00040806737,0.00002403005,0.00010836465,0.000057190704,0.00018257578],"category_scores_gemma":[0.0005915412,0.000046055084,0.00008490763,0.00076672353,0.00008865942,0.00044740358,0.000043951273,0.00012588226,0.000050281364],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053610676,0.00091479707,0.06250708,0.00007725529,0.00023946224,0.0005003427,0.51250565,0.08101654,0.002920415,0.013302326,0.27247813,0.053001888],"study_design_scores_gemma":[0.0037849995,0.00037120096,0.7770542,0.00017551005,0.00016290128,0.000023268656,0.07454868,0.03720091,0.00008267902,0.025663905,0.0806011,0.00033062257],"about_ca_topic_score_codex":0.00012689525,"about_ca_topic_score_gemma":0.00089159707,"teacher_disagreement_score":0.71454716,"about_ca_system_score_codex":0.00024661934,"about_ca_system_score_gemma":0.00034961157,"threshold_uncertainty_score":0.31385654},"labels":[],"label_agreement":null},{"id":"W4399921253","doi":"10.56645/jmde.v20i47.999","title":"Canadian Evaluation Society Tribute to Dr. Michael Scriven","year":2024,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Evaluation Society","funders":"","keywords":"Tribute; Political science; Sociology; Art; Media studies; Law","score_opus":0.23073699912654302,"score_gpt":0.5334483235436518,"score_spread":0.3027113244171088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399921253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8708482,0.0024226618,0.01210067,0.10523491,0.0054885736,0.0015768494,0.000058750407,0.000031067826,0.0022383514],"genre_scores_gemma":[0.99329364,0.00006377081,0.003452295,0.0003512015,0.0007438724,0.000050627386,0.000039989976,0.000021334386,0.0019832822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98955035,0.00095481647,0.0015377916,0.0004396861,0.0071595013,0.0003578263],"domain_scores_gemma":[0.9926752,0.00067293766,0.0004839338,0.0004313539,0.0052410965,0.0004954989],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.054276433,0.00020882023,0.00034435466,0.0010938637,0.0003798104,0.0005440928,0.00062385475,0.00013599495,0.0027846438],"category_scores_gemma":[0.002488826,0.00015393565,0.00040740482,0.0016261303,0.00003851164,0.0015215776,0.00010015877,0.0003594007,0.0008924501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014801796,0.00015546878,0.00734065,0.000028977205,0.00022418647,0.000019931427,0.021356843,0.12648906,0.010633682,0.00027297353,0.27827808,0.5550521],"study_design_scores_gemma":[0.0009935123,0.00038589467,0.068212554,0.00017312358,0.00026235988,0.00005694952,0.0035419255,0.8697288,0.0004615483,0.0116965445,0.04426735,0.00021941884],"about_ca_topic_score_codex":0.00055206654,"about_ca_topic_score_gemma":0.00963334,"teacher_disagreement_score":0.74323976,"about_ca_system_score_codex":0.002290449,"about_ca_system_score_gemma":0.0069305543,"threshold_uncertainty_score":0.9998855},"labels":[],"label_agreement":null},{"id":"W4410799851","doi":"10.56645/jmde.v21i50.1173","title":"Ray Rist: An Evaluator at the Government Accountability Office (GAO)","year":2025,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Government (linguistics); Political science; Linguistics; Philosophy; Law","score_opus":0.16430975445695797,"score_gpt":0.5301316705100111,"score_spread":0.36582191605305314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410799851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805992,0.0004298054,0.003010206,0.008600093,0.0019596857,0.0007954471,0.00001765293,0.000010270503,0.0045776125],"genre_scores_gemma":[0.99590176,0.000043773194,0.0009545726,0.0002985007,0.00025524435,0.00003699676,0.000008522961,0.000009408245,0.002491231],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98528624,0.002657589,0.001963623,0.00043786276,0.009398041,0.0002566641],"domain_scores_gemma":[0.9919024,0.002160104,0.0016168959,0.0010513888,0.0031343673,0.0001348178],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06662107,0.0002136739,0.00037771475,0.00019273146,0.0007771644,0.00026952507,0.0010909438,0.00010865917,0.0044642603],"category_scores_gemma":[0.0045581535,0.000119666794,0.00027426,0.0007931192,0.00015897791,0.0013320894,0.00036184068,0.00034654542,0.00021617002],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041069323,0.001992282,0.26310265,0.00003827945,0.00026649548,0.0000075886132,0.010247321,0.18083957,0.011053025,0.00044067053,0.04728979,0.4806154],"study_design_scores_gemma":[0.0018426218,0.00030928655,0.7232678,0.00004317644,0.0001977452,0.000012514128,0.00509185,0.2562713,0.0006819403,0.0044345134,0.0077168527,0.00013041876],"about_ca_topic_score_codex":0.000009952273,"about_ca_topic_score_gemma":0.00032062054,"teacher_disagreement_score":0.48048496,"about_ca_system_score_codex":0.0016858544,"about_ca_system_score_gemma":0.0013602324,"threshold_uncertainty_score":0.9964458},"labels":[],"label_agreement":null},{"id":"W4410799871","doi":"10.56645/jmde.v21i50.1175","title":"From Studies to Systems: Ray Rist’s Influence on Evaluation Systems: Insights from International Research Group for Policy and Program Evaluation (INTEVAL)","year":2025,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Group (periodic table); Psychology; Management science; Political science; Engineering; Chemistry","score_opus":0.42995390967908126,"score_gpt":0.6383168529536529,"score_spread":0.20836294327457167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410799871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9689114,0.0054623396,0.0029322014,0.008068181,0.0049676117,0.008732039,0.00007973056,0.000026939799,0.00081953424],"genre_scores_gemma":[0.99249446,0.00022929533,0.0027022914,0.00010387926,0.0015341974,0.0024969634,0.00013843294,0.000021205105,0.00027926054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97699106,0.0057209698,0.0027920902,0.0009479204,0.013166466,0.00038150733],"domain_scores_gemma":[0.9627817,0.007645054,0.0015845032,0.0007311038,0.027041718,0.00021588734],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06507224,0.00033652753,0.0007191424,0.002806047,0.0006954283,0.00094967184,0.00095024967,0.00021071236,0.000067625406],"category_scores_gemma":[0.04000937,0.00024761935,0.00017958341,0.0016498887,0.00017835465,0.0015831422,0.00034061685,0.00044427297,0.000061822946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00204978,0.00079019484,0.0033248037,0.00006589515,0.0007190056,0.0000022446336,0.013780809,0.5444557,0.0037258682,0.0018674593,0.010700385,0.41851786],"study_design_scores_gemma":[0.0046072593,0.0012690255,0.084568866,0.0014142067,0.00038809518,0.0000034673922,0.019850466,0.84711754,0.00015309625,0.035223555,0.005176064,0.0002283418],"about_ca_topic_score_codex":0.00028147356,"about_ca_topic_score_gemma":0.00022160322,"teacher_disagreement_score":0.4182895,"about_ca_system_score_codex":0.0035284439,"about_ca_system_score_gemma":0.0025868695,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null}]}